Load Imbalance Detection for an Induction Motor : - A Comparative Study of Machine Learning Algorithms

In 2016 the average industry downtime cost was estimated to $260.000 every hour, and with Swedish industries being an important part of the national economy it would be desirable to reduce the amount of unplanned downtime to a minimum. There are currently many different solutions for system supervis...

Full description

Bibliographic Details
Main Authors: Berg, Stina, Lilja Sjökrans, Elisabet
Format: Others
Language:English
Published: Högskolan i Halmstad, Akademin för informationsteknologi 2019
Subjects:
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-39813
id ndltd-UPSALLA1-oai-DiVA.org-hh-39813
record_format oai_dc
spelling ndltd-UPSALLA1-oai-DiVA.org-hh-398132019-06-19T05:30:56ZLoad Imbalance Detection for an Induction Motor : - A Comparative Study of Machine Learning AlgorithmsengBerg, StinaLilja Sjökrans, ElisabetHögskolan i Halmstad, Akademin för informationsteknologiHögskolan i Halmstad, Akademin för informationsteknologi2019Machine learningindustrial gatewayload imbalancefault detectionComputer and Information SciencesData- och informationsvetenskapIn 2016 the average industry downtime cost was estimated to $260.000 every hour, and with Swedish industries being an important part of the national economy it would be desirable to reduce the amount of unplanned downtime to a minimum. There are currently many different solutions for system supervision for monitoring system health but none which analyse data with machine learning in an industrial gateway.   The aim for this thesis is to test, compare and evaluate three different algorithms to find a classifier suitable for a gateway environment. The evaluated algorithms were Random Forest, K-Nearest Neighbour and Linear Discriminant Analysis. Load imbalance detection was used as a case study for evaluating these algorithms. The gateway received data from a Modbus ATV32 frequency converter, which measured specific features from an induction motor. The imbalance was created with loads that were attached on a fly-wheel at different angles to simulate different imbalances. The classifiers were compared on their accuracy, memory usage, CPU usage and execution time. The result was evaluated with tables, confusion matrices and AUC- ROC curves.  Although all algorithms performed well LDA was best based on the criteria set. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-39813application/pdfinfo:eu-repo/semantics/openAccess
collection NDLTD
language English
format Others
sources NDLTD
topic Machine learning
industrial gateway
load imbalance
fault detection
Computer and Information Sciences
Data- och informationsvetenskap
spellingShingle Machine learning
industrial gateway
load imbalance
fault detection
Computer and Information Sciences
Data- och informationsvetenskap
Berg, Stina
Lilja Sjökrans, Elisabet
Load Imbalance Detection for an Induction Motor : - A Comparative Study of Machine Learning Algorithms
description In 2016 the average industry downtime cost was estimated to $260.000 every hour, and with Swedish industries being an important part of the national economy it would be desirable to reduce the amount of unplanned downtime to a minimum. There are currently many different solutions for system supervision for monitoring system health but none which analyse data with machine learning in an industrial gateway.   The aim for this thesis is to test, compare and evaluate three different algorithms to find a classifier suitable for a gateway environment. The evaluated algorithms were Random Forest, K-Nearest Neighbour and Linear Discriminant Analysis. Load imbalance detection was used as a case study for evaluating these algorithms. The gateway received data from a Modbus ATV32 frequency converter, which measured specific features from an induction motor. The imbalance was created with loads that were attached on a fly-wheel at different angles to simulate different imbalances. The classifiers were compared on their accuracy, memory usage, CPU usage and execution time. The result was evaluated with tables, confusion matrices and AUC- ROC curves.  Although all algorithms performed well LDA was best based on the criteria set.
author Berg, Stina
Lilja Sjökrans, Elisabet
author_facet Berg, Stina
Lilja Sjökrans, Elisabet
author_sort Berg, Stina
title Load Imbalance Detection for an Induction Motor : - A Comparative Study of Machine Learning Algorithms
title_short Load Imbalance Detection for an Induction Motor : - A Comparative Study of Machine Learning Algorithms
title_full Load Imbalance Detection for an Induction Motor : - A Comparative Study of Machine Learning Algorithms
title_fullStr Load Imbalance Detection for an Induction Motor : - A Comparative Study of Machine Learning Algorithms
title_full_unstemmed Load Imbalance Detection for an Induction Motor : - A Comparative Study of Machine Learning Algorithms
title_sort load imbalance detection for an induction motor : - a comparative study of machine learning algorithms
publisher Högskolan i Halmstad, Akademin för informationsteknologi
publishDate 2019
url http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-39813
work_keys_str_mv AT bergstina loadimbalancedetectionforaninductionmotoracomparativestudyofmachinelearningalgorithms
AT liljasjokranselisabet loadimbalancedetectionforaninductionmotoracomparativestudyofmachinelearningalgorithms
_version_ 1719206940162129920