Covariance matrix adapted grey wolf optimizer tuned eXtreme gradient boost for bi-directional modelling of direct metal deposition process
作者：
Highlights：
• Applies ML techniques for both forward and backward modelling of a DMD process.
• Leverages XGBoost first time in this field for building a regressor for prediction.
• Investigates hyperparameter tuning for improving XGBoost models using meta-heuristic optimizers.
• Introduces a novel covariance matrix adapted grey wolf optimization (cmaGWO) algorithm.
• Validates cmaGWO by exhaustive benchmarking and applies successfully in prediction.
摘要
•Applies ML techniques for both forward and backward modelling of a DMD process.•Leverages XGBoost first time in this field for building a regressor for prediction.•Investigates hyperparameter tuning for improving XGBoost models using meta-heuristic optimizers.•Introduces a novel covariance matrix adapted grey wolf optimization (cmaGWO) algorithm.•Validates cmaGWO by exhaustive benchmarking and applies successfully in prediction.
论文关键词：Additive manufacturing,Direct metal deposition,Extreme gradient boost,Grey wolf optimization,Covariance matrix adaptation,Predictive system
论文评审过程：Received 18 June 2021, Revised 30 January 2022, Accepted 22 March 2022, Available online 4 April 2022, Version of Record 13 April 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116971
