Study and Optimization of Ethanol (LRF) Juliflora Biodiesel (HRF) Fuelled RCCI Engine with and without EGR System

Abstract

Over the past few decades, the use of non-renewable energy has progressively expanded, harming the environment. In this investigation, 4-stroke single-cylinder Reactivity Controlled Compression Ignition (RCCI) engine performance and emission behaviour are reduced with the help of running fuel. 20% Juliflora biodiesel and 80% diesel are used as high-reactive fuel (HRF) and Ethanol is used as the low-reactive fuel (LRF). The RCCI engine is evaluated at different input conditions by varying engine load from 0 to 100 (0, 25, 50, 75, and 100%) and LRF percentage from 30 to 60 (30, 40, 50 and 60%). Additionally Exhaust Gas Recirculation (EGR) is used to enhance the RCCI engine emission behaviour and performance.The studied output performance of RCCI engine are cylinder pressure (CP), brake thermal efficiency (BTE), heat release rate (HRR), and brake-specific fuel consumption (BSFC) respectively. Also, unburned hydrocarbon (HC), carbon monoxide (CO), nitrogen oxides (NOX), and smoke opacity (SO) are calculated on the RCCI engine for all input condition. The test results are further optimized with the help of hybrid deep belief neural network based Aquila optimization method. The proposed hybrid DBN-AO has performed better than conventional DBN method.The predicted optimal value is obtained from the regression and average regression coefficients of 0.99961. The predicted optimum values are load 80%, LRF60%, and EGR 15%, respectively. The confirmatory error analysis has shown BTE (3.7%), BSFC (4%), SO (4.7%), HC (7.775%), CO (3.44%) and NOx (3.46%) respectively. The EGR application reduces the RCCI engine emission behaviour in loading condition.

Keywords

• aquila optimization
• deep belief neural network
• ethanol
• exhaust gas recirculation
• juliflora biodiesel
• reactivity controlled compression ignition