The demand for rapid advancement in AI, mobile and automotive markets is pushing the boundaries of electronic packaging, including heterogeneous integration, high-power packages, and large-die packaging. Against this backdrop, machine learning technologies emerge as dynamic tools for correlation building and classification, revolutionizing the traditional approaches to design, manufacturing, and testing in electronic packaging, as well as the Design for Reliability (DfR) methodologies.This paper reviews the most recent AI-assisted approach for electronic packaging and then focuses on the AI-assisted DfR (AI-DfR) approaches. Our examination reveals that AI methods have been adapted to meet the specific needs of electronic packaging. The industry’s anticipation for AI-DfR stems from its potential to address prevailing reliability design challenges, yet its multidisciplinary essence poses hurdles to swift progress. This review proposes future directions for AI-DfR’s development, spotlighting critical areas such as the quality and efficiency of finite element modeling, design and optimization of training models, selection of AI models, and maintenance and value enhancement strategies.@en

Solder joint fatigue is one of the critical failure modes in ball-grid array packaging. Because the reliability test is time-consuming and geometrical/material nonlinearities are required for the physics-driven model, the AI-assisted simulation framework is developed to establish the risk estimation capability against the design and process parameters. Due to the time-dependent and nonlinear characteristics of the solder joint fatigue failure, this research follows the AI-assisted simulation framework and builds the non-sequential artificial neural network (ANN) and sequential recurrent neural network (RNN) architectures. Both are investigated to understand their capability of abstracting the time-dependent solder joint fatigue knowledge from the dataset. Moreover, this research applies the genetic algorithm (GA) optimization to decrease the influence of the initial guessings, including the weightings and bias of the neural network architectures. In this research, two GA optimizers are developed, including the “back-to-original” and “progressing” ones. Moreover, we apply the principal component analysis (PCA) to the GA optimization results to obtain the PCA gene. The prediction error of all neural network models is within 0.15% under GA optimized PCA gene. There is no clear statistical evidence that RNN is better than ANN in the wafer level chip-scaled packaging (WLCSP) solder joint reliability risk estimation when the GA optimizer is applied to minimize the impact of the initial AI model. Hence, a stable optimization with a broad design domain can be realized by an ANN model with a faster training speed than RNN, even though solder fatigue is a time-dependent mechanical behavior.

@en