15
Embedded Service Oriented Diagnostics based on Energy Consumption Data 22/06/202 2 Embedded Service Oriented Diagnostics based on Energy Consumption Data 1 Date: September, 2012 Linked to: eSONIA Contact information Tampere University of Technology, FAST Laboratory, P.O. Box 600, FIN-33101 Tampere, Finland Email: [email protected] www.tut.fi/fast Conference: 2012 IEEE International Conference on Information and Automation for Sustainability Title of the paper: Embedded Service Oriented Diagnostics based on Energy Consumption Data Authors: Corina Postelnicu, Navid Khajehzadeh, Jose Luis Martinez Lastra If you would like to receive a reprint of the original paper, please contact us

Embedded Service Oriented Diagnostics based on Energy Consumption Data

Embed Size (px)

DESCRIPTION

This paper presents an approach using power consumption to detect system deterioration (misalignment of conveyors) Power consumption data are correlated with workload of the conveyor system. Real time data coming from a real factory automation testbed are input to SVM for classification. The output is compared with the output of a rule-based engine.

Citation preview

Page 1: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Embedded Service Oriented Diagnostics based on Energy

Consumption Data

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data1

•Date: September, 2012•Linked to: eSONIA

Contact information

Tampere University of Technology,

FAST Laboratory,

P.O. Box 600,

FIN-33101 Tampere,

Finland

Email: [email protected]

www.tut.fi/fast

Conference: 2012 IEEE International Conference on Information and Automation for Sustainability

Title of the paper: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Authors: Corina Postelnicu,

Navid Khajehzadeh,

Jose Luis Martinez Lastra

If you would like to receive a reprint of the original paper, please contact us

Page 2: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Embedded Service Oriented Diagnostics based on Energy

Consumption Data

ICIAfS 2012, Beijing, China

27-29.9.2012

ARTEMIS eSONIA project (Embedded Service Oriented Monitoring, Diagnostics and Control: Towards the Asset Aware and Self Recovery Factory)

Corina Postelnicu

Navid Khajehzadeh

Jose L. Martinez Lastra

Presenter: Bin Zhang

Factory Automation Systems and Technologies

Tampere University of Technology, Finland

Page 3: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Outline

1.Introduction

2.Testbed

3.Implementation– Data collection– Support Vector Machine– Validation

4.Failure detection model

5.Conclusions and future work

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data3

Page 4: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Introduction

– Predictive maintenance techniques Passive: measuring data (vibration, temperature,

etc), then comparing with normal values Active: injecting test signals, then monitoring

responses

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data4

Unexpected failures

Financial losses & accidents

Page 5: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Introduction

– Quantification: threshold settings by running the equipments until failure occurs

– Assumption: the measured parameters should not be influenced by other parameters

– Limitation: suitable for processing workstations, not transportation devices (parameters are influenced by workload)

This paper associates the workload on a conveyor system to the power consumption information for failure detection.

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data5

Page 6: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Testbed

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data6

Page 7: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Testbed

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data7

Embedded controllers to publish the device information as web services

Each cell has 4 controllers

En

erg

y

con

sum

pti

on

Page 8: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Implementation: Data collection

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data8

Item Transfer InCell 5

Item Transfer outCell 5

Item Transfer InCell 6

Cell 5 Cell 6

1. Energy consumption 2. Workload

Page 9: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Implementation: Data collection

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data9

1. Correlation of bypass conveyor power consumption (watt) and number of pallets (0-5)

2. Power consumption of the conveyor system(watt, 1 or 2 pallets)

Class 1: 0-1 pallet

Class 2: 2 or more pallets

Page 10: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Implementation: Support Vector Machine

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data10

1.Support Vector Machine (SVM)• A classifier to provide a boundary to divide a

dataset into two classes.

2.Least Square Support Vector Machine (LS-SVM)• Classification is done using linear equations

instead of a burdensome Quadratic equation.• 70% to 80% of data are used for learning and the

rest for validation.

Page 11: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Implementation: Validation

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data11

Accuracy is computed by comparing the LS-SVM result against the rule-based engine, which shows an error percentage of 5.56%

The 2 classes identified by the rule-based engine

The 2 classes identified by LS-SVM

Page 12: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Failure detection model

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data12

Page 13: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Conclusions and future work

This paper presents an approach using power consumption to detect system deterioration (misalignment of conveyors)• Power consumption data are correlated with

workload of the conveyor system.• Real time data coming from a real factory

automation testbed are input to SVM for classification.

• The output is compared with the output of a rule-based engine.

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data13

Page 14: Embedded Service Oriented Diagnostics based on Energy Consumption Data

Conclusions and future work

Future work• Bring more parameters for analysis, i.e. vibration

and temperature

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data14

Page 15: Embedded Service Oriented Diagnostics based on Energy Consumption Data

11/04/2023Embedded Service Oriented Diagnostics

based on Energy Consumption Data15

Thank you!

[email protected]

[email protected]

ARTEMIS eSONIA project (Embedded Service Oriented Monitoring, Diagnostics and Control: Towards the Asset Aware and Self Recovery Factory)