Fault Diagnosis For A Condenser And Correlational Equipment Of It

In the nuclear power installation or the turbine of condenser, condenser as a cooler is an important auxiliary installation. Its thermodynamic characteristic has a heavy impaction on the security and economy of a running turbine and the nuclear power installation. The lower vacuum of a condenser make it easy to bring some faults within the running of a condenser, so it is very important and indispensable to forecast and confirm the operation fault accurately and in time.On the base of a fault simulation model of the condenser in an nuclear power installation which was built, the paper dynamically simulate seven kinds of faults frequently occur in the condenser operation, it gains faults data of swatch and analyses the change to every omen of every fault.At present, the mode of fault diagnosis applying artificial intelligent methods has two methods: expert system and neural net work(NN). Fuzzy NN(FNN) merits of fuzzy logic and NN, it can described fuzzy question, has great capabilities of studying and data directly disposing, has great capabilities of expression about knowledge structure, has great capabilities of fault tolerant. In a word, FNN can automatically attain to knowledge, adapt to the change of environment, adopt collateral calculation of numerical value, so that it is an effective method which solve localization of traditional fault diagnosis.With Visual C++, an expert system for the condenser fault diagnosis in a nuclear power installation was constructed based on fuzzy back-propagation neural network. The expert system for the condenser fault diagnosis adopt mutual interface between man and computer, interface is friendly and simple.