SlideShare uma empresa Scribd logo
1 de 47
Baixar para ler offline
Slide | 1Slide | 1
HOWDATAANALYTICSCANPROVIDEINTERESTING
NEWPOSSIBILITIESFORTHEFOODINDUSTRY
PhilippeMack
Slide | 2Slide | 2
Industrial internet of things
Cloud computing
Factory 4.0
Predictive Analytics
Big Data
In Memory
Hadoop DATA Lake
Slide | 3Slide | 3
Slide | 4Slide | 4
Slide | 5Slide | 5
MB
19555
Slide | 6Slide | 6
2015
5.000MB
Slide | 7Slide | 7
Connection
Transmission
Storage
Analytics
… as a service
Focus on your business…
not on complex infrastructure
Quick starts…
quick wins!
Slide | 8Slide | 8
ABOUT US
Specialised in predictive analytics solutions for industrial
applications (Yield, productivity, quality, energy optimisation, predictive
maintenance) – More than 10 years of experience
Our distinctiveness
!  Business minded consultants
!  Software technology
•  DATAmaestro: cloud based data mining software
•  DATAserver: automatic and systematic data extraction, preparation and
merging platform
!  Dedicated vertical applications
•  ENERGYmaestro: energy management solution based on data analytics and
operator participation
•  Wintell : performance tracking and predictive maintenance for wind turbines
•  FINDIT : batch tracking and performance management for aquaculture
Slide | 9Slide | 9
WHERE HAS IT BEEN APPLIED ?
Type of project Impact
Increase yield and reduce
scrap by 5%
Predict in real-time the quality of
the steel to increase yield and
reduce scrap
Analyze drilling operation
data to increase ROP
Faster drilling and less
downtimes due to reduced
well head failure
E&P drilling
operations
Predict and understand root
causes of breaks in paper
sheets
Paper making Reduce shutdowns and
increases OEE by 5%
Chemicals Optimize use of energy in
exothermic processes
Reduce energy costs by 15%
Industry
Steel
Analyse the quality of the end
products using advanced
analytics
Improve quality and find the
root causes
Carbon
technology
Electrical networks Forecast dynamic security of
transmission grid
Avoid costly curtailment of
loads or generations
Slide | 10Slide | 10
BUT WHAT
ABOUT
ADVANCED
DATA ANALYTICS
for the!
FOOD INDUSTRY?!
Slide | 11Slide | 11
for windturbines
Precision
farming
Slide | 12Slide | 12
predictive
maintenance
for windturbines
WINTELL
energy
management
system
based on
analytics,
management &
people!
BIG DATA
ANALYTICS !
in utilities to
improve
operations
forthe
FindIT
continuous
improvement
platform
fish production
industry
Slide | 13Slide | 13
Slide | 14Slide | 14
a brief 
history!
Slide | 15Slide | 15
•  FineFish project
•  Data initially collected in XLS sheet (a lot of error, many
inconsistencies, difficult to process to compute basic
statistics
•  Development of a web app prototype to gather data in
order to monitor malformation in fish
•  Evangelization on big data and advanced analytics
capabilities
•  Interest was raised in the market
•  A real need was identified to collect and centralize data
from farm operation to
•  Increase fish quality
•  Increase farm performance in general
A LITTLE HISTORY ON THE PROJECT
Slide | 16Slide | 16
THE PARTNERS
Slide | 17Slide | 17
•  Enter and store production
data in the cloud (web
based)
•  Benchmark own data, and
against the other producers
(anonymised data)
•  Use data mining to analyse
big data and extract new
knowledge, validate
hypothesis
KPI
Benchmark
Data entry Advanced
Analytics
User
hatchery A
User
hatchery B
User
hatchery C
Webinterface
Webinterface
Webinterface
THE TOOL
Slide | 18Slide | 18
Slide | 19Slide | 19
RECORDS AND TRACK OPERATION CHANGES AND
ACTIVITIES:
MEASUREMENTS, FEEDS, OBSERVATIONS
Slide | 20Slide | 20
TRACK MOVEMENTS OF FISHES : IMPORTANT TO
LINK MONITORING WITH BATCH TRACKING
Slide | 21Slide | 21
BROWSE THE BATCHES OF PRODUCTION
Slide | 22Slide | 22
KEY PERFORMANCE
CALCULATION, REPORTING
AND DASHBOARDING
Slide | 23Slide | 23
ANALYTICS FOR
QUANTITATIVE ROOT
CAUSE ANALYSIS,
PREDICTION,
OPTIMIZATION…
Slide | 24Slide | 24
•  Average SGR from start feeding
to smolt :
–  Higher than 2.29 is good (green)
–  Lower than 2.29 is bad (red)
Decision tree analysis of
Water parameters vs. KPI_SGR
THE SALMON DEMON FARM
Slide | 25Slide | 25
•  Automatic KPI calculation and reporting
•  Advanced KPI management to predict, diagnose,
optimise productivity and reduce mortality and increase
quality
•  State of the art information technology: big data,
statistics, predictive analytics with machine learning
•  Based on successful experiences in other industries
•  KISS principle
•  Secured software as a service for your tablet, your PC
FEATURES
Slide | 26Slide | 26
168.000€
energy savings
in UHT milk production
process optimization
Slide | 27Slide | 27
SAVING THROUGH OPERATIONAL MANAGEMENT
Procurement
Investments
Operations
Slide | 28Slide | 28
A PEOPLE MINDED APPROACH
Analytics People
•  Gap analysis
•  Cost driver diagnostic
•  Root cause analysis
•  Optimised targets
•  KPI
•  Workshops
•  Training
•  Monitoring
•  Culture
A continuous improvement system based on:
Slide | 29Slide | 29
APPROACH
Process &
business
understanding
Workshops Training & reviewAdvanced
analytics &
implementation
ENERGYmaestro
1 - 2 weeks 4 - 6 weeks 4 - 6 weeks 2 - 3 weeks
Steam
extraction <
maximum
Capacity of
steam
extraction
Steam
extraction down
Maintenance –
waiting for
spare parts
Sulfine plant is
not in operation
SO2 alarm
Lack of sulfur
There is no
steam for the
turbine
Capacity of LP
steam network
Low pressure
boilers at P2
HP vers LP
Boiler BERI
Boiler SO2
Demand/losses
Consumers
Start-up valves
Overall
management
Training
Communication
& coordination
Gap analysis
1 – 2 weeks
2012
11
Taux de soutirage
- moyenne
du mois
95 %
Ouverture
vannes démarrage
11 h
Cible =
2 meilleurs
mois + 5t/h
90%
HP - vanne SO2
# heures
1 h
Gain (pertes)
par rapport
à la cible du mois
1.490 t
BP - vanne HRS
# heures
10 h
Débit moyen soutirage
32,3 t/h
Uptime
96 %
Tonnes
excès BERI
5,7 t/h
Taux de soutirage
durant uptime
97 %
Tonnes
excès chaudières
P2
0,9 t/h
Gains vs taux de 75% - 2011
5.074 tPEPITE - RAPPORT
MENSUEL
Année
Mois
0
10
20
30
40
50
1/nov.
2/nov.
3/nov.
5/nov.
6/nov.
7/nov.
9/nov.
10/nov.
11/nov.
13/nov.
14/nov.
15/nov.
17/nov.
18/nov.
19/nov.
21/nov.
22/nov.
23/nov.
25/nov.
26/nov.
27/nov.
29/nov.
30/nov.
0
10
20
30
40
0
5
10
15
20
25
30
35
40
45
0
200
400
600
800
1000
1200
1400
1600
Somme
cumulative
du gain / perte par rapport
à la cible
2
4
6
8
10
12
14
16
soufre sulfine
soufre sulfine
Commentaires
: ............................
............................
............................
............................
............................
............................
............................
............................
.............
:……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
…
……………………
……………………
……………………
……………………
……………………
…………………...
:……………………
……………………
……………………
……………………
……………………
……………………
…
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
…………………...
:…
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
…
……………………
……………………
……………………
……………………
……………………
………………...:…
……………………
……………………
……………………
……………………
……………………
……………………
…
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
……………………
………………......
......
..
FLASH ANALYSIS
Slide | 30Slide | 30
ENERGY SPECIFIC CONS. (KWH/T MILK) UHT
Slide | 31Slide | 31
MOST IMPORTANT PARAMETERS TO EXPLAIN
GLOBAL CONSUMPTION
Slide | 32Slide | 32
SPECIFIC STEAM CONSUMPTION AT UHT
Target 15T/m3 milk
Slide | 33Slide | 33
STEAM SAVINGS ESTIMATES @UHT
6000 t in 6 months
Slide | 34Slide | 34
•  Process improvements
•  12 000 T in 1 year
•  168.000 EUR savings
•  Operator involvement
•  Sustainable energy culture
•  No capital investment
BENEFITS
Slide | 35Slide | 35
advanced
imaging for
automated
quality control
Slide | 36Slide | 36
OK
OK
OK
Ciabatta tomate
KO
KO
“DEFECTS” ON BREAD DIFFICULT TO DETECTS

Slide | 37Slide | 37
IMAGE COLLECTION
•  Collect Images
Slide | 38Slide | 38
CREATE A LIBRARY OF DEFECTS
Slide | 39Slide | 39
TRAIN COMPUTER TO AUTOMATE ANNOTATION &
CLASSIFICATION

Slide | 40Slide | 40
KEY BENEFITS


•  Faster and more reliable defect detection
•  React faster to correct problems
•  Identify parameters that impact quality crisis
•  Mix image information with other sensors data to
improve performance of process operations
•  Update easily annotators with newer images
Slide | 41Slide | 41
advanced
imaging for
automated
quality control 
$ 27.500
ANNUAL ENERGY
SAVINGS 
for a brewery
packaging line
Slide | 42Slide | 42
CORRELATION MATRIX GIVES RELATIONSHIP
BETWEEN PROCESS VARIABLES
Slide | 43Slide | 43
MAIN VARIABILITIES: SEASON AND PRODUCTION
LEVEL
Slide | 44Slide | 44
SIGNIFICANT VARIABILITY OF STEAM USE PER DAY
CLEAR IMPACT OF PRODUCTION SHUTDOWN
Slide | 45Slide | 45
DECISION TREE EXPLAINS THE DIFFERENCE
BETWEEN LEVELS OF STEAM USE (LOW-MED-HIGH)
levels are defined based
on distribution
CO2 filler > 3180 kg
leads to high use
Slide | 46Slide | 46
•  Process improvements
•  146 MWh energy: - 7%
•  2145 T steam: - 11%
•  28 200 m3 water: - 15%
•  EUR 27.500 direct savings annually
•  No CAPEX
BENEFITS
Slide | 47Slide | 47
Thank you !
ph.mack@pepite.be
phone: 0477 380 005
www.pepite.be

Mais conteúdo relacionado

Mais procurados

ARCHIBUS Government Solutions
ARCHIBUS Government SolutionsARCHIBUS Government Solutions
ARCHIBUS Government Solutions
Michael Willette
 
ARCHIBUS Delivering Business Intelligence
ARCHIBUS Delivering Business IntelligenceARCHIBUS Delivering Business Intelligence
ARCHIBUS Delivering Business Intelligence
Michael Willette
 

Mais procurados (20)

Akili Upstream Oil & Gas Data Conversion Solution
Akili Upstream Oil & Gas Data Conversion SolutionAkili Upstream Oil & Gas Data Conversion Solution
Akili Upstream Oil & Gas Data Conversion Solution
 
The Digital Twin For Production Optimization
The Digital Twin For Production OptimizationThe Digital Twin For Production Optimization
The Digital Twin For Production Optimization
 
SM Energy and Akili Discuss How to Accelerate Your New Asset Assimilation
SM Energy and Akili Discuss How to Accelerate Your New Asset AssimilationSM Energy and Akili Discuss How to Accelerate Your New Asset Assimilation
SM Energy and Akili Discuss How to Accelerate Your New Asset Assimilation
 
The Briefcase Cluster – Enabling Big Data Everywhere
The Briefcase Cluster – Enabling Big Data Everywhere The Briefcase Cluster – Enabling Big Data Everywhere
The Briefcase Cluster – Enabling Big Data Everywhere
 
Dish Supply Chain: Journey to Collaborative Planning
Dish Supply Chain: Journey to Collaborative PlanningDish Supply Chain: Journey to Collaborative Planning
Dish Supply Chain: Journey to Collaborative Planning
 
AVEVA presents at the Rice Global Forum 2017
AVEVA presents at the Rice Global Forum 2017AVEVA presents at the Rice Global Forum 2017
AVEVA presents at the Rice Global Forum 2017
 
Data-Centric Approach for Project Delivery
Data-Centric Approach for Project DeliveryData-Centric Approach for Project Delivery
Data-Centric Approach for Project Delivery
 
The End of Handover by AVEVA & Fiatech
The End of Handover by AVEVA & FiatechThe End of Handover by AVEVA & Fiatech
The End of Handover by AVEVA & Fiatech
 
Digital Assets Management from SAP and ARCHIBUS (TM)
Digital Assets Management from SAP and ARCHIBUS (TM)Digital Assets Management from SAP and ARCHIBUS (TM)
Digital Assets Management from SAP and ARCHIBUS (TM)
 
ARCHIBUS Government Solutions
ARCHIBUS Government SolutionsARCHIBUS Government Solutions
ARCHIBUS Government Solutions
 
Enabling DataOps with Unified Data Lineage
Enabling DataOps with Unified Data LineageEnabling DataOps with Unified Data Lineage
Enabling DataOps with Unified Data Lineage
 
Archibus Overview
Archibus OverviewArchibus Overview
Archibus Overview
 
Dickey's Barbecue Pit Heats Up Analytics with Amazon Web Services
Dickey's Barbecue Pit Heats Up Analytics with Amazon Web ServicesDickey's Barbecue Pit Heats Up Analytics with Amazon Web Services
Dickey's Barbecue Pit Heats Up Analytics with Amazon Web Services
 
Accelerating the Data to Value Journey
Accelerating the Data to Value JourneyAccelerating the Data to Value Journey
Accelerating the Data to Value Journey
 
Modern Data Platform Part 1: Data Ingestion
Modern Data Platform Part 1: Data IngestionModern Data Platform Part 1: Data Ingestion
Modern Data Platform Part 1: Data Ingestion
 
The New and Improved Partner Program
The New and Improved Partner ProgramThe New and Improved Partner Program
The New and Improved Partner Program
 
Transforming Business Operations with Blockchain
Transforming Business Operations with BlockchainTransforming Business Operations with Blockchain
Transforming Business Operations with Blockchain
 
justinTym
justinTymjustinTym
justinTym
 
IT Financial Intelligence - How the world’s largest companies are evolving th...
IT Financial Intelligence - How the world’s largest companies are evolving th...IT Financial Intelligence - How the world’s largest companies are evolving th...
IT Financial Intelligence - How the world’s largest companies are evolving th...
 
ARCHIBUS Delivering Business Intelligence
ARCHIBUS Delivering Business IntelligenceARCHIBUS Delivering Business Intelligence
ARCHIBUS Delivering Business Intelligence
 

Destaque

Destaque (20)

2015 12-02-optiwind-offshore-wind-turbine-modelling-lms-samsef-siemens
2015 12-02-optiwind-offshore-wind-turbine-modelling-lms-samsef-siemens2015 12-02-optiwind-offshore-wind-turbine-modelling-lms-samsef-siemens
2015 12-02-optiwind-offshore-wind-turbine-modelling-lms-samsef-siemens
 
2015 12-02-innovative-tools-wind-turbine-performance-assesment-3 e
2015 12-02-innovative-tools-wind-turbine-performance-assesment-3 e2015 12-02-innovative-tools-wind-turbine-performance-assesment-3 e
2015 12-02-innovative-tools-wind-turbine-performance-assesment-3 e
 
2015 11-19-card unexpected-wies_farragtech
2015 11-19-card unexpected-wies_farragtech2015 11-19-card unexpected-wies_farragtech
2015 11-19-card unexpected-wies_farragtech
 
2015 11-19-case study-motor_replacement_on_extruder_danfoss
2015 11-19-case study-motor_replacement_on_extruder_danfoss2015 11-19-case study-motor_replacement_on_extruder_danfoss
2015 11-19-case study-motor_replacement_on_extruder_danfoss
 
20151202 optiwind design validation-optimization-wp5-foundation-monitoring-wp...
20151202 optiwind design validation-optimization-wp5-foundation-monitoring-wp...20151202 optiwind design validation-optimization-wp5-foundation-monitoring-wp...
20151202 optiwind design validation-optimization-wp5-foundation-monitoring-wp...
 
3 dprinting @ sirris
3 dprinting @ sirris3 dprinting @ sirris
3 dprinting @ sirris
 
2015 12 02_optiwind_optimization-operations-maintenance-offshore-wind-farms-k...
2015 12 02_optiwind_optimization-operations-maintenance-offshore-wind-farms-k...2015 12 02_optiwind_optimization-operations-maintenance-offshore-wind-farms-k...
2015 12 02_optiwind_optimization-operations-maintenance-offshore-wind-farms-k...
 
Sirris 2016 04-12-coating possibilities in the smart coating application lab ...
Sirris 2016 04-12-coating possibilities in the smart coating application lab ...Sirris 2016 04-12-coating possibilities in the smart coating application lab ...
Sirris 2016 04-12-coating possibilities in the smart coating application lab ...
 
2015 12-02-opti wind-test-setup-validation-estimation-techniques-drivetrains-...
2015 12-02-opti wind-test-setup-validation-estimation-techniques-drivetrains-...2015 12-02-opti wind-test-setup-validation-estimation-techniques-drivetrains-...
2015 12-02-opti wind-test-setup-validation-estimation-techniques-drivetrains-...
 
2016 05 26 Robo8 inspiration day_interactieve sessie
2016 05 26 Robo8 inspiration day_interactieve sessie2016 05 26 Robo8 inspiration day_interactieve sessie
2016 05 26 Robo8 inspiration day_interactieve sessie
 
Coating types and selection
Coating types and selectionCoating types and selection
Coating types and selection
 
2016 06-07-flexible-and-efficient-production-with-am-sirris-intro
2016 06-07-flexible-and-efficient-production-with-am-sirris-intro2016 06-07-flexible-and-efficient-production-with-am-sirris-intro
2016 06-07-flexible-and-efficient-production-with-am-sirris-intro
 
Sirris Smart coating roadshow - Slips introduction 1
Sirris Smart coating roadshow - Slips introduction 1Sirris Smart coating roadshow - Slips introduction 1
Sirris Smart coating roadshow - Slips introduction 1
 
Sirris Smart coating roadshow - Slips introduction 2
Sirris Smart coating roadshow - Slips introduction 2Sirris Smart coating roadshow - Slips introduction 2
Sirris Smart coating roadshow - Slips introduction 2
 
2015 12-02-optiwind-inertial response-u_gent
2015 12-02-optiwind-inertial response-u_gent2015 12-02-optiwind-inertial response-u_gent
2015 12-02-optiwind-inertial response-u_gent
 
Coating Figure Out - hay
Coating Figure Out - hayCoating Figure Out - hay
Coating Figure Out - hay
 
Invisible but functional - uv-protecting coatings
Invisible but functional - uv-protecting coatingsInvisible but functional - uv-protecting coatings
Invisible but functional - uv-protecting coatings
 
Sirris 2016 04-12 automated coating deposition by a teach-by-demonstration- s...
Sirris 2016 04-12 automated coating deposition by a teach-by-demonstration- s...Sirris 2016 04-12 automated coating deposition by a teach-by-demonstration- s...
Sirris 2016 04-12 automated coating deposition by a teach-by-demonstration- s...
 
2016 06-07-flexible-and-efficient-production-with-am-sirris-am in-tomorrows_i...
2016 06-07-flexible-and-efficient-production-with-am-sirris-am in-tomorrows_i...2016 06-07-flexible-and-efficient-production-with-am-sirris-am in-tomorrows_i...
2016 06-07-flexible-and-efficient-production-with-am-sirris-am in-tomorrows_i...
 
Sirris 2016 04-12 towards succesfull coating application-sirris
Sirris 2016 04-12 towards succesfull coating application-sirrisSirris 2016 04-12 towards succesfull coating application-sirris
Sirris 2016 04-12 towards succesfull coating application-sirris
 

Semelhante a 2015-11-24-pepite-data-analytics

Italy MAG Wire Business case _Scada system Jan 2016 english version
Italy MAG Wire Business case _Scada system Jan 2016 english versionItaly MAG Wire Business case _Scada system Jan 2016 english version
Italy MAG Wire Business case _Scada system Jan 2016 english version
Luizclaudiomatto
 
¿Cómo las manufacturas están evolucionando hacia la Industria 4.0 con la virt...
¿Cómo las manufacturas están evolucionando hacia la Industria 4.0 con la virt...¿Cómo las manufacturas están evolucionando hacia la Industria 4.0 con la virt...
¿Cómo las manufacturas están evolucionando hacia la Industria 4.0 con la virt...
Denodo
 

Semelhante a 2015-11-24-pepite-data-analytics (20)

Optimizing Towel Manufacturing in India- SAP MII
Optimizing Towel Manufacturing in India-  SAP MIIOptimizing Towel Manufacturing in India-  SAP MII
Optimizing Towel Manufacturing in India- SAP MII
 
Data Con LA 2022 - Practical Solutions to Complex Supply Chain Problems
Data Con LA 2022 - Practical Solutions to Complex Supply Chain ProblemsData Con LA 2022 - Practical Solutions to Complex Supply Chain Problems
Data Con LA 2022 - Practical Solutions to Complex Supply Chain Problems
 
Digital cement presentation november 2019
Digital cement presentation november 2019Digital cement presentation november 2019
Digital cement presentation november 2019
 
Italy MAG Wire Business case _Scada system Jan 2016 english version
Italy MAG Wire Business case _Scada system Jan 2016 english versionItaly MAG Wire Business case _Scada system Jan 2016 english version
Italy MAG Wire Business case _Scada system Jan 2016 english version
 
SAP Intelligent Factory.pdf
SAP Intelligent Factory.pdfSAP Intelligent Factory.pdf
SAP Intelligent Factory.pdf
 
AMD at ITC 2014
AMD at  ITC 2014AMD at  ITC 2014
AMD at ITC 2014
 
Dynamics 365 finance and operations case study
Dynamics 365 finance and operations case studyDynamics 365 finance and operations case study
Dynamics 365 finance and operations case study
 
The Digital Data Center: Connect, Aggregate, Analyze and Act
The Digital Data Center: Connect, Aggregate, Analyze and ActThe Digital Data Center: Connect, Aggregate, Analyze and Act
The Digital Data Center: Connect, Aggregate, Analyze and Act
 
¿Cómo las manufacturas están evolucionando hacia la Industria 4.0 con la virt...
¿Cómo las manufacturas están evolucionando hacia la Industria 4.0 con la virt...¿Cómo las manufacturas están evolucionando hacia la Industria 4.0 con la virt...
¿Cómo las manufacturas están evolucionando hacia la Industria 4.0 con la virt...
 
Pivotal Big Data Roadshow
Pivotal Big Data Roadshow Pivotal Big Data Roadshow
Pivotal Big Data Roadshow
 
slides PTC smart factory.pdf
slides PTC smart factory.pdfslides PTC smart factory.pdf
slides PTC smart factory.pdf
 
ThingsPlay: L’« I » IOT pour les manufacturiers et les nouveaux « business mo...
ThingsPlay: L’« I » IOT pour les manufacturiers et les nouveaux « business mo...ThingsPlay: L’« I » IOT pour les manufacturiers et les nouveaux « business mo...
ThingsPlay: L’« I » IOT pour les manufacturiers et les nouveaux « business mo...
 
Capitaliser sur la valeur de l’IoT : comment démarrer sa transformation numér...
Capitaliser sur la valeur de l’IoT : comment démarrer sa transformation numér...Capitaliser sur la valeur de l’IoT : comment démarrer sa transformation numér...
Capitaliser sur la valeur de l’IoT : comment démarrer sa transformation numér...
 
Why don't you have an energy management system yet
Why don't you have an energy management system yet Why don't you have an energy management system yet
Why don't you have an energy management system yet
 
Manuel cadenas - SIEMENS
Manuel cadenas - SIEMENSManuel cadenas - SIEMENS
Manuel cadenas - SIEMENS
 
Digital Business Transformation in the Streaming Era
Digital Business Transformation in the Streaming EraDigital Business Transformation in the Streaming Era
Digital Business Transformation in the Streaming Era
 
How to drive LightsOutPlanning by bluecrux
How to drive LightsOutPlanning by bluecruxHow to drive LightsOutPlanning by bluecrux
How to drive LightsOutPlanning by bluecrux
 
Schneider Electric Presentation at the Supply Chain Insights 2018 Conference
Schneider Electric Presentation at the Supply Chain Insights 2018 ConferenceSchneider Electric Presentation at the Supply Chain Insights 2018 Conference
Schneider Electric Presentation at the Supply Chain Insights 2018 Conference
 
BICS empowers predictive analytics and customer centricity with a Hadoop base...
BICS empowers predictive analytics and customer centricity with a Hadoop base...BICS empowers predictive analytics and customer centricity with a Hadoop base...
BICS empowers predictive analytics and customer centricity with a Hadoop base...
 
Mindsphere: an open cloud-based IoT operating system for Industry
Mindsphere: an open cloud-based IoT operating system for IndustryMindsphere: an open cloud-based IoT operating system for Industry
Mindsphere: an open cloud-based IoT operating system for Industry
 

Mais de Sirris

Challenges and solutions for improved durability of materials - Opin summary ...
Challenges and solutions for improved durability of materials - Opin summary ...Challenges and solutions for improved durability of materials - Opin summary ...
Challenges and solutions for improved durability of materials - Opin summary ...
Sirris
 
Challenges and solutions for improved durability of materials - Hybrid joints...
Challenges and solutions for improved durability of materials - Hybrid joints...Challenges and solutions for improved durability of materials - Hybrid joints...
Challenges and solutions for improved durability of materials - Hybrid joints...
Sirris
 
Challenges and solutions for improved durability of materials - Coatings done...
Challenges and solutions for improved durability of materials - Coatings done...Challenges and solutions for improved durability of materials - Coatings done...
Challenges and solutions for improved durability of materials - Coatings done...
Sirris
 

Mais de Sirris (20)

Presentation - webinar embedded machine learning
Presentation - webinar embedded machine learningPresentation - webinar embedded machine learning
Presentation - webinar embedded machine learning
 
2 - Pattyn - Smart Products Webinar 03-02-2023.
2 - Pattyn - Smart Products Webinar 03-02-2023.2 - Pattyn - Smart Products Webinar 03-02-2023.
2 - Pattyn - Smart Products Webinar 03-02-2023.
 
2021 01-27 - webinar - Corrosie van 3D geprinte onderdelen
2021 01-27 - webinar - Corrosie van 3D geprinte onderdelen2021 01-27 - webinar - Corrosie van 3D geprinte onderdelen
2021 01-27 - webinar - Corrosie van 3D geprinte onderdelen
 
2021/0/15 - Solarwinds supply chain attack: why we should take it sereously
2021/0/15 - Solarwinds supply chain attack: why we should take it sereously2021/0/15 - Solarwinds supply chain attack: why we should take it sereously
2021/0/15 - Solarwinds supply chain attack: why we should take it sereously
 
20200923 inside metal am webinar_laborelec
20200923 inside metal am webinar_laborelec20200923 inside metal am webinar_laborelec
20200923 inside metal am webinar_laborelec
 
20200923 inside metal am webinar sirris-crm
20200923 inside metal am webinar sirris-crm20200923 inside metal am webinar sirris-crm
20200923 inside metal am webinar sirris-crm
 
Challenges and solutions for improved durability of materials - Opin summary ...
Challenges and solutions for improved durability of materials - Opin summary ...Challenges and solutions for improved durability of materials - Opin summary ...
Challenges and solutions for improved durability of materials - Opin summary ...
 
Challenges and solutions for improved durability of materials - Hybrid joints...
Challenges and solutions for improved durability of materials - Hybrid joints...Challenges and solutions for improved durability of materials - Hybrid joints...
Challenges and solutions for improved durability of materials - Hybrid joints...
 
Challenges and solutions for improved durability of materials - Corrosion mon...
Challenges and solutions for improved durability of materials - Corrosion mon...Challenges and solutions for improved durability of materials - Corrosion mon...
Challenges and solutions for improved durability of materials - Corrosion mon...
 
Challenges and solutions for improved durability of materials - Concrete in m...
Challenges and solutions for improved durability of materials - Concrete in m...Challenges and solutions for improved durability of materials - Concrete in m...
Challenges and solutions for improved durability of materials - Concrete in m...
 
Challenges and solutions for improved durability of materials - Coatings done...
Challenges and solutions for improved durability of materials - Coatings done...Challenges and solutions for improved durability of materials - Coatings done...
Challenges and solutions for improved durability of materials - Coatings done...
 
Futureproof by sirris- product of the future
Futureproof by sirris- product of the futureFutureproof by sirris- product of the future
Futureproof by sirris- product of the future
 
2018 11-07-verbinden-ongelijksoortige-materialen-hupico multimaterial welding
2018 11-07-verbinden-ongelijksoortige-materialen-hupico multimaterial welding2018 11-07-verbinden-ongelijksoortige-materialen-hupico multimaterial welding
2018 11-07-verbinden-ongelijksoortige-materialen-hupico multimaterial welding
 
2018 11-07-verbinden-ongelijksoortige-materialen-bil ongelijksoortige materia...
2018 11-07-verbinden-ongelijksoortige-materialen-bil ongelijksoortige materia...2018 11-07-verbinden-ongelijksoortige-materialen-bil ongelijksoortige materia...
2018 11-07-verbinden-ongelijksoortige-materialen-bil ongelijksoortige materia...
 
2018 11-07-verbinden-ongelijksoortige-materialen-sirris bil-flanders_make_mmj
2018 11-07-verbinden-ongelijksoortige-materialen-sirris bil-flanders_make_mmj2018 11-07-verbinden-ongelijksoortige-materialen-sirris bil-flanders_make_mmj
2018 11-07-verbinden-ongelijksoortige-materialen-sirris bil-flanders_make_mmj
 
2018 11-07-verbinden-ongelijksoortige-materialen-ku leuven-lijmen
2018 11-07-verbinden-ongelijksoortige-materialen-ku leuven-lijmen2018 11-07-verbinden-ongelijksoortige-materialen-ku leuven-lijmen
2018 11-07-verbinden-ongelijksoortige-materialen-ku leuven-lijmen
 
Slotevent ‘Verbinden van ongelijksoortige materialen’ - Lcv lasercladding for...
Slotevent ‘Verbinden van ongelijksoortige materialen’ - Lcv lasercladding for...Slotevent ‘Verbinden van ongelijksoortige materialen’ - Lcv lasercladding for...
Slotevent ‘Verbinden van ongelijksoortige materialen’ - Lcv lasercladding for...
 
Slotevent ‘Verbinden van ongelijksoortige materialen’ - Juno industries mecha...
Slotevent ‘Verbinden van ongelijksoortige materialen’ - Juno industries mecha...Slotevent ‘Verbinden van ongelijksoortige materialen’ - Juno industries mecha...
Slotevent ‘Verbinden van ongelijksoortige materialen’ - Juno industries mecha...
 
Slotevent ‘Verbinden van ongelijksoortige materialen’ - Castolin verbinden v...
Slotevent ‘Verbinden van ongelijksoortige materialen’ - Castolin  verbinden v...Slotevent ‘Verbinden van ongelijksoortige materialen’ - Castolin  verbinden v...
Slotevent ‘Verbinden van ongelijksoortige materialen’ - Castolin verbinden v...
 
Masterclass Mechatronics 4.0 - Indoor and outdoor localisation and positionin...
Masterclass Mechatronics 4.0 - Indoor and outdoor localisation and positionin...Masterclass Mechatronics 4.0 - Indoor and outdoor localisation and positionin...
Masterclass Mechatronics 4.0 - Indoor and outdoor localisation and positionin...
 

Último

Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
vu2urc
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 

Último (20)

Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 

2015-11-24-pepite-data-analytics

  • 1. Slide | 1Slide | 1 HOWDATAANALYTICSCANPROVIDEINTERESTING NEWPOSSIBILITIESFORTHEFOODINDUSTRY PhilippeMack
  • 2. Slide | 2Slide | 2 Industrial internet of things Cloud computing Factory 4.0 Predictive Analytics Big Data In Memory Hadoop DATA Lake
  • 5. Slide | 5Slide | 5 MB 19555
  • 6. Slide | 6Slide | 6 2015 5.000MB
  • 7. Slide | 7Slide | 7 Connection Transmission Storage Analytics … as a service Focus on your business… not on complex infrastructure Quick starts… quick wins!
  • 8. Slide | 8Slide | 8 ABOUT US Specialised in predictive analytics solutions for industrial applications (Yield, productivity, quality, energy optimisation, predictive maintenance) – More than 10 years of experience Our distinctiveness !  Business minded consultants !  Software technology •  DATAmaestro: cloud based data mining software •  DATAserver: automatic and systematic data extraction, preparation and merging platform !  Dedicated vertical applications •  ENERGYmaestro: energy management solution based on data analytics and operator participation •  Wintell : performance tracking and predictive maintenance for wind turbines •  FINDIT : batch tracking and performance management for aquaculture
  • 9. Slide | 9Slide | 9 WHERE HAS IT BEEN APPLIED ? Type of project Impact Increase yield and reduce scrap by 5% Predict in real-time the quality of the steel to increase yield and reduce scrap Analyze drilling operation data to increase ROP Faster drilling and less downtimes due to reduced well head failure E&P drilling operations Predict and understand root causes of breaks in paper sheets Paper making Reduce shutdowns and increases OEE by 5% Chemicals Optimize use of energy in exothermic processes Reduce energy costs by 15% Industry Steel Analyse the quality of the end products using advanced analytics Improve quality and find the root causes Carbon technology Electrical networks Forecast dynamic security of transmission grid Avoid costly curtailment of loads or generations
  • 10. Slide | 10Slide | 10 BUT WHAT ABOUT ADVANCED DATA ANALYTICS for the! FOOD INDUSTRY?!
  • 11. Slide | 11Slide | 11 for windturbines Precision farming
  • 12. Slide | 12Slide | 12 predictive maintenance for windturbines WINTELL energy management system based on analytics, management & people! BIG DATA ANALYTICS ! in utilities to improve operations forthe FindIT continuous improvement platform fish production industry
  • 14. Slide | 14Slide | 14 a brief history!
  • 15. Slide | 15Slide | 15 •  FineFish project •  Data initially collected in XLS sheet (a lot of error, many inconsistencies, difficult to process to compute basic statistics •  Development of a web app prototype to gather data in order to monitor malformation in fish •  Evangelization on big data and advanced analytics capabilities •  Interest was raised in the market •  A real need was identified to collect and centralize data from farm operation to •  Increase fish quality •  Increase farm performance in general A LITTLE HISTORY ON THE PROJECT
  • 16. Slide | 16Slide | 16 THE PARTNERS
  • 17. Slide | 17Slide | 17 •  Enter and store production data in the cloud (web based) •  Benchmark own data, and against the other producers (anonymised data) •  Use data mining to analyse big data and extract new knowledge, validate hypothesis KPI Benchmark Data entry Advanced Analytics User hatchery A User hatchery B User hatchery C Webinterface Webinterface Webinterface THE TOOL
  • 19. Slide | 19Slide | 19 RECORDS AND TRACK OPERATION CHANGES AND ACTIVITIES: MEASUREMENTS, FEEDS, OBSERVATIONS
  • 20. Slide | 20Slide | 20 TRACK MOVEMENTS OF FISHES : IMPORTANT TO LINK MONITORING WITH BATCH TRACKING
  • 21. Slide | 21Slide | 21 BROWSE THE BATCHES OF PRODUCTION
  • 22. Slide | 22Slide | 22 KEY PERFORMANCE CALCULATION, REPORTING AND DASHBOARDING
  • 23. Slide | 23Slide | 23 ANALYTICS FOR QUANTITATIVE ROOT CAUSE ANALYSIS, PREDICTION, OPTIMIZATION…
  • 24. Slide | 24Slide | 24 •  Average SGR from start feeding to smolt : –  Higher than 2.29 is good (green) –  Lower than 2.29 is bad (red) Decision tree analysis of Water parameters vs. KPI_SGR THE SALMON DEMON FARM
  • 25. Slide | 25Slide | 25 •  Automatic KPI calculation and reporting •  Advanced KPI management to predict, diagnose, optimise productivity and reduce mortality and increase quality •  State of the art information technology: big data, statistics, predictive analytics with machine learning •  Based on successful experiences in other industries •  KISS principle •  Secured software as a service for your tablet, your PC FEATURES
  • 26. Slide | 26Slide | 26 168.000€ energy savings in UHT milk production process optimization
  • 27. Slide | 27Slide | 27 SAVING THROUGH OPERATIONAL MANAGEMENT Procurement Investments Operations
  • 28. Slide | 28Slide | 28 A PEOPLE MINDED APPROACH Analytics People •  Gap analysis •  Cost driver diagnostic •  Root cause analysis •  Optimised targets •  KPI •  Workshops •  Training •  Monitoring •  Culture A continuous improvement system based on:
  • 29. Slide | 29Slide | 29 APPROACH Process & business understanding Workshops Training & reviewAdvanced analytics & implementation ENERGYmaestro 1 - 2 weeks 4 - 6 weeks 4 - 6 weeks 2 - 3 weeks Steam extraction < maximum Capacity of steam extraction Steam extraction down Maintenance – waiting for spare parts Sulfine plant is not in operation SO2 alarm Lack of sulfur There is no steam for the turbine Capacity of LP steam network Low pressure boilers at P2 HP vers LP Boiler BERI Boiler SO2 Demand/losses Consumers Start-up valves Overall management Training Communication & coordination Gap analysis 1 – 2 weeks 2012 11 Taux de soutirage - moyenne du mois 95 % Ouverture vannes démarrage 11 h Cible = 2 meilleurs mois + 5t/h 90% HP - vanne SO2 # heures 1 h Gain (pertes) par rapport à la cible du mois 1.490 t BP - vanne HRS # heures 10 h Débit moyen soutirage 32,3 t/h Uptime 96 % Tonnes excès BERI 5,7 t/h Taux de soutirage durant uptime 97 % Tonnes excès chaudières P2 0,9 t/h Gains vs taux de 75% - 2011 5.074 tPEPITE - RAPPORT MENSUEL Année Mois 0 10 20 30 40 50 1/nov. 2/nov. 3/nov. 5/nov. 6/nov. 7/nov. 9/nov. 10/nov. 11/nov. 13/nov. 14/nov. 15/nov. 17/nov. 18/nov. 19/nov. 21/nov. 22/nov. 23/nov. 25/nov. 26/nov. 27/nov. 29/nov. 30/nov. 0 10 20 30 40 0 5 10 15 20 25 30 35 40 45 0 200 400 600 800 1000 1200 1400 1600 Somme cumulative du gain / perte par rapport à la cible 2 4 6 8 10 12 14 16 soufre sulfine soufre sulfine Commentaires : ............................ ............................ ............................ ............................ ............................ ............................ ............................ ............................ ............. :…………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… … …………………… …………………… …………………… …………………… …………………… …………………... :…………………… …………………… …………………… …………………… …………………… …………………… … …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………... :… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… … …………………… …………………… …………………… …………………… …………………… ………………...:… …………………… …………………… …………………… …………………… …………………… …………………… … …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… …………………… ………………...... ...... .. FLASH ANALYSIS
  • 30. Slide | 30Slide | 30 ENERGY SPECIFIC CONS. (KWH/T MILK) UHT
  • 31. Slide | 31Slide | 31 MOST IMPORTANT PARAMETERS TO EXPLAIN GLOBAL CONSUMPTION
  • 32. Slide | 32Slide | 32 SPECIFIC STEAM CONSUMPTION AT UHT Target 15T/m3 milk
  • 33. Slide | 33Slide | 33 STEAM SAVINGS ESTIMATES @UHT 6000 t in 6 months
  • 34. Slide | 34Slide | 34 •  Process improvements •  12 000 T in 1 year •  168.000 EUR savings •  Operator involvement •  Sustainable energy culture •  No capital investment BENEFITS
  • 35. Slide | 35Slide | 35 advanced imaging for automated quality control
  • 36. Slide | 36Slide | 36 OK OK OK Ciabatta tomate KO KO “DEFECTS” ON BREAD DIFFICULT TO DETECTS

  • 37. Slide | 37Slide | 37 IMAGE COLLECTION •  Collect Images
  • 38. Slide | 38Slide | 38 CREATE A LIBRARY OF DEFECTS
  • 39. Slide | 39Slide | 39 TRAIN COMPUTER TO AUTOMATE ANNOTATION & CLASSIFICATION

  • 40. Slide | 40Slide | 40 KEY BENEFITS
 •  Faster and more reliable defect detection •  React faster to correct problems •  Identify parameters that impact quality crisis •  Mix image information with other sensors data to improve performance of process operations •  Update easily annotators with newer images
  • 41. Slide | 41Slide | 41 advanced imaging for automated quality control $ 27.500 ANNUAL ENERGY SAVINGS for a brewery packaging line
  • 42. Slide | 42Slide | 42 CORRELATION MATRIX GIVES RELATIONSHIP BETWEEN PROCESS VARIABLES
  • 43. Slide | 43Slide | 43 MAIN VARIABILITIES: SEASON AND PRODUCTION LEVEL
  • 44. Slide | 44Slide | 44 SIGNIFICANT VARIABILITY OF STEAM USE PER DAY CLEAR IMPACT OF PRODUCTION SHUTDOWN
  • 45. Slide | 45Slide | 45 DECISION TREE EXPLAINS THE DIFFERENCE BETWEEN LEVELS OF STEAM USE (LOW-MED-HIGH) levels are defined based on distribution CO2 filler > 3180 kg leads to high use
  • 46. Slide | 46Slide | 46 •  Process improvements •  146 MWh energy: - 7% •  2145 T steam: - 11% •  28 200 m3 water: - 15% •  EUR 27.500 direct savings annually •  No CAPEX BENEFITS
  • 47. Slide | 47Slide | 47 Thank you ! ph.mack@pepite.be phone: 0477 380 005 www.pepite.be