Effect of Exhaust Backpressure on Performance of a Diesel Engine: Neural Network based Sensitivity Analysis
| Autor: | GÜLMEZ, YİĞİT, ÖZMEN, GÜNER |
|---|---|
| Přispěvatelé: | Barbaros Hayrettin Gemi İnşaatı ve Denizcilik Fakültesi -- Gemi Makineleri İşletme Mühendisliği Bölümü, Gülmez, Yiğit |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
Diesel engine
Reducing systems Network-based Performance Waste heat utilization Transportation Efficiency Fuels Back pressures Controller Engineering & Materials Science - Combustion - Biodiesel Engineering Neural network model Back pressure Specific fuel consumption Diesel engines Exhaust backpressure Exhaust Gas Recirculation Volumetric efficiency Turbochargers Waste incineration Fuel consumption Automotive Engineering Gas back-pressure Neural-networks Waste heat Brakes Gases Sensitivity analysis Neural networks |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|