基于智能优化相关向量机的综合传动变工况直驶传递效率预测

doi:10.12382/bgxb.2022.0728

摘要/Abstract

摘要：

传递效率是表征履带车辆综合传动装置性能的重要指标之一,但综合传动装置内部复杂的动力传递路径和外部工作环境导致其传递效率预测模型建模困难,无法保证传递效率的准确计算。基于上述分析,提出一种基于综合传动装置直驶模式下多种工况传递效率数据驱动的传递效率预测方法。对75台综合传动装置不同工况下的传递效率数据进行统计分析并得到统计特征;通过统计特征选择智能优化相关向量机进行传递效率预测建模,进而实现待测综合传动装置在变工况直驶模式下的传递效率预测。结果表明,变工况下测试样本传递效率预测结果的平均绝对误差和均方根误差分别控制在0.01和0.02以内,验证了该方法的可行性和正确性。

关键词: 综合传动, 直驶, 传递效率预测, 变工况, 相关向量机

Abstract:

Transmission efficiency is one of the important indicators to characterize the performance of integrated transmission devices of tracked vehicles. However, due to the complex power transmission paths inside the integrated transmission device and external working conditions, it is difficult to establish the transmission efficiency prediction model, and thus the prediction accuracy of transmission efficiency cannot be guaranteed. An approach is proposed for transmission efficiency prediction under multiple working conditions with the straight driving of the integrated transmission device. First, the statistical features are obtained by performing statistical analysis of the transmission efficiency data of 75 integrated transmission devices under different working conditions. Then, the relevance vector machine (RVM) with intelligent optimization is employed for modeling transmission efficiency prediction based on such statistical features. Further, the transmission efficiency of the integrated transmission devices is predicted under different working conditions. The results show that the mean absolute error (MAE) and the root mean square error (RMSE) of the predictions under different working conditions are controlled to within 0.01 and 0.02, respectively, which could verify the feasibility and correctness of the approach.

Key words: integrated transmission, straight driving, transmission efficiency prediction, variable working condition, relevance vector machine

中图分类号:

U463.22

张金豹, 盖江涛, 安媛媛, 桂林, 朱炳先, 邹天刚. 基于智能优化相关向量机的综合传动变工况直驶传递效率预测[J]. 兵工学报, 2023, 44(1): 270-278.

ZHANG Jinbao, GAI Jiangtao, AN Yuanyuan, GUI Lin, ZHU Bingxian, ZOU Tiangang. Straight Driving Transmission Efficiency Prediction of Integrated Transmission under Variable Working Conditions Based on Relevance Vector Machine with Intelligent Optimization[J]. Acta Armamentarii, 2023, 44(1): 270-278.

图/表 12

图1 综合传动装置原理图

Fig.1 Schematic diagram of an integrated transmission device

图2 综合传动装置传递效率测试试验台

Fig.2 Test bench for transmission efficiency of an integrated transmission device

表1 多挡位试验方案设计

Table 1 Test schemes with multiple gear positions

速度/ (r·min^-1)	挡位
速度/ (r·min^-1)	F1	F2	F3	F4	F5	F6	R1	R2
1600	75	75	75	75	75	75	75	75
1800	75	75	75	75	75	75	75	75
2000	75	75	75	75	75	75	75	75
2200	75	75	75	75	75	75	75	75

图3 各工况下传递效率统计规律

Fig.3 Statistical variation of transmission efficiency under different conditions

图4 各挡位在2200r/min,全功率加载下的传递效率Q-Q图

Fig.4 Q-Q plot of the transmission efficiency of each gear at 2200r/min and full power load

图5 各工况下传递效率的峭度值

Fig.5 Kurtosis values of transmission efficiency under various conditions

图6 各挡位在2200r/min,全功率加载下的传递效率和输入扭矩的概率关系图

Fig.6 Probabilistic correlation plot of the transmission efficiency and the input torque of each gearat 2200r/min and full power load

表2 智能优化RVM的输入和输出

Table 2 Input and output of RVM with intelligent optimization

输入	测试变量设定值	输出
挡位	F1~F6;R1~R2
转速	1600、1800、2000、2200r/min	传递
工况	液力0(F1、F2和R1~R2)、机械1(F3~F6)	效率
负载(输入扭矩)	50%全功率、全功率

图7 粒子群优化收敛过程

Fig.7 Convergence process of particle swarm optimization

图8 训练样本的拟合误差和测试样本的预测误差

Fig.8 Fitting errors of training samples and prediction errors of test samples

图9 测试样本变工况直驶传递效率预测结果

Fig.9 Prediction results of straight driving transmission efficiency of the test samples under variable working conditions

图10 不同转速及对应输入扭矩下的传递效率趋势预测

Fig.10 Transmission efficiency trend prediction with different speeds and the corresponding input torques

参考文献 21

[1]	徐保荣, 张金豹, 姚李刚, 等. 液力机械综合传动装置低温阻力矩特性研究与验证[J/OL]. 兵工学报. doi:10.12382/bgxb.2022.0182. doi: 10.12382/bgxb.2022.0182
	XU B R, ZHANG J B, YAO L G, et al. Research and validation on resistance torque characteristics of hydro-mechanical comprehensive transmission device at low temperature condition[J/OL]. Acta Armamentarii. doi:10.12382/bgxb.2022.0182. (in Chinese) doi: 10.12382/bgxb.2022.0182
[2]	李义军, 毕小平, 马宁, 等. 车辆传动装置产热建模与计算分析[J]. 中国工程机械学报, 2013, 11(3): 216-221.
	LI Y J, BI X P, MA N, et al. Modeling and analysis on the transmission heat generation of vehicles[J]. Chinese Journal of Construction Machinery, 2013, 11(3): 216-221. (in Chinese)
[3]	王斌, 宁斌, 陈辛波, 等. 齿轮传动搅油功率损失的研究进展[J]. 机械工程学报, 2020, 56(23): 1-20. doi: 10.3901/JME.2020.23.001
	WANG B, NING B, CHEN X B, et al. Research progress in churning losses of gear transmission[J]. Journal of Mechanical Engineering, 2020, 56(23): 1-20. (in Chinese) doi: 10.3901/JME.2020.23.001
[4]	SHEN Y, RINDERKNECHT S. A method on modelling and analyzing the power losses in vehicle transmission[J]. Forsch Ingenieurwes, 2018, 82(7): 261-270. doi: 10.1007/s10010-018-0276-y URL
[5]	YANG F C, WANG Y F. Efficiency analysis of multi-speed automatic transmission with planetary gear trains[J]. Forsch Ingenieurwes, 2017, 81(8): 163-173. doi: 10.1007/s10010-017-0217-1 URL
[6]	AÏTTALEB A, CHAÂBA A, SALLAOU M. Efficiency evaluation of continuously variable transmissions including a planetary gear train[J]. Energy and Power Engineering, 2013, 5(2): 153-160. doi: 10.4236/epe.2013.52015 URL
[7]	LI L Y. Research on variable transmission efficiency of automobile transmission based on the MASTA software[J]. Applied Mechanics and Materials, 2013, 389(8): 398-403. doi: 10.4028/www.scientific.net/AMM.389.398 URL
[8]	张金豹, 邹天刚, 高秀才, 等. 基于中位秩加权的车辆传动装置直驶模式传递效率性能评估[J]. 兵工学报, 2022, 43(S1): 54-59. doi: 10.12382/bgxb.2022.A018
	ZHANG J B, ZOU T G, GAO X C, et al. Straight driving efficiency assessment of vehicle transmission device based on the median-rank weighting[J]. ACTA ARMAMENTARII, 2022, 43(S1): 54-59. (in Chinese) doi: 10.12382/bgxb.2022.A018
[9]	OLKIN I. Life distributions: a brief discussion[J]. Communications in Statistics-Simulation and Computation, 2016, 45(5): 1489-1498. doi: 10.1080/03610918.2014.966833 URL
[10]	ALMALKI S J, NADARAJAH S. Modifications of the Weibull distribution: A review[J]. Reliability Engineering and System Safety, 2014, 124(4): 32-55. doi: 10.1016/j.ress.2013.11.010 URL
[11]	杜刚, 赵冬梅, 刘鑫, 等. 基于重尾分布的风电功率波动特性概率分布[J]. 电力自动化设备, 2021, 41(7): 52-57, 72.
	DU G, ZHAO D M, LIU X, et al. Probability distribution of wind power fluctuation characteristics based on heavy-tailed distribution[J]. Electric Power Automation Equipment, 2021, 41(7): 52-57, 72. (in Chinese)
[12]	郑建锋, 王应明. 基于DEA-BP神经网络的效率置信区间预测模型研究[J]. 计算机工程与应用, 2021, 57(3): 273-278. doi: 10.3778/j.issn.1002-8331.1910-0364
	ZHENG J F, WANG Y M. Research on efficiency confidence interval prediction model based on DEA-BP neural network[J]. Computer Engineering and Applications, 2021, 57(3): 273-278. (in Chinese) doi: 10.3778/j.issn.1002-8331.1910-0364
[13]	ZOU T G, ZHANG J B, YAN Q D, et al. An approach for performance assessment of tracked vehicle transmission based on the median-rank weight and the least-square support vector machine[J]. Mathematical Problems in Engineering, 2022(7): 7084813.
[14]	MESSEM A V, CHRISTMANN A. A review on consistency and robustness properties of support vector machine for heavy-tailed distributions[J]. Advances in Data Analysis and Classification, 2010, 4(9): 199-220. doi: 10.1007/s11634-010-0067-2 URL
[15]	TIPPING M E. Sparse Bayesian learning and the relevance vector machine[J]. Journal of Machine Learning Research, 2001, 1(9): 211-244.
[16]	ZIO E, MAIO F D. Fatigue crack growth estimation by relevance vector machines[J]. Expert Systems with Applications, 2012, 39: 510681-10692.
[17]	范强飞, 廖爱华, 丁亚琦. 基于RVM和WPHM的滚动轴承剩余寿命预测[J]. 上海工程技术大学学报, 2019, 33(4): 334-338.
	FAN Q F, LIAO A H, DING Y Q. Remaining useful life prediction of rolling bearing based on RVM and WPHM[J]. Journal of Shanghai University of Engineering Science, 2019, 33(4): 334-338. (in Chinese)
[18]	刘月峰, 赵光权, 彭喜元. 多核相关向量机优化模型的锂电池剩余寿命预测方法[J]. 电子学报, 2019, 47(6): 1285-1292.
	LIU Y F, ZHAO G Q, PENG X Y. A lithium-ion battery remaining using life prediction method based on multi-kernel relevance vector machine optimized model[J]. ACTA ELECTRONICA SINICA, 2019, 47(6): 1285-1292. (in Chinese)
[19]	雷亚国, 陈吴, 李乃鹏, 等. 自适应多核组合相关向量机预测方法及其在机械设备剩余寿命预测中的应用[J]. 机械工程学报, 2016, 52(1): 87-93. doi: 10.3901/JME.2016.01.087
	LEI Y G, CHEN W, LI N P, et al. A relevance vector machine prediction method based on adaptive multi-kernel combination and its application to remaining useful life prediction of machinery[J]. Chinese Journal of Mechanical Engineering, 2016, 52(1): 87-93. (in Chinese)
[20]	KENNEDY J, EBERHART R. Particle swarm optimization[C]∥Proceedings of IEEE International Conference on Neural Network, 1995, 4: 1942-1948.
[21]	张金豹. 基于全寿命数据的滚动轴承运行状态评估和剩余寿命预测[D]. 哈尔滨: 哈尔滨工业大学, 2020.
	ZHANG J B. Operating condition assessment and remaining life prediction of rolling bearings based on the life-cycle data[D]. Harbin: Harbin Institute of Technology, 2020. (in Chinese)