LAUSR

Grinding is a key process in machining and has direct impacts on the accuracy, performance, and service life of the finished workpiece. Process changes have a significant effect on quality and efficiency. Therefore, it is very important to select the best process combination. The traditional optimization methods are complex in analysis and poor in generalization. In this paper, a novel optimization algorithm is proposed. A bidirectional long short-term memory network is used to construct a prediction model of the relationship between the process parameters and evaluation parameters, and the chaos sparrow search algorithm is used to solve for the optimal process combination in the search space. Moreover, this paper focuses on belt grinding and considers three process parameters—belt linear velocity, grinding pressure, and feed speed—and two evaluation parameters: machining accuracy and grinding efficiency. The overall goal is to maximize grinding efficiency within the range of machining accuracy requirements. Grinding experiments are carried out on 20CrMnTi cylindrical bars. The model is verified based on the experimental data, and the results prove the feasibility of the model.