Building an expert system for debugging FEM input data with artificial neural networks

Abstract Debugging of the input data of a Finite Element Method (FEM) structural analysis program is a troublesome task, which is heavily dependent on empirical knowledge. An effort to build an expert system for the problem is described in this paper. To overcome the bottleneck of knowledge acquisition, an artificial neural network is used as the learning mechanism to transfer engineering experience into formulated knowledge. The back-propagation learning algorithm is employed to train the network for extracting knowledge from training examples. Furthermore, the influences of various control parameters, including learning rate and momentum factors, and various network architecture factors, including the number of hidden units and the number of hidden layers, are examined. The results prove that the artificial neural network can work sufficiently as a knowledge acquisition tool for the debugging problem. To apply the knowledge in the trained network, a reasoning strategy that hybridizes forward-reasoning and backward-reasoning schemes is proposed to realize the inference mechanism.