PCA-WA Based Approach for Concurrent Control Chart Pattern Recognition

IF 2.4 Q3 MANAGEMENT
A. Akaaboune, Ammar Elhassan, Ghazanfar Latif, J. Alghazo
{"title":"PCA-WA Based Approach for Concurrent Control Chart Pattern Recognition","authors":"A. Akaaboune, Ammar Elhassan, Ghazanfar Latif, J. Alghazo","doi":"10.31387/oscm0510360","DOIUrl":null,"url":null,"abstract":"Accurate and speedy automatic recognition of Statistical Process Control Chart Patterns (SPCC) is a vital task for supervising manufacturing processes. This is done for better control to produce high-quality products. The motivation of this work is to increase the recognition accuracy of concurrent patterns. In this paper, a novel approach is proposed, using neural networks (NN) with Wavelet Analysis (WA) and Principal Component Analysis (PCA) to address the (CCP) recognition problem in concurrent patterns. Eight types of concurrent patterns based on a combination of normal patterns and unnatural patterns are addressed namely; stratification, systematic, increasing trend, decreasing trend, upshift, downshift, and cyclic. Thirteen statistical and shape features are proposed as inputs to the model. The main contribution of this work is the enhancement of the performance of NN through the augmentation of the signal (control chart data) using WA and proposing better extracted statistical features through the use of PCA. Our work shows that improving the original signal and using the right features improves the accuracy of the CCP recognition significantly. The proposed approach has an overall accuracy of 96.3%. The method was compared with four other methods from the previous literature, and it outperformed these methods.","PeriodicalId":43857,"journal":{"name":"Operations and Supply Chain Management-An International Journal","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Operations and Supply Chain Management-An International Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.31387/oscm0510360","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MANAGEMENT","Score":null,"Total":0}
引用次数: 0

Abstract

Accurate and speedy automatic recognition of Statistical Process Control Chart Patterns (SPCC) is a vital task for supervising manufacturing processes. This is done for better control to produce high-quality products. The motivation of this work is to increase the recognition accuracy of concurrent patterns. In this paper, a novel approach is proposed, using neural networks (NN) with Wavelet Analysis (WA) and Principal Component Analysis (PCA) to address the (CCP) recognition problem in concurrent patterns. Eight types of concurrent patterns based on a combination of normal patterns and unnatural patterns are addressed namely; stratification, systematic, increasing trend, decreasing trend, upshift, downshift, and cyclic. Thirteen statistical and shape features are proposed as inputs to the model. The main contribution of this work is the enhancement of the performance of NN through the augmentation of the signal (control chart data) using WA and proposing better extracted statistical features through the use of PCA. Our work shows that improving the original signal and using the right features improves the accuracy of the CCP recognition significantly. The proposed approach has an overall accuracy of 96.3%. The method was compared with four other methods from the previous literature, and it outperformed these methods.
基于PCA-WA的并行控制图模式识别方法
准确、快速地自动识别统计过程控制图模式(SPCC)是监督制造过程的一项重要任务。这样做是为了更好地控制生产高质量的产品。这项工作的动机是提高并发模式的识别精度。本文提出了一种利用神经网络(NN)结合小波分析(WA)和主成分分析(PCA)来解决并发模式(CCP)识别问题的新方法。基于正常模式和非自然模式的组合,讨论了八种类型的并发模式,即;分层、系统性、上升趋势、下降趋势、上升趋势、下降趋势和循环。提出了13个统计和形状特征作为模型的输入。这项工作的主要贡献是通过使用WA增强信号(控制图数据)来增强神经网络的性能,并通过使用PCA提出更好的提取统计特征。我们的工作表明,改进原始信号并使用正确的特征可以显著提高CCP识别的准确性。该方法的总体准确率为96.3%。将该方法与以往文献中的其他四种方法进行了比较,结果表明该方法优于这些方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
5.40
自引率
27.80%
发文量
22
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信