Grant: Engage Grants Program
University of Alberta
$25,000.00
Equipment failure detection through the analysis of data from induction motors
EF 2016-17
Résumé
3-phase induction motors are a critical part of many Alberta industries as they are a vital cost effective tool for using electrical power to control many industrial processes, especially relevant in Alberta because of the oil and gas, mining and petro-chemical industries. Typically, 60-80% of industrial electrical power is consumed by induction motors. Hence, high energy conversion efficiency, reliability and failure avoidance of induction motors, significantly improves productivity by lowering energy bills, reducing expensive maintenance procedures and avoiding costly plant downtimes. Many of these goals can be achieved by monitoring the electrical performance of motors, condition monitoring, and predicting commonly occurring fault conditions before they happen; the latter allows for maintenance to be scheduled when it is convenient for the industrial plant; predictive maintenance.This project will address the problem of mass scale real-time electrical power monitoring by using plant data currently being collected using existing infrastructure. Performance degradation, servicing downtimes and failure modes of induction motors will be linked to specific Alberta industries. Although there are many commercial products for condition monitoring of equipment, these are not cost-effective on a mass scale. This project will seek to address this problem by enabling the mass analysis of real-time and historical plant data using existing sensors and infrastructure. The prime focus of this project is to identify electrical signatures that are available from a range of standard industrial electrical sensors. The results of this work will provide the foundation for the analysis of mass data for the purposes of fault detection and condition monitoring. The project will explore new and existing electrical signatures from laboratory measurements that allow for anomaly detection under given constraints. This will then be used to identify unusual motor behaviour using relatively low quality data. The project will then seek to identify the framework whereby Artificial Intelligence and Machine Learning methods may be applied in future work for the analysis of mass data.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
503190-2016
Name nom
Salmon, John
Department département
Electrical and Computer Engineering
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1555
Committee name en
Prairie Internal Decision Committee
Committee name fr
Comité de décision interne pour les Prairies
Area of application code
304
Area of application group en
Energy resources
Area of application group fr
Ressources d'énergie
Area of application en
Electrical energy
Area of application fr
Énergie électrique
Research subject code
2516
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Energy conversion and distribution
Research subject fr
Conversion et distribution de l'énergie
Partie
1
Nb partie
1
Application title
Equipment failure detection through the analysis of data from induction motors
Keyword
NSERC
Application summary
3-phase induction motors are a critical part of many Alberta industries as they are a vital cost effective tool for using electrical power to control many industrial processes, especially relevant in Alberta because of the oil and gas, mining and petro-chemical industries. Typically, 60-80% of industrial electrical power is consumed by induction motors. Hence, high energy conversion efficiency, reliability and failure avoidance of induction motors, significantly improves productivity by lowering energy bills, reducing expensive maintenance procedures and avoiding costly plant downtimes. Many of these goals can be achieved by monitoring the electrical performance of motors, condition monitoring, and predicting commonly occurring fault conditions before they happen; the latter allows for maintenance to be scheduled when it is convenient for the industrial plant; predictive maintenance.This project will address the problem of mass scale real-time electrical power monitoring by using plant data currently being collected using existing infrastructure. Performance degradation, servicing downtimes and failure modes of induction motors will be linked to specific Alberta industries. Although there are many commercial products for condition monitoring of equipment, these are not cost-effective on a mass scale. This project will seek to address this problem by enabling the mass analysis of real-time and historical plant data using existing sensors and infrastructure. The prime focus of this project is to identify electrical signatures that are available from a range of standard industrial electrical sensors. The results of this work will provide the foundation for the analysis of mass data for the purposes of fault detection and condition monitoring. The project will explore new and existing electrical signatures from laboratory measurements that allow for anomaly detection under given constraints. This will then be used to identify unusual motor behaviour using relatively low quality data. The project will then seek to identify the framework whereby Artificial Intelligence and Machine Learning methods may be applied in future work for the analysis of mass data.