基于改进PSO-BPNN的拖拉机液压油品质监测

doi:10.13733/j.jcam.issn.2095-5553.2024.10.021

摘要/Abstract

摘要： 为实现对拖拉机液压油品质的有效监测，保障拖拉机液压系统的平稳运行，基于改进PSO-BPNN设计一种针对拖拉机液压油品质的监测方法。首先，为研究拖拉机液压油品质恶化情况，在液压油新油的基础上配制不同比例的液压油油样。随后，搭建拖拉机液压油品质监测试验装置，并依据试验装置采集与监测液压油粘度、介电常数和温度参数。然后，设计并搭建一种基于改进PSO-BPNN的拖拉机液压油品质监测模型，该模型利用正弦调整惯性权重的PSO算法优化BPNN的权值和阈值初始值，提高模型收敛效率。最后，为验证基于改进PSO-BPNN的液压油品质监测方法的可行性，与基于传统BPNN、标准PSO-BPNN的拖拉机液压油品质监测模型进行对比。结果表明，基于改进PSO-BPNN的拖拉机液压油品质监测方法具有较快的收敛速度，监测正确率达到97.78%，为优化拖拉机液压油品质监测方法提供参考。

关键词: 拖拉机, 液压油品质, 改进PSO算法, BP神经网络

Abstract: In order to effectively monitor the quality of tractor hydraulic oil and ensure the smooth operation of the tractor hydraulic system, a monitoring method for tractor hydraulic oil quality was designed by using improved PSO-BPNN. Firstly, in order to study the deterioration of tractor hydraulic oil quality, different proportions of hydraulic oil samples were prepared on the basis of new hydraulic oil. Subsequently, a tractor hydraulic oil quality monitoring test device was built, and the viscosity, dielectric constant, and temperature of the hydraulic oil were collected and monitored based on the test device. Secondly, a tractor hydraulic oil quality monitoring model by using improved PSO-BPNN was designed. The model utilized the PSO algorithm with sine adjusted inertia weights to optimize the weights and initial threshold values of BPNN, improving the convergence efficiency of the model. Finally, for verifying the feasibility of the hydraulic oil quality monitoring method by using improved PSO-BPNN, a comparison was made with the tractor hydraulic oil quality monitoring models by using traditional BPNN and standard PSO-BPNN. The comparison results show that the tractor hydraulic oil quality monitoring method by using improved PSO-BPNN has a fast convergence speed, with a monitoring accuracy of 97.78%, which can provide reference for optimizing the tractor hydraulic oil quality monitoring method.

Key words: tractor, hydraulic oil quality, improved PSO algorithm, BP neural network

中图分类号:

S219
TP137

李仲兴, 朱方喜, 刘炳晨, 郗少华. 基于改进PSO-BPNN的拖拉机液压油品质监测[J]. 中国农机化学报, 2024, 45(10): 140-146.

Li Zhongxing, Zhu Fangxi, Liu Bingchen, Xi Shaohua. Quality monitoring of tractor hydraulic oil based on improved PSO-BPNN[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(10): 140-146.

参考文献

[ 1 ] 董志磊, 潘燕, 王月行. 液压油污染度和水分含量在线检测研究[J]. 润滑与密封, 2015, 40(7): 129-132.
[ 2 ] Ng F, Harding J A, Glass J. Improving hydraulic excavator performance through in line hydraulic oil contamination monitoring [J]. Mechanical Systems and Signal Processing, 2017, 83: 176-193.
[ 3 ] 陈希明. 商用车传动系统机油品质监测预警系统研究[D]. 长春: 吉林大学, 2021.
Chen Ximing. Research on monitoring and early warning system for oil quality of commercial vehicle transmission system [D]. Changchun: Jilin University, 2021.
[ 4 ] 郝延龙. 基于微流体与图像识别技术的润滑油磨粒分析方法[D]. 大连: 大连海事大学, 2017.
Hao Yanlong. Recognition for particles in lubricating oil based on microfluidics and image processing technology [D]. Dalian: Dalian Maritime University, 2017.
[ 5 ] 宋云清, 丁晓强. 液压伺服控制系统油液污染及控制[J]. 设备管理与维修, 2021(15): 135-137.
[ 6 ] 孙衍山, 邓可, 王钧. 液压油水污染在线连续检测传感器研究[J]. 润滑与密封, 2015, 40(7): 103-105, 132.
[ 7 ] 龚烈航, 王强, 徐群章, 等. 液压系统污染控制[M]. 北京: 国防工业出版社, 2010.
[ 8 ] Zeng R, Zhang Y, Lin Z R, et al. Contamination analysis and monitoring methods of hydraulic fluid [C]. 3rd Annual International Conference on Mechanics and Mechanical Engineering, Atlantis Press, 2016: 377-381.
[ 9 ] 李美威, 谢小鹏, 冯伟, 等. 基于ARMA模型的在线油液监测故障预警研究[J]. 润滑与密封, 2019, 44(12): 108-113.
[10] 林歆悠, 黄强, 张光吉. 基于PSO的新型双电机多模式驱动系统转矩分配策略优化[J]. 汽车工程, 2022, 44(8): 1218-1225.
Lin Xinyou, Huang Qiang, Zhang Guangji. Torque distribution strategy optimization of a novel dual‑motor multi‑mode drive system using PSO algorithm [J]. Automotive Engineering, 2022, 44(8): 1218-1225.
[11] 张扬, 朱志宇. 改进PSO算法优化LSSVM的柴油机排气预测[J]. 重庆理工大学学报(自然科学), 2020, 34(1): 103-110.
Zhang Yang, Zhu Zhiyu. Diesel engine exhaust prediction based on improved PSO algorithm optimized ISSVM model [J]. Journal of Chongqing University of Technology (Natural Science), 2020, 34(1): 103-110.
[12] 张拓, 余何, 何爱民, 等. 基于混合特征与 PSO‑SVM的旋转部件故障诊断方法[J]. 重庆理工大学学报(自然科学), 2022, 36(8): 117-125.
Zhang Tuo, Yu He, He Aimin, et al. Rotating parts fault diagnosis method considering mixed feature and PSO‑SVM [J]. Journal of Chongqing University of Technology (Natural Science), 2022, 36(8): 117-125.
[13] 张安玲, 王中. 一种混合粒子群优化算法的研究[J]. 计算机工程与应用, 2011, 47(31): 27-29, 37.
Zhang Anling, Wang Zhong. Research on hybrid particle swarm optimization algorithm [J]. Computer Engineering and Applications, 2011, 47(31): 27-29, 37.
[14] 罗兵, 张建敏. 基于BP神经网络的农机安全评价敏感性分析[J]. 中国农机化学报, 2022, 43(3): 120-126.
Luo Bing, Zhang Jianmin. Sensitivity analysis of agricultural machinery safety evaluation based on BP neural network [J]. Journal of Chinese Agricultural Mechanization, 2022, 43(3): 120-126.
[15] 姚璐峤, 张小军, 王凯, 等. BP神经网络辅助的氢气泄漏检测方法研究[J]. 重庆理工大学学报(自然科学), 2022, 36(3): 289-294.
Yao Luqiao, Zhang Xiaojun, Wang Kai, et al. Hydrogen leakage detection method by using BP neural network [J]. Journal of Chongqing University of Technology (Natural Science), 2022, 36(3): 289-294.
[16] 梁旺, 秦兆博, 陈亮, 等. 基于改进BP神经网络的智能车纵向控制方法[J]. 汽车工程, 2022, 44(8): 1162-1172.
Liang Wang, Qin Zhaobo, Chen Liang, et al. Longitudinal control method of intelligent vehicles based on the improved BP neural network [J]. Automotive Engineering, 2022, 44(8): 1162-1172.
[17] 杨涛锋, 彭艺. 基于改进PSO的ARIMA‑SVM空气质量预测研究[J]. 云南大学学报(自然科学版), 2020, 42(5): 854-862.
Yang Taofeng, Peng Yi. A hybrid ARIMA‑SVM model for the study of air quality prediction based on improved PSO [J]. Journal of Yunnan University (Natural Sciences Edition), 2020, 42(5): 854-862.
[18] 韩志国, 王基铭, 陈智高. 基于人工神经网络的石油化工工程建设项目管理绩效评价[J]. 石油学报(石油加工), 2021, 37(1): 79-87.
[19] 汪宇航. 发动机润滑油粘度在线检测传感器研究[D]. 广州: 华南理工大学, 2020.
Wang Yuhang. Research on on‑line detection sensor of engine lubricating oil viscosity [D]. Guangzhou: South China University of Technology, 2020.

[1]	李玲玲, 李广宇, 徐峰, 王华泽, 高瑞遥, 张煜晗. 丘陵山地拖拉机坡地自适应控制系统仿真分析与试验[J]. 中国农机化学报, 2024, 45(9): 141-146.
[2]	闫祥海, 闫宇翔, 张俊江, 王伟, 徐立友, . 基于自适应阈值优化的插电并联式混合动力拖拉机节能控制研究[J]. 中国农机化学报, 2024, 45(9): 147-152.
[3]	李伟 , 张秀梅 , 邵明玺 . 丘陵山地拖拉机悬挂液压集成阀块结构参数设计及优化[J]. 中国农机化学报, 2024, 45(9): 153-158.
[4]	杨俊茹, 于小东, 李瑞川, 徐继康, 韩宗冉, 李艳超, . 拖拉机多路阀节流槽动态特性研究与试验[J]. 中国农机化学报, 2024, 45(8): 126-131.
[5]	邵明玺, 张秀梅, 李伟. 先导式节流阀比例电磁铁参数设计及优化[J]. 中国农机化学报, 2024, 45(7): 152-159.
[6]	窦文豪, 孙三民, 徐鹏翔. 基于Stacking集成学习的枣树智能灌溉系统设计与试验[J]. 中国农机化学报, 2024, 45(6): 270-276.
[7]	毛恩荣, 王皓洁, 杜岳峰, 朱忠祥, 翟志强, 张丽榕. 大功率拖拉机多工况换挡自适应控制策略[J]. 中国农机化学报, 2024, 45(5): 122-127.
[8]	王顺, 马心坦, 贺明佳. 拖拉机驾驶室内低频噪声控制研究[J]. 中国农机化学报, 2024, 45(5): 134-139.
[9]	张九通, 唐维东, 刘鸿瑞, 杨思存, 廖明亮, 蒋猛. 基于RFID与GPS的拖拉机机库信息管理系统的设计与开发[J]. 中国农机化学报, 2024, 45(5): 154-160.
[10]	魏国俊, 王鸿翔, 王圣杰, 王振雨, 肖茂华. 基于CKF的大型拖拉机状态参数估计研究[J]. 中国农机化学报, 2024, 45(4): 117-122.
[11]	祝贺, 戚彬, 李衍豪, 赵树行, 王莉. 基于主客观组合加权法的拖拉机座椅舒适度评价[J]. 中国农机化学报, 2024, 45(3): 140-147.
[12]	吐尔逊·买买提, 谢海巍, 孔庆好, 陈俊豪, 马洁, 曲古拉·图马尔拜. 农用拖拉机不同工况下排放特性[J]. 中国农机化学报, 2024, 45(2): 164-172.
[13]	缪皓楠, 尹必峰, 黄幼林, 朱亚辉, 解玄, 恽龙. 基于动态规划算法的串联式混合动力拖拉机犁耕工况能量管理研究[J]. 中国农机化学报, 2024, 45(10): 147-153.
[14]	赵文科, 付帅, 张丽媛, 董云蓬, 贾强, 朱昊. 大功率拖拉机悬浮前桥设计、调试与试验[J]. 中国农机化学报, 2024, 45(10): 162-169.
[15]	徐钊睿, 赵业慧, 刘风平, 薛丽君, 杨延强, 王光明, . 拖拉机液压功率分流无级变速箱设计[J]. 中国农机化学报, 2024, 45(1): 138-143.