RBF neural network based fault diagnosis for the thermodynamic system of a thermal power generating unit

In this paper, a new style radial basis function (RBF) neural network is used for fault diagnosis of the thermodynamic cycle system in a thermal power generating unit. The structure of the RBF network and its training algorithm are discussed. Besides, another important factor to realize neural network based diagnosis, fault symptom calculating methods for different fault symptoms, are discussed in detail. At last, the high-pressure feed-water heater system of a 300 MW thermal power generating unit is taken as an example of thermodynamic system fault diagnosis. The fault knowledge library of the system is summarized with the fault symptom calculation method, and the fault diagnosis is further realized based on above RBF neural network.