Optimization of process parameters for synthesis of high entropy shape memory alloys using hybrid ANN-GA approach
摘要
High Entropy Shape Memory Alloys (HESMAs), are a family of unique materials with the combination of five or more componential elements that have the potentials to form various compositions in a solid solution. Owing to their unique properties, these materials are in a drastic upsurge in demand for a variety of applications and are grabbing the attention of researchers and academicians. The aim of the given research is to optimize process parameters for synthesis of HESMAs oriented for the processing of data using an evolutionary approach. In this, different in put parameters were used to optimize the process parameters, such as sintering temperature, sintering time, compaction pressure, compaction time, and milling time. RSM with BBD employed for data analysis. ANN with BP is used for empirical modeling and prediction, and global solution with the help of GA. The data trend reveals the different patterns between input parameters in sustaining relationships among these parameters. Lastly, the performance of the proposed framework is validated and compared based on evaluation metrics such as R2 (%), and MSE. The proposed model is the first attempt to employ optimization of process parameters of powder metallurgy utilizing a hybrid ANN-GA based strategy for the synthesis of HESMAs generating significantly to maximize density.