Abstract
Abstract
Automobile mesh is a typical large plastic part prone to warping deformation in the manufacturing process, which seriously affects the quality of products. The traditional method is to find the optimal combination parameters to reduce warping deformation in the forming process through repeated trial or mold flow analysis with high cost. In this study, An optimization method based on an artificial intelligence algorithm is proposed to optimize the warping deformation of the automobile mesh. In the optimization method, artificial intelligence regression algorithm-support vector machine regression was used to establish the nonlinear function relationship (prediction function) between the molding process parameters and the warpage of automobile mesh, and the performance of the prediction function was optimized by a genetic algorithm. The optimized prediction function was taken as the fitness function, the warping value was regarded as the fitness value, and genetic algorithm is used again to obtain a set of optimal process parameters and minimum warpage values. Finally, the reliability of the optimization method is verified by the modal flow analysis software.
Subject
Computer Science Applications,History,Education
Reference13 articles.
1. Optimization of injection moulding conditions with user-definable objective functions based on a genetic algorithm;Deng;International Journal of Production Research,2004
2. Multi-objective process parameter optimization for energy saving in injection molding process;Ning-yun;Journal of Zhejiang Universityence A.,2012
3. Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm;Meiabadi;Journal of Optimization in Industrial Engineering,2013
4. Comparison of the warpage optimization in the plastic injection molding using Anova, neural network model and genetic algorithm;Ozcelik;Journal of Materials Processing Tech,2006
5. Vulnerability Assessment of Equipment Excited by Disturbances Based on Support Vector Machine and Gaussian Process Regression;Chen;IEEE Transactions on Electromagnetic Compatibility,2020