{"title":"温度挖掘促进机器学习电池热化学预测","authors":"","doi":"10.1016/j.joule.2024.07.002","DOIUrl":null,"url":null,"abstract":"<div><p>Advancing battery technologies requires precise predictions of thermochemical reactions among multiple components to efficiently exploit the stored energy and conduct thermal management. Recently, machine learning (ML) promised to address this complex thermochemical prediction task; however, it failed due to the huge gap between high problem complexity and extremely limited experimental data available for model training. Here, we innovate and validate the temperature excavation (TE) method that interprets the kinetic preferences of thermochemical reactions within minimal experiments into millions of training data. With the help of the TE method, we build the first universally applicable battery thermal runaway model, which achieves high prediction accuracy across a 500°C range on 15 distinct commercial and advanced chemistries with different battery formats and covers all normal working conditions. The TE method also demonstrates broad adaptability and training stability on various ML algorithms, opening new interdisciplinary opportunities for ML in thermochemistry and all thermal-related studies.</p></div>","PeriodicalId":343,"journal":{"name":"Joule","volume":null,"pages":null},"PeriodicalIF":38.6000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Temperature excavation to boost machine learning battery thermochemical predictions\",\"authors\":\"\",\"doi\":\"10.1016/j.joule.2024.07.002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Advancing battery technologies requires precise predictions of thermochemical reactions among multiple components to efficiently exploit the stored energy and conduct thermal management. Recently, machine learning (ML) promised to address this complex thermochemical prediction task; however, it failed due to the huge gap between high problem complexity and extremely limited experimental data available for model training. Here, we innovate and validate the temperature excavation (TE) method that interprets the kinetic preferences of thermochemical reactions within minimal experiments into millions of training data. With the help of the TE method, we build the first universally applicable battery thermal runaway model, which achieves high prediction accuracy across a 500°C range on 15 distinct commercial and advanced chemistries with different battery formats and covers all normal working conditions. The TE method also demonstrates broad adaptability and training stability on various ML algorithms, opening new interdisciplinary opportunities for ML in thermochemistry and all thermal-related studies.</p></div>\",\"PeriodicalId\":343,\"journal\":{\"name\":\"Joule\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":38.6000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Joule\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2542435124003040\",\"RegionNum\":1,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Joule","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2542435124003040","RegionNum":1,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0
摘要
电池技术的发展需要对多个组件之间的热化学反应进行精确预测,以便有效利用存储的能量并进行热管理。最近,机器学习(ML)有望解决这一复杂的热化学预测任务;然而,由于问题复杂性高,而可用于模型训练的实验数据极其有限,两者之间存在巨大差距,机器学习(ML)失败了。在此,我们创新并验证了温度挖掘(TE)方法,该方法能在数百万个训练数据中,以最少的实验解释热化学反应的动力学偏好。在 TE 方法的帮助下,我们建立了第一个普遍适用的电池热失控模型,该模型在 500°C 范围内对 15 种不同的商业和先进化学物质以及不同的电池格式实现了高预测精度,并涵盖了所有正常工作条件。TE 方法还展示了对各种 ML 算法的广泛适应性和训练稳定性,为热化学和所有热相关研究中的 ML 开辟了新的跨学科机会。
Temperature excavation to boost machine learning battery thermochemical predictions
Advancing battery technologies requires precise predictions of thermochemical reactions among multiple components to efficiently exploit the stored energy and conduct thermal management. Recently, machine learning (ML) promised to address this complex thermochemical prediction task; however, it failed due to the huge gap between high problem complexity and extremely limited experimental data available for model training. Here, we innovate and validate the temperature excavation (TE) method that interprets the kinetic preferences of thermochemical reactions within minimal experiments into millions of training data. With the help of the TE method, we build the first universally applicable battery thermal runaway model, which achieves high prediction accuracy across a 500°C range on 15 distinct commercial and advanced chemistries with different battery formats and covers all normal working conditions. The TE method also demonstrates broad adaptability and training stability on various ML algorithms, opening new interdisciplinary opportunities for ML in thermochemistry and all thermal-related studies.
期刊介绍:
Joule is a sister journal to Cell that focuses on research, analysis, and ideas related to sustainable energy. It aims to address the global challenge of the need for more sustainable energy solutions. Joule is a forward-looking journal that bridges disciplines and scales of energy research. It connects researchers and analysts working on scientific, technical, economic, policy, and social challenges related to sustainable energy. The journal covers a wide range of energy research, from fundamental laboratory studies on energy conversion and storage to global-level analysis. Joule aims to highlight and amplify the implications, challenges, and opportunities of novel energy research for different groups in the field.