Genetic algorithm based approaches for medium-thick plate stress analysis feature extraction and product defect prediction

In order to accurately predict the plate production process defects, and increase the rate of finished products, and improve enterprise profits, on the base of large-scale industrial data accumulated in medium-thick plate production process, this paper uses the hybrid data analysis theory method that combines GA and machine learning to study intelligent modeling and analysis method of stress and product defect prediction model of plate. The method proposed in this paper uses the 0–1 coding mechanism of GA to realize the selection of data features, and uses the logistic classification prediction model and the cross validation method to decode the individual coding in the genetic algorithm to calculate the fitness value of the individual. The evolutionary mechanism of genetic algorithm is used to realize the optimal selection of data features. The experimental results show that the feature extraction and prediction model can accurately predict the stress defect classification of the medium-thick plate production process.