集成神经网络信息融合在故障诊断中的应用  

THE INFORMATION FUSION OF INTEGRATE NEURAL NETWORK＇S APPLICATION IN FAULT DIAGNOSIS

作　　者：周超强[1] 刘荣[1] 程永鑫[1] 

机构地区：[1]重庆通信学院,重庆400035

出　　处：《重庆通信学院学报》2005年第4期84-88,共5页

摘　　要：随着设备复杂性的提高，采用单子神经网络信息融合在故障诊断中已无法给出正确的判断。根据实际应用的需要，在讨论集成神经网络信息融合优点的基础上，提出一种集成神经网络信息融合的故障诊断方法，给出了它的组成结构、组建原则以及集成神经网络信息融合在故障诊断中的应用，最后应用集成神经网络对工业CT系统中的驱动器故障诊断进行了仿真。该方法通用性强，为工业CT系统其它部件的故障诊断提供了较好的模型和方法。With the increasing of equipment fault complexity, the information fusion of neural network in fault diagnosis can not provide accurate decision. In this paper, based on the merit of the information fusion, a fault diagnosis method of integrate neural network is provided. The structure, the constitute principle and the application of the integrate neural network in fault diagnosis are given, Finally, the driver fault diagnosis is simulated in ICT by applying integrate neural network, the method and model are general realizable, and can be diagnosis on other parts of ICT.

关 键 词：集成神经网络 信息融合 故障诊断 工业CT系统 驱动器 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]