A quality evaluation model for diesel engine using RBF neural network based on trial run data

摘要

This paper aims to provide a model for evaluate the quality of diesel engine using radial basis function(RBF) neural network based on the trial run data. Quality evaluation in the manufacturing process is the key link to improve the quality of the diesel engine. However, it has not been fully researched especially that the quality evaluation of diesel engine based on the trial run data. Therefore, the quality evaluation model using RBF neural network method is proposed in this study. Firstly, trial run data were preprocessed and analyzed on the basis of eliminating information redundancy and mining potential information. Afterwards, the RBF model was established to evaluate the quality of the diesel engine. Considering that there is a certain correlation between the input variables, the Mahalanobis distance is adopted in the radial basis function. Finally, the validity of the model is proved by the data experiment.