Abstract
The study's major purpose was to find the best predictors for biodiesel efficiency based on emission variables and using jojoba oil as a fuel. Given the importance of biodiesel in reducing carbon dioxide emissions, a more thorough examination of such engines is required. As a result, the study's major goal was to use a selection technique to determine the best predictors for brake thermal efficiency (%), unburnt hydrocarbons (ppm vol.) and oxides of nitrogen (ppm vol.) of the biodiesel engine. For such a purpose several factors are selected and analyzed. The input variables are blending (%), fuel injection timing (obTDC), fuel injection pressure (bar) and engine load (%). The analyzing procedure was performed by adaptive neuro fuzzy inference system (ANFIS) and all available parameters are included. The ANFIS model could be used as simplification of the analysis since there is no need for knowledge of internal physical and chemical characteristics of the biodiesel engine. The results from the function clearly indicate that the input attribute "Engine load" (RMSE = 1.8002) is the most influential for the brake thermal efficiency. Furthermore, the input attribute "Fuel injection pressure" (RMSE = 4.2620) is the most influential for the unburnt hydrocarbons. "Engine load" (RMSE = 4.7484) is the most influential for the oxides of nitrogen. In this paper, an adaptive neuro fuzzy inference system (ANFIS) was used to develop a prediction approach for determining the influence of hydrolysis time, cellulase loading, bGlucosidase loading, substrate loading and working volume on the enzymatic saccharification on the yield of glucose. The ideal combination of two input attributes or two predictors for enzymatic saccharification on glucose yield was discovered to be "substrate loading" and "working volume" (RMSE = 4.1625). The findings could be useful in reducing the cost of the procedure by optimizing enzymatic saccharification on glucose response yield. (C) 2021 Elsevier Ltd. All rights reserved.