摘要
常规的复杂机电设备故障诊断方法主要使用欧式向量矩阵确定故障逻辑特征,易受故障动态判断关联作用的影响,导致故障特征提取指标不拟合,因此基于深度信念网络设计了一种全新的复杂机电设备故障诊断方法。利用经验模态分解(Empirical Mode Decomposition,EMD)提取复杂机电设备故障的诊断特征,构建多Agent复杂机电设备故障诊断模型,并结合深度信念网络设计了设备故障诊断深度信念网络(Deep Belief Network,DBN)分类器,从而实现了复杂机电设备故障的诊断。实验结果表明,设计的复杂机电设备深度信念网络故障诊断方法提取的不同故障指标和实际故障指标拟合,证明设计的复杂机电设备故障诊断方法的诊断效果较好,为降低复杂机电设备的运行风险贡献力量。
The conventional fault diagnosis method of complex mechanical and electrical equipment mainly uses European vector matrix to determine the fault logic characteristics,which is susceptible to the influence of fault dynamic judgment,leading to the unfitting of fault feature extraction index.Therefore,it is necessary to design a new fault diagnosis method of complex mechanical and electrical equipment based on deep belief network.The Empirical Mode Decomposition(EMD)is used to extract the fault diagnosis characteristics of complex electromechanical equipment,the multi-Agent complex electromechanical equipment fault diagnosis model is constructed,and the equipment fault diagnosis Deep Belief Network(DBN)classifier is designed in combination with the deep belief network,so as to realize the fault diagnosis of complex electromechanical equipment.Experimental results show that the design of complex electromechanical equipment depth belief network fault diagnosis method to extract different fault index and actual fault index ftting,prove the design of complex electromechanical equipment fault diagnosis method diagnosis effect is good,to reduce the operation risk of complex electromechanical equipment has made certain contribution.
作者
李烈熊
LI Liexiong(Fujian Chuanzheng Communications College,Fuzhou Fujian 350007,China)
出处
《信息与电脑》
2023年第13期101-103,共3页
Information & Computer
关键词
深度信念网络(DBN)
复杂机电设备
故障诊断
方法
Deep Belief Network(DBN)
complex mechanical and electrical equipment
fault diagnosis
method
