민경덕 교수

Recently, deep learning has played an important role in the rise of artificial intelligence, and its accuracy has gained recognition in various research fields. Although engine phenomena are very complicated, they can be predicted with high accuracy using deep learning because they are based on the fundamentals of physics and chemistry. In this research, models were built with deep neural networks for gasoline engine prediction. The model consists of two sub-models. The first predicts the knock

Deep-learning models were developed and evaluated for predicting the engine-out emission of NO x —one of the main pollutants emitted from diesel engines—under transient conditions, that is, the Worldwide Harmonized Light Vehicles Test Procedure (WLTP). Phenomena of transient conditions are difficult to predict accurately via the conventional modeling approaches. Two algorithms—the deep neural network (DNN) and long short-term memory (LSTM)—were evaluated regarding the accuracy and calculation ti

This study describes the development of a semi-physical, real-time nitric oxide (NO) prediction model that is capable of cycle-by-cycle prediction in a light-duty diesel engine. The model utilizes the measured in-cylinder pressure and information obtained from the engine control unit (ECU). From the inputs, the model takes into account the pilot injection burning and mixing, which affects the in-cylinder mixture formation. The representative in-cylinder temperature for NO formation was determine

Nitrogen oxides (NO x ) are one of the main harmful emissions from diesel engines. Regulations on emissions are becoming more stringent; consequently, research should aim at reducing both engine-out NO x and tail-pipe NO x emissions. Exhaust gas recirculation is mainly used to reduce engine-out NO x emissions. After-treatment methods such as lean NO x trap systems and selective catalyst reduction are used to minimize tail-pipe NO x emissions. Real-time feedback control during transient condition