4.5 Article

Expectation-maximization machine learning model for micromechanical evaluation of thermally-cycled solder joints in a semiconductor

Journal

JOURNAL OF PHYSICS-CONDENSED MATTER
Volume 35, Issue 30, Pages -

Publisher

IOP Publishing Ltd
DOI: 10.1088/1361-648X/accdab

Keywords

machine learning; solder joint; micromechanical properties; nanoindentation

Ask authors/readers for more resources

This paper investigates the changes in microstructure and micromechanical properties of solder joints in a semiconductor subjected to thermal-cycling loading. A model was developed using expectation-maximization machine learning and nanoindentation mapping, allowing for prediction and interpretation of the microstructural features of solder joints through micromechanical variations. The ML model successfully classified the Sn-based matrix, intermetallic compounds (IMCs), and grain boundaries based on their elastic modulus ranges. However, overestimations were observed in the regression process when the interfacial regions thickened. The ML outcomes also revealed that thermal-cycling led to stiffening and growth of IMCs, while the portion of Sn-based matrix decreased in the microstructure. The stiffness gradient became intensified in the treated samples, indicating increased mechanical mismatch between the matrix and the IMCs.
This paper aims to study the microstructural and micromechanical variations of solder joints in a semiconductor under the evolution of thermal-cycling loading. For this purpose, a model was developed on the basis of expectation-maximization machine learning (ML) and nanoindentation mapping. Using this model, it is possible to predict and interpret the microstructural features of solder joints through the micromechanical variations (i.e. elastic modulus) of interconnection. According to the results, the classification of Sn-based matrix, intermetallic compounds (IMCs) and the grain boundaries with specified elastic-modulus ranges was successfully performed through the ML model. However, it was detected some overestimations in regression process when the interfacial regions got thickened in the microstructure. The ML outcomes also revealed that the thermal-cycling evolution was accompanied with stiffening and growth of IMCs; while the spatial portion of Sn-based matrix decreased in the microstructure. It was also figured out that the stiffness gradient becomes intensified in the treated samples, which is consistent with this fact that the thermal cycling increases the mechanical mismatch between the matrix and the IMCs.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.5
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available