Health Status Assessment of Hydraulic Pumps Based on Multi-sensor Information Fusion and Multi-grained Cascade Forest Model

doi:10.3969/j.issn.1004-132X.2021.19.013

Abstract

Abstract: The health status assessment of hydraulic pumps was of great significance to the operating state monitoring of engineering equipment. The existing methods based on vibration signal analysis had single data source and low reliability， therefore a method was proposed for evaluating the health status of hydraulic pumps based on multi-sensor information fusion and multi-grained cascade forest. The pressure， temperature， flow and other signals of the hydraulic pumps were collected under different working hours through the test system， and the time-domain features of the signals were extracted to form preliminary features. Multiple classifiers were used to obtain the category probability vectors of the preliminary features， and the results were stitched with the important features selected by the random forest model to form the final features， and then the multi-grained cascade forest was used to evaluate the health status.The testing results show that the classification precision of the proposed method may still reach 99.5% when the training ratio is only 5%， which may effectively improve the accuracy of hydraulic pump health assessment.

Key words: , hydraulic pump, multi-sensor fusion, multi-grained cascade forest model, health assessment

摘要： 液压泵健康状态评估对工程设备的运行状态监测有极其重要的意义，现有基于振动信号分析的方法数据来源单一、可靠性低，为此，提出了一种基于多传感器信息融合和多粒度级联森林模型的液压泵健康状态评估方法。通过试验系统采集了不同工作时间下液压泵的压力、温度、流量等信号，分别提取信号的时域特征组成初步特征。使用多个分类器获取初步特征的类别概率向量，将其与随机森林模型选出来的重要特征进行拼接形成最终特征，并使用多粒度级联森林模型进行健康状态评估。试验结果表明，所提方法在仅有5%训练比例的情况下分类精确率仍可达99.5%，可以有效提高液压泵健康状态评估的准确度。

关键词: 液压泵, 多传感器融合, 多粒度级联森林模型, 健康评估

CLC Number:

TH113.1

SHAN Zenghai, LI Zhiyuan, ZHANG Xu, HUANG Yixiang, LI Yanming, LIU Chengliang, ZHANG Xuan. Health Status Assessment of Hydraulic Pumps Based on Multi-sensor Information Fusion and Multi-grained Cascade Forest Model[J]. China Mechanical Engineering, 2021, 32(19): 2374-2382.

单增海, 李志远, 张旭, 黄亦翔, 李彦明, 刘成良, 张轩. 基于多传感器信息融合和多粒度级联森林模型的液压泵健康状态评估[J]. 中国机械工程, 2021, 32(19): 2374-2382.

References

［1］杨正强，杜随更. 现代机械设备液压系统状态评估及故障诊断综述［J］. 西安航空学院学报， 2015， 33（5）：47-53.
YANG Zhengqiang， DU Suigeng. Review of State Evaluation and Fault Diagnosis Technology in Hydraulic System of Modern Mechanical Equipment ［J］. Journal of Xi’an Aeronautical University， 2015， 33（5）：47-53
［2］HANCOCK K M， ZHANG Q. A Hybrid Approach to Hydraulic Vane Pump Condition Monitoring and Fault Detection［J］. Transactions of the ASABE， 2006， 49（4）：1203-1211.
［3］ZHU Huijie， RUI Ting， WANG Xinqing，et al. Fa-ult Diagnosis of Hydraulic Pump Based on Stacked Autoencoders［C］∥12th IEEE International Conference on Electronic Measurement & Instruments（ICEMI）. Qingdao， 2015：58-62.
［4］刘志宇，黄亦翔. 基于深度学习和迁移学习的液压泵健康评估方法［J］. 机械与电子， 2018， 36（9）：67-71.
LIU Zhiyu， HUANG Yixiang. Health Assessment for Hydraulic Pump Based on Deep Learning and Transfer Learning［J］. Machinery and Electronics， 2018，36（9）：67-71.
［5］王浩任，黄亦翔，赵帅，等. 基于小波包和拉普拉斯特征值映射的柱塞泵健康评估方法［J］. 振动与冲击， 2017， 36（22）：45-50.
WANG Haoren， HUANG Yixiang， ZHAO Shuai， et al. Health Assessment for a Piston Pump Based on WPD and LE［J］. Journal of Vibration and Shock， 2017， 36（22）：45-50.
［6］GAO Yingjie， ZHANG Qin， KONG Xiangdong. Wavelet-based Pressure Analysis for Hydraulic Pump Health Diagnosis［J］. Transactions of the ASAE， 2003， 46（4）：969-976.
［7］GAO Yingjie， ZHANG Qin. A Wavelet Packet and Residual Analysis Based Method for Hydraulic Pump Health Diagnosis［J］. Proceedings of the Institution of Mechanical Engineers， Part D：Journal of Automobile Engineering，2006，220（6）：735-745.
［8］ZHAO Zhen， JIA Mingxing， WANG Fuli， et al. Intermittent Chaos and Sliding Window Symbol Sequence Statistics-based Early Fault Diagnosis for Hydraulic Pump on Hydraulic Tube Tester［J］. Mechanical Systems and Signal Processing， 2009， 23（5）：1573-1585.
［9］LLINAS J， HALL D L. An Introduction to Multi-sensor Data Fusion［C］∥Proceedings of the 1998 IEEE International Symposium on Circuits and Systems. Monterey：IEEE， 1998：537-540.
［10］谢振南. 多传感器信息融合技术研究［D］. 广州：广东工业大学， 2013.
XIE Zhennan. Research of Multi-sensor Information Fusion Technology［D］. Guangzhou：Guangdong University of Technology， 2013.
［11］张静. 基于信息融合的变电站设备健康评估及多系统协同诊断方法［C］∥2016智能电网发展研讨会论文集.北京，2016：264-266.
ZHANG Jing. Information Fusion-based Substation Equipment Health Assessment and Multi-system Collaborative Diagnosis Method［C］∥Proceedings of the 2016 Smart Grid Development Symposium. Beijing， 2016：264-266.
［12］陈俊康，陈小虎，郑东辉. 基于异类信息融合的齿轮健康评估方法［J］. 振动与冲击，2020，39（3）：219-226.
CHEN Junkang， CHEN Xiaohu， ZHENG Donghui. Gear Health Assessment Method Based on Heterogeneous Information Fusion［J］. Journal of Vibration and Shock， 2020，39（3）：219-226.
［13］刘振宇. 面向多层级信息融合的液压泵故障诊断系统设计［J］. 机械设计与制造工程，2018，47（6）：56-58.
LIU Zhenyu. Development of the Failure Diagnosis System for Hydraulic Pump with Multi-layers Information Fusion ［J］. Machine Design and Manufacturing Engineering，2018，47（6）：56-58.
［14］李松柏，康子剑，陶洁. 基于信息融合及堆栈降噪自编码的齿轮故障诊断［J］. 振动与冲击，2019，38（5）：216-221.
LI Songbai， KANG Zijian， TAO Jie. Gear Fault Diagnosis Based on Information Fusion and Stacked De-noising Auto-encoder［J］. Journal of Vibration and Shock， 2019， 38（5）：216-221
［15］任凤娟. 多传感器信息融合技术在液压系统故障诊断中的应用［J］. 液压气动与密封，2019，39（7）：52-55.
REN Fengjuan. Application of Multi-sensor Information Fusion for Hydraulic System Fault Diagnosis ［J］. Hydraulics Pneumatics & Seals， 2019，39（7）：52-55.
［16］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.
LIU Siyuan， HE Yue， LI Xiaoming， et al. Multi-information Intensity Characteristic State Assessment Method of Hydraulic Pump Based on Fault Mechanism［J］. China Mechanical Engineering， 2019，30（12）：1460-1465.
［17］LU Chuanqi， WANG Shaoping， WANG Xingjian. A Multi-source Information Fusion Fault Diagnosis for Aviation Hydraulic Pump Based on the New Evidence Similarity Distance［J］. Aerospace Science and Technology， 2017， 71：392-401.
［18］ZHOU Z H， FENG J. Deep Forest［J］. National Science Review， 2018， 6（1）：74-86.
［19］杨晓梅，张菊玲，赵忠华. 多源信息融合技术及其应用研究［J］. 无线互联科技，2019，16（18）：133-134.
YANG Xiaomei， ZHANG Juling， ZHAO Zhonghua. Research on Multi-source Information Fusion Technology and Its Application［J］. Wireless Internet Technology， 2019，16（18）：133-134.
［20］CABRAL E F， TERUYA M Y，SORIA R A B.Using MLPS for Fault Analysis in Analog Circuits.［C］∥38th Midwest Symposium on Circuits and Systems. Rio de Janeiro,1995:1172-1174.
［21］CORTES C， VAPNIK V. Support-vector Networks［J］. Machine Learning, 1995， 20（3）：273-297.
［22］ALTMAN N S. An Introduction to Kernel and Nearest-neighbor Nonparametric Regression［J］. The American Statistician, 1992， 46（3）：175-185.
［23］PODGORELEC V， KOKOL P， STIGLIC B， et al. Decision Trees：an Overview and Their Use in Medicine［J］. Journal of Medical Systems， 2002， 26（5）：445-463.
［24］李志远，黄亦翔，刘成良，等. 基于经验模态分解与深度森林的液压泵健康评估［J］. 机械与电子， 2020， 38（5）：3-8.
LI Zhiyuan， HUANG Yixiang， LIU Chengliang， et al. Health Assessment of Hydraulic Pump Based on Empirical Mode Decomposition and Deep Forest［J］. Machinery and Electronics， 2020，38（5）：3-8.

[1]	DING Kai, LI Qilin, LEI Weining, XU Mingzhou, WANG Xu. Material Removal Mechanism during UAG of SiC Ceramic with a Brazed Single Abrasive Grain Tool [J]. China Mechanical Engineering, 2021, 32(19): 2331-2339.
[2]	LI Xinqing, ZHAO Qinghai, ZHANG Hongxin, ZHANG Tiezhu, CHEN Jianliang. Steady-state Heat Conduction Topology Optimization Design for Periodic Functional Gradient Structures [J]. China Mechanical Engineering, 2021, 32(19): 2348-2356.
[3]	. Quasi-Hertz Loaded Tooth Contact Analysis of Gears Based on Ease-off Surface Topology [J]. China Mechanical Engineering, 2021, 32(18): 2174-2180.
[4]	LIU Yanxiong, WANG Genju, HUA Lin, ZHAO Xinhao, . Double-drive Coordinated Control Systems of Fine Stamping Machines Based on Adaptive Sliding Mode Variable Structure Control [J]. China Mechanical Engineering, 2021, 32(18): 2189-2196.
[5]	GE Jimin, DENG Zhaohui, LI Wei, LI Chongyang, CHEN Xi, PENG Deping. Research Progresses of Robot Grinding and Polishing Force Compliance Controls [J]. China Mechanical Engineering, 2021, 32(18): 2217-2230,2238.
[6]	MAO Meijiao, XU Qing, LIU Jingli, YUAN Julong, LI Min, HU Zihua. Contact States of Workpiece-Abrasive Particles-Polishing Pad in Cemented Carbide CMP Processes [J]. China Mechanical Engineering, 2021, 32(17): 2074-2081.
[7]	NIU Bin, YAN Jiaming, MAO Yuming, LIU Haiyang. Collaborative Design Optimization of Damping Layers and Stiffener Layout of Thin-walled Stiffened Plate Structures for Dynamics Performances [J]. China Mechanical Engineering, 2021, 32(16): 1912-1920.
[8]	LU Hao, CHEN Yang, WU Huaiyu, CHENG Lei, . Path Planning of Substation Inspection Robot under Road Network and Measurement Constraints [J]. China Mechanical Engineering, 2021, 32(16): 1972-1982.
[9]	ZHOU Xiaochun, LIANG Jun, CHEN Long, WANG Yafei, GONG Jinfeng. Intelligent Connected Vehicle PnP Networking Model and Decision Fusion Algorithm [J]. China Mechanical Engineering, 2021, 32(16): 1983-1993.
[10]	GU Zhenhua, LI Ke, GU Jiefei, , SU Lei, SU Wensheng. Fatigue Crack Growth Prediction Based on NPF Algorithm [J]. China Mechanical Engineering, 2021, 32(14): 1709-1715.
[11]	GE Kedi, ZHAO Huan, CHEN Pengfei, DING Han. Programming by Demonstration with Virtual Fixture Assistance for Robotic Machining of Complex Surfaces [J]. China Mechanical Engineering, 2021, 32(14): 1716-1725.
[12]	ZHANG Ying, SUN Hao, MA Shuaishuai. Design of a Kind of Multi-dimensional Attitude Adjustment and Vibration Isolation Platform Based on 4-UPS/CPC Parallel Mechanisms#br# [J]. China Mechanical Engineering, 2021, 32(13): 1513-1522,1529.
[13]	LI Yujia, HUANG Bing, LU Juan, ZHONG Qijing, CHEN Chaoyi, LIAO Xiaoping, MA Junyan. Multi-objective Optimization of Cutting Parameters in Ti6Al4V Milling Processes Based on Finite Element Simulation#br# [J]. China Mechanical Engineering, 2021, 32(13): 1555-1561,1570.
[14]	WANG Yiyu, ZHAO Jianshe, GU Minkai, JI Tao. Flow Field Design and Process Stability in Electrochemical Machining of Involute Internal Splines#br# [J]. China Mechanical Engineering, 2021, 32(13): 1562-1570.
[15]	WANG Dengfeng, LI Shenhua. Lightweight Optimization Design of Side Collision Safety Parts for BIW Based on Pareto Mining#br# [J]. China Mechanical Engineering, 2021, 32(13): 1584-1590,1637.