| Summary: | 博士 === 國立臺灣海洋大學 === 系統工程暨造船學系 === 97 === Normally, a mechanical pumping system is equipped to monitor some of the important input and output signals, which are set to the prescribed values. This paper addressed dealing with these signals to establish the database of input-output relation by using a number of neural network models through learning algorithms. These signals encompass normal and abnormal running conditions. The abnormal running conditions are artificially generated. Meanwhile, for the purpose of setting up an on-line diagnosis network, the learning speed and accuracy of three kinds of networks, viz., the backpropagation (BPN), radial basis function (RBF) and adaptive linear (ADALINE) neural networks have been compared and assessed. The assessment criteria of the networks are compared with the correlation result matrix in terms of the neuron vectors. Both BPN and RBF are judged by the maximum vector based on the post-regression analysis, and the ADALINE is judged by the minimum vector based on the least mean square error analysis. By ignoring the neural network training time, it has been shown that if the mechanical diagnosis system is tackled off-line, the RBF method is suggested. However, for on-line diagnosis, the BPN method is recommended. This convenient, practical and valid diagnostic mechanism by using relative parameters that are monitoring regularly from significant level analysis and diagnosing the best regression or the least mean square error indicates the distinguishing characteristic.
|
|---|
