Fault diagnosis algorithm of diesel engine cooling system based on physical model and support vector machine

doi:10.3969/j.issn.1674-8484.2020.04.013

Abstract

Abstract:

An intelligent fault diagnosis algorithm was developed by using synchronous operating physical model and small sample data-driven to effectively monitor and accurately diagnose the faults of the cooling system of diesel engine with strong coupling, large time scale and few variables to be monitored. A simplified physical model that based on the physical principle of cooling system was built in the algorithm. The support vector machine (SVM) was used to classify the fault information based on the residual of actual water temperature of the engine and the predicted water temperature of the synchronous operating model to identify the cause of the fault. The algorithm was tested on a precisely calibrated GT-Power diesel engine model and a real bus with fault. The results show that the identification accuracy of the algorithm is above 97%, and the diagnosis time is within 45 s after fault occurred; the algorithm has good monitoring ability and accurate identification potential for cooling system faults.

Key words: diesel engine, cooling system, fault diagnosis, physical model, support vector machine (SVM)

CLC Number:

TK428

ZHU Guanhong, SONG Kang, XIE Hui, CHEN Tao, QIAN Zhenhuan. Fault diagnosis algorithm of diesel engine cooling system based on physical model and support vector machine[J]. Journal of Automotive Safety and Energy, 2020, 11(4): 529-537.

Figures/Tables 16

References 22

[1]	赵焱明. 大功率车用发动机冷却系统研究[D]. 哈尔滨: 哈尔滨工业大学, 2017.
	ZHAO Yanming. Research on cooling systerm of high power vehicle engine[D]. Harbin: Harbin Institute of Technology, 2017. (in Chinese)
[2]	Song J, Lee Z, Song J, et al. Effects of injection strategy and coolant temperature on hydrocarbon and particulate emissions from a gasoline direct injection engine with high pressure injection up to 50 MPa[J]. Energy, 2018,164:512-522.
[3]	Eriksson L, Nielsen L. Modeling and control of engines and drivelines[M]. John Wiley and Sons, Chichester, 2014: 382-421.
[4]	吴瑞莉. 船舶柴油机机械磨损故障诊断方法[J]. 舰船科学技术, 2018,40(14):109-111.
	WU Ruili. Fault diagnosis method for mechanical wear of marine diesel engine[J]. Ship Sci Tech, 2018,40(14):109-111. (in Chinese)
[5]	蒋佳炜, 胡以怀, 柯赟, 等. 基于小波能量谱分析与SVM的柴油机气阀间隙异常故障诊断[J]. 机电设备, 2018,35(4):58-65.
	JIANG Jiawei, HU Yihuai, KE Yun, et al. Abnormal fault diagnosis of gas valve clearance in diesel engine based on wavelet energy spectrum analysis & SVM[J]. Mech Electr Equip, 2018,35(4):58-65. (in Chinese)
[6]	沈绍辉. 基于人工蜂群算法优化支持向量机的柴油机故障诊断研究[D]. 太原: 中北大学, 2016.
	SHEN Shaohui. Research on diesel engine fault diagnosis based on support vector machine optimized by artificial bee colony algorithm[D]. Taiyuan: University of North, 2016. (in Chinese)
[7]	李常镱. 基于贝叶斯网络的发动机故障诊断[D]. 太原: 中北大学, 2012.
	LI Changyi. Engine fault diagnosis based on Bayesian network[D]. Taiyuan: University of North, 2012. (in Chinese)
[8]	王海澜. 基于故障树的天然气发动机故障诊断专家系统设计[J]. 电子技术与软件工程, 2019,5:29-30.
	WANG Hailan. Design of natural gas engine fault diagnosis expert system based on fault tree[J]. Electr Tech Soft Engi, 2019,5:29-30. (in Chinese)
[9]	XU Xiaojian, ZHAO Zhuangzhuang, XU Xiaobin, et al. Machine learning-based wear fault diagnosis for marine diesel engine by fusing multiple data-driven models[J]. Knowledge-Based Syst, 2020,190:105324.
[10]	Namigtle-Jiménez A, Escobar-Jiménez R F, Gómez-Aguilar J F, et al. Online ANN-based fault diagnosis implementation using an FPGA: Application in the EFI system of a vehicle[J]. ISA Trans, 2019,11:003.
[11]	Nahim H M, Younes R, Shraim H, et al. Modeling with fault integration of the cooling and the lubricating systems in marine diesel engine: Experimental validation[J]. IFAC Papers OnLine, 2016,49-11:570-575.
[12]	Pagán J A, Vera-García F, Grau J H, et al. Marine diesel engine failure simulator Based on Thermodynamic model[J]. Appl Therm Engi, 2018,144:982-995.
[13]	武磊. 发动机冷却控制系统设计及节温器诊断[D]. 重庆: 重庆交通大学, 2017.
	WU Lei. Engine cooling control system design and thermostat diagnosis[D]. Chongqing: Chongqing Jiaotong University, 2017. (in Chinese)
[14]	褚良宇. 汽车发动机冷却系统故障诊断方法研究[D]. 重庆: 重庆邮电大学, 2019.
	CHU Liangyu. Research on fault diagnosis method of automobile engine cooling system[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2019. (in Chinese)
[15]	Cristianini N, Shawe-Taylor J. 支持向量机导论[M]. 李国正, 王猛, 曾华军, 译. 北京: 电子工业出版社, 2004: 8-22.
	Cristianini N, Shawe-Taylor J. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods [M]. LI Guozheng, WANG Meng, ZENG Huajun, translation. Beijing: Electronic Industry Press, 2004: 8-22. (in Chinese)
[16]	Nasiri A, Taheri-Garavand A, Omid M, et al. Intelligent fault diagnosis of cooling radiator based on deep learning analysis of infrared thermal images[J]. Appl Therm Engi, 2019,163:114410.
[17]	袁兆成. 内燃机设计(第2版) [M]. 北京: 机械工业出版社, 2016: 255-268.
	YUAN Zhaocheng. Internal Combustion Engine Design (2nd Ed.) [M]. Beijing: Machinery Industry Press, 2016: 255-268. (in Chinese)
[18]	圆山重直. 传热学[M]. 王世学, 张信荣, 译. 北京: 北京大学出版社, 2011: 215-233.
	Yuanshan C. Heat Transfer [M]. WANG Shixue, ZHANG Xinrong (translation). Beijing: Peking University Press. 2011: 215-233. (in Chinese)
[19]	Elsaid A M. Experimental study on the heat transfer performance and friction factor characteristics of Co₃O₄ and Al₂O₃ based H₂O / (CH₂OH) ₂ nanofluids in a vehicle engine radiator[J]. Int’l Commun Heat Mass Transfer, 2019,108:104263.
[20]	Sahoo R R, Ghosh P, Sarkar J. Energy and exergy comparisons of water based optimum brines as coolants for rectangular fin automotive radiator[J]. Int’l J Heat Mass Transfer, 2017,105:690-696.
[21]	吴勇灵, 杨娜, 潘晓慧, 等. 基于莱以特准则和数据融合的温湿度检测系统[J]. 科技通报, 2017,33(3):96-99.
	WU Yonging, YANG Na, PAN Xiaohui, et al. Temperature and humidity detection system based on Letts criterion and data fuse[J]. Bullet Sci Tech, 2017,33(3):96-99. (in Chinese)
[22]	鲍伟, 葛建军. 基于稀疏采样数据的电动公交车电池SOC预测方法研究[J]. 汽车工程, 2020,42(3):367-374.
	BAO Wei, GE Jianjun. Study on battery SOC prediction method for electric bus based on sparsely sampled data[J]. Autom Engi, 2020,42(3):367-374. (in Chinese)

柴油机类型	六缸直列增压
排量	6.2 L
额定功率	201 kW
额定转速	2 300 r·min^-1
最大转矩	1.06 kNm
最大转矩转速	1 200~1 800 r·min^-1
水泵驱动方式	曲轴皮带传动
风扇驱动方式	电机带动
正常出水温度	80 ~ 95 ℃
车辆质量	10.5 t
迎风面积	8.192 m²
风阻系数	0.362
滚阻系数	0.059
主减速比	3.89
轮胎半径	0.478 m

柴油机类型	六缸直列增压
排量	6.2 L
额定功率	201 kW
额定转速	2 300 r·min^-1
最大转矩	1.06 kNm
最大转矩转速	1 200~1 800 r·min^-1
水泵驱动方式	曲轴皮带传动
风扇驱动方式	电机带动
正常出水温度	80 ~ 95 ℃
车辆质量	10.5 t
迎风面积	8.192 m²
风阻系数	0.362
滚阻系数	0.059
主减速比	3.89
轮胎半径	0.478 m

评估项目	采样点比例 / %	最大误差值
稳态工况进出水温差	92.7	0.6 K
道路工况出水温度	90.6	3.2 ℃
道路工况升温速度	97.2	0.05 K/s

评估项目	采样点比例 / %	最大误差值
稳态工况进出水温差	92.7	0.6 K
道路工况出水温度	90.6	3.2 ℃
道路工况升温速度	97.2	0.05 K/s

状态编号	状态描述	r_out 状态	r_int状态
1	水泵停滞	-1	-1
2	水泵卡滞	-1	1
3	散热器水路堵塞	-1	-1
4	散热器气路堵塞	1	-1
5	节温器卡滞（升程< 4 mm)	1	-1
6	节温器卡滞（升程>9 mm）	1	1
7	正常	1	1