首页|Researchers from SRM Institute of Science and Technology DiscussFindings in Mac hine Learning (Predicting Thermal Performance InSolar Air Heaters With V-corrug ated, Shot-blasted Absorber Plate,and Black Pebble-based Sensible Heat Storage: a ...)
Researchers from SRM Institute of Science and Technology DiscussFindings in Mac hine Learning (Predicting Thermal Performance InSolar Air Heaters With V-corrug ated, Shot-blasted Absorber Plate,and Black Pebble-based Sensible Heat Storage: a ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Investigators discuss new findings in Machine Learning. According to news reportingfrom Tamil Nadu, India, by NewsRx journalists, research stated, “The construction of the solar air heater(SAH) sy stem is associated with enhancing the absorber plates’ surface area through the incorporationof V-corrugation, shot-blasting processes, nano-coated, and black pebble stone (BPS) integration. Shotblasting (SB) is a surface treatment proces s that impacts the bombarding of the surface with high-speedabrasive particles. ”Financial support for this research came from Deputyship for Research and Innova tion, Ministry ofEducation in Saudi Arabia.The news correspondents obtained a quote from the research from the SRM Institut e of Science andTechnology, “After the SB process, the surface is coated with a ctivated carbon (AC)-based nanomaterialsdispersed in matt paint. The augmented contact area owing to the roughened and corrugated absorberplate allows more he at to be transferred to the air and subsequently to the BPS. BPS can impact as athermal mass, storing grasped heat and releasing it slowly, which helps preserv e a consistent temperatureand enhances the overall efficiency of the SAH. This augmented absorption capacity permits the plate toefficiently transfer the abso rbed heat to the black pebble stones. In this study, experimental findings arec ompared with machine learning (ML) models to evaluate the thermal transfer effic iency of conventionaland surface-modified absorbers in the SAH system. The expe rimental data is subjected to predictionusing diverse ML techniques, namely ran dom forest regression (RFR), linear regression (LR), and supportvector regressi on (SVR). By comparing the experimental results with predictions from LR, RFR, a nd SVRmodels, the study effectively evaluates the impacts of surface modificati ons and BPS incorporations onthe SAH thermal efficiency. The efficacy of the ML -based thermal efficiency and ‘Nu’ models is comparedusing mean squared error a nd root mean squared error. Amongst the algorithms estimated, LR, RFR,and SVR p roduced the highest correlation coefficient of 0.997, 0.993, 0.972 for conventio nal SAH and0.9976, 0.999, and 0.975 for SAH in estimating the ‘Nu’, respectivel y.”
Tamil NaduIndiaAsiaCyborgsEmergi ng TechnologiesMachine LearningSRM Institute of Science and Technology
NETL
NSTL
