PCA-based ANN approach to leak classification in the main pipes of VVER-1000

Abstract

Abstract This paper presents a neural network based fault diagnosing approach which allows dynamic crack and leaks fault identification. The method utilizes the Principal Component Analysis (PCA) technique to reduce the problem dimension. Such a dimension reduction approach leads to faster diagnosing and allows a better graphic presentation of the results. To show the effectiveness of the proposed approach, two methodologies are used to train the neural network (NN). At first, a training matrix composed of 14 variables is used to train a Multilayer Perceptron neural network (MLP) with Resilient Backpropagation (RBP) algorithm. Employing the proposed method, a more accurate and simpler network is designed where the input size is reduced from 14 to 6 variables for training the NN. In short, the application of PCA highly reduces the network topology and allows employing more efficient training algorithms. The accuracy, generalization ability, and reliability of the designed networks are verified using 10 simulated events data from a VVER-1000 simulation using DINAMIKA-97 code. Noise is added to the data to evaluate the robustness of the method and the method again shows to be effective and powerful.