Search Results

Performance predictions of advanced turbocharged engines are becoming difficult because conventional engine models are built using performance map data of turbochargers with a proportional integral derivative (PID) controller. Improving prediction capabilities under transient test cycles or real driving conditions is a challenging task. This study applies a machine learning technique to predict turbocharger performances with high accuracy under steady-state and transient conditions. The manipulated signals of engine speed and torque created based on Compressed High-Intensity Radiated Pulse (Chirp signal) and Amplitude-modulated Pseudo-Random Binary Signal (APRBS) are used as inputs to the engine testbed. Data from the engine experiments are used as training data for the AI-based turbocharger model. High prediction accuracy of the AI turbocharger model is achieved with the co-efficient of determination in the model, and cross-validation results are higher than 0.8.

Alternative propulsion systems such as renewable fuels and electric powertrains are expensive; thus, efficient internal combustion engines (ICE) with hybrid powertrains still play significant roles in the transportation fleet in the coming decades. Modern engine technologies have been adopted to meet stringent emissions and fuel economy standards. As a result, engine control systems are becoming more complex. Furthermore, as ICE control parameters increase exponentially, engine calibration and design become bottlenecks in the development process. While a map-based feed-forward control method is a current de facto standard in combustion control, online closed-loop feedback control can improve engine performance and robustness. However, adding physical sensors to measure the various data for the online feedback control and calibration increase the vehicle cost.

Emission regulations are becoming tighter, and Real Driving Emissions (RDE) is proposed as a testing cycle for evaluating modern engine emissions under a wide operation range. For this reason, engine manufacturers have been developing a method to effectively assess engine performances and emissions under a wide range of transient conditions. Transient engine performances can be evaluated efficiently by applying time-series data created by chirp signals. However, when the time-series data produced by the chirp signal are used directly, the engine hardware may damage, and emission performances deteriorate drastically. It is therefore essential to develop a method to avoid these undesirable operating conditions. This work aims to develop an algorithm to avoid such unrealistic operation conditions for engine performance evaluation. A virtual diesel engine (VDE) model is developed based on a four-cylinder engine using GT-POWER software.