Status and prospects in data-driven fault diagnosis for hot rolling process
MA Liang1,2, SHI Fuzhong1,2, PENG Kaixiang1,2
1. Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, Beijing 100083, China; 2. School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China
Abstract:Hot rolling process is an important cohering link in the whole production process of iron and steel, whose safe production and efficient operation are of great significance to the high-quality developments of iron and steel industry. Due to the complex and variable working conditions, clear system hierarchy of hot rolling process as well as the interconnection and coupling of loops, faults of multiple processes, equipment, subsystems or control loops may occur at the same time or cascade successively, which make the theories and methods of fault diagnosis for hot rolling process become research hotspots in the field of process control. Based on the analysis of characteristics and main fault types of hot rolling process, the research status of data-driven fault diagnosis methods for hot rolling process is emphatically summarized, the advantages and disadvantages of mainstream methods are qualitatively analyzed. Moreover, the existing problems of fault diagnosis for hot rolling process are sorted out, and the development directions in the future are further prospected.
马亮, 施富中, 彭开香. 数据驱动的热轧过程故障诊断研究现状与展望[J]. 中国冶金, 2023, 33(12): 12-17.
MA Liang, SHI Fuzhong, PENG Kaixiang. Status and prospects in data-driven fault diagnosis for hot rolling process[J]. China Metallurgy, 2023, 33(12): 12-17.
DONG M,LIU C. Design and fault diagnosis observer for HAGC system on strip rolling mill[J]. Journal of Iron and Steel Research,International,2006,13(4):27.
[11]
GU D W,POON F W. A robust fault-detection approach with application in a rolling-mill process[J]. IEEE Transactions on Control Systems Technology,2003,11(3):408.
LIU Q,ZHU Q Q,QIN S J,et al. Dynamic concurrent kernel CCA for strip-thickness relevant fault diagnosis of continuous annealing processes[J]. Journal of Process Control,2018,67:12.
ZHANG K,DONG J,PENG K X. A novel dynamic non-Gaussian approach for quality-related fault diagnosis with application to the hot strip mill process[J]. Journal of the Franklin Institute,2017,354(2):702.
[25]
MA L,DONG J,PENG K X,et al. Hierarchical monitoring and root-cause diagnosis framework for key performance indicator-related multiple faults in process industries[J]. IEEE Transactions on Industrial Informatics,2019,15(4):2091.
[26]
PENG K X,ZHANG K,DONG J,et al. Quality-relevant fault detection and diagnosis for hot strip mill process with multi-specification and multi-batch measurements[J]. Journal of the Franklin Institute,2015,352(3):987.
ELSHENAWY L M,CHAKOUR C,MAHMOUD T A. Fault detection and diagnosis strategy based on k-nearest neighbors and fuzzy C-means clustering algorithm for industrial processes[J]. Journal of the Franklin Institute,2022,359(13):711.
[32]
YANG W T,REIS M S,BORODIN V. An interpretable unsupervised Bayesian network model for fault detection and diagnosis[J]. Control Engineering Practice,2022,127:105304.
KATZEF M,CULLEN A C,ALPCAN T,et al. Generative adversarial networks for anomaly detection on decentralised data[J]. Annual Reviews in Control,2022,53:329.
[40]
WELLSANDT S,KLEIN K,HRIBERNIK K,et al. Hybrid-augmented intelligence in predictive maintenance with digital intelligent assistants[J]. Annual Reviews in Control,2022,53:382.
[41]
ALINEZHAD H S,ROOHI M H,CHEN T W. A review of alarm root cause analysis in process industries:Common methods,recent research status and challenges[J]. Chemical Engineering Research and Design,2022,188:846.
CACCIARELLI D,KULAHCI M. A novel fault detection and diagnosis approach based on orthogonal autoencoders[J]. Computers and Chemical Engineering,2022,163:107853.
ZHU Z,SHI H B,SONG B,et al. Convolutional neural network based feature learning for large-scale quality-related process monitoring[J]. IEEE Transactions on Industrial Informatics,2022,18(7):4555.