A zero-shot industrial process fault diagnosis method based on domain-shift constraints

被引:0
作者
Tang, Siyu [1 ]
Shi, Hongbo [1 ]
Song, Bing [1 ]
Tao, Yang [1 ]
机构
[1] East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China
关键词
Zero-shot learning; Fault diagnosis; Domain shift; Prototype learning; NETWORKS;
D O I
10.1016/j.jtice.2024.105784
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Background: Fault diagnosis is crucial for industrial maintenance, but existing supervised methods rely on extensive data, which is often difficult to collect. The challenge of gathering comprehensive fault samples limits the performance of traditional fault diagnosis methods. Method: In this paper, we propose a fault diagnosis method named ZSIDM-OC to address the zero-shot problem in industrial processes, specifically concerning the domain shift issue. This novel framework includes three key modules: the Hierarchical Global-Local Feature Integration Module for capturing both global and local features of the fault data; the Prototype-Based Discriminative Loss Module, which reduces feature redundancy and enhances the model's ability to recognize unknown fault classes; and the Bidirectional Consistency Enforcement Module ensuring consistent data distribution in both low-dimensional and high-dimensional spaces, thereby reducing domain shift. Significant Findings: Our analysis indicates that the domain shift problem is inevitable in a zero-shot setting and significantly affects the performance of existing methods. Experimental results demonstrate that under zero-shot conditions, ZSIDM-OC offers significant advantages on both the Energy Storage Plant dataset and the Tennessee Eastman dataset. This method effectively mitigates the challenges posed by domain shift and limited fault sample availability, showcasing its potential to improve fault diagnosis in industrial processes.
引用
收藏
页数:10
相关论文
共 36 条
  • [31] Supervised convolutional autoencoder-based fault-relevant feature learning for fault diagnosis in industrial processes
    Yu, Feng
    Liu, Jianchang
    Liu, Dongming
    Wang, Honghai
    [J]. JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS, 2022, 132
  • [32] A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures
    Yu, Yong
    Si, Xiaosheng
    Hu, Changhua
    Zhang, Jianxun
    [J]. NEURAL COMPUTATION, 2019, 31 (07) : 1235 - 1270
  • [33] Zhao B, 2017, Arxiv, DOI arXiv:1711.07302
  • [34] Neighborhood preserving neural network for fault detection
    Zhao, Haitao
    Lai, Zhihui
    [J]. NEURAL NETWORKS, 2019, 109 : 6 - 18
  • [35] Zhao Y, 2024, Proc Inst Mech Eng Part I J Syst Control Eng
  • [36] Generalized Zero-Shot Recognition based on Visually Semantic Embedding
    Zhu, Pengkai
    Wang, Hanxiao
    Saligrama, Venkatesh
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 2990 - 2998