Applying PCA to establish artificial neural network for condition prediction on equipment in power plant

Aiming at the problem that the equipment in power plant are complex and difficult to predict their conditions accurately, an artificial neural network for condition prediction on equipment in power plant based on principal component analysis is proposed on the basis of characteristic condition parameter extraction. By fully using the operating parameters, condition monitoring parameters and operation statistic parameters, the conditions of equipment are predicted. It is shown by the instance that the model has higher efficiency and precision than those of the traditional BP neural network. The predicted results can be used as a support next in making scientific maintenance decision.