Application of Machine Learning for Optimization of HVOF Process Parameters

The quality of coatings can be improved by the optimization of spraying process parameters. Recently, using machine learning has become popular among variety of manufacturing industries. However, in the field of thermal spraying, the accuracy of models is questionable because of using small set of data. Here, a larger data set, “Big Data” is required to enable machine learning models to achieve a higher degree of accuracy compared to mathematical models. In this study, a large set of data is used to create a variety of machine learning models for the optimization of HVOF deposited coatings with the goal of minimizing porosity and maximizing hardness. Optimal process parameters for HVOF-deposition of WC-17CO predicted from a subset of models will be used as the process parameters for validation runs. Then, coatings will be deposited using those process parameters and the porosity and hardness of the coatings will be measured and compared to the predicted results from each model to determine an ideal model for the optimization of HVOF process parameters. Through this study, a robust machine learning model for the optimization of HVOF process parameters will be developed that could be used for other coatings and thermal spraying techniques.