Abstract：To accurately predict the emissions of gasoline engine exhaust pollutants, the emissions prediction was performed based on the BP neural network model. Aiming at the characteristics of nonlinear gasoline engine exhaust emission prediction, many characteristic parameters and large sample data, the data flow information of the characteristic parameters were used as input, and the vehicle emission level was used as output. Based on the BP neural network, the gasoline engine emission prediction models of CO, HC and NOx were respectively established, and the real vehicle test verification was completed in three modes of normal state, abnormal fuel pressure and abnormal intake pressure sensor. The test results of the vehicle exhaust gas analyzer were compared with the predicted results. The results show that the prediction system can predict three kinds of gases with high prediction accuracy and fast convergence speed, which can reach the expected results with good reliability.
