Diesel engine performance and emission analysis running on jojoba biodiesel using intelligent hybrid prediction techniques

In this work, an analysis of the efficiency and emission variables of a jojoba-fuelled engine is carried out using optimization techniques. This research study investigates the introduction of intelligent hybrid prediction models using an adaptive neuro-fuzzy inference system (ANFIS), the ANFIS-genetic algorithm (GA), and the ANFIS-particle swarm optimization (PSO). The input variables are injection pressure, fuel injection timing, biodiesel blends and engine load, while associated output responses such as BTE, UHC, and (NOX) are considered during the investigation. The experiment and anticipated estimates of BTE, UHC, and NOX of the engine fuelled with jojoba biodiesel, acquired by ANFIS, ANFIS-GA, and ANFIS-PSO have been found to be significant. Three statistical measures of mean square error (MSE), root mean square error (RMSE), and determination coefficient (R-2) were used to assess and compare the performance of the proposed model. The MSE and RMSE of the ANFIS-GA and ANFIS-PSO models have been noticed to be less than the ANFIS models. However, the determination coefficient has shown that the ANFIS-PSO models with R-2 (0.9825, 0.9877, and 0.9895 for BTE, UHC, and NOx) show a reasonable upgrade in consistency, particularly in comparison to the suggested ANFIS model. Thus, the ANFIS-PSO system demonstrated as a better optimization process considered while considering the responses when contrasted with ANFIS and the ANFIS-GA. In short, the whole study concludes that hybrid techniques like ANFIS-GA and ANFIS-PSO are an effective and reliable method for effective assessment of engine emission parameters.