An ANN approach to evaluate effect of injection timing, engine speed and load on a diesel engine cylinder pressure

In this study, a back-propagation neural network model has been developed to predicting the cylinder pressure of a DI diesel engine. The inputs of the model were injection timing, crankshaft angle, engine speed, and engine load. An optimal design has been completed for the number of hidden layers, the number of hidden neurons, the activation function, and the goal errors in the back-propagation neural network model. After training, it was found that the R2 values are closely 1 for the training and testing data. The results may easily be considered to be within the acceptable limits. Cylinder pressure has been predicted with the model, the effects of injection timing, crankshaft angle, engine speed and engine load on it have also been analyzed, and better results have been achieved. The relationship between input parameter and engine cylinder pressure can be determined by using the network. Therefore, the usage of ANNs may be highly recommended to predict the engine cylinder pressure instead of complex and time-consuming experimental studies.