典型文献
Adaptive multiscale convolutional neural network model for chemical process fault diagnosis
文献摘要：
Intelligent fault recognition techniques are essential to ensure the long-term reliability of manufacturing.Due to the variations in material,equipment and environment,the process variables monitored by sen-sors contain diverse data characteristics at different time scales or in multiple operating modes.Despite much progress in statistical learning and deep learning for fault recognition,most models are constrained by abundant diagnostic expertise,inefficient multiscale feature extraction and unruly multimode condi-tion.To overcome the above issues,a novel fault diagnosis model called adaptive multiscale convolu-tional neural network(AMCNN)is developed in this paper.A new multiscale convolutional learning structure is designed to automatically mine multiple-scale features from time-series data,embedding the adaptive attention module to adjust the selection of relevant fault pattern information.The triplet loss optimization is adopted to increase the discrimination capability of the model under the multimode condition.The benchmarks CSTR simulation and Tennessee Eastman process are utilized to verify and illustrate the feasibility and efficiency of the proposed method.Compared with other common models,AMCNN shows its outstanding fault diagnosis performance and great generalization ability.
文献关键词：
中图分类号：
作者姓名：
Ruoshi Qin;Jinsong Zhao
作者机构：
State Key Laboratory of Chemical Engineering,Department of Chemical Engineering,Tsinghua University,Beijing 100084,China;Beijing Key Laboratory of Industrial Big Data System and Application,Tsinghua University,Beijing 100084,China
文献出处：
引用格式：
[1]Ruoshi Qin;Jinsong Zhao-.Adaptive multiscale convolutional neural network model for chemical process fault diagnosis)[J].中国化学工程学报（英文版）,2022(10):398-411
A类：
unruly,AMCNN
B类：
Adaptive,multiscale,convolutional,neural,network,chemical,process,fault,diagnosis,Intelligent,recognition,techniques,essential,ensure,long,term,reliability,manufacturing,Due,variations,material,equipment,environment,variables,monitored,by,sors,contain,diverse,data,characteristics,different,scales,multiple,operating,modes,Despite,much,progress,statistical,learning,deep,most,models,constrained,abundant,diagnostic,expertise,inefficient,extraction,multimode,To,overcome,above,issues,novel,called,adaptive,developed,this,paper,new,structure,designed,automatically,mine,features,from,series,embedding,attention,module,adjust,selection,relevant,pattern,information,triplet,loss,optimization,adopted,increase,discrimination,capability,under,condition,benchmarks,CSTR,simulation,Tennessee,Eastman,utilized,verify,illustrate,feasibility,efficiency,proposed,method,Compared,other,common,shows,its,outstanding,performance,great,generalization
AB值：
0.619089
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
