基于补偿模糊神经网络的制冷系统故障诊断研究  

Fault Diagnosis for Refrigeration System Based on Compensatory Fuzzy Neural Network

作　　者：胡正定[1] 杨晨[1] 

机构地区：[1]重庆大学动力工程学院,重庆400044

出　　处：《计算机仿真》2007年第10期148-151,共4页Computer Simulation

摘　　要：选择反映制冷系统故障状态的热力参数集组成特征向量,并对其进行模糊化处理,利用补偿模糊神经网络建立故障状态与热力参数特征向量之间的映射关系。将神经网络和补偿模糊逻辑相结合,采用动态、全局优化的运算,充分利用了相互间的优点。网络不仅能适当调整输入输出模糊隶属函数,也能借助于补偿逻辑算法动态优化相应的模糊推理。仿真实验证明该模型在智能诊断中具有收敛速度快,诊断精度高,而且适应性强等优点。A set of thermal parameters are selected and measured to form the characteristic vector that represents the malfunction state of refrigeration system.Compensatory Fuzzy Neural Network is introduced to accomplish the pattern recognition task of＂fault symptom fault source＂relationship mapping.The CFNN combines compensative fuzzy logic with neural network,and is composed of control oriented cell and decision making cell.Compared to BP neural networks,the convergence speed and the error precision are improved a lot.Practice has proved that the method is worth further extending.

关 键 词：制冷系统 故障诊断 补偿模糊神经网络 补偿模糊运算 

分 类 号：TK14[动力工程及工程热物理—热能工程]