Machine Learning Inversion Method for Elastoplastic Constitutive Parameters of Encapsulation Materials.

Abstract

Accurate measurement of material mechanics parameters is crucial for evaluating process quality and product reliability and is a major challenge in the development of 3D heterogeneous integration technology. Aiming to perform high-accuracy measurements of the elastoplastic nonlinear constitutive parameters of microelectronic materials using the nanoindentation testing technique, we take advantage of a neural network to construct a forward characterization model to characterize these response characteristic parameters for different materials, design an improved algorithm for obtaining a reverse iterative solution of the forward characterization model, and develop a material mechanics parameter measurement method to solve overdetermined equations using the least-squares method. This method was further improved by addressing the issues of algorithm stability and solution uniqueness, achieving high-precision and fast reverse solutions for elastoplastic constitutive parameters. The relative error of the material parameters is less than 3% (95% confidence interval), the maximum error is less than 8%, and the inversion convergence error of the key indentation response characteristic parameters is less than 0.1%. The difference between the measured material parameters and the theoretical model in the influence on the process stress of TCV (through ceramic via) products is verified through finite element simulation.