A diesel engine to predict exhaust emissions from the engine. To acquire data for training and testing of the proposed RNA, a single cylinder, four-stroke test engine was fed with biodiesel mixed with diesel and operated at different loads. Using some of the experimental data for training, an ANN model was developed based on the neural forward power network for the motor. Next, we measured the performance of RNA predictions by comparing predictions with experimental results that were not used in the training process. It was observed that the ANN model can predict the exhaust emissions of the engine quite well with correlation coefficients, with very low root mean squared errors.
The digital computer provided a rapid means of performing many calculations involving Artificial Neural Network (ANN) methods. Along with the development of high-speed digital computers, the application of the ANN approach could be progressed at a very impressive rate. In recent years, this method has been applied to various disciplines, including automotive engineering, in the forecast of the thermal characteristics of the engine for different working conditions. Some researchers studied this method to predict the characteristics of the internal combustion engine.