Enviar pesquisa
Carregar
A new wavelet feature for fault diagnosis
•
0 gostou
•
478 visualizações
IAEME Publication
Seguir
Tecnologia
Negócios
Denunciar
Compartilhar
Denunciar
Compartilhar
1 de 15
Baixar agora
Baixar para ler offline
Recomendados
Sensors 14-00283
Sensors 14-00283
Sidra Khanam
Sensors multi fault detection
Sensors multi fault detection
Sidra Khanam
2014 procedia
2014 procedia
Sidra Khanam
Bearing fault detection using acoustic emission signals analyzed by empirical...
Bearing fault detection using acoustic emission signals analyzed by empirical...
eSAT Publishing House
Fault Diagnostics of Rolling Bearing based on Improve Time and Frequency Doma...
Fault Diagnostics of Rolling Bearing based on Improve Time and Frequency Doma...
ijsrd.com
Handheld Solution for Measurement of Residual Stresses on Railway Wheels usin...
Handheld Solution for Measurement of Residual Stresses on Railway Wheels usin...
Innerspec Technologies
IRJET- Design of two Dimensional Photonic Crystal Based Pressure Sensor us...
IRJET- Design of two Dimensional Photonic Crystal Based Pressure Sensor us...
IRJET Journal
Condition Monitoring and Vibrational Analysis of Proposed Shaft through Exper...
Condition Monitoring and Vibrational Analysis of Proposed Shaft through Exper...
IJERA Editor
Recomendados
Sensors 14-00283
Sensors 14-00283
Sidra Khanam
Sensors multi fault detection
Sensors multi fault detection
Sidra Khanam
2014 procedia
2014 procedia
Sidra Khanam
Bearing fault detection using acoustic emission signals analyzed by empirical...
Bearing fault detection using acoustic emission signals analyzed by empirical...
eSAT Publishing House
Fault Diagnostics of Rolling Bearing based on Improve Time and Frequency Doma...
Fault Diagnostics of Rolling Bearing based on Improve Time and Frequency Doma...
ijsrd.com
Handheld Solution for Measurement of Residual Stresses on Railway Wheels usin...
Handheld Solution for Measurement of Residual Stresses on Railway Wheels usin...
Innerspec Technologies
IRJET- Design of two Dimensional Photonic Crystal Based Pressure Sensor us...
IRJET- Design of two Dimensional Photonic Crystal Based Pressure Sensor us...
IRJET Journal
Condition Monitoring and Vibrational Analysis of Proposed Shaft through Exper...
Condition Monitoring and Vibrational Analysis of Proposed Shaft through Exper...
IJERA Editor
Free vibration analysis on cantilever beam-A review
Free vibration analysis on cantilever beam-A review
IRJET Journal
Ph.D thesis sample
Ph.D thesis sample
Dr.NAGARAJAN. S
Characterization of transients and fault diagnosis in transformer by discrete
Characterization of transients and fault diagnosis in transformer by discrete
IAEME Publication
Applications of Artificial Neural Network and Wavelet Transform For Conditio...
Applications of Artificial Neural Network and Wavelet Transform For Conditio...
IJMER
PhD viva voce Presentation
PhD viva voce Presentation
Dr.NAGARAJAN. S
IRJET- A Review on Boiler Tube Assessment in Power Plant using Ultrasonic Tes...
IRJET- A Review on Boiler Tube Assessment in Power Plant using Ultrasonic Tes...
IRJET Journal
40220130405008
40220130405008
IAEME Publication
Induction Motors Faults Detection Based on Instantaneous Power Spectrum Analy...
Induction Motors Faults Detection Based on Instantaneous Power Spectrum Analy...
IDES Editor
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE WITH ON-LINE PARAMETER PR...
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE WITH ON-LINE PARAMETER PR...
Sheikh R Manihar Ahmed
Structural health monitoring
Structural health monitoring
HITESH KUMAR
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
IJERD Editor
A real time instrumentation approach for bridges and tunnels
A real time instrumentation approach for bridges and tunnels
Derya Dinçer
Iaetsd detection, recognition and localization of partial discharge
Iaetsd detection, recognition and localization of partial discharge
Iaetsd Iaetsd
Applying Condition Based Monitoring Approach in Engineering Management Services
Applying Condition Based Monitoring Approach in Engineering Management Services
Ismail Yusof
Structural Health Monitoring: The paradigm and the benefits shown in some mon...
Structural Health Monitoring: The paradigm and the benefits shown in some mon...
Full Scale Dynamics
Cpen 11 presentation abhisar
Cpen 11 presentation abhisar
Dr. Sandeep Kumar
Free Vibrational Analysis of Cracked and Un-cracked Cantilever Beam
Free Vibrational Analysis of Cracked and Un-cracked Cantilever Beam
IRJET Journal
Bridge Assessment & Monitoring
Bridge Assessment & Monitoring
RekaNext Capital
Introduction to Nondestructive Testing
Introduction to Nondestructive Testing
Dr. Sajjad Mangi
Ultrasonic Inspection Without Couplant
Ultrasonic Inspection Without Couplant
Innerspec Technologies
Fault Diagnosis Guide
Fault Diagnosis Guide
Mike Lacsa
SIGNAL PROCESSING TECHNIQUES USED FOR GEAR FAULT DIAGNOSIS
SIGNAL PROCESSING TECHNIQUES USED FOR GEAR FAULT DIAGNOSIS
Jungho Park
Mais conteúdo relacionado
Mais procurados
Free vibration analysis on cantilever beam-A review
Free vibration analysis on cantilever beam-A review
IRJET Journal
Ph.D thesis sample
Ph.D thesis sample
Dr.NAGARAJAN. S
Characterization of transients and fault diagnosis in transformer by discrete
Characterization of transients and fault diagnosis in transformer by discrete
IAEME Publication
Applications of Artificial Neural Network and Wavelet Transform For Conditio...
Applications of Artificial Neural Network and Wavelet Transform For Conditio...
IJMER
PhD viva voce Presentation
PhD viva voce Presentation
Dr.NAGARAJAN. S
IRJET- A Review on Boiler Tube Assessment in Power Plant using Ultrasonic Tes...
IRJET- A Review on Boiler Tube Assessment in Power Plant using Ultrasonic Tes...
IRJET Journal
40220130405008
40220130405008
IAEME Publication
Induction Motors Faults Detection Based on Instantaneous Power Spectrum Analy...
Induction Motors Faults Detection Based on Instantaneous Power Spectrum Analy...
IDES Editor
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE WITH ON-LINE PARAMETER PR...
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE WITH ON-LINE PARAMETER PR...
Sheikh R Manihar Ahmed
Structural health monitoring
Structural health monitoring
HITESH KUMAR
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
IJERD Editor
A real time instrumentation approach for bridges and tunnels
A real time instrumentation approach for bridges and tunnels
Derya Dinçer
Iaetsd detection, recognition and localization of partial discharge
Iaetsd detection, recognition and localization of partial discharge
Iaetsd Iaetsd
Applying Condition Based Monitoring Approach in Engineering Management Services
Applying Condition Based Monitoring Approach in Engineering Management Services
Ismail Yusof
Structural Health Monitoring: The paradigm and the benefits shown in some mon...
Structural Health Monitoring: The paradigm and the benefits shown in some mon...
Full Scale Dynamics
Cpen 11 presentation abhisar
Cpen 11 presentation abhisar
Dr. Sandeep Kumar
Free Vibrational Analysis of Cracked and Un-cracked Cantilever Beam
Free Vibrational Analysis of Cracked and Un-cracked Cantilever Beam
IRJET Journal
Bridge Assessment & Monitoring
Bridge Assessment & Monitoring
RekaNext Capital
Introduction to Nondestructive Testing
Introduction to Nondestructive Testing
Dr. Sajjad Mangi
Ultrasonic Inspection Without Couplant
Ultrasonic Inspection Without Couplant
Innerspec Technologies
Mais procurados
(20)
Free vibration analysis on cantilever beam-A review
Free vibration analysis on cantilever beam-A review
Ph.D thesis sample
Ph.D thesis sample
Characterization of transients and fault diagnosis in transformer by discrete
Characterization of transients and fault diagnosis in transformer by discrete
Applications of Artificial Neural Network and Wavelet Transform For Conditio...
Applications of Artificial Neural Network and Wavelet Transform For Conditio...
PhD viva voce Presentation
PhD viva voce Presentation
IRJET- A Review on Boiler Tube Assessment in Power Plant using Ultrasonic Tes...
IRJET- A Review on Boiler Tube Assessment in Power Plant using Ultrasonic Tes...
40220130405008
40220130405008
Induction Motors Faults Detection Based on Instantaneous Power Spectrum Analy...
Induction Motors Faults Detection Based on Instantaneous Power Spectrum Analy...
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE WITH ON-LINE PARAMETER PR...
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE WITH ON-LINE PARAMETER PR...
Structural health monitoring
Structural health monitoring
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
A real time instrumentation approach for bridges and tunnels
A real time instrumentation approach for bridges and tunnels
Iaetsd detection, recognition and localization of partial discharge
Iaetsd detection, recognition and localization of partial discharge
Applying Condition Based Monitoring Approach in Engineering Management Services
Applying Condition Based Monitoring Approach in Engineering Management Services
Structural Health Monitoring: The paradigm and the benefits shown in some mon...
Structural Health Monitoring: The paradigm and the benefits shown in some mon...
Cpen 11 presentation abhisar
Cpen 11 presentation abhisar
Free Vibrational Analysis of Cracked and Un-cracked Cantilever Beam
Free Vibrational Analysis of Cracked and Un-cracked Cantilever Beam
Bridge Assessment & Monitoring
Bridge Assessment & Monitoring
Introduction to Nondestructive Testing
Introduction to Nondestructive Testing
Ultrasonic Inspection Without Couplant
Ultrasonic Inspection Without Couplant
Destaque
Fault Diagnosis Guide
Fault Diagnosis Guide
Mike Lacsa
SIGNAL PROCESSING TECHNIQUES USED FOR GEAR FAULT DIAGNOSIS
SIGNAL PROCESSING TECHNIQUES USED FOR GEAR FAULT DIAGNOSIS
Jungho Park
FAULT DETECTION AND FAULT DIAGNOSIS
FAULT DETECTION AND FAULT DIAGNOSIS
Anand Kumar
Principal Component Analysis
Principal Component Analysis
Ricardo Wendell Rodrigues da Silveira
Advanced automotive fault diagnosis tom denton
Advanced automotive fault diagnosis tom denton
moncefbenj
PCA-CompChem_seminar
PCA-CompChem_seminar
Anne D'cruz
Basics of process fault detection and diagnostics
Basics of process fault detection and diagnostics
Rahul Dey
PPT_Final_Presentation
PPT_Final_Presentation
Sleeba Paul
PCA (Principal Component Analysis)
PCA (Principal Component Analysis)
Jungho Park
Fault diagnosis notes
Fault diagnosis notes
iteclearners
5 data analysis case study
5 data analysis case study
Dmitry Grapov
Introduction to principal component analysis (pca)
Introduction to principal component analysis (pca)
Mohammed Musah
3 principal components analysis
3 principal components analysis
Dmitry Grapov
Introduction to Wavelet Transform with Applications to DSP
Introduction to Wavelet Transform with Applications to DSP
Hicham Berkouk
Pca ppt
Pca ppt
Dheeraj Dwivedi
Study Of The Fault Diagnosis Based On Wavelet And Fuzzy Neural Network For Th...
Study Of The Fault Diagnosis Based On Wavelet And Fuzzy Neural Network For Th...
IJRES Journal
Introduction to wavelet transform
Introduction to wavelet transform
Raj Endiran
07. PCA
07. PCA
Jeonghun Yoon
Destaque
(18)
Fault Diagnosis Guide
Fault Diagnosis Guide
SIGNAL PROCESSING TECHNIQUES USED FOR GEAR FAULT DIAGNOSIS
SIGNAL PROCESSING TECHNIQUES USED FOR GEAR FAULT DIAGNOSIS
FAULT DETECTION AND FAULT DIAGNOSIS
FAULT DETECTION AND FAULT DIAGNOSIS
Principal Component Analysis
Principal Component Analysis
Advanced automotive fault diagnosis tom denton
Advanced automotive fault diagnosis tom denton
PCA-CompChem_seminar
PCA-CompChem_seminar
Basics of process fault detection and diagnostics
Basics of process fault detection and diagnostics
PPT_Final_Presentation
PPT_Final_Presentation
PCA (Principal Component Analysis)
PCA (Principal Component Analysis)
Fault diagnosis notes
Fault diagnosis notes
5 data analysis case study
5 data analysis case study
Introduction to principal component analysis (pca)
Introduction to principal component analysis (pca)
3 principal components analysis
3 principal components analysis
Introduction to Wavelet Transform with Applications to DSP
Introduction to Wavelet Transform with Applications to DSP
Pca ppt
Pca ppt
Study Of The Fault Diagnosis Based On Wavelet And Fuzzy Neural Network For Th...
Study Of The Fault Diagnosis Based On Wavelet And Fuzzy Neural Network For Th...
Introduction to wavelet transform
Introduction to wavelet transform
07. PCA
07. PCA
Semelhante a A new wavelet feature for fault diagnosis
Assessment of Gearbox Fault DetectionUsing Vibration Signal Analysis and Acou...
Assessment of Gearbox Fault DetectionUsing Vibration Signal Analysis and Acou...
IOSR Journals
Fault diagnosis of rolling element bearings using artificial neural network
Fault diagnosis of rolling element bearings using artificial neural network
IJECEIAES
[IJET V2I5P7] Authors: Mr. Vaibhav A. Kalhapure, Dr.R.R.Navthar
[IJET V2I5P7] Authors: Mr. Vaibhav A. Kalhapure, Dr.R.R.Navthar
IJET - International Journal of Engineering and Techniques
J046015861
J046015861
IJERA Editor
Fault diagnosis of bearing
Fault diagnosis of bearing
prj_publication
Acoustic emission condition monitoring an application for wind turbine fault...
Acoustic emission condition monitoring an application for wind turbine fault...
eSAT Journals
Acoustic emission condition monitoring an application for wind turbine fault ...
Acoustic emission condition monitoring an application for wind turbine fault ...
eSAT Publishing House
Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...
Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...
IJMERJOURNAL
Mems Based Motor Fault Detection in Windmill Using Neural Networks
Mems Based Motor Fault Detection in Windmill Using Neural Networks
IJRES Journal
Mems Based Motor Fault Detection
Mems Based Motor Fault Detection
Neelam Kumawat
A0260105
A0260105
researchinventy
201421402011.pptx
201421402011.pptx
PrakashDuraisamyCIT
18 syed kamruddin_ahamed_163-176
18 syed kamruddin_ahamed_163-176
Alexander Decker
Report on Fault Diagnosis of Ball Bearing System
Report on Fault Diagnosis of Ball Bearing System
Sridhara R
Comparative Analysis of Natural Frequency of Transverse Vibration of a Cantil...
Comparative Analysis of Natural Frequency of Transverse Vibration of a Cantil...
IRJET Journal
Conditioning Monitoring of Gearbox Using Different Methods: A Review
Conditioning Monitoring of Gearbox Using Different Methods: A Review
IJMER
Various Types of Faults and Their Detection Techniquesin Three Phase Inductio...
Various Types of Faults and Their Detection Techniquesin Three Phase Inductio...
IJERA Editor
Development of a Condition Monitoring Algorithm for Industrial Robots based o...
Development of a Condition Monitoring Algorithm for Industrial Robots based o...
IJECEIAES
A Study of Ball Bearing’s Crack Using Acoustic Signal / Vibration Signal and ...
A Study of Ball Bearing’s Crack Using Acoustic Signal / Vibration Signal and ...
INFOGAIN PUBLICATION
A Study of Ball Bearing’s Crack Using Acoustic Signal / Vibration Signal and ...
A Study of Ball Bearing’s Crack Using Acoustic Signal / Vibration Signal and ...
INFOGAIN PUBLICATION
Semelhante a A new wavelet feature for fault diagnosis
(20)
Assessment of Gearbox Fault DetectionUsing Vibration Signal Analysis and Acou...
Assessment of Gearbox Fault DetectionUsing Vibration Signal Analysis and Acou...
Fault diagnosis of rolling element bearings using artificial neural network
Fault diagnosis of rolling element bearings using artificial neural network
[IJET V2I5P7] Authors: Mr. Vaibhav A. Kalhapure, Dr.R.R.Navthar
[IJET V2I5P7] Authors: Mr. Vaibhav A. Kalhapure, Dr.R.R.Navthar
J046015861
J046015861
Fault diagnosis of bearing
Fault diagnosis of bearing
Acoustic emission condition monitoring an application for wind turbine fault...
Acoustic emission condition monitoring an application for wind turbine fault...
Acoustic emission condition monitoring an application for wind turbine fault ...
Acoustic emission condition monitoring an application for wind turbine fault ...
Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...
Condition Monitoring of Rotating Equipment Considering the Cause and Effects ...
Mems Based Motor Fault Detection in Windmill Using Neural Networks
Mems Based Motor Fault Detection in Windmill Using Neural Networks
Mems Based Motor Fault Detection
Mems Based Motor Fault Detection
A0260105
A0260105
201421402011.pptx
201421402011.pptx
18 syed kamruddin_ahamed_163-176
18 syed kamruddin_ahamed_163-176
Report on Fault Diagnosis of Ball Bearing System
Report on Fault Diagnosis of Ball Bearing System
Comparative Analysis of Natural Frequency of Transverse Vibration of a Cantil...
Comparative Analysis of Natural Frequency of Transverse Vibration of a Cantil...
Conditioning Monitoring of Gearbox Using Different Methods: A Review
Conditioning Monitoring of Gearbox Using Different Methods: A Review
Various Types of Faults and Their Detection Techniquesin Three Phase Inductio...
Various Types of Faults and Their Detection Techniquesin Three Phase Inductio...
Development of a Condition Monitoring Algorithm for Industrial Robots based o...
Development of a Condition Monitoring Algorithm for Industrial Robots based o...
A Study of Ball Bearing’s Crack Using Acoustic Signal / Vibration Signal and ...
A Study of Ball Bearing’s Crack Using Acoustic Signal / Vibration Signal and ...
A Study of Ball Bearing’s Crack Using Acoustic Signal / Vibration Signal and ...
A Study of Ball Bearing’s Crack Using Acoustic Signal / Vibration Signal and ...
Mais de IAEME Publication
IAEME_Publication_Call_for_Paper_September_2022.pdf
IAEME_Publication_Call_for_Paper_September_2022.pdf
IAEME Publication
MODELING AND ANALYSIS OF SURFACE ROUGHNESS AND WHITE LATER THICKNESS IN WIRE-...
MODELING AND ANALYSIS OF SURFACE ROUGHNESS AND WHITE LATER THICKNESS IN WIRE-...
IAEME Publication
A STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURS
A STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURS
IAEME Publication
BROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURS
BROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURS
IAEME Publication
DETERMINANTS AFFECTING THE USER'S INTENTION TO USE MOBILE BANKING APPLICATIONS
DETERMINANTS AFFECTING THE USER'S INTENTION TO USE MOBILE BANKING APPLICATIONS
IAEME Publication
ANALYSE THE USER PREDILECTION ON GPAY AND PHONEPE FOR DIGITAL TRANSACTIONS
ANALYSE THE USER PREDILECTION ON GPAY AND PHONEPE FOR DIGITAL TRANSACTIONS
IAEME Publication
VOICE BASED ATM FOR VISUALLY IMPAIRED USING ARDUINO
VOICE BASED ATM FOR VISUALLY IMPAIRED USING ARDUINO
IAEME Publication
IMPACT OF EMOTIONAL INTELLIGENCE ON HUMAN RESOURCE MANAGEMENT PRACTICES AMONG...
IMPACT OF EMOTIONAL INTELLIGENCE ON HUMAN RESOURCE MANAGEMENT PRACTICES AMONG...
IAEME Publication
VISUALISING AGING PARENTS & THEIR CLOSE CARERS LIFE JOURNEY IN AGING ECONOMY
VISUALISING AGING PARENTS & THEIR CLOSE CARERS LIFE JOURNEY IN AGING ECONOMY
IAEME Publication
A STUDY ON THE IMPACT OF ORGANIZATIONAL CULTURE ON THE EFFECTIVENESS OF PERFO...
A STUDY ON THE IMPACT OF ORGANIZATIONAL CULTURE ON THE EFFECTIVENESS OF PERFO...
IAEME Publication
GANDHI ON NON-VIOLENT POLICE
GANDHI ON NON-VIOLENT POLICE
IAEME Publication
A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...
A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...
IAEME Publication
ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...
ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...
IAEME Publication
INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...
INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...
IAEME Publication
A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...
A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...
IAEME Publication
EXPERIMENTAL STUDY OF MECHANICAL AND TRIBOLOGICAL RELATION OF NYLON/BaSO4 POL...
EXPERIMENTAL STUDY OF MECHANICAL AND TRIBOLOGICAL RELATION OF NYLON/BaSO4 POL...
IAEME Publication
ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...
ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...
IAEME Publication
OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...
OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...
IAEME Publication
APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...
APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...
IAEME Publication
A MULTIPLE – CHANNEL QUEUING MODELS ON FUZZY ENVIRONMENT
A MULTIPLE – CHANNEL QUEUING MODELS ON FUZZY ENVIRONMENT
IAEME Publication
Mais de IAEME Publication
(20)
IAEME_Publication_Call_for_Paper_September_2022.pdf
IAEME_Publication_Call_for_Paper_September_2022.pdf
MODELING AND ANALYSIS OF SURFACE ROUGHNESS AND WHITE LATER THICKNESS IN WIRE-...
MODELING AND ANALYSIS OF SURFACE ROUGHNESS AND WHITE LATER THICKNESS IN WIRE-...
A STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURS
A STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURS
BROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURS
BROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURS
DETERMINANTS AFFECTING THE USER'S INTENTION TO USE MOBILE BANKING APPLICATIONS
DETERMINANTS AFFECTING THE USER'S INTENTION TO USE MOBILE BANKING APPLICATIONS
ANALYSE THE USER PREDILECTION ON GPAY AND PHONEPE FOR DIGITAL TRANSACTIONS
ANALYSE THE USER PREDILECTION ON GPAY AND PHONEPE FOR DIGITAL TRANSACTIONS
VOICE BASED ATM FOR VISUALLY IMPAIRED USING ARDUINO
VOICE BASED ATM FOR VISUALLY IMPAIRED USING ARDUINO
IMPACT OF EMOTIONAL INTELLIGENCE ON HUMAN RESOURCE MANAGEMENT PRACTICES AMONG...
IMPACT OF EMOTIONAL INTELLIGENCE ON HUMAN RESOURCE MANAGEMENT PRACTICES AMONG...
VISUALISING AGING PARENTS & THEIR CLOSE CARERS LIFE JOURNEY IN AGING ECONOMY
VISUALISING AGING PARENTS & THEIR CLOSE CARERS LIFE JOURNEY IN AGING ECONOMY
A STUDY ON THE IMPACT OF ORGANIZATIONAL CULTURE ON THE EFFECTIVENESS OF PERFO...
A STUDY ON THE IMPACT OF ORGANIZATIONAL CULTURE ON THE EFFECTIVENESS OF PERFO...
GANDHI ON NON-VIOLENT POLICE
GANDHI ON NON-VIOLENT POLICE
A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...
A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...
ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...
ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...
INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...
INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...
A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...
A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...
EXPERIMENTAL STUDY OF MECHANICAL AND TRIBOLOGICAL RELATION OF NYLON/BaSO4 POL...
EXPERIMENTAL STUDY OF MECHANICAL AND TRIBOLOGICAL RELATION OF NYLON/BaSO4 POL...
ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...
ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...
OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...
OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...
APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...
APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...
A MULTIPLE – CHANNEL QUEUING MODELS ON FUZZY ENVIRONMENT
A MULTIPLE – CHANNEL QUEUING MODELS ON FUZZY ENVIRONMENT
Último
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
Igalia
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
Khem
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
Maria Levchenko
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
UK Journal
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
Delhi Call girls
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
The Digital Insurer
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
The Digital Insurer
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Igalia
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
Delhi Call girls
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Earley Information Science
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Drew Madelung
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
wesley chun
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
The Digital Insurer
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
Malak Abu Hammad
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
naman860154
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
Enterprise Knowledge
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
Anna Loughnan Colquhoun
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
hans926745
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
ThousandEyes
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
Rafal Los
Último
(20)
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
A new wavelet feature for fault diagnosis
1.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN International Journal of Mechanical Engineering 0976 – 6359(Online) Volume 2, Issue 0976 6340(Print) and Technology (IJMET), ISSN2, May-–July (2011), © IAEME ISSN 0976 – 6359(Online) Volume 2 Issue 2, May – July (2011), pp. 70-84 ©IAEME © IAEME, http://www.iaeme.com/ijmet.html IJMET A NEW WAVELET FEATURE FOR FAULT DIAGNOSIS OF ROLLER BEARINGS USING DECISION TREE 1 Manju B R, 2A.R. Rajan. 3V. Sugumaran 1 Department of Mathematics, Sree Buddha College of Engineering, Kerala, India, manjubrrajendran@yahoo.co.in 2 Department of Mathematics, university of Kerala, Thiruvandapuram, Kerala, India 3 SMBS, VIT University, Chennai campus, Chennai, Tamil Nadu, India, v_sugu@yahoo.com ABSTRACT “Fault diagnosis of the roller bearings” as pattern classification problem has three main steps namely, feature extraction, feature selection, and classification. A number of machine-learning algorithms have been successfully used to solve the problem with the help of vibration signals. Feature extraction is one of the most important activities in the whole process, as the strength of the features determines the classification accuracy of the classifiers. This paper investigates the use of new discrete wavelet features for feature extraction and compares the result with that of energy definition of discrete wavelet features using Haar wavelet. The extracted features are then classified using decision tree as classifier. The study reveals that the new proposed feature performs better than that of existing energy definition features. Key words: Fault diagnosis; Discrete Wavelet Transform; New Wavelet Features; Machine Learning 1.0 INTRODUCTION Roller bearing failures can be caused by several factors, say 1. incorrect design or installation, 2. acid corrosion, 3. poor lubrication, 4. plastic deformation. The most common defects are produced by material fatigue after a certain running time. This phenomenon begins with the appearance of minute cracks below the surface of the bearing elements. During operation, the cracks progress to the surface due to the cyclic loads, giving rise to surface pitting and spalling. Statistically [1], 90% of the total amount of different roller bearing faults is related to either an inner or outer race fault; the remaining malfunctions are mostly due to a rolling element fault but rarely a cage fault. Hence the focus of the present work is on inner race fault, outer race fault and their combinations. Such defects generate a series of impact vibrations every time a running 70
2.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME roller passes over the surfaces of the defects, and as is well known, for different fault types, the impacts will appear with different frequency. Roller bearings, as important components, are widely used in rotary machines; faults occurring in bearings must be detected as early as possible to avoid fatal breakdowns of machines that may lead to loss of production. A visual inspection of certain features of the spectral analysis is prima-facie adequate for fault identification; however, it doesn’t suffice in case of multiple faults or when fault advancement is slow. Vibration signal is seen to be a preferable source in such cases. To detect the faults in bearings many kinds of methods have been developed and without exception, the most important part of the methods is various signal analysis technique. In the early studies, Fourier analysis has been the dominating signal analysis tool for bearing fault detection. But, there are some limitations of the Fourier transform [2]: the signal to be analysed must be strictly periodic or stationary; otherwise, the resulting Fourier spectrum will make little physical sense. Unfortunately, the rolling bearing vibration signals are often non-stationary processes, and their frequency components will change with time. Therefore, the Fourier transform often cannot fulfil the bearing fault diagnosis task well. A technique which accounts for the variation of spectral components with time will be more effective here. Hence, one has to have recourse to time-frequency analysis methods. These generate both time and frequency information of a signal simultaneously through mapping the one-dimensional signal to a two-dimensional time–frequency plane. In fact, in recent studies, the time–frequency analysis methods are widely used to diagnose the faults in bearings. They can determine the time of the impact of occurrence as well as the frequency ranges of the impact location; In effect they identify the existence of faults as well as the causes. Amongst the available frequency analysis, the wavelet transforms stand out due to their unique features; they have been widely used for roller bearing fault detection [3-4]. For roller bearing fault detection, the frequency ranges of the vibration signals that are to be analysed, are often wide; and hence according to the Shannon sampling theorem[18], a high sampling rate is needed, Further the sequence of samples to be collected and processed for meaningful fault detection is quite large in size. Therefore, it is expected that the desired method should have good computing efficiency. Unfortunately, the computing of continuous wavelet transform (CWT) is somewhat time consuming and is not suitable for large size data analysis and on-line fault diagnosis which is of interest here. The Discrete Wavelet Transform (DWT), which is based on sub-band coding can be used effectively to analyse the signal as long as the time duration of the wavelet is large compared to the sampling period. Note that this requirement is same as the sampling theorem (discussed above) put in a different form. In other words, we are not loosing any substantial information in the process of resorting to DWT. The real benefit in the use of DWT is a conspicuous reduction in computation time. It is easy to implement and reduces the computation time and resources required. Hence, it is taken up for study. J. Lin et. Al [3] reported the use of Morlet wavelet for decomposition and feature extraction from vibration signals from the rolling bearing and the gearbox. [3]. Only Morlet wavelet was used in the study. Goumas et al [4]. used discrete wavelet transform to analyse the transient signals of the vibration velocity in washing machines and fault 71
3.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME features were extracted from the wavelet coefficient [4]. In works reported in literature, researchers mostly have used energy level of each wavelet decomposition co-efficient at each level as features. There is a mechanical energy analogy that they quote for justifying the usage. This measure gives an idea about the energy content of the wavelet coefficients. In the literature it is established that the information required for fault diagnosis problem is hidden in the wavelet decomposition co-efficients. The challenge is, how one taps that information by using a measure?’. This is the fundamental motivation to look forward to a new measure which will perform better. As a result many measures were tried and the one which performed better alone is presented in this paper. This forms the primary contribution of the paper. The morlet wavelet was used because of its fault diagnosis capability [19-21]. 2. EXPERIMENTAL SET UP The fault simulator setup used for conducting the experiment is shown in Fig. 1. It can simulate faults in bearings, gears, belts etc. It is also designed to study misalignments and eccentricity. A variable speed DC motor (0.5hp) with speed up to 3000 rpm is the drive. A short shaft of 30mm diameter is attached to the shaft of the motor through a flexible coupling; this is to minimize the effects of misalignment and transmission of vibration from motor. Shaft is supported at its ends through two taper roller bearings. The bearing that is closer to the motor is a good bearing. The bearing at the farther end is the bearing under test; provision is made to change it easily. Sensor is mounted on top of the bearing housing. The selected area is made flat and smooth to ensure effective coupling. A piezoelectric accelerometer (Dytron) is mounted on the flat surface using direct adhesive mounting technique. The voltage output of accelerometers is proportional to acceleration. Accelerometers are preferred as transducers in machine condition monitoring due to the following reasons: i) Extreme ruggedness, ii) Large frequency response, iii) Large dynamic range (accelerometers can detect very small vibrations without being damaged by large vibrations) iv) Output is proportional to forces which are the cause of internal damage. v) High-frequency sensitivity for detecting bearing faults. The accelerometer is connected to the signal-conditioning unit, DACTRON FFT analyzer, where the signal goes through the charge amplifier and an Analogue-to Digital converter (ADC). The vibration signal in digital form is input to the computer through an USB port. It is stored directly in the computer’s secondary memory. The signal is then read from the memory and processed to extract different features. 72
4.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME Figure 1 Bearing Test Rig 3. EXPERIMENTAL PROCEDURE In the present study, four SKF30206 roller bearings were used. One was a brand new bearing and was taken to be free of defects. In the other three roller bearings, defects were created. Electron Discharge Machining (EDM) was used to ensure to get precisely defined defect. The size of inner race defect is 0.525mm wide and 0.827 mm deep and that of outer race defect is 0.652 mm wide and 0.981 mm deep. The sizes of the defects are a bit larger than that one encountered in any practical situations; however, it is in-line with work reported in literature [13]. The vibration signal from the piezoelectric pickup mounted on the test bearing was taken, after allowing for initial running of the bearing. The sampling frequency was 12000 Hz and sample length was 8192 for all speeds and all conditions. The sample length is chosen long enough to ensure data consistency; In addition to data consistency, the following points were considered. Statistical measures are more meaningful, when the number of samples is sufficiently large. On the other hand, as the number of samples increases the computation time increases. To strike a balance, sample length of around 10000 was chosen. In techniques like wavelet based feature extraction, the number of samples is preferably 2n. The nearest 2n to 10000 is 8192 and hence, it was taken as sample length. Extensive trials were taken at the set speed (700 rpm) and vibration signal was stored in the data file. 73
5.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME Fig 2 Time domain plots of signals In line with the justification earlier (in section 1), four cases were considered – i) Normal bearing (without any fault), ii) Bearing with inner race defect, iii) Bearing with outer race defect iv) Bearing with both inner race and outer race defects. Time domain plots of these cases are shown in Fig. 2. 4. WAVELET ANALYSIS AND FEATURE EXTRACTION 4.1 Brief review of wavelet theory Wavelet Transform is defined as the integral of the signal s (t ) multiplied by scaled, shifted versions of a basic wavelet function ψ (t ) —a real-valued function whose Fourier Transform satisfies the admissibility criteria [14]: 1 t −b C (a, b) = ∫ s (t ) ψ dt a a (1) R a ∈ R + − {0} , b ∈ R. where, C - Continuous wavelet coefficients t - time a - scaling parameter, b - time localisation parameter. Both ‘a’ and ‘b’ can be continuous or discrete variables. Multiplication of each coefficient by an appropriately scaled and shifted wavelet yields the constituent wavelets of the original signal. For signals of finite energy, continuous wavelet synthesis provides the reconstruction formula: 1 1 t − b da s (t ) = (2) ∫ ∫+ C (a, b) aψ a a 2 db Kψ R R 74
6.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME Use of Discrete Wavelet Transform (DWT) for analysis retains effectiveness without sacrificing accuracy. In this scheme, ‘a’ and ‘b’ are given by: ( j , k ) ∈ Z 2 : a = 2 j , b = k 2 j , Z = {0, ±1, ±2} Defining ( j , k ) ∈ Z 2 :ψ j , k (t ) = 2− j 2ψ ( 2− j t − k ) φ j ,k (t ) = 2− j 2 φ ( 2− j t − k ) A wavelet filter with impulse g, plays the role of the wavelet ψ and a scaling filter with impulse response h, plays the role of scaling function φ , g and h are defined on a regular grid ∆Z , where ∆ is the sampling period (here, without loss of generality, set ∆ = 1 ).Discrete wavelet analysis yields C ( a, b ) = c( j , k ) = ∑ s ( n )g j , k ( n ) n∈Z (3) j j a = 2 ,b = k2 , j ∈ N, k ∈ N Corresponding synthesis relation is: s (t ) = ∑∑ c ( j , k ) j ,k ( t ) ψ (4) j∈Z k∈Z The detail at level j is defined as: D j (t ) = ∑ c ( j , k ) j ,k ( t ) ψ (5) k∈Z And the approximation to s(t) at any level is: AJ −1 = ∑ D j (6) j>J The following equations hold: A j −1 = A j + D j (7) s = AJ + ∑ D j (8) j≤J In practice, the decomposition can be determined iteratively, with successive approximations being computed in turn, so that a signal is decomposed into many lowerresolution components. This is known as the wavelet decomposition tree. 4.2 Wavelet analysis and feature definition Figs. 3 to 6 show a combination of signals and their decomposition details at different levels designated ‘d1’ to ‘d5’. Actually, for analysis, thirteen levels are considered (from ‘d1’ to ‘d13’). A careful perusal of the signal details under different conditions bring out that there are considerable changes in the average energy level of some details with respect to its conditions. Feature extraction constitutes computation of specific measures which characterise the signal. The discrete wavelet transform (DWT) provides an effective method for generating features. There are many ways in which researchers defined the measures for DWT. However, amongst them the most common and popular definition is taken as bench mark for comparison. The bench mark ‘energy definition’ of a feature vector is given by 75
7.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME T v dwt = {v1dwt , v2 dwt ,..., v12 dwt } (9) dwt A component vi in the feature vector is related to the individual resolutions by the following equation 1 ni vidwt = ∑ wi2, j , i = 1, 2,...12 (10) ni j =1 where, n1 = 212 , n2 = 211 ,..., n12 = 20. vidwt is the ith feature element in a DWT feature vector. ni is the number of samples in an individual sub-band, wi2, j is the jth coefficient of the ith sub-band. The proposed feature vector is defined as follows: n vidwt = ∑ d i2 (11) i =1 where, i is an index, n is number of data points in each wavelet decomposition coefficients at a given level and di is the detail coefficient of nth decomposition. In the new definition, the co-efficients are squared and summed (sum squared definition). The other feature definitions which were considered for the study include mean of the detail coefficients, root mean square of the detail coefficients, standard error of the detail coefficients etc. Good Condition signal 100 0 -100 0 1000 2000 3000 4000 5000 6000 7000 8000 0 500 1000 1500 2000 2500 3000 3500 4000 d1 50 0 -50 d2 50 0 -50 0 200 400 600 0 100 200 300 0 50 100 150 800 1000 1200 1400 1600 1800 2000 400 500 600 700 800 900 1000 200 250 300 350 400 450 500 d3 50 0 -50 d4 50 0 -50 d5 100 0 -100 0 20 40 60 Sample Number 80 100 120 Fig.3. DWT decomposition plot of details using DB2 up to 5 levels for signal of good bearing 76
8.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME Signal IRF Condition 200 0 -200 0 1000 2000 3000 4000 5000 6000 7000 8000 0 500 1000 1500 2000 2500 3000 3500 4000 200 d1 0 -200 d2 200 0 d3 -200 0 200 400 600 800 1000 1200 1400 1600 1800 2000 0 100 200 300 400 500 600 700 800 900 1000 50 100 150 200 250 300 350 400 450 500 100 0 -100 d4 50 0 -50 0 d5 100 0 -100 0 50 100 150 Sample Number 200 250 Fig.4 DWT decomposition plot of details using DB2 up to 5 levels for signal of inner race fault bearing d1 Signal ORF Condition 100 0 -100 0 1000 2000 3000 4000 5000 6000 7000 8000 0 500 1000 1500 2000 2500 3000 3500 4000 200 0 -200 d2 200 0 d3 -200 100 0 -100 0 200 400 600 800 1000 1200 1400 1600 1800 2000 0 100 200 300 400 500 600 700 800 900 1000 50 100 150 200 250 300 350 400 450 500 d4 50 0 -50 0 d5 100 0 -100 0 50 100 150 Sample Number 200 250 Fig.5 DWT decomposition plot of details using DB2 up to 5 levels for signal of outer race fault bearing 77
9.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME Siganl IORF Condition 500 0 -500 0 1000 2000 3000 4000 5000 6000 7000 8000 0 500 1000 1500 2000 2500 3000 3500 4000 d1 200 0 -200 d2 200 0 d3 -200 0 200 400 600 800 1000 1200 1400 1600 1800 2000 0 100 200 300 400 500 600 700 800 900 1000 50 100 150 200 250 300 350 400 450 500 100 0 -100 d4 50 0 -50 0 d5 100 0 -100 0 50 100 150 Sample Number 200 250 Fig.6. DWT decomposition plot of details using DB2 up to 5 levels for signal of inner and outer race fault bearing 5. CLASSIFIER (C4.5 ALGORITHM) Fault diagnosis can be viewed as a data mining problem where one extracts information from the acquired data through a classification process. A predictive model for classification invokes the idea of branches and trees identified through a logical process. The classification is done through a decision tree with its leaves representing the different conditions of the bearings. The sequential branching process ending up with the leaves here is based on conditional probabilities associated with individual features. Any good classifier should have the following properties [16]: (1) It should have good predictive accuracy; It is the ability of the model to correctly predict the class label of new or previously unseen data. (2) It should have good speed. (3) The computational cost involved in generating and using the model should be as low as possible. (4) It should be robust; Robustness is the ability of the model to make correct predictions given the noisy data or data with missing values. (5) The level of understanding and insight that is provided by classification model should be high enough. It is reported that C4.5 model introduced by J.R. Quinlan [17] satisfies with the above criteria and hence the same is used in the present study. Decision tree algorithm (C4.5) has two phases: building and pruning. The building phase is also called as ‘growing phase’. Both these are briefly discussed here. 78
10.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME 5.1 Building Phase Training sample set with discrete-valued attributes is recursively partitioned until all the records in a partition have the same class. This forms the building phase. The tree has a single root node for the entire training set. For every partition, a new node is added to the decision tree. For a set of samples in a partition S , a test attribute X is selected for further partitioning the set into S1 , S 2 ,..., and S L . New nodes for S1 , S 2 ,..., S L are created and these are added to the decision tree as children of the node for S . Further, the node for S is labeled with test X , and partitions S1 , S 2 ,..., S L are recursively partitioned. A partition in which all the records have identical class label is not partitioned further, and the leaf corresponding to it is labeled with the corresponding class. The construction of decision tree depends very much on how a test attribute X is selected. C4.5 uses information entropy evaluation function as the selection criteria [17]. The entropy evaluation function is arrived at through the following steps. Step 1: Calculate Info(S) to identify the class in the training set S . K Info( S ) = −∑ freq ( Ci , S / S ) log 2 freq ( Ci , S / S ) i =1 { } (12) where, S is the number of cases in the training set. Ci is a class, i = 1, 2,..., K . K is the number of classes and freq (Ci, S ) is the number of cases included in Ci . Step 2: Calculate the expected information value, InfoX ( S ) for test X to partition S . K InfoX ( S ) = −∑ ( Si / S ) Info( Si ) (13) i =1 where L is the number of outputs for test X , Si is a subset of S corresponding to ith output and is the number of cases of subset Si . Step 3: Calculate the information gain after partition according to test X . Gain( X ) = Info( S ) − Info X ( S ) Step 4: Calculate the partition information value SplitInfo( X ) partitioned into L subsets. S S S 1 L S SplitInfo( X ) = − ∑ i log 2 i + 1 − i log 2 1 − i 2 i =1 S S S S (14) acquiring for S (15) Step 5: Calculate the gain ratio of Gain( X ) over SplitInfo( X ) . GainRatio( X ) = Gain( X ) − SplitInfo( X ) (16) The GainRatio( X ) compensates for the weak point of Gain( X ) which represents the quantity of information provided by X in the training set. Therefore, an attribute with the highest GainRatio( X ) is taken as the root of the decision tree. 79
11.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME 5.1 Pruning phase Usually a training set in the sample space leads to a decision tree which may be too large to be an accurate model; this is due to over-training or over-fitting. Such a fully grown decision tree needs to be pruned by removing the less reliable branches to obtain better classification performance over the whole instance space even though it may have a higher error over the training set. The C4.5 algorithm uses an error-based post-pruning strategy to deal with over-training problem. For each classification node C4.5 calculates a kind of predicted error rate based on the total aggregate of misclassifications at that particular node. The error-based pruning technique essentially reduces to the replacement of vast sub-trees in the classification structure by singleton nodes or simple branch collections if these actions contribute to a drop in the overall error rate of the root node. 5.3 Application of Decision Tree for the Problem under Study As is customary the samples are divided into two parts: i) Training set ii) Testing set. Training set is used to train classifier and testing set is used to test the validity of the classifier. Ten-fold cross-validation is employed to evaluate classification accuracy. The training process of C4.5 using the samples with continuous-valued attributes is as follows. (1) The tree starts as a single node representing the training samples. (2) If the samples are all of the same class, then the node becomes a leaf and is labeled with the class. (3) Otherwise, the algorithm discretises every attribute to select the optimal threshold and uses the entropy-based measure called information gain (discussed in Section 5.1) as heuristic for selecting the attribute that will best separate the samples into individual classes. (4) A branch is created for each best discrete interval of the test attribute, and the samples are partitioned accordingly. (5) The algorithm uses the same process recursively to form a decision tree for the samples at each partition. (6) The recursive partitioning stops only when one of the following conditions is true: (a) All the samples for a given node belong to the same class or (b) There are no remaining attributes on which the samples may be further partitioned. (c) There are no samples for the branch test attribute. In this case, a leaf is created with the majority class in samples. (7) A pessimistic error pruning method (discussed in Section 2.2) is used to prune the grown tree to improve its robustness and accuracy. 6. Results and Discussions The fault diagnosis problem is modeled as machine learning problem in which wavelet decomposition co-efficients are used for feature extraction. In defining the features from wavelet decomposition co-efficients, a new measure (root square 80
12.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME definition) is proposed and the corresponding feature vectors are extracted. Refer eqn.(11) for feature definition; The V1, V2, … Vn represents the feature defined at nth level. The features are classified with C4.5 decision tree algorithm. The decision tree built out of new features is shown in Fig. 7. A similar procedure is followed for already existing benchmark definition (energy definition) and the corresponding decision tree is shown in Fig.8. In Fig.7, the number of leaves is 8 and the size of the tree is 15 for new feature. The corresponding values of existing features are 9 and 16 as shown in Fig.8. One can appreciate that if the size and number of leaves are less, it clearly shows the higher strength of the features. If the strength of the features is more, it will have less entropy and can classify the output data points easily leading to small tree. The vice versa is also true. Fig. 7 Decision tree with energy measure Fig. 8 Decision tree with new measure 81
13.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME The detailed accuracy like true positives (TP), False positives(FP), precision, recall, and F-measure for existing features is presented in Table 1 and that of proposed feature is presented in Table 3. From Table 1 and Table 3, one can understand that the proposed features are better by noting the TP rate values, Precision, Recall and Fmeasure, which are supposed to be high for a better feature set. These parameters are higher compared to that of existing features. Also the result is supplemented by the FP rate values which supposed to be less for a better feature and it confirms the above discussion. Table 1 Detailed accuracy by class for existing feature TP Rate 0.98 0.87 0.85 0.99 FP Rate 0.003 0.053 0.04 0.007 Precision 0.99 0.845 0.876 0.98 Recall 0.98 0.87 0.85 0.99 F-Measure 0.985 0.857 0.863 0.985 Class Good Irf Orf Iorf F-Measure 0.985 0.882 0.888 0.985 Class Good Irf Orf Iorf Table 2 Confusion matrix for existing features Good Irf Orf Iorf Good 98 1 0 0 Irf 2 87 13 1 Orf 0 12 85 0 Iorf 0 0 2 99 Table 3 Detailed accuracy by class for proposed features TP Rate 0.98 0.90 0.87 0.99 FP Rate 0.003 0.047 0.03 0.007 Precision 0.99 0.865 0.906 0.98 Recall 0.98 0.90 0.87 0.99 Table 4 Confusion matrix for proposed features Good Irf Orf Iorf Good 98 1 0 0 Irf 2 90 11 1 Orf 0 9 87 0 Iorf 0 0 2 99 The misclassification details are presented in the form of confusion matrix in Table 2 and Table 4. Before going to the discussion of the confusion matrix the way of interpretation of confusion matrix is presented here. Referring to Table 2, the first row of the confusion matrix represents the good condition. The first element in first row, i.e. 82
14.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME location (1, 1), 98 represents the number of data points that belong to the good condition and have been classified correctly as ‘good’. The second element in the first row i.e. location (1, 2), ‘2’ depicts as to how many of the good condition have been misclassified as ‘Irf’. The third element represents the number of data points that has been misclassified as ‘Orf’. The fourth element in the first row i.e. location (1, 4), ‘0’ depicts as to how many of the good condition have been misclassified as ‘Iorf’. Similarly the second row represents the ‘Irf’ condition. The second element in second row represents the correctly classified instances for ‘Irf’ condition and rest of them are misclassified details as explained earlier. Similar interpretation can be given for other elements as well. To summarize, the diagonal elements shown in the confusion matrix represents the correctly classified points and non-diagonal elements are misclassified ones. Comparing element by element wise in the confusion matrix shown in Table 2 and Table 4, one will appreciate that the proposed feature set is performing well or equal to that of existing feature set. It is to be emphasised that in none of the instances, the proposed features performed inferior to that existing features. The total classification accuracy of existing feature set is 92.5% while that of proposed feature set is 93.5%. The difference is one percentage only; however, it is an increment from 92.5% to 93.5%. In that context, it is a good improvement and can be used for fault diagnosis applications 7. CONCLUSION A comparative study of bearing faults and their classification involving a new wavelet feature set and an existing wavelet energy feature set has been carried out leading to some interesting conclusions regarding classification and fault identification. Feature definition based on the root square and average energy level of signals is central to the study here. The results show that the proposed feature set performs better than the existing feature set. This proposed feature set is much suited for practical fault diagnosis of roller bearings compared to energy definition. 8. REFERENCE [1] D. BENTLY, 1989 Bently Nevada Co., Applications Note, ANO44, pp. 2-8. Predictive maintenance through the monitoring and diagnostics of rolling element bearings. [2] N.E. Huang, Z. Shen, S.R. Long, M.L.C. Wu, H.H. Shih, Q.N. Zheng, N.C. Yen, C.C. Tung, H.H. Liu, The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proceeding of the Royal Society of London Series A—Mathematical Physical and Engineering Sciences 454 (1998) 903– 995. [3] J. Lin, L.S. Qu, Feature extraction based on Morlet wavelet and its application for mechanical fault diagnostics, Journal of Sound and Vibration 234 (2000) 135–148. [4] S. Goumas, M. Zervakis, A. Pouliezos, et al., Intelligent on-line quality control using discrete wavelet analysis features and likelihood classification, Proceedings of SPIE 4072 (2000) 500–511. [5] V. Sugumaran, V.Muralidharan, K.I. Ramachandran ,Feature selection using Decision tree and classification through Proximal Support Vector Machine for fault diagnostics of roller bearings, Mechanical Systems and Signal Processing 21(2007) ,930-942. [6] J.A.K Suykens, T. Van Gestel , J. Vandewalle ,B. De Moor, A support Vector Machine Formulation to PCA analysis and its Kernel version, ESAT-SCD-SISTA Technical Report. 83
15.
International Journal of
Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online) Volume 2, Issue 2, May- July (2011), © IAEME [7] C. Serviere, P. Fabry, 2005, Principal Component Analysis and Blind Source Separation of Modulated Sources for Electro-Mechanical Systems Diagnostic, Mechanical Systems and Signal Processing 19, pp1293–1311, 2002-68. [8] B.S. Yang, D.S. Lim, C.C. Tan, VIBEX: an expert system for vibration fault diagnosis of rotating machinery using decision tree and decision table, Expert System with Application 28 (2005) 735–742. [9] C.Z. Chen, C.T. Mo, A method for intelligent fault diagnosis of rotating machinery, Digital Signal Processing 14 (2004) 203–217. [10] D. Gayme, S. Menon, C. Ball, et al., Fault detection and diagnosis in turbine engines using fuzzy logic, in: 22nd International Conference of Digital Object Identifier, vol. 24– 26, North American Fuzzy Information Processing Society, 2003, pp. 341–346. [11] Y.G. Wang, B. Liu, Z.B. Guo, et al., Application of rough set neural network in fault diagnosing of test-launching control system of missiles, in: Proceedings of the Fifth World Congress on Intelligent Control and Automation, Hangzhou, PR China, 2004, pp. 1790–1792. [12] X.J. Xiang, J.F. Shan, F.W. Fuchs, The study of transformer failure diagnose expert system based on rough set theory, in: Power Electronics and Motion Control Conference, vol. 2, IPEMC 2004. The Fourth International, pp. 533–536. [13] Hongyu Yang, Joseph Mathew, Lin Ma, Fault Diagnosis of Rolling Element Bearings using Basis Pursuit, Mechanical Systems and Signal Processing 19 (2005) 341356. [14] I. Daubechies, Ten lectures on wavelets, CBMS-NSF Series in Applied Mathematics (SIAM), 1991. [15] J. R. Quinlan, Improved use of Continuous Attributes in C4.5, Journal of Artificial Research 4 (1996), 77-90. [16] J.W. Han, M. Kamber, Data Mining: Concepts and Techniques, Morgan Kaufmann Publishers, Los Altos, CA, 2001. [17] J.R. Quinlan, C4.5: Programs for Machine Learning, Morgan, Kaufmann, San Mateo, CA, 1993. [18] H. P. Urbach, Generalised sampling theorem for band-limited functions, Mathematical and Computer Modelling, Volume 38, Issues 1-2, July 2003, Pages 133140, ISSN 0895-7177, DOI: 10.1016/S0895-7177(03)90011-2. [19] Baoping Tang, Wenyi Liu, Tao Song, Wind turbine fault diagnosis based on Morlet wavelet transformation and Wigner-Ville distribution, Renewable Energy, Volume 35, Issue 12, December 2010, Pages 2862-2866, ISSN 0960-1481, DOI: 10.1016/j.renene.2010.05.012. [20] N. Saravanan, V.N.S. Kumar Siddabattuni, K.I. Ramachandran, A comparative study on classification of features by SVM and PSVM extracted using Morlet wavelet for fault diagnosis of spur bevel gear box, Expert Systems with Applications, Volume 35, Issue 3, October 2008, Pages 1351-1366, ISSN 0957-4174, DOI: 10.1016/j.eswa.2007.08.026. [21] Jing Lin, Liangsheng Qu, Feature Extraction Based On Morlet Wavelet and Its Application For Mechanical Fault Diagnosis, Journal of Sound and Vibration, Volume 234, Issue 1, 29 June 2000, Pages 135-148, ISSN 0022-460X, DOI: 10.1006/jsvi.2000.2864. 84
Baixar agora