论文部分内容阅读
低温共烧陶瓷(LTCC)基板制作工艺复杂,产品质量对工艺参数十分敏感,微小的成型缺陷就会影响其功能特性。文章将BP神经网络和多目标遗传算法——NSGA-Ⅱ(Nondominated Sorting Genetic AlgorithmⅡ)相结合用于LTCC基板在层压和烧结工艺过程中的工艺参数优化。根据LTCC基板成型过程中出现的微通道变形、互联金属柱错位、基板翘曲三种主要成型缺陷与相关工艺参数的正交仿真实验结果,对神经网络模型进行训练,建立了三种成型缺陷与工艺参数之间的神经网络预测模型。在此基础上,采用多目标遗传算法对三种成型缺陷相关工艺参数进行多目标优化求解,得到了较优的工艺参数组合,用于指导相关产品制作工艺设计。
The manufacturing process of LTCC substrate is complex, the product quality is very sensitive to the process parameters, and the tiny molding defects will affect its functional properties. In this paper, BP neural network and multi-objective genetic algorithm (NSGA-Ⅱ) are combined to optimize the process parameters of LTCC substrate in lamination and sintering process. According to the orthogonality simulation results of microchannel deformation, dislocation of interconnected metal columns and substrate warpage and the related process parameters in LTCC substrate forming process, the neural network model was trained and three forming defects and Neural Network Prediction Model Between Process Parameters. On this basis, the multi-objective genetic algorithm is used to solve the multi-objective optimization of the three process parameters related to forming defects, and the optimal combination of process parameters is obtained, which is used to guide the design process of related products.