首页|Study Data from Zhejiang University of Technology Update Knowledge of Machine Le arning (Experimental Investigation and Validation On an Air-source Heat Pump Fro sting State Recognition Method Based On Fan Current Fluctuation Signal and Machi ne...)
Study Data from Zhejiang University of Technology Update Knowledge of Machine Le arning (Experimental Investigation and Validation On an Air-source Heat Pump Fro sting State Recognition Method Based On Fan Current Fluctuation Signal and Machi ne...)
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 Daily News Daily News-A new study on Machine Learning is now available. According to news originating from Hangzhou, People's Republic of Ch ina, by NewsRx correspondents, research stated, "Thick frost on the evaporators of air-source heat pumps and refrigeration systems can degrade system performanc e. Defrosting in time based on precise frosting state recognition method is of g reat importance." Financial supporters for this research include Key R & D project o f Zhejiang Province, Research Project of Zhejiang University of Technology. Our news journalists obtained a quote from the research from the Zhejiang Univer sity of Technology, "Indirect measuring recognition method with low accuracy is widely used in commercial systems, for cheapness and simpleness, needing improve ment urgently. While accurate direct measuring methods are usually expensive and complicated. Therefore, a novel frosting state recognition method with high acc uracy is proposed, which can be realized with a simple current sensor. The metho d is based on the micro fluctuation in the evaporator fan current (rather than c urrent amplitude) caused by the perturbed air due to frost. An experimental setu p is built to obtain fan current samples. Combining three feature extraction app roaches and three classifiers, four frost state recognition methods using fan cu rrent fluctuation are merged. They are compared and studied based on the experim ental samples. Results show original signal + 1D-CNN method has the best identif ication performance, reaching 95.74 +/- N; 1.73 % accuracy at -10 C evaporator air temperature. It reveals 94.53 +/- 1.06 % accuracy in a temperature range of - 5 -20 C-degrees, and 94.73 +/- 1.00 % accuracy for another fan with the same model."
HangzhouPeople's Republic of ChinaAs iaCyborgsEmerging TechnologiesMachine LearningZhejiang University of Tec hnology
NETL
NSTL
