Shilpa Suresh, Augustine B. V. Barboza, K. Ashwini, Pijakala Dinesha
Machine learning techniques are gaining momentum in the present-day context in most engineering applications due to their versatility and accuracy. They facilitate faster data processing coupled with a high degree of accuracy. They are extensively used in understanding and modeling engine combustion and emissions. Engine emissions significantly contribute to environmental degradation. In the current study, an effort has been made to compare the emissions recorded from a four-stroke single-cylinder biodiesel engine with those obtained using artificial neural network (ANN) models, where the hyperparameters have been optimized using nature-inspired metaheuristic optimization algorithms like JAYA, WOA, ROA, and WaOA. The study was conducted using diesel and cardanol-methanol-diesel blends of B10M10, B20M10, and B30M10, by varying the fuel injection pressure from 180 bar (standard injection timing) to 220 bar with an interval of 20 bar. Furthermore, experiments were conducted with oxygen enrichment at concentrations of 3%, 5%, and 7% w/w on the standard oxygen concentration of air. The study showed a remarkable reduction of 59% in CO emissions at 220 bar fuel injection pressure with 7% w/w oxygen enrichment for the B30M10 blend as compared to 180 bar without oxygen enrichment. A similar reduction of 32.6% and 16.6% were observed for HC emissions and smoke opacity for the same operating conditions. However, a rising trend of 50% was observed for NOx emissions for the same blend and operating conditions. The findings indicate that the data recorded conforms with that obtained by using the ANN model optimized through these metaheuristic algorithms.
{"title":"Optimization of ANN Models Using Metaheuristic Algorithms for Prediction of Tailpipe Emissions in Biodiesel Engine","authors":"Shilpa Suresh, Augustine B. V. Barboza, K. Ashwini, Pijakala Dinesha","doi":"10.1002/htj.23216","DOIUrl":"https://doi.org/10.1002/htj.23216","url":null,"abstract":"<p>Machine learning techniques are gaining momentum in the present-day context in most engineering applications due to their versatility and accuracy. They facilitate faster data processing coupled with a high degree of accuracy. They are extensively used in understanding and modeling engine combustion and emissions. Engine emissions significantly contribute to environmental degradation. In the current study, an effort has been made to compare the emissions recorded from a four-stroke single-cylinder biodiesel engine with those obtained using artificial neural network (ANN) models, where the hyperparameters have been optimized using nature-inspired metaheuristic optimization algorithms like JAYA, WOA, ROA, and WaOA. The study was conducted using diesel and cardanol-methanol-diesel blends of B10M10, B20M10, and B30M10, by varying the fuel injection pressure from 180 bar (standard injection timing) to 220 bar with an interval of 20 bar. Furthermore, experiments were conducted with oxygen enrichment at concentrations of 3%, 5%, and 7% w/w on the standard oxygen concentration of air. The study showed a remarkable reduction of 59% in CO emissions at 220 bar fuel injection pressure with 7% w/w oxygen enrichment for the B30M10 blend as compared to 180 bar without oxygen enrichment. A similar reduction of 32.6% and 16.6% were observed for HC emissions and smoke opacity for the same operating conditions. However, a rising trend of 50% was observed for NO<sub><i>x</i></sub> emissions for the same blend and operating conditions. The findings indicate that the data recorded conforms with that obtained by using the ANN model optimized through these metaheuristic algorithms.</p>","PeriodicalId":44939,"journal":{"name":"Heat Transfer","volume":"54 2","pages":"1189-1201"},"PeriodicalIF":2.8,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/htj.23216","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Evaluations were conducted on the thermal performance of an organic Rankine cycle (ORC) system using three fluids as the evaporative system at a low-grade heat source. The modified ORC evaporators were replaced with a three-fluid system, which included hot fluids at the top and bottom and an isopentane working fluid in the middle section. Furthermore, the thermal performance assessment with a hot fluid heat transfer ratio in the outer and inner tubes (Q2/Q1) varying from 25:75 to 75:25 has been investigated. The impact of the hot fluid's (Q2/Q1) heat transfer ratios to saturated steam on the modified ORC's thermal performance assessment was examined, with an evaporative temperature range of 45–65°C and a pinch point temperature difference (PPTD) of 3–10°C. The Taguchi technique solves multiparameter optimization using the L9 orthogonal array. The findings showed that in three-fluid-based modified ORC systems, the network output, exergetic efficiency, and irreversibility went down with PPTD for all three Q2/Q1 cases. For Q2/Q1 of 75:25, the ORC's energetic efficiency and overall irreversibility reached their optimum, while a PPTD of 3–10°C reduced the exergetic efficiency by 19.71%. Also, Q2/Q1 of 75:25 showed the highest and 200% higher ORC system work done at PPTD of 3°C than Q2/Q1 of 25:75—the lowest. Modified ORC network generation, energy output, and heat transfer rate showed excellent results at an evaporative temperature of 58.33°C. For optimal network productivity, Q2/Q1 of 75:25 was 160% and 40% greater than 50:50 and 25:75 at 58.33°C, respectively. The three-fluid-based modified ORC system performs better with a 75:25 Q2/Q1 ratio. According to Taguchi's analysis, evaporation temperature affects the improved ORC system's thermal, exergy, and network generation. Also, heat transfer ratios (F = Q2/Q1) largely affect system irreversibility.
{"title":"Exergetic analysis and multiparametric optimization of a novel three-fluid-based organic Rankine cycle evaporative system via Taguchi method","authors":"Rashmi Rekha Sahoo","doi":"10.1002/htj.23204","DOIUrl":"https://doi.org/10.1002/htj.23204","url":null,"abstract":"<p>Evaluations were conducted on the thermal performance of an organic Rankine cycle (ORC) system using three fluids as the evaporative system at a low-grade heat source. The modified ORC evaporators were replaced with a three-fluid system, which included hot fluids at the top and bottom and an isopentane working fluid in the middle section. Furthermore, the thermal performance assessment with a hot fluid heat transfer ratio in the outer and inner tubes (<i>Q</i><sub>2</sub>/<i>Q</i><sub>1</sub>) varying from 25:75 to 75:25 has been investigated. The impact of the hot fluid's (<i>Q</i><sub>2</sub>/<i>Q</i><sub>1</sub>) heat transfer ratios to saturated steam on the modified ORC's thermal performance assessment was examined, with an evaporative temperature range of 45–65°C and a pinch point temperature difference (PPTD) of 3–10°C. The Taguchi technique solves multiparameter optimization using the L9 orthogonal array. The findings showed that in three-fluid-based modified ORC systems, the network output, exergetic efficiency, and irreversibility went down with PPTD for all three <i>Q</i><sub>2</sub>/<i>Q</i><sub>1</sub> cases. For <i>Q</i><sub>2</sub>/<i>Q</i><sub>1</sub> of 75:25, the ORC's energetic efficiency and overall irreversibility reached their optimum, while a PPTD of 3–10°C reduced the exergetic efficiency by 19.71%. Also, <i>Q</i><sub>2</sub>/<i>Q</i><sub>1</sub> of 75:25 showed the highest and 200% higher ORC system work done at PPTD of 3°C than <i>Q</i><sub>2</sub>/<i>Q</i><sub>1</sub> of 25:75—the lowest. Modified ORC network generation, energy output, and heat transfer rate showed excellent results at an evaporative temperature of 58.33°C. For optimal network productivity, <i>Q</i><sub>2</sub>/<i>Q</i><sub>1</sub> of 75:25 was 160% and 40% greater than 50:50 and 25:75 at 58.33°C, respectively. The three-fluid-based modified ORC system performs better with a 75:25 <i>Q</i><sub>2</sub>/<i>Q</i><sub>1</sub> ratio. According to Taguchi's analysis, evaporation temperature affects the improved ORC system's thermal, exergy, and network generation. Also, heat transfer ratios (<i>F</i> = <i>Q</i><sub>2</sub>/<i>Q</i><sub>1</sub>) largely affect system irreversibility.</p>","PeriodicalId":44939,"journal":{"name":"Heat Transfer","volume":"54 1","pages":"1116-1141"},"PeriodicalIF":2.8,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142860227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}