钻机回转液压系统仿真与健康评估  

Simulation and health evaluation of rotary hydraulic system of drilling rig

作　　者：李兆奎 田慕琴[1] 宋建成[1] LI Zhaokui;TIAN Muqin;SONG Jiancheng(National&Local Joint Engineering Laboratory of Mining Intelligent Electrical Apparatus Technology,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]太原理工大学矿用智能电器技术国家地方联合工程实验室,山西太原030024

出　　处：《现代电子技术》2022年第23期105-108,共4页Modern Electronics Technique

基　　金：山西省重点研发计划项目(202003D111008);山西省自然科学基金重点项目(201901D111008(ZD))。

摘　　要：针对钻机实际故障数据获取较难和性能退化的非线性等问题,提出一种基于RBF神经网络的钻机回转液压系统健康状态评估方法。使用AMEsim软件搭建回转液压系统仿真模型,模拟了液压泵内泄露和液压马达内泄露,采集了样本数据并提取特征量,通过主成分分析法(PCA)对特征量进行降维处理,使用K均值算法(K⁃means)和粒子群优化算法(PSO)优化RBF神经网络参数,通过训练建立RBF神经网络健康评估模型,输入PCA处理后的数据,评估模型自动输出评估结果,实现了钻机回转液压系统健康状态的智能评估。结果表明,该方法具有较高准确性和可靠性,可用于钻机回转液压系统的健康评估,并为进一步开展钻机液压系统智能故障诊断和健康评估奠定了研究基础。Since it is difficult to obtain the actual fault data and there is the nonlinearity of performance degradation of drilling rigs,a drilling rig rotary hydraulic system′s health status evaluation method based on RBF neural network is proposed.A simulation model of the rotary hydraulic system is built with AMEsim to simulate the internal leakage of the hydraulic pump and the hydraulic motor.The sample data are collected and the feature quantities are extracted.The feature quantities are subjected to processing of dimensionality reduction by principal component analysis(PCA)method.The K⁃means algorithm and particle swarm optimization(PSO)algorithm are used to optimize the parameters of RBF neural network.The health evaluation model of RBF neural network is established by training.The data processed by PCA method is input into the evaluation model,and the evaluation results are automatically output to realize the intelligent evaluation of health status of the drilling rig rotary hydraulic system.The results show this method has high accuracy and reliability,so it can be used for the health evaluation of the drilling rig rotary hydraulic system,and lays a research foundation for further development of the intelligent fault diagnosis and health evaluation of the drilling rig hydraulic system.

关 键 词：钻机回转液压系统 智能化 健康评估 RBF神经网络 主成分分析 K⁃means⁃PSO⁃RBF神经网络 AMESIM仿真 

分 类 号：TN919-34[电子电信—通信与信息系统] TH137[电子电信—信息与通信工程] TP183[机械工程—机械制造及自动化]