Process optimization of SiC/(Mo, W)Si₂ nanocomposites preparation based on BOA-SSA

Silicon carbide/(molybdenum, tungsten) disilicide nanocomposites have important application value in aerospace, high-temperature structural materials and other fields, but the current preparation process still needs to be optimized. In order to prepare high-performance silicon carbide/(molybdenum, tungsten) disilicide nanocomposites, a three-layer structure backpropagation neural network model is constructed, and the specific construction process and training structure are analyzed. Sparrow search algorithm is used for model optimization. At the same time, in response to the problem easily getting stuck in local optima, the butterfly optimization algorithm is proposed to optimize it and solve the optimal preparation process. The results indicated that the error between the predicted and experimental values of the bending strength of the prepared material using the backpropagation neural network model was less than 2%, and the minimum relative error was only 0.15%. Meanwhile, the best process combination obtained by the Butterfly Optimization Algorithm-Sparrow Search achieved a bending strength of up to 752 MPa, while the traditional Sparrow Search only achieved a bending strength of 662 MPa. The material preparation process optimization method has significant advantages and can effectively improve the bending strength of the prepared silicon carbide/(molybdenum, tungsten) disilicide nanocomposites, providing an effective solution for solving multidimensional nonlinear optimization problems.