Drop impact analysis of TSV-based 3D packaging structure by PSO-BP and GA-BP neural networks

作     者：Mao Minghui Liu Jiansong Tian Mengke Lin Pengrong Long Xu 毛明晖;刘建松;田梦珂;林鹏荣;龙旭

作者机构：School of Civil EngineeringLiaoning Petrochemical UniversityFushun 113001China Beijing Microelectronics Technology InstituteBeijing 100076China School of MechanicsCivil Engineering and ArchitectureNorthwestern Polytechnical UniversityXi’an 710072China 

出 版 物：《China Welding》 (中国焊接（英文版）)

年 卷 期：2022年第31卷第1期

页      面：37-46页

学科分类：080903[工学-微电子学与固体电子学] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0809[工学-电子科学与技术（可授工学、理学学位）] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China (No. 52175148) the Natural Science Foundation of Shaanxi Province (No. 2021KW-25) the Astronautics Supporting Technology Foundation of China (No. 2019-HT-XG) 

主　　题：drop impact through silicon via particle swarm algorithm genetic algorithm dynamic response 

摘      要：Particle swarm algorithm(PSO) and genetic algorithm(GA) were used to optimize the back propagation(BP) artificial neural network for predicting the dynamic responses of the through silicon via(TSV) based three-dimensional packaging structures.A finite element model of the TSV packaging structure with a strain-rate dependent constitutive model for solder joints was created to simulate the drop impact due to a free fall of 0.8 m to the rigid ground to investigate the structural dynamic responses during the whole impact *** spatial coordinates of the solder joints were used as the input parameters of the hybrid neural network model for the drop impact responses,while the maximum Von Mises stress and PEEQ(plastic strain) values are identified the output *** correlation coefficient(R),the mean absolute percentage error(MAPE) and the training time were used as the measures to validate and compare the proposed PSO-BP and GA-BP neural *** results show that both the PSO-BP model and the GA-BP model can achieve high accuracy predictions with strong generalization ***,both optimized algorithms outperform the original BP model,but the PSO-BP model is slightly more superior than the GA-BP *** is also demonstrated that the proposed optimized algorithms efficiently predict the drop impact responses of TSV packaging structures by greatly saving the computational and experimental cost of drop impact tests.