Jinming Sun, Yanqiu Huang, Wanli Yu, Alberto Garcia-Ortiz
{"title":"递归调节器:非线性系统的深度学习和实时模型自适应策略。","authors":"Jinming Sun, Yanqiu Huang, Wanli Yu, Alberto Garcia-Ortiz","doi":"10.1038/s44172-025-00477-4","DOIUrl":null,"url":null,"abstract":"<p><p>Adaptive modeling is imperative for analyzing nonlinear systems deployed in natural dynamic environments. It facilitates filtering, prediction, and automatic control of the target object in real time to respond to unpredictable and non-repetitive sudden physical impairment caused by ambient impacts, such as corrosion, thermal drift, interference, etc. Existing nonlinear modeling approaches, however, are too complex for online training or fall short in rapid model recalibration under such conditions. To address this challenge, here we present a strategy that applies a regulator to the Koopman operator, enabling real-time model adaptation for nonlinear systems. In our approach, the regulator is directly implemented in nonlinear state-space without disrupting the pre-trained black-box predictor. The proposed technique demonstrates efficacy in capturing a broad spectrum of nonlinear dynamics and exhibits rapid adaptability to system changes without requiring offline retraining. Furthermore, its lightweight implementation and high-speed performance make it well-suited for embedded systems and applications demanding fast model recalibration and robustness.</p>","PeriodicalId":72644,"journal":{"name":"Communications engineering","volume":"4 1","pages":"140"},"PeriodicalIF":0.0000,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12316969/pdf/","citationCount":"0","resultStr":"{\"title\":\"Recursive regulator: a deep-learning and real-time model adaptation strategy for nonlinear systems.\",\"authors\":\"Jinming Sun, Yanqiu Huang, Wanli Yu, Alberto Garcia-Ortiz\",\"doi\":\"10.1038/s44172-025-00477-4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Adaptive modeling is imperative for analyzing nonlinear systems deployed in natural dynamic environments. It facilitates filtering, prediction, and automatic control of the target object in real time to respond to unpredictable and non-repetitive sudden physical impairment caused by ambient impacts, such as corrosion, thermal drift, interference, etc. Existing nonlinear modeling approaches, however, are too complex for online training or fall short in rapid model recalibration under such conditions. To address this challenge, here we present a strategy that applies a regulator to the Koopman operator, enabling real-time model adaptation for nonlinear systems. In our approach, the regulator is directly implemented in nonlinear state-space without disrupting the pre-trained black-box predictor. The proposed technique demonstrates efficacy in capturing a broad spectrum of nonlinear dynamics and exhibits rapid adaptability to system changes without requiring offline retraining. Furthermore, its lightweight implementation and high-speed performance make it well-suited for embedded systems and applications demanding fast model recalibration and robustness.</p>\",\"PeriodicalId\":72644,\"journal\":{\"name\":\"Communications engineering\",\"volume\":\"4 1\",\"pages\":\"140\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12316969/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Communications engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1038/s44172-025-00477-4\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Communications engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1038/s44172-025-00477-4","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Recursive regulator: a deep-learning and real-time model adaptation strategy for nonlinear systems.
Adaptive modeling is imperative for analyzing nonlinear systems deployed in natural dynamic environments. It facilitates filtering, prediction, and automatic control of the target object in real time to respond to unpredictable and non-repetitive sudden physical impairment caused by ambient impacts, such as corrosion, thermal drift, interference, etc. Existing nonlinear modeling approaches, however, are too complex for online training or fall short in rapid model recalibration under such conditions. To address this challenge, here we present a strategy that applies a regulator to the Koopman operator, enabling real-time model adaptation for nonlinear systems. In our approach, the regulator is directly implemented in nonlinear state-space without disrupting the pre-trained black-box predictor. The proposed technique demonstrates efficacy in capturing a broad spectrum of nonlinear dynamics and exhibits rapid adaptability to system changes without requiring offline retraining. Furthermore, its lightweight implementation and high-speed performance make it well-suited for embedded systems and applications demanding fast model recalibration and robustness.