Artificial Intelligence and Machine Learning for Process Optimization in Thermal Spray Coatings: A Review

This article examines the current state of advanced digital technologies, such as Artificial Intelligence (AI) and Machine Learning (ML), in smart material design and thermal spray coatings (TSCs), and the advantages they offer. The increasing adoption of AI and ML in materials processing is driven by their capability to optimize process parameters, enhance process control, and accelerate data-driven decision-making. This review discusses the use of AI/ML in thermal spraying, including APS, HVOF, and CS. Recent AI and ML applications have led to shorter product development cycles and faster R&D feedback loops during planning. It also offers a detailed roadmap to solutions to current problems and further research. This can be achieved using cutting-edge algorithms on multidimensional datasets of process parameters to support predictive modeling, parameter optimization, and dynamic process modification. These processes involve complex thermophysical mechanisms, including phase transitions, extremely rapid melting/solidification, and nonlinear material-process interactions, which are difficult to model using standard analytical or physics-based models. The review further examines the application of AI/ML algorithms, including regression models, decision trees, neural networks, and genetic algorithms, for intelligent process control, real-time monitoring, and quality prediction, using data obtained from sensors, simulations, and experimental studies.AI/ML models can be assessed for effectiveness using industry-specific frameworks and methods. Finally, the AIML solution for developing the global coating market is discussed, and an outlook is presented.