Bidirectional Recurrent Neural Network-Based Chemical Process Fault Diagnosis

被引:77
作者
Zhang, Shuyuan [1 ,2 ]
Bi, Kexin [1 ,2 ]
Qiu, Tong [1 ,2 ]
机构
[1] Tsinghua Univ, Dept Chem Engn, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Beijing Key Lab Ind Big Data Syst & Applicat, Beijing 100084, Peoples R China
基金
英国工程与自然科学研究理事会;
关键词
QUALITATIVE TREND ANALYSIS; DATA-DRIVEN; MODEL; MANAGEMENT; SYSTEMS; SIGNAL;
D O I
10.1021/acs.iecr.9b05885
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Correct and timely fault diagnosis is of great importance for enhancing the safety and reliability of modern chemical industrial processes. With the arrival of the big data era, data-driven fault detection and diagnosis (FDD) methods offer enormous potential for complex chemical processes. Deep learning-based data-driven FDD methods, which extract features from raw data using an artificial neural network (ANN), are attracting widespread attention. Among various types of neural networks, recurrent neural network (RNN) performs excellently when dealing with time-series data. However, a regular unidirectional RNN proceeds only in the positive time direction, resulting in insufficient feature extraction and inferior fault diagnosis performance. In this study, a bidirectional RNN (BiRNN) was employed to construct FDD models with sophisticated RNN cells. When applied to the benchmark Tennessee Eastman process, BiRNN-based FDD models exhibited a dramatically impressive performance, demonstrating the effectiveness of implementing BiRNN in chemical process fault diagnosis.
引用
收藏
页码:824 / 834
页数:11
相关论文
共 49 条
  • [1] A Bibliometric Review and Analysis of Data-Driven Fault Detection and Diagnosis Methods for Process Systems
    Alauddin, Md
    Khan, Faisal
    Imtiaz, Syed
    Ahmed, Salim
    [J]. INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2018, 57 (32) : 10719 - 10735
  • [2] Process system fault detection and diagnosis using a hybrid technique
    Amin, Md Tanjin
    Imtiaz, Syed
    Khan, Faisal
    [J]. CHEMICAL ENGINEERING SCIENCE, 2018, 189 : 191 - 211
  • [3] Artificial neural networks: fundamentals, computing, design, and application
    Basheer, IA
    Hajmeer, M
    [J]. JOURNAL OF MICROBIOLOGICAL METHODS, 2000, 43 (01) : 3 - 31
  • [4] Revision of the Tennessee Eastman Process Model
    Bathelt, Andreas
    Ricker, N. Lawrence
    Jelali, Mohieddine
    [J]. IFAC PAPERSONLINE, 2015, 48 (08): : 309 - 314
  • [5] LEARNING LONG-TERM DEPENDENCIES WITH GRADIENT DESCENT IS DIFFICULT
    BENGIO, Y
    SIMARD, P
    FRASCONI, P
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02): : 157 - 166
  • [6] CHO K., 2014, LEARNING PHRASE REPR, DOI DOI 10.3115/V1/D14-1179
  • [7] Smart plant operations: Vision, progress and challenges
    Christofides, Panagiotis D.
    Davis, James F.
    El-Farra, Nael H.
    Clark, Don
    Harris, Kevin R. D.
    Gipson, Jerry N.
    [J]. AICHE JOURNAL, 2007, 53 (11) : 2734 - 2741
  • [8] Chung J., 2014, ARXIV
  • [9] Abnormal situation management for smart chemical process operation
    Dai, Yiyang
    Wang, Hangzhou
    Khan, Faisal
    Zhao, Jinsong
    [J]. CURRENT OPINION IN CHEMICAL ENGINEERING, 2016, 14 : 49 - 55
  • [10] Challenges in the industrial applications of fault diagnostic systems
    Dash, S
    Venkatasubramanian, V
    [J]. COMPUTERS & CHEMICAL ENGINEERING, 2000, 24 (2-7) : 785 - 791