Optimization of multistage femtosecond laser drilling process using machine learning coupled with molecular dynamics

Although femtosecond laser percussion drilling is widely used in many key industrial manufacturing fields, the quality of micro-holes limits its service performance. The traditional trial and error method and physical model are always time and cost consuming for process optimization. To address this problem, a process optimization framework coupled with molecular dynamics simulation, machine learning and a high-throughput optimization algorithm is proposed. The physical information obtained by molecular dynamics enriches the data set used to train machine learning model, and thus reducing the amount of data required. Machine learning can quickly and accurately establish the regression model between laser parameters and target machining performance, and high-throughput optimization algorithm is responsible for determining the optimal process in the process space. For femtosecond laser percussion drilling, a new four-stage drilling process is proposed and optimized using the coupling process optimization framework to solve efficiency and quality problems. Finally, the experimental validation for Ni-based single crystal superalloy verifies the reliability of the optimized process. The framework can be extended to other complex systems to realize process optimization with high efficiency and low cost in laser material processing technology.

Automated summary

In this study, a process optimization framework combining molecular dynamics simulation, machine learning, and high-throughput optimization algorithm is proposed to solve efficiency and quality problems in femtosecond laser percussion drilling. The framework can establish the relationship between laser parameters and target machining performance quickly and accurately, and determine the optimal process.