Classifying machinery condition using oil samples and binary logistic regression. Phillips, J., Cripps, E., Lau, J. W., & Hodkiewicz, M. R. Mechanical Systems and Signal Processing, 60-61:316–325, August, 2015. ![Classifying machinery condition using oil samples and binary logistic regression [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically “black box” approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.
@article{phillips_classifying_2015,
title = {Classifying machinery condition using oil samples and binary logistic regression},
volume = {60-61},
issn = {0888-3270},
url = {https://www.sciencedirect.com/science/article/pii/S0888327014005093},
doi = {10.1016/j.ymssp.2014.12.020},
abstract = {The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically “black box” approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.},
language = {en},
urldate = {2021-09-30},
journal = {Mechanical Systems and Signal Processing},
author = {Phillips, J. and Cripps, E. and Lau, John W. and Hodkiewicz, M. R.},
month = aug,
year = {2015},
keywords = {Classification, Logistic regression, Machine health, Mining trucks, Neural networks, Oil analysis, Receiver operating characteristic curve, Support vector machine},
pages = {316--325},
}
Downloads: 0
{"_id":"7pToyBt8Lk2mj7nLj","bibbaseid":"phillips-cripps-lau-hodkiewicz-classifyingmachineryconditionusingoilsamplesandbinarylogisticregression-2015","author_short":["Phillips, J.","Cripps, E.","Lau, J. W.","Hodkiewicz, M. R."],"bibdata":{"bibtype":"article","type":"article","title":"Classifying machinery condition using oil samples and binary logistic regression","volume":"60-61","issn":"0888-3270","url":"https://www.sciencedirect.com/science/article/pii/S0888327014005093","doi":"10.1016/j.ymssp.2014.12.020","abstract":"The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically “black box” approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.","language":"en","urldate":"2021-09-30","journal":"Mechanical Systems and Signal Processing","author":[{"propositions":[],"lastnames":["Phillips"],"firstnames":["J."],"suffixes":[]},{"propositions":[],"lastnames":["Cripps"],"firstnames":["E."],"suffixes":[]},{"propositions":[],"lastnames":["Lau"],"firstnames":["John","W."],"suffixes":[]},{"propositions":[],"lastnames":["Hodkiewicz"],"firstnames":["M.","R."],"suffixes":[]}],"month":"August","year":"2015","keywords":"Classification, Logistic regression, Machine health, Mining trucks, Neural networks, Oil analysis, Receiver operating characteristic curve, Support vector machine","pages":"316–325","bibtex":"@article{phillips_classifying_2015,\n\ttitle = {Classifying machinery condition using oil samples and binary logistic regression},\n\tvolume = {60-61},\n\tissn = {0888-3270},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0888327014005093},\n\tdoi = {10.1016/j.ymssp.2014.12.020},\n\tabstract = {The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically “black box” approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.},\n\tlanguage = {en},\n\turldate = {2021-09-30},\n\tjournal = {Mechanical Systems and Signal Processing},\n\tauthor = {Phillips, J. and Cripps, E. and Lau, John W. and Hodkiewicz, M. R.},\n\tmonth = aug,\n\tyear = {2015},\n\tkeywords = {Classification, Logistic regression, Machine health, Mining trucks, Neural networks, Oil analysis, Receiver operating characteristic curve, Support vector machine},\n\tpages = {316--325},\n}\n\n","author_short":["Phillips, J.","Cripps, E.","Lau, J. W.","Hodkiewicz, M. R."],"key":"phillips_classifying_2015","id":"phillips_classifying_2015","bibbaseid":"phillips-cripps-lau-hodkiewicz-classifyingmachineryconditionusingoilsamplesandbinarylogisticregression-2015","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S0888327014005093"},"keyword":["Classification","Logistic regression","Machine health","Mining trucks","Neural networks","Oil analysis","Receiver operating characteristic curve","Support vector machine"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["classification","logistic regression","machine health","mining trucks","neural networks","oil analysis","receiver operating characteristic curve","support vector machine"],"search_terms":["classifying","machinery","condition","using","oil","samples","binary","logistic","regression","phillips","cripps","lau","hodkiewicz"],"title":"Classifying machinery condition using oil samples and binary logistic regression","year":2015}