Prediction of Lubricating Oil Metal Element Concentration of One Aero-Engine Based on Bp Neural Network

In this paper, based on the detection data of the metal element concentration in the lubricating oil of one aero-engine, the BP neural network model was used to predict the next concentration value of the lubricating oil metal element. And three sets of different data were used to test the applicability of the model. By comparison, the BP neural network with 14 hidden layer neurons was chosen to predict the concentration of Fe, Ag and Cu with the minimum error. The failure prediction and maintenance mode of the aero-engine can be transformed through the prediction of the concentration of lubricating oil metal elements.