A prediction method for the precision of extrusion grinding of a needle valve body

The needle valve body is an important part of the fuel injection nozzle of a diesel engine, and its machining precision will affect the performance of the diesel engine. As an important process of needle valve finishing, extrusion grinding can reduce the flow error and improve the flow consistency. However, it is difficult to determine the non-linear relationship between the precision of the grinding process and the processing parameters using conventional experimental methods. Firstly, the various parameters affecting the grinding precision of the needle valve body are analyzed. Secondly, an experiment is designed to acquire the test data with our grinding machine. The method based on support vector machine combined with particle swarm optimization (PSO-SVM) is proposed to predict the precision of the extrusion grinding of the needle valve body. The particle swarm optimization (PSO) algorithm is used to optimize the parameters of the SVM. The results show that our optimized prediction model is more accurate and faster than the BP neural network algorithm. The proposed prediction method provides guidance for selecting the grinding parameters of the needle valve body to further improve the precision of processing.