The construction method of typical engine fault identification model based on Simulink

被引:1
作者
Xin Bo [1 ]
Zhu Cheng [2 ]
Hu RuiJie [2 ]
Jiang Zhinong [3 ]
Gao Zhilong [3 ]
机构
[1] Beijing Univ Chem Technol, Key Lab Engine Hlth Monitoring Control & Networki, Minist Educ, Beijing, Peoples R China
[2] China North Engine Res Inst, Tianjin, Peoples R China
[3] Beijing Univ Chem Technol, Minist Educ, Beijing Key Lab Hlth Monitoring Control & Fault S, Key Lab Engine Hlth Monitoring Control & Networki, Beijing, Peoples R China
关键词
Diesel Engine; Fault Identification; Model Construction; Simulink;
D O I
10.1016/j.ifacol.2024.11.113
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper provides a summary and overview of methods for constructing typical fault identification model for diesel engines based on Simulink, aiming at improving the efficiency of engine fault diagnosis and maintenance. First of all, the common types of diesel engine faults were analyzed, including intake and exhaust system faults, cooling system faults, lubrication system faults and fuel system faults. Then, the basic steps and methods of Simulink modeling are introduced in detail, by using data acquisition and preprocessing techniques, a large amount of sensor data was converted into signals that can be used as inputs. Next, this paper discussed the specific process of the fault identification model, including the data reading module, speed discrimination module, threshold discrimination module and state identification module, and the feasibility of the model is verified through practical application cases. The research show that the fault identification model based on Simulink can effectively improve the accuracy and efficiency of engine fault diagnosis, providing a new technical method to enhance the operational safety and reliability of engines, and also offering valuable reference for subsequent related research. Copyright (c) 2024 The Authors.
引用
收藏
页码:19 / 24
页数:6
相关论文
共 15 条
[1]   Methodology and application of digital twin-driven diesel engine fault diagnosis and virtual fault model acquisition [J].
Bo, Yaqing ;
Wu, Han ;
Che, Weifan ;
Zhang, Zeyu ;
Li, Xiangrong ;
Myagkov, Leonid .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 131
[2]  
Duma I., 2024, IOP Conference Series: Materials Science and Engineering, V1
[3]   Machine learning and IoT - Based predictive maintenance approach for industrial applications [J].
Elkateb, Sherien ;
Metwalli, Ahmed ;
Shendy, Abdelrahman ;
Abu-Elanien, Ahmed E. B. .
ALEXANDRIA ENGINEERING JOURNAL, 2024, 88 :298-309
[4]  
Ghadimi P, 2014, Journal of the Brazilian Society of Mechanical Sciences and Engineering
[5]   Research on bearing fault diagnosis based on novel MRSVD-CWT and improved CNN-LSTM [J].
Guo, Yuan ;
Zhou, Jun ;
Dong, Zhenbiao ;
She, Huan ;
Xu, Weijia .
MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (09)
[6]   Fault diagnosis of a wave energy converter gearbox based on an Adam optimized CNN-LSTM algorithm [J].
Kang, Jichuan ;
Zhu, Xu ;
Shen, Li ;
Li, Mingxin .
RENEWABLE ENERGY, 2024, 231
[7]  
Li K., 2023, Internal Combustion Engines and Accessories, V16, P80, DOI [10.19475/j.cnki.issn1674, DOI 10.19475/J.CNKI.ISSN1674]
[8]   Research on Diesel Engine Fault Status Identification Method Based on Synchro Squeezing S-Transform and Vision Transformer [J].
Li, Siyu ;
Liu, Zichang ;
Yan, Yunbin ;
Wang, Rongcai ;
Dong, Enzhi ;
Cheng, Zhonghua .
SENSORS, 2023, 23 (14)
[9]  
Qu G., 2023, 2023 INT C IM PROC C
[10]  
Udaya Sri K, 2021, Int J Innovative Technol Explor Eng, V10, P42