Sensitivity Analysis Of Intercoolers Structural Parameter's And Optimization And Design

With the development of the automotive industry, the tube-fins intercooler with its compact, excellent heat transfer performance in the automotive cooling system had been more widely used. According to the different structure parameters, Domestic and foreign scientists had deep and systematic studied in Heat transfer mechanism and fluid flow characteristics.This article discusses the general principles of structural design in the tube-fins intercooler inlet chamber,analyze the flow distribution and pressure losses on the performance of the tube-fins intercooler.And through comparing the two different inlet structures, Obtain the vintage structural design.Two different 3-layer back propagation BP neural network models were established in order to explore the feasibility of applying neural network technology to analyze the parametric effect on performance in tube-fins intercooler.The models were trained and optimized to predict the heat transfer performance and flow resistance of a plate-fin tube-fins intercooler.The parameter sensitivity analysis of fin was conducted according to the prediction results.The data of train and test samples were from many wind tunnel tests and simulation results. The models had three and six hidden layer neurons irrespectively after optimized. The transfer function of hidden and output layers were tansig and purelin function irrespectively,and the train function was based on Levenberg-Marquardt method. Results show that neural network can predict the effect of fin parameter on tube-fins intercooler performance, meet the actual needs of project and reduces the amount of experimental work. The results of fin parameter sensitivity analysis accorded well with the engineering experience.