Search Results

In the present study, the research of the exhaust system is performed in three steps. In the first step, the average driving degree of freedom displacement (ADDOFD) is calculated by the free modal analysis of the exhaust system. It is easy to find the reasonable location of the hanger according to the value of the ADDOFD, since it represents the relative size of some DOF's response displacement at excitation state. The second of which is to analyse the vibration isolation performance of the exhaust system based on the first step. The dynamic analysis of the exhaust system together with the powertrain is studied, by which way the unit sinusoidal excitation is applied at the powertrain's mass centre, so that the response force at the hanger can be obtained. Finally, the relationship between the constrained model of the exhaust system and the stiffness of the hanger is investigated, which is significant in engineering.

In the foreseeable future, the growing energy crisis and environmental pollution problem pose severe challenges to the automobile powertrains and exhaust systems. However, conventional optimization methods, including multi-dimensional computational fluid dynamics model and bench experiments, are very time-consuming or expensive. Adding the application of data-driven models to engine research and development has the potential to reduce computational costs or the number of in-depth experiments. This purpose of this study was to compare the performance of widely used artificial neural network (ANN) and random forest (RF) model for predicting the fuel consumption and engine-out emissions of a calibrated spark ignition (SI) engine for any given condition.