Abstract: In order to improve the efficency of performance predicting and decrease the cost of testing in the procedure of product development, a CAD method for engine oil pump which based on co-application of flow field analyzing and intelligent modeling was introduced. Numerical simulation model of oil pump internal flow field based on CFD was developed combining with the structural parameters of oil pump. And infromation data about oil pump rotate speed, supplying pressure, oil temperature and oil flow rate were obtained by CFD simulating. A BP neural network model that describeed the delivery performance of oil pump was established, and the model was trained by learning samples which selected from those above information data. And lastly, predicting for the delivery performance of oil pump under various operating conditions was carried out by this BP intelligent model. Experiments showed that the simulation results fitted the testing results quite well. From these results, the conclusion is that the method introduced here can give useful support for optimization design of structural parameters of engine oil pump and control of its delivery performance in the procedure of new product development.