AN EXPLORATORY-STUDY OF A NEURAL-NETWORK APPROACH FOR RELIABILITY DATA-ANALYSIS

The results of this paper show that neural networks could be a very pr omising tool for reliability data analysis. Identifying the underlying distribution of a set of failure data and estimating its distribution parameters are necessary in reliability engineering studies. In gener al, either a chi-square or a nonparametric goodness-of-fit test is use d in the distribution identification process which includes the patter n interpretation of the failure data histograms. However, those proced ures can guarantee neither an accurate distribution identification nor a robust parameter estimation when small data samples are available. Basically, the graphical approach of distribution fitting is a pattern recognition problem and parameter estimation is a classification prob lem where neural networks have been proved to be a suitable tool. This paper presents an exploratory study of a neural network approach, val idated by simulated experiments, for analysing small-sample reliabilit y data. A counter-propagation network is used in classifying normal, u niform, exponential and Weibull distributions. A back-propagation netw ork is used in the parameter estimation of a two-parameter Weibull dis tribution.