The condensing equipment is an important component of the condensing steam turbine, it occupy the extremely important position in the generating set of heating power station. The working performance of condenser influences the economy and security of the whole steam turbine group directly, so it is significant to study the fault diagnose of condenser. We adopt the SOM neural network and PNN to diagnose the condenser system. The SOM neural network has the characteristics that has not supervised study , it is simple and ocular to diagnose the result. PNN can be trained quickly and the new trained samples can be added to PNN easily. The fault instance of condenser system indicates the method above is effective and feasible. |