Process-monitoring-for-quality — A machine learning-based modeling for rare event detection
Process Monitoring for Quality is a Big Data-driven quality philosophy aimed at defect detection through binary classification and empirical knowledge discovery. It is founded on Big Models, a predictive modeling paradigm that applies Machine Learning, statistics and optimization techniques to proce...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2020-09-01
|
Series: | Array |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2590005620300199 |
id |
doaj-1856fa5c665745cda8b58e8de3ff81bd |
---|---|
record_format |
Article |
spelling |
doaj-1856fa5c665745cda8b58e8de3ff81bd2020-11-25T03:21:26ZengElsevierArray2590-00562020-09-017100034Process-monitoring-for-quality — A machine learning-based modeling for rare event detectionCarlos A. Escobar0Ruben Morales-Menendez1Daniela Macias2Global Research & Development, General Motors, Warren, MI, USA; Corresponding author.Tecnológico de Monterrey, School of Engineering and Sciences, Monterrey NL, MexicoTecnológico de Monterrey, School of Engineering and Sciences, Monterrey NL, MexicoProcess Monitoring for Quality is a Big Data-driven quality philosophy aimed at defect detection through binary classification and empirical knowledge discovery. It is founded on Big Models, a predictive modeling paradigm that applies Machine Learning, statistics and optimization techniques to process data to create a manufacturing functional model. Functional refers to a parsimonious model with high detection ability that can be trusted by engineers, and deployed to control production. A parsimonious modeling scheme is presented aimed at rare quality event detection, parsimony is induced through feature selection and model selection. Its unique ability to deal with highly/ultra-unbalanced data structures and diverse learning algorithms is validated with four case studies, using the Support Vector Machine, Logistic Regression, Naive Bayes and k-Nearest Neighbors learning algorithms. And according to experimental results, the proposed learning scheme significantly outperformed typical learning approaches based on the l1-regularized logistic regression and Random Undersampling Boosting learning algorithms, with respect to parsimony and prediction.http://www.sciencedirect.com/science/article/pii/S2590005620300199Quality controlManufacturing systemsMachine learningFeature eliminationModel selectionUnbalanced binary data |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Carlos A. Escobar Ruben Morales-Menendez Daniela Macias |
spellingShingle |
Carlos A. Escobar Ruben Morales-Menendez Daniela Macias Process-monitoring-for-quality — A machine learning-based modeling for rare event detection Array Quality control Manufacturing systems Machine learning Feature elimination Model selection Unbalanced binary data |
author_facet |
Carlos A. Escobar Ruben Morales-Menendez Daniela Macias |
author_sort |
Carlos A. Escobar |
title |
Process-monitoring-for-quality — A machine learning-based modeling for rare event detection |
title_short |
Process-monitoring-for-quality — A machine learning-based modeling for rare event detection |
title_full |
Process-monitoring-for-quality — A machine learning-based modeling for rare event detection |
title_fullStr |
Process-monitoring-for-quality — A machine learning-based modeling for rare event detection |
title_full_unstemmed |
Process-monitoring-for-quality — A machine learning-based modeling for rare event detection |
title_sort |
process-monitoring-for-quality — a machine learning-based modeling for rare event detection |
publisher |
Elsevier |
series |
Array |
issn |
2590-0056 |
publishDate |
2020-09-01 |
description |
Process Monitoring for Quality is a Big Data-driven quality philosophy aimed at defect detection through binary classification and empirical knowledge discovery. It is founded on Big Models, a predictive modeling paradigm that applies Machine Learning, statistics and optimization techniques to process data to create a manufacturing functional model. Functional refers to a parsimonious model with high detection ability that can be trusted by engineers, and deployed to control production. A parsimonious modeling scheme is presented aimed at rare quality event detection, parsimony is induced through feature selection and model selection. Its unique ability to deal with highly/ultra-unbalanced data structures and diverse learning algorithms is validated with four case studies, using the Support Vector Machine, Logistic Regression, Naive Bayes and k-Nearest Neighbors learning algorithms. And according to experimental results, the proposed learning scheme significantly outperformed typical learning approaches based on the l1-regularized logistic regression and Random Undersampling Boosting learning algorithms, with respect to parsimony and prediction. |
topic |
Quality control Manufacturing systems Machine learning Feature elimination Model selection Unbalanced binary data |
url |
http://www.sciencedirect.com/science/article/pii/S2590005620300199 |
work_keys_str_mv |
AT carlosaescobar processmonitoringforqualityamachinelearningbasedmodelingforrareeventdetection AT rubenmoralesmenendez processmonitoringforqualityamachinelearningbasedmodelingforrareeventdetection AT danielamacias processmonitoringforqualityamachinelearningbasedmodelingforrareeventdetection |
_version_ |
1724614759086555136 |