Importance Measures for Vehicle Dust Pump Impeller Blade Fixture Parameters Based on BP Neural Network

The reliability of the dust pump in an engine air filtration system significantly affects vehicle performance. Therefore, the extent to which the parameters of the dust pump impeller blade fixture affect its reliability is a critical consideration during blade design. This study investigated the influences of various impeller blade fixture parameters on reliability. First, a three-dimensional finite element model of the vehicle dust pump was established to analyse the reliability of the impeller blade fixture in terms of deflection and stress according to parameter value. Next, a parametric model was established, and parameter uncertainties were defined for reliability analysis. The relationships between the different parameters and the reliability of the impeller blade fixture were subsequently predicted by a BP neural network model trained and tested using 400 and 100 samples, respectively. Finally, the output of the BP neural network model was applied to analyse the principal and total importance measures of each considered impeller blade parameter to fixture reliability. This study shows that in the reliability design of the dust pump impeller blades, priority should be given to rotational speed, blade thickness, and material density, as these factors have the greatest impact on the reliability of the blade mounting system.