智慧矿山背景下我国煤矿机械故障诊断研究现状与展望

Research status and prospect of fault diagnosis of China’s coal mine machines under background of intelligent mine

目前,煤炭依然是我国主体能源,煤矿井下环境复杂恶劣,使煤矿设备故障频发,对采煤安全造成严重威胁。目前机械故障诊断技术以振动为主要手段,研究涉及动力学与故障机理、信号处理与特征提取、基于振动数据的智能诊断等。故障机理研究为信号特征提取和智能诊断提供基础,主要研究轴承、齿轮及机械系统在故障状态下的振动规律,特别是频率构成。信号处理算法的目的在于从实测信号中提取反映故障信息的成分,根据信号特点主要包括频谱分析、小波分析和经验模态分解等。基于数据的智能诊断方法发展迅速,其主要对监测数据进行分类、聚类和回归分析,根据数据特点有支持向量机、浅层神经网络和深度学习方法等,种群智能算法常用于这些方法的参数优化。研究表明煤矿设备机械故障诊断研究滞后,亟需加强理论研究、算法开发和工程应用,为我国智慧矿山和煤炭绿色、安全和高效开采提供支持。

At present,coal is still the main energy source of China.Coal mine underground environment is complex and bad,which makes coal mine equipment malfunction frequently,and poses a serious threat to mining safety.Mechanical fault diagnosis technology is mainly based on vibration,including dynamics and fault mechanism,signal processing and feature extraction,intelligent diagnosis based on data.Study of fault mechanism provides a basis for signal feature extraction and intelligent diagnosis;it mainly studies vibration law of bearing,gear and mechanical system under fault condition,especially frequency constitution.The purpose of signal processing algorithms is to extract components reflecting fault information from measured signals,which includes spectrum analysis,wavelet analysis,and empirical mode decomposition.Data-based intelligent diagnosis has developed rapidly,which is mainly used to classify,cluster and regress monitoring data,according to characteristics of data.There are support vector machine,shallow neural network and deep learning algorithms.Population intelligent algorithms are often used to optimize parameters of these methods.Research on mechanical fault diagnosis of coal mine equipment is lagging behind,and more efforts should be made in basic theory,algorithm development and engineering application to support China’s intelligent mine and green,safe and efficient development of coal industry.