Cylinder Pressure Prediction of An HCCI Engine Using Deep Learning

Abstract Engine tests are both costly and time consuming in developing a new internal combustion engine. Therefore, it is of great importance to predict engine characteristics with high accuracy using artificial intelligence. Thus, possible reduce testing costs speed up the development process. Deep Learning an effective intelligence method that shows performance many research areas through its ability learn high-level hidden features data samples. The present paper describes cylinder pressure Homogeneous Charge Compression Ignition (HCCI) for various excess air coefficients by Neural Network, which one methods based on Artificial Network (ANN). results were compared ANN experimental results. show difference between (DNN) less than 1%. best obtained method. was predicted maximum 97.83% value ANN. On other hand, increased 99.84% DNN. These DNN can be used effectively pressures engines.