Investigation of parametric control method and model in abrasive belt grinding of nickel-based superalloy blade

Abrasive belt grinding is gradually recognized as an effective machining technology for blade. However, the complex contact characteristics of this technology make the grinding quality of blade unable to be precisely controlled. In order to solve this problem, a parametric control method for precision abrasive belt grinding of blade was proposed, and a multi-parameter test platform for state parameters (grinding force, vibration, and temperature) was established. The grinding experiments of nickel-based superalloy samples were carried out, and the prediction model of state parameters based on back propagation neural network was constituted. The prediction accuracy of the model was 93.58%. On this basis, the grinding experiments of nickel-based superalloy blade were conducted. The influence of state parameters on the evaluation parameters (material removal, profile accuracy, surface quality) was analyzed and the optimal grinding parameters were determined. The experimental results showed that the machining quality of new-type aeroengine blades can be effectively improved by this parametric control method and model.