Industrial process fault diagnosis based on domain adaptive broad echo network

被引:3
作者
Mou, Miao [1 ]
Zhao, Xiaoqiang [1 ,2 ,3 ]
机构
[1] Lanzhou Univ Technol, Coll Elect & Informat Engn, Lanzhou 730050, Peoples R China
[2] Lanzhou Univ Technol, Gansu Key Lab Adv Control Ind Proc, Lanzhou 730050, Peoples R China
[3] Lanzhou Univ Technol, Natl Expt Teaching Ctr Elect & Control Engn, Lanzhou 730050, Peoples R China
基金
中国国家自然科学基金;
关键词
Fault diagnosis; Domain adaption; Broad learning system; Transfer learning; LEARNING-SYSTEM; KERNEL;
D O I
10.1016/j.jtice.2024.105453
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Background: In response to the challenge that traditional fault diagnosis models are difficult to maintain satisfactory accuracy when data distribution changes due to changes in process conditions, a fault diagnosis model of industrial process based on domain adaptive broad echo network (DABEN) is proposed. Methods: The DABEN model first constructs feature nodes through random feature mapping to extract shallow features of process data, and then inputs feature nodes into cascade reservoirs to extract dynamic features of different levels. On this basis, the objective function of DABEN is constructed, which starts from the four goals of minimizing the prediction error, maximum mean discrepancy distribution alignment, manifold regularization and minimizing cross-domain error to ensure that the features are as similar as possible between the source domain and the target domain. Significant Findings: Finally, two simulation cases show that DABEN can achieve good transfer fault diagnosis performance under different data distributions
引用
收藏
页数:15
相关论文
共 56 条
[1]   Data-Driven Fault Diagnostics for Industrial Processes: An Application to Penicillin Fermentation Process [J].
Abbasi, Muhammad Asim ;
Khan, Abdul Qayyum ;
Mustafa, Ghulam ;
Abid, Muhammad ;
Khan, Aadil Sarwar ;
Ullah, Nasim .
IEEE ACCESS, 2021, 9 :65977-65987
[2]  
Ajakan H, 2015, Arxiv, DOI arXiv:1412.4446
[3]  
Aldrich C, 2019, Process fault diagnosis for continuous dynamic systems over multivariate time series. Time series analysis-data, methods, and applications
[4]   An analysis of process fault diagnosis methods from safety perspectives [J].
Arunthavanathan, Rajeevan ;
Khan, Faisal ;
Ahmed, Salim ;
Imtiaz, Syed .
COMPUTERS & CHEMICAL ENGINEERING, 2021, 145
[5]   A Survey on Fault Detection and Diagnosis Methods [J].
Avila Okada, Kenji Fabiano ;
de Morais, Aniel Silva ;
Oliveira-Lopes, Luis Claudio ;
Ribeiro, Laura .
2021 14TH IEEE INTERNATIONAL CONFERENCE ON INDUSTRY APPLICATIONS (INDUSCON), 2021, :1422-1429
[6]   One step forward for smart chemical process fault detection and diagnosis [J].
Bi, Xiaotian ;
Qin, Ruoshi ;
Wu, Deyang ;
Zheng, Shaodong ;
Zhao, Jinsong .
COMPUTERS & CHEMICAL ENGINEERING, 2022, 164
[7]   Incipient fault detection for nonlinear processes based on dynamic multi-block probability related kernel principal component analysis [J].
Cai, Peipei ;
Deng, Xiaogang .
ISA TRANSACTIONS, 2020, 105 :210-220
[8]   Monitoring multi-domain batch process state based on fuzzy broad learning system [J].
Chang Peng ;
Ding ChunHao .
EXPERT SYSTEMS WITH APPLICATIONS, 2022, 187
[9]   Universal Approximation Capability of Broad Learning System and Its Structural Variations [J].
Chen, C. L. Philip ;
Liu, Zhulin ;
Feng, Shuang .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 30 (04) :1191-1204
[10]   Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture [J].
Chen, C. L. Philip ;
Liu, Zhulin .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (01) :10-24