Analysis of machine learning techniques for the intelligent diagnosis of Ni-MH battery cells

Juan P. Ortiz, Juan D. Valladolid, Cristian L. Garcia, Gina Novillo, Felipe Berrezueta

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Scopus citations

Abstract

This paper presents a comparison of different machine learning techniques for classification of the unbalance and damage Niquel-Metal Hydride (Ni-MH) battery cells used in hybrid electric vehicles (HEV) and electric vehicles (EV). The implemented linear and non-linear classification algorithms used in this study are: logistic regression (LR), k-nearest neighbors (k-NN), kernel space vector machine (KSVM), Gaussian naive Bayes (GNB) and a neural network (NN); the classifiers in this work used the principal component analysis (PCA) in dual variables to reduce the high dimensional data set. To evaluate the performance of the classifiers, experimental results and a detailed analysis of the confusion matrix are used where the effectiveness of the algorithms are demonstrated.

Original languageEnglish
Title of host publication2018 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538659359
ISBN (Print)9781538659359
DOIs
StatePublished - 5 Mar 2019
Event2018 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2018 - Ixtapa, Guerrero, Mexico
Duration: 14 Nov 201816 Nov 2018

Publication series

Name2018 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2018

Conference

Conference2018 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2018
Country/TerritoryMexico
CityIxtapa, Guerrero
Period14/11/1816/11/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Keywords

  • Classifier
  • Hybrid electric vehicle
  • Machine learning
  • Ni-MH

Fingerprint

Dive into the research topics of 'Analysis of machine learning techniques for the intelligent diagnosis of Ni-MH battery cells'. Together they form a unique fingerprint.

Cite this