Optimization of biodiesel yield from waste cooking oil and sesame oil using RSM and ANN techniques.

In the era of global energy crises and the pressing concern of fossil fuel depletion, the quest for sustainable alternatives has become paramount. The current study aims to optimize biodiesel extraction from a combination of waste cooking oil (WCO) and sesame seed oil (SSO) through response surface methodology (RSM) and artificial neural network (ANN). The cold flow properties of biodiesel produced from WCO are a major obstacle to the commercial use of biodiesel. On the other hand, SSO possesses better oxidation stability and cold flow properties. A mixture of waste cooking oil (i.e. 70 % by volume) and sesame seed oil (i.e. 30 % by volume) has been prepared for biodiesel production via a microwave-assisted transesterification process. For biodiesel yield optimization, the interaction among the operating parameters is developed by RSM, whereas biodiesel yield is predicted by ANN. The operating parameters include reaction speed, RPM (100-600 rpm), reaction time (1-5 min), methanol to oil ratio (8:1-12:1 v/v), and catalyst concentration (0.1-2 % w/w). The highest biodiesel yield of 94 % is found at a reaction speed of 350 rpm, reaction time of 3 min, catalyst concentration of 1.05 w/w, and methanol to oil ratio of 10:1. Furthermore, it is discovered that when estimating biodiesel production rate depending on reaction constraints, ANN shows lower comparative error compared to RSM. The results show that ANN outperforms RSM in terms of percentage improvement when it comes to biodiesel production prediction.

Managing energy transition alongside environmental protection by making use of AI-led butanol powered SI engine optimization in compliance with SDGs.

Enormous consumption of fossil fuel resources has risked energy accessibility in the upcoming years. The price fluctuation and depletion rate of fossil fuels instigate the urgent need for searching their reliable substitute. The current study tries to address these issues by presenting butanol as a replacement for gasoline in SI engines at various speeds and loading conditions. The emission and performance parameters were ascertained for eight distinct butanol-gasoline fuel blends. The oxygenated butanol substantially increases engine efficiency and boosts power with lower fuel consumption. The carbon emissions were also observed to be lower in comparison with gasoline. Furthermore, the Artificial Intelligence (AI) approach was used in predicting engine performance running on the butanol blends. The correlation coefficients for the data training, validation, and testing were found to be 0.99986, 0.99942, and 0.99872, respectively. It was confirmed that the ANN predicted results were in accordance with the established statistical criteria. ANN was paired with Response Surface Methodology (RSM) technique to comprehend the influence of the sole design parameters along with their statistical interactions controlling the responses. Similarly, the R2 value of responses in case of RSM were close to unity and mean relative errors (MRE) were confined under specified range. A comparative study between ANN and RSM models unveiled that the ANN model should be preferred. Therefore, a joint utilization of the RSM and ANN can be more effective for reliable statistical interactions and predictions.

Application of ANN to predict performance and emissions of SI engine using gasoline-methanol blends.

The deployment of methanol like alternative fuels in engines is a necessity of the present time to comprehend power requirements and environmental pollution. Furthermore, a comprehensive prediction of the impact of the methanol-gasoline blend on engine characteristics is also required in the era of artificial intelligence. The current study analyzes and compares the experimental and Artificial Neural Network (ANN) aided performance and emissions of four-stroke, single-cylinder SI engine using methanol-gasoline blends of 0%, 3%, 6%, 9%, 12%, 15%, and 18%. The experiments were performed at engine speeds of 1300-3700 rpm with constant loads of 20 and 40 psi for seven different fractions of fuels. Further, an ANN model has developed setting fuel blends, speed and load as inputs, and exhaust emissions and performance parameters as the target. The dataset was randomly divided into three groups of training (70%), validation (15%), and testing (15%) using MATLAB. The feedforward algorithm was used with tangent sigmoid transfer active function (tansig) and gradient descent with an adaptive learning method. It was observed that the continuous addition of methanol up to 12% (M12) increased the performance of the engine. However, a reduction in emissions was observed except for NOx emissions. The regression correlation coefficient (R) and the mean relative error (MRE) were in the range of 0.99100-0.99832 and 1.2%-2.4% respectively, while the values of root mean square error were extremely small. The findings depicted that M12 performed better than other fractions. ANN approach was found suitable for accurately predicting the performance and exhaust emissions of small-scaled SI engines.