LAUSR

Abstract Laser beam machining (LBM) as an efficient tool for material removal has attracted the attention of manufacturing industries. Accordingly, there is a great motivation in the modeling and optimization of this non-conventional machining process. In this paper, the focus is on the most common LBM process, including cutting, grooving, turning, milling, and drilling. The development of an accurate model between the input and output variables of the LBM process is difficult and complex due to the non-linear behavior of the process under various conditions. In the case of LBM, the input variables are system, material, and process parameters, and the output variables are the quality characteristics of laser machined workpiece, including geometry characteristics, metallurgical characteristics, surface roughness, and material removal rate (MRR). Recently, among computational methods, artificial intelligence (AI) has been studied by scientists as a pioneer in the field of modeling and optimizing quality features of LBM. AI techniques utilize the empirical findings and existing knowledge for modeling, optimization, monitoring, and controlling of the LBM process. In this paper, the applications of AI techniques, including artificial neural network (ANN), fuzzy logic (FL), metaheuristic optimization algorithms, and hybrid approaches in modeling and optimization of the quality characteristics of LBM are reviewed. It is shown that AI techniques are successfully capable of predicting and improving the features of the laser machined workpiece. It is also demonstrated that AI can be used as a powerful tool to obtain a comprehensive model and optimal setting parameters of LBM. In addition, according to the potential and capability of AI techniques, several ideas have been offered for future studies.