Virtual Exhaust Gas Recirculation (EGR) Mass Flow Sensor for Internal Combustion Engines

Exhaust Gas Recirculation (EGR) systems are used in internal combustion engines to reduce harmful emissions such as nitrogen oxides NOx. The accuracy of EGR mass flow estimation is critical for optimizing the performance of EGR systems. Traditionally, this has been achieved through the use of physical sensors, but there has been a growing interest in the use of virtual sensors as a viable alternative. This thesis discusses two different approaches to developing virtual sensors for EGR systems: physics-based modeling and neural network modeling. The experiments in this thesis aim to compare the accuracy and performance of these approaches in estimating the EGR mass flow rate. The neural network model employs neural networks to learn the mapping between different sensor measurements and the desired EGR mass flow rate. In this thesis, a feed-forward neural network (FFNN) is discussed. In addition, a diagnostic algorithm is developed to identify the leakage in the EGR branch and to provide a fault indication as an outcome. The diagnostic algorithm is developed by using the two different physics-based models and the FFNN model that estimate EGR mass flow. The difference in the faulty condition of these models' outputs allows the development of an algorithm to recognize the difference in the models' outputs and to raise a flag in the case of leakage detection. The results of the experiments indicate that the virtual sensor can accurately estimate the EGR mass flow rate and can be used to improve the performance of EGR systems. The diagnostic algorithm is able to accurately identify and classify leaks in the EGR system.