离心输油泵故障诊断专家系统的研究与实现

Expert System of Fault Diagnosis of Centrifugal Pump for Oil Delivery

提出了一种新的对基本神经网络进行组合的思路 ,将基本神经网络分层联接 ,每一层对应对象的某一属性 ,并根据属性分类。以这一思路为指导 ,组建了 BP网络与竞争网络组织相结合的神经网络 ,并以此为核心 ,搭建了离心输油泵故障诊断专家系统的框架。

This paper puts forward a new idea of building combined neural network,which is composed of basic neural networks,such as back propagation neural network and competitive neural network based on self-organization and self-adaptation. The basic neural networks are linked by layers,and each layer corresponds to its own fault property vector set(or fault omen vector set). Based on this concept,we integrated BP network and competitive network into one as a learning and reasoning core of fault diagnosis expert system of centrifugal pump for oil delivery and built up its initial frame.