Based on molecular dynamics (MD), in this study, a model was established to simulate the initial coating morphology of silver paste by using a random algorithm, and the effects of different sizes of particles on sintering porosity were also analyzed. The MD result reveals that compared with the sintering process using large-scale silver particles, the sintering process using multi-scale silver particles would enhance the densification under the same sintering conditions, which authenticates the feasibility of adding small silver particles to large-scale silver particles in theory. In addition, to further verify the feasibility of the multi-scale sintering, a semi in-situ observation was prepared for a sintering experiment using micro-nano multi-scale silver paste. The feasibility of multi-scale silver sintering is proved by theoretical and experimental means, which can provide a meaningful reference for optimizing the sintering process and the preparation of silver paste for die-attach in powering electronics industry. In addition, it is hoped that better progress can be made on this basis in the future.

Machine learning models solute segregation energy based on appropriate features of segregation sites. Lumping many features together can give a decent accuracy but may suffer the curse of dimensionality. Here, we modeled the segregation energy with efficient machine learning using physics-informed features identified based on solid physical understanding. The features outperform the many features used in the literature work and the spectral neighbor analysis potential features by giving the best balance between accuracy and feature dimension, with the extent depending on machine learning algorithms and alloy systems. The excellence is attributed to the strong relevance to segregation energies and the mutual independence ensured by physics. In addition, the physics-informed features contain much less redundant information originating from the energy-only-concerned calculations in equilibrium states. This work showcases the merit of integrating physics in machine learning from the perspective of feature identification other than that of physics-informed machine learning algorithms.

Machine learning models solute segregation energy based on appropriate features of segregation sites. Lumping many features together can give a decent accuracy but may suffer the curse of dimensionality. Here, we modeled the segregation energy with efficient machine learning using physics-informed features identified based on solid physical understanding. The features outperform the many features used in the literature work and the spectral neighbor analysis potential features by giving the best balance between accuracy and feature dimension, with the extent depending on machine learning algorithms and alloy systems. The excellence is attributed to the strong relevance to segregation energies and the mutual independence ensured by physics. In addition, the physics-informed features contain much less redundant information originating from the energy-only-concerned calculations in equilibrium states. This work showcases the merit of integrating physics in machine learning from the perspective of feature identification other than that of physics-informed machine learning algorithms.