Based on the radial basal function neural network (RBFNN) and the OLS arithmetic, an on-line sensor fault detection diagnostic strategy on the diesel engine cold starting is proposed. This diagnostic strategy is conducted by RBFNN .The data of sensor sampling is the input and the sensor faults is the output of RBFNN. Some samples could be trained and studied by RBFNN. The parameters, such as, short circuit, open circuit and the stuck-at fault of the electric current, the voltage and the rotational speed have been made by the RBFNN and the OLS arithmetic. The test results indicate that the sensor fault diagnostic accuracy can reach 95.6%. It is value that this diagnostic strategy could be achieved the IV emissions regulations of China in the diesel engine cold starting cycle and also can be used in the vehicle on board diagnosis system. Keywords-diesel engine;sensor;neural network;cold start;on board diagnosisI.

In order to discuss linearity of throttle position sensor. Based on the synergetic theory of the radial basal function neural network (RBFNN) and the contractive mapping genetic arithmetic (CMGA), the throttle position sensor structural parameters, such as, the length and radius of the primary coil, prejudicial distance and radius of prejudicial disc, primary exciting current were optimally forecasted by RBF-CMGA. Several analogue test of diesel engine are made on the basis of throttle position sensor control system of adding loads and decreasing loads. The optimal parameter has been calculated on the well-balanced state of throttle position sensor, and it was very good in the aspect of both dynamic state that is 0.25×10 -3 sounds and linearity is 0.4% in the throttle position sensor control system of diesel engine, which can meet the needs of well-balanced state of diesel engine, It is feasible that the throttle position sensor linearity and structural parameters are optimized by RBF-CMGA.

No abstract

Based on the particular structure of the ω combustion chamber, the three-dimensional dynamic CFD model of the diesel engine fuel injection characteristics was established, the changing mechanism on the fuel mixture flow field and pressure field in the combustion chamber were predicted by the commercial Fluent software. The results showed that after the fuel began to spray, the oil-beam-driven vortex flow was essential to maintain. Late in the combustion, fuel droplet particles sprayed into the wall, and fuel components concentrated near the wall in the combustion chamber. The reverse squish was formatted in the initial expansion stroke.

No abstract