{"title":"基于新型无监督深度神经网络(DNN)的刀具状态监测研究","authors":"Jingjing Gao, Jing Liu, Xinli Yu","doi":"10.21595/jve.2023.23361","DOIUrl":null,"url":null,"abstract":"In order to improve the recognition precision and accuracy of tool wear monitoring, an unsupervised deep neural network (DNN) based on stack denoising autoencoder (SDA) is proposed. After feature extraction and selection, the stack denoising automatic coding network reduces the dimensionality of the feature vector. On this basis, principal component analysis (PCA) and T-distributed random neighbor embedding (t-SNE) are used to reduce the dimensionality of the features twice, and finally a simple two-dimensional feature matrix is obtained. Finally, the deep neural network model of SDA is established by adding SoftMax regression layer, and the tool wear monitoring results are taken as new labeled data, and the deep neural network parameters are fine-tuned by secondary backpropagation. The experimental results show that the proposed method can learn adaptively and obtain effective feature expression, and the tool wear state recognition results are highly accurate. The proposed method can effectively identify the tool wear state.","PeriodicalId":49956,"journal":{"name":"Journal of Vibroengineering","volume":"113 ","pages":"0"},"PeriodicalIF":0.7000,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research on tool condition monitoring (TCM) using a novel unsupervised deep neural network (DNN)\",\"authors\":\"Jingjing Gao, Jing Liu, Xinli Yu\",\"doi\":\"10.21595/jve.2023.23361\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In order to improve the recognition precision and accuracy of tool wear monitoring, an unsupervised deep neural network (DNN) based on stack denoising autoencoder (SDA) is proposed. After feature extraction and selection, the stack denoising automatic coding network reduces the dimensionality of the feature vector. On this basis, principal component analysis (PCA) and T-distributed random neighbor embedding (t-SNE) are used to reduce the dimensionality of the features twice, and finally a simple two-dimensional feature matrix is obtained. Finally, the deep neural network model of SDA is established by adding SoftMax regression layer, and the tool wear monitoring results are taken as new labeled data, and the deep neural network parameters are fine-tuned by secondary backpropagation. The experimental results show that the proposed method can learn adaptively and obtain effective feature expression, and the tool wear state recognition results are highly accurate. The proposed method can effectively identify the tool wear state.\",\"PeriodicalId\":49956,\"journal\":{\"name\":\"Journal of Vibroengineering\",\"volume\":\"113 \",\"pages\":\"0\"},\"PeriodicalIF\":0.7000,\"publicationDate\":\"2023-10-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Vibroengineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.21595/jve.2023.23361\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, MECHANICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Vibroengineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.21595/jve.2023.23361","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
Research on tool condition monitoring (TCM) using a novel unsupervised deep neural network (DNN)
In order to improve the recognition precision and accuracy of tool wear monitoring, an unsupervised deep neural network (DNN) based on stack denoising autoencoder (SDA) is proposed. After feature extraction and selection, the stack denoising automatic coding network reduces the dimensionality of the feature vector. On this basis, principal component analysis (PCA) and T-distributed random neighbor embedding (t-SNE) are used to reduce the dimensionality of the features twice, and finally a simple two-dimensional feature matrix is obtained. Finally, the deep neural network model of SDA is established by adding SoftMax regression layer, and the tool wear monitoring results are taken as new labeled data, and the deep neural network parameters are fine-tuned by secondary backpropagation. The experimental results show that the proposed method can learn adaptively and obtain effective feature expression, and the tool wear state recognition results are highly accurate. The proposed method can effectively identify the tool wear state.
期刊介绍:
Journal of VIBROENGINEERING (JVE) ISSN 1392-8716 is a prestigious peer reviewed International Journal specializing in theoretical and practical aspects of Vibration Engineering. It is indexed in ESCI and other major databases. Published every 1.5 months (8 times yearly), the journal attracts attention from the International Engineering Community.