SlideShare uma empresa Scribd logo
1 de 34
Baixar para ler offline
KES2014, Gdynia, Poland 
Background picture is Creative Commons by Paul Joyce 
Online Detection of Shutdown Periods 
in Chemical Plants: A Case Study 
Manuel Martín Salvadora, Bogdan Gabrysa, Indrė Žliobaitėb 
aFaculty of Science and Technology, Bournemouth University, United Kingdom 
bDept. of Information and Computer Science, Aalto University, Finland
Outline 
1. INFER Project 
2. Motivation 
3. Data Preparation 
4. Shutdown Identification 
4.1. What is a shutdown period? 
4.2. Problems and solutions 
4.3. Shutdown and startup phases 
4.4. Multi-sensor change-point detection methods 
4.5. Our method 
5. Evaluation 
6. Results 
7. Conclusion
MMoottiivvaattiioonn 
Company goal: To improve 
the production of acrylic acid. 
Acrylic acid 
molecule (C3H4O2) 
is used for plastics, 
coatings, 
adhesives, 
elastomers, floor 
polishes and paints.
MMoottiivvaattiioonn 
Company goal: To improve 
the production of acrylic acid. 
Initial status: Process monitoring is 
carried out by human operators to 
control the production. 
Concentration of acrylic acid is 
measured in the laboratory by 
taking samples every 4 hours. 
Acrylic acid 
molecule (C3H4O2) 
is used for plastics, 
coatings, 
adhesives, 
elastomers, floor 
polishes and paints. 
Picture is Creative Commons by Jm3
MMoottiivvaattiioonn 
Company goal: To improve 
the production of acrylic acid. 
Initial status: Process monitoring is 
carried out by human operators to 
control the production. 
Concentration of acrylic acid is 
measured in the laboratory by 
taking samples every 4 hours. 
Research goal: To build a soft sensor for 
predicting acrylic acid concentration every minute. 
Acrylic acid 
molecule (C3H4O2) 
is used for plastics, 
coatings, 
adhesives, 
elastomers, floor 
polishes and paints. 
Picture is Creative Commons by Jm3
Data Preparation 
The chemical plant contains hundreds of 
sensors, but only 53 of them were selected 
with the help of experts.
Data Preparation 
The chemical plant contains hundreds of 
sensors, but only 53 of them were selected 
with the help of experts. 
Collected every minute within the period from May 2010 
to November 2012 (1,268,582 instances).
Data Preparation 
The chemical plant contains hundreds of 
sensors, but only 53 of them were selected 
with the help of experts. 
Collected every minute within the period from May 2010 
to November 2012 (1,268,582 instances). 
Data pre-processing tasks: 
● Target back-shifting 
● Handling of missing values 
● Shutdown identification 
● Detecting and handling outliers 
● Steady state identification 
● Finding variable delays and synchronization 
● Adding new variables
Shutdown Identification 
Task: To robustly and accurately 
identify the shutdown periods 
even in case of multiple sensor 
failures. 
Why? To avoid the updating of 
soft sensors with irrelevant data.
What is a shutdown period? 
A shutdown period is an undefined period of 
time in which the production plant is stopped.
Problems and solutions 
Problem: There is no single variable indicating on/off.
Problems and solutions 
Problem: There is no single variable indicating on/off. 
Solution: Monitor a sensor and detect abrupt changes.
Problems and solutions 
Problem: There is no single variable indicating on/off. 
Solution: Monitor a sensor and detect abrupt changes. 
Problem: A single sensor may fail.
Problems and solutions 
Problem: There is no single variable indicating on/off. 
Solution: Monitor a sensor and detect abrupt changes. 
Problem: A single sensor may fail. 
Solution: Monitor multiple sensors at the same time.
Problems and solutions 
Problem: There is no single variable indicating on/off. 
Solution: Monitor a sensor and detect abrupt changes. 
Problem: A single sensor may fail. 
Solution: Monitor multiple sensors at the same time. 
Problem: There are delays between sensors due to 
physical location in the plant.
Problems and solutions 
Problem: There is no single variable indicating on/off. 
Solution: Monitor a sensor and detect abrupt changes. 
Problem: A single sensor may fail. 
Solution: Monitor multiple sensors at the same time. 
Problem: There are delays between sensors due to 
physical location in the plant. 
Solution: Synchronize variables (not easy) or use right 
change-point detection methods.
Shutdown and startup phases 
Only 11 flow sensors were selected because they are the most responsive.
Multi-Sensor Change-Point 
Detection Methods 
T=inf {t : st (Xt )⩾τ } 
time input 
data 
detection 
threshold 
shutdown statistic 
change-point
Multi-Sensor Change-Point 
Detection Methods 
T=inf {t : st (Xt)⩾τ } 
time input 
data 
detection 
threshold 
shutdown statistic 
change-point 
T=inf {t : st (Xt )<τ } 
startup 
change-point
Multi-Sensor Change-Point 
Detection Methods 
Memory requirements: 
Incremental Sliding window 
st (X0…t) st (Xt−r…t)
Multi-Sensor Change-Point 
Detection Methods 
Memory requirements: 
Incremental Sliding window 
st (X0…t) st (Xt−r…t) 
Sensors relevance: 
Fixed Dynamic 
st (W Xt) st (Wt Xt )
Our method 
binary 
weight for 
sensor n 
number of outliers 
in the window 
● Sliding window 
● Dynamic weights 
● Based on control charts 
Thresholds by Hampel identifier: 
Median ± 3*MAD 
Quick detection 
for shutdowns 
and deferred 
detection for 
startups
binary 
weight for 
sensor n 
2000 2200 2400 2600 2800 3000 3200 3400 
2 
0 
-2 
30 
20 
10 
number of outliers 
in the window 
● Sliding window 
● Dynamic weights 
● Based on control charts 
Thresholds by Hampel identifier: 
Median ± 3*MAD 
DATA 
2000 2200 2400 2600 2800 3000 3200 3400 
0 
SGZ 
t 
s 
t 
Our method 
Quick detection 
for shutdowns 
and deferred 
detection for 
startups
Evaluation 
5 Multi-sensor change-point detection 
methods have been evaluated: 4 based 
on likelihood and 1 on control charts. 
TV: Tartakovsky, A. & Veeravalli, V., 2008. Asymptotically Optimal Quickest Change 
Detection in Distributed Sensor Systems. Sequential Analysis, 27(4), pp.441–475 
MEI: Mei, Y., 2010. Efficient scalable schemes for monitoring a large number of data 
streams. Biometrika, 97(2), pp.419–433 
XS1, XS2: Xie, Y. & Siegmund, D., 2013. Sequential multi-sensor change-point detection. 
The Annals of Statistics, 41(2), pp.670–692 
SGZ: Salvador, M.M., Gabrys, B. & Žliobaitė, I., 2014. Online Detection of Shutdown 
Periods in Chemical Plants: A Case Study. Procedia Computer Science, 35, pp.580–588
Evaluation 
5 Multi-sensor change-point detection 
methods have been evaluated: 4 based 
on likelihood and 1 on control charts. 
TV: Tartakovsky, A. & Veeravalli, V., 2008. Asymptotically Optimal Quickest Change 
Detection in Distributed Sensor Systems. Sequential Analysis, 27(4), pp.441–475 
MEI: Mei, Y., 2010. Efficient scalable schemes for monitoring a large number of data 
streams. Biometrika, 97(2), pp.419–433 
XS1, XS2: Xie, Y. & Siegmund, D., 2013. Sequential multi-sensor change-point detection. 
The Annals of Statistics, 41(2), pp.670–692 
SGZ: Salvador, M.M., Gabrys, B. & Žliobaitė, I., 2014. Online Detection of Shutdown 
Periods in Chemical Plants: A Case Study. Procedia Computer Science, 35, pp.580–588 
44 change points in total 
Dataset split: 50% train, 50% test
Evaluation 
5 Multi-sensor change-point detection 
methods have been evaluated: 4 based 
on likelihood and 1 on control charts. 
TV: Tartakovsky, A. & Veeravalli, V., 2008. Asymptotically Optimal Quickest Change 
Detection in Distributed Sensor Systems. Sequential Analysis, 27(4), pp.441–475 
MEI: Mei, Y., 2010. Efficient scalable schemes for monitoring a large number of data 
streams. Biometrika, 97(2), pp.419–433 
XS1, XS2: Xie, Y. & Siegmund, D., 2013. Sequential multi-sensor change-point detection. 
The Annals of Statistics, 41(2), pp.670–692 
SGZ: Salvador, M.M., Gabrys, B. & Žliobaitė, I., 2014. Online Detection of Shutdown 
Periods in Chemical Plants: A Case Study. Procedia Computer Science, 35, pp.580–588 
44 change points in total 
Dataset split: 50% train, 50% test 
Goal: Detect all the change points while 
minimizing both the (positive) detection 
delay and the number of false detections.
Results 
1800 2000 2200 2400 2600 2800 3000 3200 3400 
2 
0 
-2 
-4 
DATA 
t 
1800 2000 2200 2400 2600 2800 3000 3200 3400 
40 
30 
20 
10 
1000 
500 
0 
XS1 
t 
st 
1800 2000 2200 2400 2600 2800 3000 3200 3400 
30 
20 
10 
40 
30 
20 
10 
40 
30 
20 
10 
0 
XS2 
t 
st 
1800 2000 2200 2400 2600 2800 3000 3200 3400 
0 
MEI 
t 
st 
1800 2000 2200 2400 2600 2800 3000 3200 3400 
0 
TV 
t 
st 
1800 2000 2200 2400 2600 2800 3000 3200 3400 
0 
SGZ 
t 
st 
Snapshot of the observed data and st values for r=25
Results 
20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 
80 
60 
40 
20 
0 
-20 
-40 
Window s ize 
De lay 
Startups ' me dian de lay 
TV 
MEI 
XS1 
XS2 
SGZ 
20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 
14 
12 
10 
8 
6 
4 
2 
0 
Window s ize 
Delay 
Shutdowns ' me dian de lay 
TV 
MEI 
XS1 
XS2 
SGZ 
Window size doesn't affect too much the shutdown 
detection. However, it has a considerable impact in 
the startup detection.
Results 
20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 
80 
60 
40 
20 
0 
-20 
-40 
Window s ize 
De lay 
Startups ' me dian de lay 
TV 
MEI 
XS1 
XS2 
SGZ 
20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 
14 
12 
10 
8 
6 
4 
2 
0 
Window s ize 
Delay 
Shutdowns ' me dian de lay 
TV 
MEI 
XS1 
XS2 
SGZ 
MEI is a quick detector but also raises false alarms
Results 
20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 
80 
60 
40 
20 
0 
-20 
-40 
Window s ize 
De lay 
Startups ' me dian de lay 
TV 
MEI 
XS1 
XS2 
SGZ 
20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 
14 
12 
10 
8 
6 
4 
2 
0 
Window s ize 
Delay 
Shutdowns ' me dian de lay 
TV 
MEI 
XS1 
XS2 
SGZ 
The method that presents lower positive delay both in 
shutdowns and startups while minimizing the memory 
requirements (i.e. window size) is XS1.
Results 
20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 
80 
60 
40 
20 
0 
-20 
-40 
Window s ize 
De lay 
Startups ' me dian de lay 
TV 
MEI 
XS1 
XS2 
SGZ 
20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 
14 
12 
10 
8 
6 
4 
2 
0 
Window s ize 
Delay 
Shutdowns ' me dian de lay 
TV 
MEI 
XS1 
XS2 
SGZ 
Our method has a slightly higher detection delay but 
on the other hand is robust against sensor failures.
Conclusion 
State-of-the-art multi-sensor change-point 
detection methods have been compared in 
a real case scenario which is novel in the 
literature. 
Shutdown and startups have to be treated 
differently. 
Our method is prepared for sensor failures. 
Next step is to study the impact of the 
shutdown detection on the soft sensor 
performance.
Thanks! 
Slides available in http://slideshare.net/draxus 
Source code available in 
https://github.com/draxus/online-shutdown-identification 
msalvador@bournemouth.ac.uk

Mais conteúdo relacionado

Mais procurados

SENSOR FAULT IDENTIFICATION IN COMPLEX SYSTEMS | J4RV3I12007
SENSOR FAULT IDENTIFICATION IN COMPLEX SYSTEMS | J4RV3I12007SENSOR FAULT IDENTIFICATION IN COMPLEX SYSTEMS | J4RV3I12007
SENSOR FAULT IDENTIFICATION IN COMPLEX SYSTEMS | J4RV3I12007Journal For Research
 
Evaluating Model Testing and Model Checking for Finding Requirements Violatio...
Evaluating Model Testing and Model Checking for Finding Requirements Violatio...Evaluating Model Testing and Model Checking for Finding Requirements Violatio...
Evaluating Model Testing and Model Checking for Finding Requirements Violatio...Lionel Briand
 
Testing of Cyber-Physical Systems: Diversity-driven Strategies
Testing of Cyber-Physical Systems: Diversity-driven StrategiesTesting of Cyber-Physical Systems: Diversity-driven Strategies
Testing of Cyber-Physical Systems: Diversity-driven StrategiesLionel Briand
 
Testing Machine Learning-enabled Systems: A Personal Perspective
Testing Machine Learning-enabled Systems: A Personal PerspectiveTesting Machine Learning-enabled Systems: A Personal Perspective
Testing Machine Learning-enabled Systems: A Personal PerspectiveLionel Briand
 
Practical Constraint Solving for Generating System Test Data
Practical Constraint Solving for Generating System Test DataPractical Constraint Solving for Generating System Test Data
Practical Constraint Solving for Generating System Test DataLionel Briand
 
Cutting pub subs1244 4069_al-habaibeh
Cutting pub subs1244 4069_al-habaibehCutting pub subs1244 4069_al-habaibeh
Cutting pub subs1244 4069_al-habaibehAnkanMallick1
 
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUES
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUESNEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUES
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUEScscpconf
 
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUES
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUESNEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUES
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUEScsitconf
 
AI in SE: A 25-year Journey
AI in SE: A 25-year JourneyAI in SE: A 25-year Journey
AI in SE: A 25-year JourneyLionel Briand
 
Le Bauer: Data Driven Model Development
Le Bauer:  Data Driven Model DevelopmentLe Bauer:  Data Driven Model Development
Le Bauer: Data Driven Model DevelopmentquestRCN
 
IMPLEMENTATION OF COMPACTION ALGORITHM FOR ATPG GENERATED PARTIALLY SPECIFIED...
IMPLEMENTATION OF COMPACTION ALGORITHM FOR ATPG GENERATED PARTIALLY SPECIFIED...IMPLEMENTATION OF COMPACTION ALGORITHM FOR ATPG GENERATED PARTIALLY SPECIFIED...
IMPLEMENTATION OF COMPACTION ALGORITHM FOR ATPG GENERATED PARTIALLY SPECIFIED...VLSICS Design
 
Design and construction of thermo-vision objective for the middle infrared range
Design and construction of thermo-vision objective for the middle infrared rangeDesign and construction of thermo-vision objective for the middle infrared range
Design and construction of thermo-vision objective for the middle infrared rangeEvdokiya Belina
 
Navy security contest-bigdataforsecurity
Navy security contest-bigdataforsecurityNavy security contest-bigdataforsecurity
Navy security contest-bigdataforsecuritystelligence
 
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...Lionel Briand
 
Approximation-Refinement Testing of Compute-Intensive Cyber-Physical Models: ...
Approximation-Refinement Testing of Compute-Intensive Cyber-Physical Models: ...Approximation-Refinement Testing of Compute-Intensive Cyber-Physical Models: ...
Approximation-Refinement Testing of Compute-Intensive Cyber-Physical Models: ...Lionel Briand
 
Automated Test Suite Generation for Time-Continuous Simulink Models
Automated Test Suite Generation for Time-Continuous Simulink ModelsAutomated Test Suite Generation for Time-Continuous Simulink Models
Automated Test Suite Generation for Time-Continuous Simulink ModelsLionel Briand
 
Software Analytics In Action: A Hands-on Tutorial on Mining, Analyzing, Model...
Software Analytics In Action: A Hands-on Tutorial on Mining, Analyzing, Model...Software Analytics In Action: A Hands-on Tutorial on Mining, Analyzing, Model...
Software Analytics In Action: A Hands-on Tutorial on Mining, Analyzing, Model...Chakkrit (Kla) Tantithamthavorn
 
The Impact of Class Rebalancing Techniques on the Performance and Interpretat...
The Impact of Class Rebalancing Techniques on the Performance and Interpretat...The Impact of Class Rebalancing Techniques on the Performance and Interpretat...
The Impact of Class Rebalancing Techniques on the Performance and Interpretat...Chakkrit (Kla) Tantithamthavorn
 

Mais procurados (20)

SENSOR FAULT IDENTIFICATION IN COMPLEX SYSTEMS | J4RV3I12007
SENSOR FAULT IDENTIFICATION IN COMPLEX SYSTEMS | J4RV3I12007SENSOR FAULT IDENTIFICATION IN COMPLEX SYSTEMS | J4RV3I12007
SENSOR FAULT IDENTIFICATION IN COMPLEX SYSTEMS | J4RV3I12007
 
Evaluating Model Testing and Model Checking for Finding Requirements Violatio...
Evaluating Model Testing and Model Checking for Finding Requirements Violatio...Evaluating Model Testing and Model Checking for Finding Requirements Violatio...
Evaluating Model Testing and Model Checking for Finding Requirements Violatio...
 
Testing of Cyber-Physical Systems: Diversity-driven Strategies
Testing of Cyber-Physical Systems: Diversity-driven StrategiesTesting of Cyber-Physical Systems: Diversity-driven Strategies
Testing of Cyber-Physical Systems: Diversity-driven Strategies
 
Testing Machine Learning-enabled Systems: A Personal Perspective
Testing Machine Learning-enabled Systems: A Personal PerspectiveTesting Machine Learning-enabled Systems: A Personal Perspective
Testing Machine Learning-enabled Systems: A Personal Perspective
 
Practical Constraint Solving for Generating System Test Data
Practical Constraint Solving for Generating System Test DataPractical Constraint Solving for Generating System Test Data
Practical Constraint Solving for Generating System Test Data
 
Cutting pub subs1244 4069_al-habaibeh
Cutting pub subs1244 4069_al-habaibehCutting pub subs1244 4069_al-habaibeh
Cutting pub subs1244 4069_al-habaibeh
 
Bt34433436
Bt34433436Bt34433436
Bt34433436
 
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUES
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUESNEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUES
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUES
 
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUES
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUESNEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUES
NEURAL NETWORKS WITH DECISION TREES FOR DIAGNOSIS ISSUES
 
AI in SE: A 25-year Journey
AI in SE: A 25-year JourneyAI in SE: A 25-year Journey
AI in SE: A 25-year Journey
 
Le Bauer: Data Driven Model Development
Le Bauer:  Data Driven Model DevelopmentLe Bauer:  Data Driven Model Development
Le Bauer: Data Driven Model Development
 
IMPLEMENTATION OF COMPACTION ALGORITHM FOR ATPG GENERATED PARTIALLY SPECIFIED...
IMPLEMENTATION OF COMPACTION ALGORITHM FOR ATPG GENERATED PARTIALLY SPECIFIED...IMPLEMENTATION OF COMPACTION ALGORITHM FOR ATPG GENERATED PARTIALLY SPECIFIED...
IMPLEMENTATION OF COMPACTION ALGORITHM FOR ATPG GENERATED PARTIALLY SPECIFIED...
 
Design and construction of thermo-vision objective for the middle infrared range
Design and construction of thermo-vision objective for the middle infrared rangeDesign and construction of thermo-vision objective for the middle infrared range
Design and construction of thermo-vision objective for the middle infrared range
 
Navy security contest-bigdataforsecurity
Navy security contest-bigdataforsecurityNavy security contest-bigdataforsecurity
Navy security contest-bigdataforsecurity
 
RSI_ReportPDF
RSI_ReportPDFRSI_ReportPDF
RSI_ReportPDF
 
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
 
Approximation-Refinement Testing of Compute-Intensive Cyber-Physical Models: ...
Approximation-Refinement Testing of Compute-Intensive Cyber-Physical Models: ...Approximation-Refinement Testing of Compute-Intensive Cyber-Physical Models: ...
Approximation-Refinement Testing of Compute-Intensive Cyber-Physical Models: ...
 
Automated Test Suite Generation for Time-Continuous Simulink Models
Automated Test Suite Generation for Time-Continuous Simulink ModelsAutomated Test Suite Generation for Time-Continuous Simulink Models
Automated Test Suite Generation for Time-Continuous Simulink Models
 
Software Analytics In Action: A Hands-on Tutorial on Mining, Analyzing, Model...
Software Analytics In Action: A Hands-on Tutorial on Mining, Analyzing, Model...Software Analytics In Action: A Hands-on Tutorial on Mining, Analyzing, Model...
Software Analytics In Action: A Hands-on Tutorial on Mining, Analyzing, Model...
 
The Impact of Class Rebalancing Techniques on the Performance and Interpretat...
The Impact of Class Rebalancing Techniques on the Performance and Interpretat...The Impact of Class Rebalancing Techniques on the Performance and Interpretat...
The Impact of Class Rebalancing Techniques on the Performance and Interpretat...
 

Destaque

Towards Automatic Composition of Multicomponent Predictive Systems
Towards Automatic Composition of Multicomponent Predictive SystemsTowards Automatic Composition of Multicomponent Predictive Systems
Towards Automatic Composition of Multicomponent Predictive SystemsManuel Martín
 
Chemical Engineering and its Applications (2)
Chemical Engineering and its Applications (2)Chemical Engineering and its Applications (2)
Chemical Engineering and its Applications (2)Cumali KALKAN
 
Practical Fundamentals of Chemical Engineering
Practical Fundamentals of Chemical Engineering Practical Fundamentals of Chemical Engineering
Practical Fundamentals of Chemical Engineering Living Online
 
Responsive Web Design: Clever Tips and Techniques
Responsive Web Design: Clever Tips and TechniquesResponsive Web Design: Clever Tips and Techniques
Responsive Web Design: Clever Tips and TechniquesVitaly Friedman
 
Process engineering of chemical plant
Process engineering of chemical plantProcess engineering of chemical plant
Process engineering of chemical plantPankaj Khandelwal
 
Affordances in Modern Web Design
Affordances in Modern Web DesignAffordances in Modern Web Design
Affordances in Modern Web DesignUX Booth
 

Destaque (9)

Towards Automatic Composition of Multicomponent Predictive Systems
Towards Automatic Composition of Multicomponent Predictive SystemsTowards Automatic Composition of Multicomponent Predictive Systems
Towards Automatic Composition of Multicomponent Predictive Systems
 
Facility layout
Facility layoutFacility layout
Facility layout
 
Chemical Engineering and its Applications (2)
Chemical Engineering and its Applications (2)Chemical Engineering and its Applications (2)
Chemical Engineering and its Applications (2)
 
Pom ppt
Pom pptPom ppt
Pom ppt
 
Practical Fundamentals of Chemical Engineering
Practical Fundamentals of Chemical Engineering Practical Fundamentals of Chemical Engineering
Practical Fundamentals of Chemical Engineering
 
Coca cola-plant-layout
Coca cola-plant-layoutCoca cola-plant-layout
Coca cola-plant-layout
 
Responsive Web Design: Clever Tips and Techniques
Responsive Web Design: Clever Tips and TechniquesResponsive Web Design: Clever Tips and Techniques
Responsive Web Design: Clever Tips and Techniques
 
Process engineering of chemical plant
Process engineering of chemical plantProcess engineering of chemical plant
Process engineering of chemical plant
 
Affordances in Modern Web Design
Affordances in Modern Web DesignAffordances in Modern Web Design
Affordances in Modern Web Design
 

Semelhante a Online Detection of Shutdown Periods in Chemical Plants: A Case Study

20160219 - M. Agostini - Nuove tecnologie per lo studio del DNA tumorale libe...
20160219 - M. Agostini - Nuove tecnologie per lo studio del DNA tumorale libe...20160219 - M. Agostini - Nuove tecnologie per lo studio del DNA tumorale libe...
20160219 - M. Agostini - Nuove tecnologie per lo studio del DNA tumorale libe...Roberto Scarafia
 
Veracel andritz - i io-t - online wirelless vibration project implementa...
Veracel    andritz - i io-t -  online wirelless vibration project  implementa...Veracel    andritz - i io-t -  online wirelless vibration project  implementa...
Veracel andritz - i io-t - online wirelless vibration project implementa...Jaques Valle
 
Magnetic Cable CE-EMC Test Report - Shenzhen YouCable Technology Co., Ltd
Magnetic Cable CE-EMC Test Report - Shenzhen YouCable Technology Co., LtdMagnetic Cable CE-EMC Test Report - Shenzhen YouCable Technology Co., Ltd
Magnetic Cable CE-EMC Test Report - Shenzhen YouCable Technology Co., LtdErin Yan
 
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W2 Multi - vari Studies
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W2 Multi - vari StudiesJavier Garcia - Verdugo Sanchez - Six Sigma Training - W2 Multi - vari Studies
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W2 Multi - vari StudiesJ. García - Verdugo
 
6Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)
6Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)6Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)
6Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)Bibhuti Prasad Nanda
 
Soft And Handling
Soft And HandlingSoft And Handling
Soft And Handlinghiratufail
 
Impact of novel ms ms all acquisition and processing techniques on forensic t...
Impact of novel ms ms all acquisition and processing techniques on forensic t...Impact of novel ms ms all acquisition and processing techniques on forensic t...
Impact of novel ms ms all acquisition and processing techniques on forensic t...SCIEX
 
PosterFormatRNYF(1)
PosterFormatRNYF(1)PosterFormatRNYF(1)
PosterFormatRNYF(1)Usman Khalid
 
Runlite 38mm Filament LED LM-80 test report.PDF
Runlite  38mm Filament LED  LM-80 test report.PDFRunlite  38mm Filament LED  LM-80 test report.PDF
Runlite 38mm Filament LED LM-80 test report.PDFNancy Yu
 
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W4 Monte Carlo Simulat...
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W4 Monte Carlo Simulat...Javier Garcia - Verdugo Sanchez - Six Sigma Training - W4 Monte Carlo Simulat...
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W4 Monte Carlo Simulat...J. García - Verdugo
 
Q46-84-Hydrogen-Peroxide-Measurement-System-Manual.pdf
Q46-84-Hydrogen-Peroxide-Measurement-System-Manual.pdfQ46-84-Hydrogen-Peroxide-Measurement-System-Manual.pdf
Q46-84-Hydrogen-Peroxide-Measurement-System-Manual.pdfENVIMART
 
International Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentInternational Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentIJERD Editor
 
Runlite 26mm Filament LED LM-80 test report.PDF
Runlite  26mm Filament LED  LM-80 test report.PDFRunlite  26mm Filament LED  LM-80 test report.PDF
Runlite 26mm Filament LED LM-80 test report.PDFNancy Yu
 
Runlite 67mm Filament LED LM-80 test report.PDF
Runlite  67mm Filament LED  LM-80 test report.PDFRunlite  67mm Filament LED  LM-80 test report.PDF
Runlite 67mm Filament LED LM-80 test report.PDFNancy Yu
 
Med day presentation
Med day presentationMed day presentation
Med day presentationCarsten Lund
 
LN_Series_brochure
LN_Series_brochureLN_Series_brochure
LN_Series_brochureFrank Baird
 
Sequip Ppt 2011
Sequip Ppt 2011Sequip Ppt 2011
Sequip Ppt 2011Sequip
 
Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)
Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)
Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)Bibhuti Prasad Nanda
 

Semelhante a Online Detection of Shutdown Periods in Chemical Plants: A Case Study (20)

20160219 - M. Agostini - Nuove tecnologie per lo studio del DNA tumorale libe...
20160219 - M. Agostini - Nuove tecnologie per lo studio del DNA tumorale libe...20160219 - M. Agostini - Nuove tecnologie per lo studio del DNA tumorale libe...
20160219 - M. Agostini - Nuove tecnologie per lo studio del DNA tumorale libe...
 
Veracel andritz - i io-t - online wirelless vibration project implementa...
Veracel    andritz - i io-t -  online wirelless vibration project  implementa...Veracel    andritz - i io-t -  online wirelless vibration project  implementa...
Veracel andritz - i io-t - online wirelless vibration project implementa...
 
Magnetic Cable CE-EMC Test Report - Shenzhen YouCable Technology Co., Ltd
Magnetic Cable CE-EMC Test Report - Shenzhen YouCable Technology Co., LtdMagnetic Cable CE-EMC Test Report - Shenzhen YouCable Technology Co., Ltd
Magnetic Cable CE-EMC Test Report - Shenzhen YouCable Technology Co., Ltd
 
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W2 Multi - vari Studies
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W2 Multi - vari StudiesJavier Garcia - Verdugo Sanchez - Six Sigma Training - W2 Multi - vari Studies
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W2 Multi - vari Studies
 
6Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)
6Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)6Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)
6Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)
 
Soft And Handling
Soft And HandlingSoft And Handling
Soft And Handling
 
Reliable On-Line sensing
Reliable On-Line sensingReliable On-Line sensing
Reliable On-Line sensing
 
Impact of novel ms ms all acquisition and processing techniques on forensic t...
Impact of novel ms ms all acquisition and processing techniques on forensic t...Impact of novel ms ms all acquisition and processing techniques on forensic t...
Impact of novel ms ms all acquisition and processing techniques on forensic t...
 
PosterFormatRNYF(1)
PosterFormatRNYF(1)PosterFormatRNYF(1)
PosterFormatRNYF(1)
 
Runlite 38mm Filament LED LM-80 test report.PDF
Runlite  38mm Filament LED  LM-80 test report.PDFRunlite  38mm Filament LED  LM-80 test report.PDF
Runlite 38mm Filament LED LM-80 test report.PDF
 
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W4 Monte Carlo Simulat...
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W4 Monte Carlo Simulat...Javier Garcia - Verdugo Sanchez - Six Sigma Training - W4 Monte Carlo Simulat...
Javier Garcia - Verdugo Sanchez - Six Sigma Training - W4 Monte Carlo Simulat...
 
Noninvesive Lie Detection
Noninvesive Lie DetectionNoninvesive Lie Detection
Noninvesive Lie Detection
 
Q46-84-Hydrogen-Peroxide-Measurement-System-Manual.pdf
Q46-84-Hydrogen-Peroxide-Measurement-System-Manual.pdfQ46-84-Hydrogen-Peroxide-Measurement-System-Manual.pdf
Q46-84-Hydrogen-Peroxide-Measurement-System-Manual.pdf
 
International Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentInternational Journal of Engineering Research and Development
International Journal of Engineering Research and Development
 
Runlite 26mm Filament LED LM-80 test report.PDF
Runlite  26mm Filament LED  LM-80 test report.PDFRunlite  26mm Filament LED  LM-80 test report.PDF
Runlite 26mm Filament LED LM-80 test report.PDF
 
Runlite 67mm Filament LED LM-80 test report.PDF
Runlite  67mm Filament LED  LM-80 test report.PDFRunlite  67mm Filament LED  LM-80 test report.PDF
Runlite 67mm Filament LED LM-80 test report.PDF
 
Med day presentation
Med day presentationMed day presentation
Med day presentation
 
LN_Series_brochure
LN_Series_brochureLN_Series_brochure
LN_Series_brochure
 
Sequip Ppt 2011
Sequip Ppt 2011Sequip Ppt 2011
Sequip Ppt 2011
 
Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)
Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)
Six sigma-in-measurement-systems-evaluating-the-hidden-factory (2)
 

Mais de Manuel Martín

Automatizando el aprendizaje basado en datos
Automatizando el aprendizaje basado en datosAutomatizando el aprendizaje basado en datos
Automatizando el aprendizaje basado en datosManuel Martín
 
Modelling Multi-Component Predictive Systems as Petri Nets
Modelling Multi-Component Predictive Systems as Petri NetsModelling Multi-Component Predictive Systems as Petri Nets
Modelling Multi-Component Predictive Systems as Petri NetsManuel Martín
 
Brand engagement with mobile gamification apps from a developer perspective
Brand engagement with mobile gamification apps from a developer perspectiveBrand engagement with mobile gamification apps from a developer perspective
Brand engagement with mobile gamification apps from a developer perspectiveManuel Martín
 
Effects of change propagation resulting from adaptive preprocessing in multic...
Effects of change propagation resulting from adaptive preprocessing in multic...Effects of change propagation resulting from adaptive preprocessing in multic...
Effects of change propagation resulting from adaptive preprocessing in multic...Manuel Martín
 
Improving transport timetables usability for mobile devices
Improving transport timetables usability for mobile devicesImproving transport timetables usability for mobile devices
Improving transport timetables usability for mobile devicesManuel Martín
 
Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Manuel Martín
 
From sensor readings to prediction: on the process of developing practical so...
From sensor readings to prediction: on the process of developing practical so...From sensor readings to prediction: on the process of developing practical so...
From sensor readings to prediction: on the process of developing practical so...Manuel Martín
 
Quick presentation for the OpenML workshop in Eindhoven 2014
Quick presentation for the OpenML workshop in Eindhoven 2014Quick presentation for the OpenML workshop in Eindhoven 2014
Quick presentation for the OpenML workshop in Eindhoven 2014Manuel Martín
 
Artificial Intelligence for Automating Data Analysis
Artificial Intelligence for Automating Data AnalysisArtificial Intelligence for Automating Data Analysis
Artificial Intelligence for Automating Data AnalysisManuel Martín
 
Handling concept drift in data stream mining
Handling concept drift in data stream miningHandling concept drift in data stream mining
Handling concept drift in data stream miningManuel Martín
 
Minería de secuencias de datos
Minería de secuencias de datosMinería de secuencias de datos
Minería de secuencias de datosManuel Martín
 
Minería de secuencias de datos
Minería de secuencias de datosMinería de secuencias de datos
Minería de secuencias de datosManuel Martín
 
AndalucíaPeople: Un sistema de recomendación para sitios de ocio de Andalucía
AndalucíaPeople: Un sistema de recomendación para sitios de ocio de AndalucíaAndalucíaPeople: Un sistema de recomendación para sitios de ocio de Andalucía
AndalucíaPeople: Un sistema de recomendación para sitios de ocio de AndalucíaManuel Martín
 
Operaciones Colectivas en MPI
Operaciones Colectivas en MPIOperaciones Colectivas en MPI
Operaciones Colectivas en MPIManuel Martín
 
Introducción a GNU/Linux
Introducción a GNU/LinuxIntroducción a GNU/Linux
Introducción a GNU/LinuxManuel Martín
 
Presentación Día de la Libertad del Software 2011
Presentación Día de la Libertad del Software 2011Presentación Día de la Libertad del Software 2011
Presentación Día de la Libertad del Software 2011Manuel Martín
 
Presentacion Taller de Introducción a Linux SFD2010
Presentacion Taller de Introducción a Linux SFD2010Presentacion Taller de Introducción a Linux SFD2010
Presentacion Taller de Introducción a Linux SFD2010Manuel Martín
 
Presentación Gnome 3.0 en Granada
Presentación Gnome 3.0 en GranadaPresentación Gnome 3.0 en Granada
Presentación Gnome 3.0 en GranadaManuel Martín
 

Mais de Manuel Martín (20)

Hogar (Des)Conectado
Hogar (Des)ConectadoHogar (Des)Conectado
Hogar (Des)Conectado
 
Automatizando el aprendizaje basado en datos
Automatizando el aprendizaje basado en datosAutomatizando el aprendizaje basado en datos
Automatizando el aprendizaje basado en datos
 
Modelling Multi-Component Predictive Systems as Petri Nets
Modelling Multi-Component Predictive Systems as Petri NetsModelling Multi-Component Predictive Systems as Petri Nets
Modelling Multi-Component Predictive Systems as Petri Nets
 
Brand engagement with mobile gamification apps from a developer perspective
Brand engagement with mobile gamification apps from a developer perspectiveBrand engagement with mobile gamification apps from a developer perspective
Brand engagement with mobile gamification apps from a developer perspective
 
Effects of change propagation resulting from adaptive preprocessing in multic...
Effects of change propagation resulting from adaptive preprocessing in multic...Effects of change propagation resulting from adaptive preprocessing in multic...
Effects of change propagation resulting from adaptive preprocessing in multic...
 
Improving transport timetables usability for mobile devices
Improving transport timetables usability for mobile devicesImproving transport timetables usability for mobile devices
Improving transport timetables usability for mobile devices
 
Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?
 
From sensor readings to prediction: on the process of developing practical so...
From sensor readings to prediction: on the process of developing practical so...From sensor readings to prediction: on the process of developing practical so...
From sensor readings to prediction: on the process of developing practical so...
 
Quick presentation for the OpenML workshop in Eindhoven 2014
Quick presentation for the OpenML workshop in Eindhoven 2014Quick presentation for the OpenML workshop in Eindhoven 2014
Quick presentation for the OpenML workshop in Eindhoven 2014
 
Artificial Intelligence for Automating Data Analysis
Artificial Intelligence for Automating Data AnalysisArtificial Intelligence for Automating Data Analysis
Artificial Intelligence for Automating Data Analysis
 
Handling concept drift in data stream mining
Handling concept drift in data stream miningHandling concept drift in data stream mining
Handling concept drift in data stream mining
 
Minería de secuencias de datos
Minería de secuencias de datosMinería de secuencias de datos
Minería de secuencias de datos
 
Minería de secuencias de datos
Minería de secuencias de datosMinería de secuencias de datos
Minería de secuencias de datos
 
AndalucíaPeople: Un sistema de recomendación para sitios de ocio de Andalucía
AndalucíaPeople: Un sistema de recomendación para sitios de ocio de AndalucíaAndalucíaPeople: Un sistema de recomendación para sitios de ocio de Andalucía
AndalucíaPeople: Un sistema de recomendación para sitios de ocio de Andalucía
 
Decompiladores
DecompiladoresDecompiladores
Decompiladores
 
Operaciones Colectivas en MPI
Operaciones Colectivas en MPIOperaciones Colectivas en MPI
Operaciones Colectivas en MPI
 
Introducción a GNU/Linux
Introducción a GNU/LinuxIntroducción a GNU/Linux
Introducción a GNU/Linux
 
Presentación Día de la Libertad del Software 2011
Presentación Día de la Libertad del Software 2011Presentación Día de la Libertad del Software 2011
Presentación Día de la Libertad del Software 2011
 
Presentacion Taller de Introducción a Linux SFD2010
Presentacion Taller de Introducción a Linux SFD2010Presentacion Taller de Introducción a Linux SFD2010
Presentacion Taller de Introducción a Linux SFD2010
 
Presentación Gnome 3.0 en Granada
Presentación Gnome 3.0 en GranadaPresentación Gnome 3.0 en Granada
Presentación Gnome 3.0 en Granada
 

Último

ALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptxALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptxolyaivanovalion
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023ymrp368
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% SecurePooja Nehwal
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...shambhavirathore45
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxolyaivanovalion
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxolyaivanovalion
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxfirstjob4
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Delhi Call girls
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFxolyaivanovalion
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...amitlee9823
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfRachmat Ramadhan H
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Delhi Call girls
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAroojKhan71
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfLars Albertsson
 

Último (20)

ALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptxALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptx
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
 
Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptx
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdf
 

Online Detection of Shutdown Periods in Chemical Plants: A Case Study

  • 1. KES2014, Gdynia, Poland Background picture is Creative Commons by Paul Joyce Online Detection of Shutdown Periods in Chemical Plants: A Case Study Manuel Martín Salvadora, Bogdan Gabrysa, Indrė Žliobaitėb aFaculty of Science and Technology, Bournemouth University, United Kingdom bDept. of Information and Computer Science, Aalto University, Finland
  • 2. Outline 1. INFER Project 2. Motivation 3. Data Preparation 4. Shutdown Identification 4.1. What is a shutdown period? 4.2. Problems and solutions 4.3. Shutdown and startup phases 4.4. Multi-sensor change-point detection methods 4.5. Our method 5. Evaluation 6. Results 7. Conclusion
  • 3.
  • 4. MMoottiivvaattiioonn Company goal: To improve the production of acrylic acid. Acrylic acid molecule (C3H4O2) is used for plastics, coatings, adhesives, elastomers, floor polishes and paints.
  • 5. MMoottiivvaattiioonn Company goal: To improve the production of acrylic acid. Initial status: Process monitoring is carried out by human operators to control the production. Concentration of acrylic acid is measured in the laboratory by taking samples every 4 hours. Acrylic acid molecule (C3H4O2) is used for plastics, coatings, adhesives, elastomers, floor polishes and paints. Picture is Creative Commons by Jm3
  • 6. MMoottiivvaattiioonn Company goal: To improve the production of acrylic acid. Initial status: Process monitoring is carried out by human operators to control the production. Concentration of acrylic acid is measured in the laboratory by taking samples every 4 hours. Research goal: To build a soft sensor for predicting acrylic acid concentration every minute. Acrylic acid molecule (C3H4O2) is used for plastics, coatings, adhesives, elastomers, floor polishes and paints. Picture is Creative Commons by Jm3
  • 7. Data Preparation The chemical plant contains hundreds of sensors, but only 53 of them were selected with the help of experts.
  • 8. Data Preparation The chemical plant contains hundreds of sensors, but only 53 of them were selected with the help of experts. Collected every minute within the period from May 2010 to November 2012 (1,268,582 instances).
  • 9. Data Preparation The chemical plant contains hundreds of sensors, but only 53 of them were selected with the help of experts. Collected every minute within the period from May 2010 to November 2012 (1,268,582 instances). Data pre-processing tasks: ● Target back-shifting ● Handling of missing values ● Shutdown identification ● Detecting and handling outliers ● Steady state identification ● Finding variable delays and synchronization ● Adding new variables
  • 10. Shutdown Identification Task: To robustly and accurately identify the shutdown periods even in case of multiple sensor failures. Why? To avoid the updating of soft sensors with irrelevant data.
  • 11. What is a shutdown period? A shutdown period is an undefined period of time in which the production plant is stopped.
  • 12. Problems and solutions Problem: There is no single variable indicating on/off.
  • 13. Problems and solutions Problem: There is no single variable indicating on/off. Solution: Monitor a sensor and detect abrupt changes.
  • 14. Problems and solutions Problem: There is no single variable indicating on/off. Solution: Monitor a sensor and detect abrupt changes. Problem: A single sensor may fail.
  • 15. Problems and solutions Problem: There is no single variable indicating on/off. Solution: Monitor a sensor and detect abrupt changes. Problem: A single sensor may fail. Solution: Monitor multiple sensors at the same time.
  • 16. Problems and solutions Problem: There is no single variable indicating on/off. Solution: Monitor a sensor and detect abrupt changes. Problem: A single sensor may fail. Solution: Monitor multiple sensors at the same time. Problem: There are delays between sensors due to physical location in the plant.
  • 17. Problems and solutions Problem: There is no single variable indicating on/off. Solution: Monitor a sensor and detect abrupt changes. Problem: A single sensor may fail. Solution: Monitor multiple sensors at the same time. Problem: There are delays between sensors due to physical location in the plant. Solution: Synchronize variables (not easy) or use right change-point detection methods.
  • 18. Shutdown and startup phases Only 11 flow sensors were selected because they are the most responsive.
  • 19. Multi-Sensor Change-Point Detection Methods T=inf {t : st (Xt )⩾τ } time input data detection threshold shutdown statistic change-point
  • 20. Multi-Sensor Change-Point Detection Methods T=inf {t : st (Xt)⩾τ } time input data detection threshold shutdown statistic change-point T=inf {t : st (Xt )<τ } startup change-point
  • 21. Multi-Sensor Change-Point Detection Methods Memory requirements: Incremental Sliding window st (X0…t) st (Xt−r…t)
  • 22. Multi-Sensor Change-Point Detection Methods Memory requirements: Incremental Sliding window st (X0…t) st (Xt−r…t) Sensors relevance: Fixed Dynamic st (W Xt) st (Wt Xt )
  • 23. Our method binary weight for sensor n number of outliers in the window ● Sliding window ● Dynamic weights ● Based on control charts Thresholds by Hampel identifier: Median ± 3*MAD Quick detection for shutdowns and deferred detection for startups
  • 24. binary weight for sensor n 2000 2200 2400 2600 2800 3000 3200 3400 2 0 -2 30 20 10 number of outliers in the window ● Sliding window ● Dynamic weights ● Based on control charts Thresholds by Hampel identifier: Median ± 3*MAD DATA 2000 2200 2400 2600 2800 3000 3200 3400 0 SGZ t s t Our method Quick detection for shutdowns and deferred detection for startups
  • 25. Evaluation 5 Multi-sensor change-point detection methods have been evaluated: 4 based on likelihood and 1 on control charts. TV: Tartakovsky, A. & Veeravalli, V., 2008. Asymptotically Optimal Quickest Change Detection in Distributed Sensor Systems. Sequential Analysis, 27(4), pp.441–475 MEI: Mei, Y., 2010. Efficient scalable schemes for monitoring a large number of data streams. Biometrika, 97(2), pp.419–433 XS1, XS2: Xie, Y. & Siegmund, D., 2013. Sequential multi-sensor change-point detection. The Annals of Statistics, 41(2), pp.670–692 SGZ: Salvador, M.M., Gabrys, B. & Žliobaitė, I., 2014. Online Detection of Shutdown Periods in Chemical Plants: A Case Study. Procedia Computer Science, 35, pp.580–588
  • 26. Evaluation 5 Multi-sensor change-point detection methods have been evaluated: 4 based on likelihood and 1 on control charts. TV: Tartakovsky, A. & Veeravalli, V., 2008. Asymptotically Optimal Quickest Change Detection in Distributed Sensor Systems. Sequential Analysis, 27(4), pp.441–475 MEI: Mei, Y., 2010. Efficient scalable schemes for monitoring a large number of data streams. Biometrika, 97(2), pp.419–433 XS1, XS2: Xie, Y. & Siegmund, D., 2013. Sequential multi-sensor change-point detection. The Annals of Statistics, 41(2), pp.670–692 SGZ: Salvador, M.M., Gabrys, B. & Žliobaitė, I., 2014. Online Detection of Shutdown Periods in Chemical Plants: A Case Study. Procedia Computer Science, 35, pp.580–588 44 change points in total Dataset split: 50% train, 50% test
  • 27. Evaluation 5 Multi-sensor change-point detection methods have been evaluated: 4 based on likelihood and 1 on control charts. TV: Tartakovsky, A. & Veeravalli, V., 2008. Asymptotically Optimal Quickest Change Detection in Distributed Sensor Systems. Sequential Analysis, 27(4), pp.441–475 MEI: Mei, Y., 2010. Efficient scalable schemes for monitoring a large number of data streams. Biometrika, 97(2), pp.419–433 XS1, XS2: Xie, Y. & Siegmund, D., 2013. Sequential multi-sensor change-point detection. The Annals of Statistics, 41(2), pp.670–692 SGZ: Salvador, M.M., Gabrys, B. & Žliobaitė, I., 2014. Online Detection of Shutdown Periods in Chemical Plants: A Case Study. Procedia Computer Science, 35, pp.580–588 44 change points in total Dataset split: 50% train, 50% test Goal: Detect all the change points while minimizing both the (positive) detection delay and the number of false detections.
  • 28. Results 1800 2000 2200 2400 2600 2800 3000 3200 3400 2 0 -2 -4 DATA t 1800 2000 2200 2400 2600 2800 3000 3200 3400 40 30 20 10 1000 500 0 XS1 t st 1800 2000 2200 2400 2600 2800 3000 3200 3400 30 20 10 40 30 20 10 40 30 20 10 0 XS2 t st 1800 2000 2200 2400 2600 2800 3000 3200 3400 0 MEI t st 1800 2000 2200 2400 2600 2800 3000 3200 3400 0 TV t st 1800 2000 2200 2400 2600 2800 3000 3200 3400 0 SGZ t st Snapshot of the observed data and st values for r=25
  • 29. Results 20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 80 60 40 20 0 -20 -40 Window s ize De lay Startups ' me dian de lay TV MEI XS1 XS2 SGZ 20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 14 12 10 8 6 4 2 0 Window s ize Delay Shutdowns ' me dian de lay TV MEI XS1 XS2 SGZ Window size doesn't affect too much the shutdown detection. However, it has a considerable impact in the startup detection.
  • 30. Results 20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 80 60 40 20 0 -20 -40 Window s ize De lay Startups ' me dian de lay TV MEI XS1 XS2 SGZ 20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 14 12 10 8 6 4 2 0 Window s ize Delay Shutdowns ' me dian de lay TV MEI XS1 XS2 SGZ MEI is a quick detector but also raises false alarms
  • 31. Results 20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 80 60 40 20 0 -20 -40 Window s ize De lay Startups ' me dian de lay TV MEI XS1 XS2 SGZ 20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 14 12 10 8 6 4 2 0 Window s ize Delay Shutdowns ' me dian de lay TV MEI XS1 XS2 SGZ The method that presents lower positive delay both in shutdowns and startups while minimizing the memory requirements (i.e. window size) is XS1.
  • 32. Results 20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 80 60 40 20 0 -20 -40 Window s ize De lay Startups ' me dian de lay TV MEI XS1 XS2 SGZ 20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 14 12 10 8 6 4 2 0 Window s ize Delay Shutdowns ' me dian de lay TV MEI XS1 XS2 SGZ Our method has a slightly higher detection delay but on the other hand is robust against sensor failures.
  • 33. Conclusion State-of-the-art multi-sensor change-point detection methods have been compared in a real case scenario which is novel in the literature. Shutdown and startups have to be treated differently. Our method is prepared for sensor failures. Next step is to study the impact of the shutdown detection on the soft sensor performance.
  • 34. Thanks! Slides available in http://slideshare.net/draxus Source code available in https://github.com/draxus/online-shutdown-identification msalvador@bournemouth.ac.uk