Effect of Exhaust Backpressure on Performance of a Diesel Engine: Neural Network based Sensitivity Analysis

Abstract

Various types of emission-reducing systems or waste heat recovery systems installed on exhaust pipes of internal combustion engines are a source of high exhaust gas backpressure. Increased backpressure can cause negative impacts on the performance of internal combustion engines. This study aims to explore the relationship between exhaust gas backpressure and diesel engine performance indication parameters such as volumetric efficiency and brake specific fuel consumption. A neural network model was generated to identify the relation between the input variables (engine backpressure, engine speed, torque and exhaust temperature) and performance indicators (volumetric efficiency and brake specific fuel consumption). A single cylinder, naturally aspirated, 13 kW diesel engine was used for experiments and the results of the experiments were used to develop the neural network model. Then, a sensitivity analysis was performed to identify the influence of any input parameter including exhaust gas backpressure on volumetric efficiency and brake specific fuel consumption. The results of the study showed that engine backpressure is a critical parameter for both volumetric efficiency and fuel consumption. Besides, the study demonstrated that neural network modelling is a suitable method to explore the relationship between inputs and outputs of an internal combustion engine system.