{"title":"Surveillance of high‐yield processes using deep learning models","authors":"Musaddiq Ibrahim, Chunxia Zhang, Tahir Mahmood","doi":"10.1002/qre.3635","DOIUrl":null,"url":null,"abstract":"Quality testing and monitoring advancements have allowed modern production processes to achieve extremely low failure rates, especially in the era of Industry 4.0. Such processes are known as high‐yield processes, and their data set consists of an excess number of zeros. Count models such as Poisson, Negative Binomial (NB), and Conway‐Maxwell‐Poisson (COM‐Poisson) are usually considered good candidates to model such data, but the excess zeros are larger than the number of zeros, which these models fit inherently. Hence, the zero‐inflated version of these count models provides better fitness of high‐quality data. Usually, linearly/non‐linearly related variables are also associated with failure rate data; hence, regression models based on zero‐inflated count models are used for model fitting. This study is designed to propose deep learning (DL) based control charts when the failure rate variables follow the zero‐inflated COM‐Poisson (ZICOM‐Poisson) distribution because DL models can detect complicated non‐linear patterns and relationships in data. Further, the proposed methods are compared with existing control charts based on neural networks, principal component analysis designed based on Poisson, NB, and zero‐inflated Poisson (ZIP) and non‐linear principal component analysis designed based on Poisson, NB, and ZIP. Using run length properties, the simulation study evaluates monitoring approaches, and a flight delay application illustrates the implementation of the research. The findings revealed that the proposed methods have outperformed all existing control charts.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Quality and Reliability Engineering International","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1002/qre.3635","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, INDUSTRIAL","Score":null,"Total":0}
引用次数: 0
Abstract
Quality testing and monitoring advancements have allowed modern production processes to achieve extremely low failure rates, especially in the era of Industry 4.0. Such processes are known as high‐yield processes, and their data set consists of an excess number of zeros. Count models such as Poisson, Negative Binomial (NB), and Conway‐Maxwell‐Poisson (COM‐Poisson) are usually considered good candidates to model such data, but the excess zeros are larger than the number of zeros, which these models fit inherently. Hence, the zero‐inflated version of these count models provides better fitness of high‐quality data. Usually, linearly/non‐linearly related variables are also associated with failure rate data; hence, regression models based on zero‐inflated count models are used for model fitting. This study is designed to propose deep learning (DL) based control charts when the failure rate variables follow the zero‐inflated COM‐Poisson (ZICOM‐Poisson) distribution because DL models can detect complicated non‐linear patterns and relationships in data. Further, the proposed methods are compared with existing control charts based on neural networks, principal component analysis designed based on Poisson, NB, and zero‐inflated Poisson (ZIP) and non‐linear principal component analysis designed based on Poisson, NB, and ZIP. Using run length properties, the simulation study evaluates monitoring approaches, and a flight delay application illustrates the implementation of the research. The findings revealed that the proposed methods have outperformed all existing control charts.
期刊介绍:
Quality and Reliability Engineering International is a journal devoted to practical engineering aspects of quality and reliability. A refereed technical journal published eight times per year, it covers the development and practical application of existing theoretical methods, research and industrial practices. Articles in the journal will be concerned with case studies, tutorial-type reviews and also with applications of new or well-known theory to the solution of actual quality and reliability problems in engineering.
Papers describing the use of mathematical and statistical tools to solve real life industrial problems are encouraged, provided that the emphasis is placed on practical applications and demonstrated case studies.
The scope of the journal is intended to include components, physics of failure, equipment and systems from the fields of electronic, electrical, mechanical and systems engineering. The areas of communications, aerospace, automotive, railways, shipboard equipment, control engineering and consumer products are all covered by the journal.
Quality and reliability of hardware as well as software are covered. Papers on software engineering and its impact on product quality and reliability are encouraged. The journal will also cover the management of quality and reliability in the engineering industry.
Special issues on a variety of key topics are published every year and contribute to the enhancement of Quality and Reliability Engineering International as a major reference in its field.