首页|New Machine Learning Study Results from University of Utah Described (A Physics- Guided Machine Learning Approach for Capacity Fading Mechanism Detection and Fad ing Rate Prediction Using Early Cycle Data)
New Machine Learning Study Results from University of Utah Described (A Physics- Guided Machine Learning Approach for Capacity Fading Mechanism Detection and Fad ing Rate Prediction Using Early Cycle Data)
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 artificial intelligence is now available. According to news originating from Salt Lake City, Utah, by N ewsRx correspondents, research stated, "Lithium-ion battery development necessit ates predicting capacity fading using early cycle datato minimize testing time and costs." Funders for this research include National Natural Science Foundation of China; Tsinghua-toyota Joint Research Fund. The news editors obtained a quote from the research from University of Utah: "Th is study introduces a hybrid physics-guided data-driven approach to address this challenge by accurately determining the dominant fading mechanism and predictin g the average capacity fading rate. Physics-guided features, derived from the el ectrochemical properties and behaviors within the battery, are extracted from th e first five cycles to provide meaningful, interpretable, and predictive data. U nlike previous models that rely on a single regression approach, our method util izes two separate regression models tailored to the identified dominant fading m echanisms. Our model achieves 95.6% accuracy in determining the do minant fading mechanism using data from the second cycle and a mean absolute per centage error of 17.09% in predicting lifetime capacity fade from the first five cycles. This represents a substantial improvement over state-of-t he-art models, which have an error rate approximately three times higher."
University of UtahSalt Lake CityUtahUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMach ine Learning
NETL
NSTL
