基于姿态检测的直线振动筛弹簧故障诊断研究与应用  

Research and Application of Fault Diagnosis for Linear Vibrating Screen Spring Based on Attitude Detection

作　　者：娄昭远 王韶巍 周生朋 苏奕欣 Lou Zhaoyuan;Wang Shaowei;Zhou Shengpeng;Su Yixin(Intelligent Power Business Department,CHN Energy Digital Intelligence Technology(Beijing)Co.,Ltd.,Beijing 100011,China;Department of Health and Safety,CHN Energy Yulin Energy Co.,Ltd.,Yulin 719000,China;Technology Center,Shandong Keda M&E Technology Co.,Ltd.,Jining 272100,China;School of Mechanical and Electrical Engineering,Shandong University of Science and Technology,Qingdao 266590,China)

机构地区：[1]国能数智科技开发(北京)有限公司智能电力业务部,北京100011 [2]国能榆林能源有限责任公司安健部,陕西榆林719000 [3]山东科大机电科技股份有限公司技术中心,山东济宁272100 [4]山东科技大学机电工程学院,山东青岛266590

出　　处：《煤矿机械》2024年第6期173-177,共5页Coal Mine Machinery

基　　金：国家能源集团科技项目(GJNY-21-166);济宁市重点研发计划项目(2020ZDZP015)。

摘　　要：针对直线振动筛早期弹簧非破坏性损伤很难分辨与检测的问题,提出了一种基于姿态解算原理的筛箱运行姿态的故障诊断方法。以筛箱运行姿态解算为核心,通过对多种振动筛隔振弹簧故障进行模拟实验、搭建实验平台及极限学习机(ELM)诊断算法对不同故障数据进行训练和分析,设计了一套双轴直线振动筛筛箱姿态数据采集系统。通过ELM对7种不同故障进行训练和分析表明:ELM分类算法在故障识别和诊断方面具有更高的准确率,且通过检测振动筛筛箱姿态可以诊断隔振弹簧不同程度刚度降低的故障。在MATLAB环境中开发了基于ELM故障分类算法的故障诊断系统,包括系统主界面、数据回放、故障诊断等功能模块。实验结果表明,该系统可用于双轴直线振动筛的故障诊断与分析。In view of the problem that it is difficult to accurately distinguish and predict the non-destructive damage of spring rate in the early stage of linear vibrating screen,a fault diagnosis method of screen box operation attitude based on the principle of attitude solving was proposed.Taking the operation attitude solution of the sieve box as the core,a gesture of biaxial linear vibrating screen attitude data acquisition system was designed by further simulating the faults of various vibration screen isolation springs,building an experimental platform and extreme learning machine(ELM)diagnosis algorithm to train and analyze different fault data.The training and analysis of seven different faults by ELM show that the ELM classification algorithm has higher accuracy in fault identification and diagnosis,and the fault of varying degrees of stiffness reduction of the vibration isolation spring can be diagnosed by detecting the attitude of the vibrating screen box.A fault diagnosis system based on the fault classification algorithm of ELM was developed in the MATLAB environment,which includes the main interface of the system,data playback,fault diagnosis and other functional modules.The test results show that the system can be used for fault diagnosis and analysis of two-axis linear vibrating screen.

关 键 词：直线振动筛 故障诊断 姿态解算 ELM MATLAB 

分 类 号：TD452[矿业工程—矿山机电]