基于深度信念网络多参数智能融合的滑靴副性能退化状态评估方法

doi:10.3901/JME.2024.04.178

机械工程学报 ›› 2024, Vol. 60 ›› Issue (4): 178-188.doi: 10.3901/JME.2024.04.178

• 特邀专栏：智能液压元件及系统基础技术 • 上一篇下一篇

扫码分享

基于深度信念网络多参数智能融合的滑靴副性能退化状态评估方法

刘思远^1,2,3, 艾超^1,2,3, 郁春嵩^1,2,3, 张伟哲^1,2,3, 陈文婷^1,2,3, 康伟⁴

1. 燕山大学河北省重型机械流体动力传输与控制实验室秦皇岛 066004;
2. 燕山大学先进锻压成形技术与科学教育部重点实验室秦皇岛 066004;
3. 燕山大学机械工程学院秦皇岛 066004;
4. 中国人民解放军 95092 部队开封 475000

收稿日期:2023-05-01 修回日期:2023-11-02 出版日期:2024-02-20 发布日期:2024-05-25
通讯作者: 陈文婷,女,1990年出生,博士。主要研究方向为液压型风力发电机组控制技术。E-mail:went_chen@ysu.edu.cn
作者简介:刘思远,男,1981年出生,博士,教授。主要研究方向为液压基础元件。E-mail:liusiyuan@ysu.edu.cn
基金资助:
国家自然科学基金(52275069,52175065); 河北省自然科学基金(E2022203041,E2021203020)资助项目

Evaluation Method of Slipper Pair Performance Degradation State Based on Multi-parameter Intelligent Fusion of Deep Belief Network

LIU Siyuan^1,2,3, AI Chao^1,2,3, YU Chunsong^1,2,3, ZHANG Weizhe^1,2,3, CHEN Wenting^1,2,3, KANG Wei⁴

1. Hebei Province Key Laboratory of Heavy Machinery Fluid Power Transmission and Control, Yanshan University, Qinhuangdao 066004;
2. Key Laboratory of Advanced Forging&Stamping Technology and Science, Ministry of Education of China, Yanshan University, Qinhuangdao 066004;
3. School of Mechanical Engineering, Yanshan University, Qinhuangdao 066004;
4. Chinese People's Liberation Army Unit 95092, Kaifeng 475000

Received:2023-05-01 Revised:2023-11-02 Online:2024-02-20 Published:2024-05-25

摘要/Abstract

摘要： 滑靴副磨损过程的性能退化状态受到表面形貌、摩擦特性等多个方面的影响,单独提取其中任何一个表征参数作为指标,评估其性能退化状态都是不准确的,为提高评估精度,提出基于深度信念网络多参数智能融合的滑靴副性能退化状态评估方法。应用分形理论从滑靴表面形貌特征中提取分形维数、尺度系数和特征粗糙度等分形参数作为表面形貌评估指标,应用摩擦因数作为摩擦特性参数评估指标,构建性能退化状态评估指标体系;计算摩擦因数信号与完全平稳的高斯白噪声序列信号之间的灰色关联度,并根据灰色关联度的大小对性能退化状态进行区域划分;应用深度信念网络理论对多指标参数进行智能融合和特征提取,建立性能退化状态评估模型;开展滑靴副磨损过程模拟试验,分析指标参数和灰色关联度对性能退化状态的影响规律,通过构建出的样本数据集,对评估模型进行训练和测试验证,结果表明评估模型对性能退化状态的评估准确率能够达到97%以上,由此证实该方法对滑靴副性能退化状态评估的有效性,且具有较高的评估精度。

关键词: 滑靴副, 性能退化状态评估, 分形理论, 深度信念网络

Abstract: The performance degradation state of the wear process of the slipper pair is affected by many aspects such as surface morphology and friction characteristics. It is inaccurate to extract any one of the characteristic parameters as indicators to evaluate its performance degradation state. In order to improve the evaluation accuracy, a multi-parameter intelligent fusion method based on deep belief network is proposed to evaluate the performance degradation state of the slipper pair. Fractal parameters such as fractal dimension, scale coefficient and characteristic roughness are extracted from the surface topography of slipper by fractal theory, and friction coefficient is used as the evaluation index of friction characteristics to construct the evaluation index system of performance degradation state. The gray correlation degree between the friction coefficient signal and the completely stationary Gaussian white noise sequence signal is calculated, and the degradation state is divided into regions according to the gray correlation degree. Deep belief network theory is applied to perform intelligent fusion and feature extraction of multiple index parameters, and a performance degradation state assessment model is established. The simulation test of slipper wear process is carried out to analyze the influence rule of index parameters and gray correlation degree on performance degradation state. The evaluation model is trained and tested through the constructed sample data set. The results show that the evaluation accuracy of the model for performance degradation state can reach more than 97%, which verifies the effectiveness and high accuracy of the method for performance degradation state evaluation of slipper pair.

Key words: slipper pair, performance degradation status assessment, fractal theory, deep belief network

中图分类号:

TH137

刘思远, 艾超, 郁春嵩, 张伟哲, 陈文婷, 康伟. 基于深度信念网络多参数智能融合的滑靴副性能退化状态评估方法[J]. 机械工程学报, 2024, 60(4): 178-188.

LIU Siyuan, AI Chao, YU Chunsong, ZHANG Weizhe, CHEN Wenting, KANG Wei. Evaluation Method of Slipper Pair Performance Degradation State Based on Multi-parameter Intelligent Fusion of Deep Belief Network[J]. Journal of Mechanical Engineering, 2024, 60(4): 178-188.

参考文献

[1] TANG Hesheng, REN Yan, ZHANG Xianglei.Tribological performance of mos2 coating on slipper pair in axial piston pump[J]. Journal of Central South University,2020,27(5):1515-1529.
[2] KE Jian,LIU Henglong,LIU Sining,et al. Analysis and computation on hydrostatic bearing for sliding shoes of water hydraulic axial piston pump[J]. China Mechanical Engineering,2003,14(2):101.
[3] ZHANG Dongya,SUN Xizhou,GAO Feng,et al. Effect of texture parameters on tribological performance of slipper surface in hydraulic motor[J]. Surface Technology,2019,48(4):230-236.
[4] TANG Hesheng, YIN Yaobao, LI Jing. Lubrication characteristics analysis of slipper bearing in axial piston pump considering thermal effect[J]. Lubrication Science,2016,28(2):107-124.
[5] CANBULUT F,SINANOGLU C,KOC E. Experimental analysis of frictional power loss of hydrostatic slipper bearings[J]. Industrial Lubrication and Tribology,2009,61(2-3):123-131.
[6] 张振华.海水泵滑靴副的磨损机理及性能退化预测[D].北京:北京工业大学,2016.ZHANG Zhenhua. Wear mechanism and performance degradation prediction of seawater pump slipper pair[D].Beijing:Beijing University of Technology,2016.
[7] 雷亚国,杨彬,杜兆钧,等.大数据下机械装备故障的深度迁移诊断方法[J].机械工程学报,2019,55(7):1-8.LEI Yaguo,YANG Bin,DU Zhaojun,et al. Deep transfer diagnosis method for machinery in big data era[J]. Journal of Mechanical Engineering,2019,55(7):1-8.
[8] HOSAMELDIN O A, ASOKE K N. Connected components-based colour image representations of vibrations for a two-stage fault diagnosis of roller bearings using convolutional neural networks[J]. Chinese Journal of Mechanical Engineering,2021,34(3):86-106.
[9] OZKAN O,CEM S,ABDULLAH C,et al. Prediction of leakage from an axial piston pump slipper with circular dimples using deep neural networks[J]. Chinese Journal of Mechanical Engineering,2020,33(2):119-129.
[10] HONG Jiyu,WANG Huawei,NI Xiaomei. Assessment of performance degradation for aero-engine based on denoising autoencoder[J]. Journal of Aerospace Power,2018,33(8):2041-2048.
[11] YU He,TIAN Zaike,LI Hongru,et al. A novel deep belief network model constructed by improved conditional rbms and its application in rul prediction for hydraulic pumps[J].International Journal of Acoustics and Vibrations,2020,25(3):373-382.
[12] DAI Juying,TANG Jian, HUANG Shuzhan, et al.Signal-based intelligent hydraulic fault diagnosis methods:Review and prospects[J]. Chinese Journal of Mechanical Engineering,2019,32(5):11-32.
[13] 沈长青,汤盛浩,江星星,等.独立自适应学习率优化深度信念网络在轴承故障诊断中的应用研究[J].机械工程学报,2019,55(7):81-88.SHEN Changqing,TANG Shenghao,JIANG Xingxing,et al. Bearings fault diagnosis based on improved deep belief network by self-individual adaptive learning rate[J].Journal of Mechanical Engineering,2019,55(7):81-88.
[14] 张鑫,郭顺生,李益兵,等.基于拉普拉斯特征映射和深度置信网络的半监督故障识别[J].机械工程学报,2020,56(1):70-81.ZHANG Xin, GUO Shunsheng, LI Yibing, et al.Semi-supervised fault identification based on laplacian eigenmap and deep belief networks[J]. Journal of Mechanical Engineering,2020,56(1):70-81.
[15] 刘宇,邓宏盛,张生芳,等.基于W-M分形函数的三维粗糙表面摩擦生热研究[J].中国工程机械学报,2018,16(3):194-201.LIU Yu,DENG Hongsheng,ZHANG Shengfang,et al.Research on friction heat generation of three dimensional rough surface based on W-M fractal function[J]. Chinese Journal of Construction Machinery,2018,16(3):194-201.
[16] 朱华,陆斌斌,历健全,等.摩擦学问题研究的非线性理论方法[J].机械工程学报,2010,46(15):82-88.ZHU Hua,LU Binbin,LI Jianquan,et al. Nonlinear theory and methods of researching tribological problems[J]. Journal of Mechanical Engineering,2010,46(15):82-88.
[17] 邓可月,刘政,邓居月,等. W-M函数模型下表面轮廓形貌的变化规律[J].机械设计与制造,2017,55(1):47-50.DENG Keyue,LIU Zheng,DENG Juyue,et al. Variation of surface profile topography based on w-m function model[J]. Manufacture,2017,55(1):47-50.
[18] SUN Guodong,ZHU Hua,DING Cong,et al. On the boundedness of running-in attractors based on recurrence plot and recurrence qualification analysis[J]. Friction,2019,7(5):432-443.
[19] 魏子茹,卢延辉,王鹏宇,等.基于CRITIC法的灰色关联理论在无人驾驶车辆测试评价中的应用[J].机械工程学报,2021,57(12):99-108.WEI Ziru,LU Yanhui,WANG Pengyu,et al. Application of grey correlation theory based on critic method in autonomous vehicles test and evaluation[J]. Journal of Mechanical Engineering,2021,57(12):99-108.
[20] SUN Guodong,ZHU Hua,DING Cong. Using recurrence plots for stability analysis of ring-on-disc tribopairs[J].Industrial Lubrication and Tribology, 2019, 71(4):532-539.
[21] 贾俊,胡晓松,邓忠伟,等.数据驱动的锂离子电池健康状态综合评分及异常电池筛选[J].机械工程学报,2021,57(14):141-149.JIA Jun, HU Xiaosong, DENG Zhongwei, et al.Data-driven comprehensive evaluation of lithium-ion battery state of health and abnormal battery screening[J].Journal of Mechanical Engineering, 2021, 57(14):141-149.
[22] MAO Jingyang,MENG Xiangyu,DING Derui. Fuzzy set-membership filtering for discrete-time nonlinear systems[J]. IEEE/CAA Journal of Automatica Sinica,2022,9(6):1026-1036.
[23] SCHERGE M, LINSLER D, SCHLARB T. The running-in corridor of lubricated metal-metal contacts[J].Wear,2015,342:60-64.
[24] ABUDUREHEMAN A, NILUPAER A, HE Yi.Performance evaluation of enterprises'innovation capacity based on fuzzy system model and convolutional neural network[J]. Journal of Intelligent,2020,39(2):1563-1571.
[25] 刘思远,何跃,李晓明,等.基于故障机理的液压泵多信息烈度特征状态评估方法[J].中国机械工程,2019,30(12):1460-1465,1473.LIU Siyuan, HE Yue, LI Xiaoming, et al.Multi-information intensity characteristic state assessment method of hydraulic pums based on fault mechanism[J].China Mechanical Engineering,2019,39(2):1460-1465,1473.

基于深度信念网络多参数智能融合的滑靴副性能退化状态评估方法

Evaluation Method of Slipper Pair Performance Degradation State Based on Multi-parameter Intelligent Fusion of Deep Belief Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	雷俊杰, 刘美红, HU Xiangping, 王娟, 王学良. 基于分形理论的椭圆弧型指尖密封磨损特性分析[J]. 机械工程学报, 2023, 59(3): 144-157.
[2]	冯华渊, 上官文斌, 康英姿. 考虑粗糙表面特性的驱动轴系统轴向派生力的区间不确定性优化[J]. 机械工程学报, 2022, 58(1): 221-230.
[3]	叶楠, 常佩泽, 张露予, 王嘉. 基于改进后半监督深度信念网络的多工况轴承故障诊断研究[J]. 机械工程学报, 2021, 57(15): 80-90.
[4]	孟庆宇, 刘杨, 鄢欣欣, 马亚新, 李炎臻. 基于分形理论的电主轴系统热态分布特性研究[J]. 机械工程学报, 2021, 57(13): 63-69.
[5]	王晓鹏, 刘世军. 微点蚀齿轮法向接触刚度分形预估模型[J]. 机械工程学报, 2021, 57(1): 68-76.
[6]	沈长青, 汤盛浩, 江星星, 石娟娟, 王俊, 朱忠奎. 独立自适应学习率优化深度信念网络在轴承故障诊断中的应用研究[J]. 机械工程学报, 2019, 55(7): 81-88.
[7]	陈永会, 张学良, 温淑花, 兰国生. 考虑弹塑性阶段的结合面法向接触阻尼分形模型[J]. 机械工程学报, 2019, 55(16): 58-68.
[8]	王润琼, 朱立达, 朱春霞. 基于域扩展因子和微凸体相互作用的结合面接触刚度模型研究[J]. 机械工程学报, 2018, 54(19): 88-95.
[9]	李小彭, 潘五九, 高建卓, 李树军, 赵光辉, 闻邦椿. 结合面形貌特性对模态耦合不稳定系统的影响^*[J]. 机械工程学报, 2017, 53(5): 116-127.
[10]	陈奇, 黄守武, 张振, 邱明明. 考虑摩擦因素的两圆柱体表面接触承载能力的分形模型研究[J]. 机械工程学报, 2016, 52(7): 114-121.
[11]	陈奇, 张振, 刘鹏, 黄守武, 马运波. 考虑摩擦的圆柱面切向接触刚度分形模型研究^*[J]. 机械工程学报, 2016, 52(23): 168-175.
[12]	金雷, 贾振元, 刘巍. 压电力传感器晶片与电极接触刚度影响研究^*[J]. 机械工程学报, 2016, 52(22): 15-23.
[13]	马登秋, 侯力, 魏永峭, 陈建. 基于分形理论的圆弧齿轮滑动摩擦接触力学模型^*[J]. 机械工程学报, 2016, 52(15): 121-127.
[14]	梁瑛娜, 高殿荣, 毋少峰. 凹坑形仿生非光滑表面滑靴副的动压润滑计算[J]. 机械工程学报, 2015, 51(24): 153-160.
[15]	李小彭;王伟;赵米鹊;聂慧凡;闻邦椿. 考虑摩擦因素影响的结合面切向接触阻尼分形预估模型及其仿真[J]. , 2012, 48(23): 46-50.