Fault Diagnosis of Armored Vehicle Engine Based on KLDA-IDBO-BP

doi:10.12382/bgxb.2024.0083

Abstract

Abstract:

Lubricating oil plays a pivotal role in engines due to carrying a wealth of information about the engine state,and is crucial for characterizing the faults of engine.The engine of an armored vehicle is studied,and a fault diagnosis method for the engine is proposed,which leverages the kernel linear discriminant analysis (KLDA) and an improved dung beetle optimization (DBO) algorithm to optimize a back propagation (BP) neural network.The dimensionality reduction of the acquired lubricating oil data is performed through KLDA,and the dimensionality reduced data is taken as input for the BP neural network.The DBO algorithm is then enhanced by integrating optimal Latin hypercube sampling method,weighting factors and Levy flight strategy in order to further optimize the key parameters of neural network.A fault diagnosis model is established to predict the faults in test data effectively.Experimental results affirm the proposed method’s efficacy in rapidly and accurately predicting the faults,providing a scientific basis for the maintenance and repair of engines in armored vehicles.

Key words: lubricating oil information, engine, fault diagnosis, dung beetle optimization algorithm, back propagation neural network, kernel linear discriminant analysis

CLC Number:

TJ811

LI Yingshun, YU Ang, LI Mao, HE Zhe, LIU Shiming. Fault Diagnosis of Armored Vehicle Engine Based on KLDA-IDBO-BP[J]. Acta Armamentarii, 2025, 46(3): 240083-.

Figures/Tables 11

References 22

[1]	杜志岐, 唐镜. 基于系统工程的装甲车辆总体设计[J]. 兵工学报, 2022, 43(增刊1):1-10.
	DU Z Q, TANG J. Overall design of armored vehicles based on system engineering[J]. Acta Armamentarii, 2022, 43(S1):1-10. (in Chinese) doi: 10.12382/bgxb.2022.A016
[2]	李英顺, 周通, 刘海洋, 等. IGWO-SVM在火控系统故障预测中的应用[J]. 火炮发射与控制学报, 2022, 43(6):57-63.
	LI Y S, ZHOU T, LIU H Y, et al. Application of IGWO-SVM in fault prediction of fire control systems[J]. Journal of Gun Launch & Control, 2022, 43(6):57-63. (in Chinese)
[3]	ZHAN Z Q, YANG D Q, WANG J, et al. Transformer fault diagnosis method based on neural network and DS evidence theory[J]. Journal of Physics:Conference Series, 2022, 2260:012002.
[4]	方喜峰, 于超, 章振, 等. 基于支持向量机的船用柴油机装配质量预测[J]. 组合机床与自动化加工技术, 2021(9):62-66. doi: 10.13462/j.cnki.mmtamt.2021.09.014
	FANG X F, YU C, ZHANG Z, et al. SVM-based prediction of assembly quality for marine diesel engines[J]. Combination Machine Tools & Automated Machining Technology, 2021(9):62-66. (in Chinese)
[5]	LIANG X, LUO Y X, DENG F, et al. Application of improved MFDFA and DS evidence theory in fault diagnosis[J]. Applied Sciences, 2022, 12(10):4976.
[6]	胡静, 吴迪. 基于改进神经网络的航空发动机故障预测[J]. 信息工程大学学报, 2020, 21(5):534-538.
	HU J, WU D. Aero-engine fault prediction based on improved neural network[J]. Journal of Information Engineering University, 2020, 21(5):534-538. (in Chinese)
[7]	张福生, 潘学文, 路超. 基于SSA优化BP神经网络的故障诊断系统研究[J]. 中国工程机械学报, 2022, 20(1):81-85,90.
	ZHANG F S, PAN X W, LU C. Research on fault diagnosis system based on SSA optimized BP neural network[J]. China Journal of Construction Machinery, 2022, 20(1):81-85,90. (in Chinese)
[8]	XUE J K, SHEN B. Dung beetle optimizer:a new meta-heuristic algorithm for global optimization[J]. The Journal of Supercomputing, 2023, 79(7):7305-7336.
[9]	KEMPFERT K C, WANG Y S, CHEN C X, et al. A comparison study on nonlinear dimension reduction methods with kernel variations:visualization,optimization and classification[J]. Intelligent Data Analysis, 2020, 24(2):267-290.
[10]	LI W W, TAN H L, FENG J W, et al. Kernel reverse neighborhood discriminant analysis[J]. Electronics, 2023, 12(6):1322.
[11]	HOFMANN T, SMOLA B S, SMOLA A. Kernel methods in machine learning[J]. The Annals of Statistics, 2008, 36(3):1171-1220.
[12]	QU Z X, MAO W Q, ZHANG K Q, et al. Multi-step wind speed forecasting based on a hybrid decomposition technique and an improved back-propagation neural network[J]. Renewable Energy, 2019, 133:919-929.
[13]	LIU H F, REN C, ZHENG Z T, et al. Study of a gray genetic BP neural network model in fault monitoring and a diagnosis system for dam safety[J]. ISPRS International Journal of Geo-Information, 2017, 7(1):4.
[14]	LIU P F, ZHANG W. A fault diagnosis intelligent algorithm based on improved BP neural network[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2019, 33(9):1959028.
[15]	SHEN Q W, ZHANG D M, XIE M S, et al. Multi-strategy enhanced dung beetle optimizer and its application in three-dimensional UAV path planning[J]. Symmetry, 2023, 15(7):1432.
[16]	MOUSAVIRAD S J, BIDGOLI A A, RAHNAMAYAN S. Tackling deceptive optimization problems using opposition-based DE with center-based Latin hypercube initialization[C]// Proceedings of the 2019 14th International Conference on Computer Science & Education. Toronto,ON,Canada: IEEE, 2019:394-400.
[17]	LIANG S J, PAN Y M, ZHANG H L, et al. Marine predators algorithm based on adaptive weight and chaos factor and its application[J]. Scientific Programming, 2022, 2022(1):4623980.
[18]	CHEN Y H, XI J F, WANG H B, et al. Grey wolf optimization algorithm based on dynamically adjusting inertial weight and levy flight strategy[J]. Evolutionary Intelligence, 2023, 16(3):917-927.
[19]	DHAWALE P G, KAMBOJ V K, BATH S K. A levy flight based strategy to improve the exploitation capability of arithmetic optimization algorithm for engineering global optimization problems[J]. Transactions on Emerging Telecommunications Technologies, 2023, 34(4):e4739.
[20]	薛鹏. 发动机润滑系统结构与主要部件的检修研究[J]. 内燃机与配件, 2020( 23):149-150.
	XUE P. Overhaul study of engine lubrication system structure and main components[J]. Internal Combustion Engines and Accessories, 2020(23):149-150. (in Chinese)
[21]	BENESTY J, CHEN J D, HUANG Y T, et al. Pearson correlation coefficient[M]// BENESTYJ, KELLERMANNW. Noise reduction in speech processing. Berlin,Heidelberg,Germany: Springer, 2009:37-40.
[22]	NTI I K, NYARKO-BOATENG O, ANING J. Performance of machine learning algorithms with different K values in K-fold cross-validation[J]. International Journal of Information Technology and Computer Science, 2021, 13(6):61-71.

故障类型	油液温度	油液压力	伴随现象
润滑油泵故障	不变	偏低	油液水分、密度产生变化,伴随异响
润滑油滤器阻塞	偏高	偏低	油液污染度、磨粒含量上升
润滑油冷却器故障	偏高	不变	油液黏度下降, 变稀
磨损机械故障	不变	偏高	油液磨粒含量上升,水分、密度产生变化

故障类型	油液温度	油液压力	伴随现象
润滑油泵故障	不变	偏低	油液水分、密度产生变化,伴随异响
润滑油滤器阻塞	偏高	偏低	油液污染度、磨粒含量上升
润滑油冷却器故障	偏高	不变	油液黏度下降, 变稀
磨损机械故障	不变	偏高	油液磨粒含量上升,水分、密度产生变化

故障类型编号	故障名称	训练集数据组数	测试集数据组数
1	润滑油冷却器故障	65	35
2	润滑油泵故障	65	35
3	润滑油滤器阻塞	65	35
4	磨损机械故障	65	35
5	其他故障	65	35

故障类型编号	故障名称	训练集数据组数	测试集数据组数
1	润滑油冷却器故障	65	35
2	润滑油泵故障	65	35
3	润滑油滤器阻塞	65	35
4	磨损机械故障	65	35
5	其他故障	65	35

水分/ %	密度/ (kg·m^-3)	温度/ ℃	黏度/ (mm²·s^-1)	污染度级	磨粒浓度	故障类型
0.16	841.52	88.93	70.86	2.23	3.28	1
0.15	842.36	68.92	27.36	2.26	3.35	1
0.11	690.63	31.13	86.98	1.95	2.89	2
0.18	850.42	55.37	26.87	2.15	1.43	2
0.09	870.27	20.81	89.45	1.93	2.18	3
0.14	673.46	54.74	46.46	1.85	4.55	3
0.21	899.05	89.37	62.21	2.21	5.29	4
0.15	880.73	38.39	90.75	2.63	4.36	4
0.18	697.30	50.54	61.56	2.23	3.98	5
0.06	828.33	20.35	70.86	2.26	2.85	5