Research on the Intelligent Approach of Material Property Prediction and Optimization

摘要

In this paper, a prediction model based on improved SLFM network was proposed to predict material properties. The topology, algorithms of learning and prediction, and parameter selection of this network were discussed when the prediction model was implemented. An engineering application example on Ti-26 alloy was introduced to show that this prediction model possesses advantages of high speed of learning (253 iterations for 20 learning samples), high learning accuracy (100 percent in recalling accuracy), and quite good prediction performance (the value of relative error can be mostly controlled in 3 percent). Based on its good performance, part factors affecting the properties of Ti-26 alloy are optimized. The prediction results and practical results present a good conformity.