{"title":"利用深度卷积神经网络和粒子群优化-极梯度提升技术进行风能系统故障分类和检测","authors":"Chun‐Yao Lee, Edu Daryl C. Maceren","doi":"10.1049/esi2.12144","DOIUrl":null,"url":null,"abstract":"Wind energy is crucial in the global shift towards a sustainable energy system. Thus, this research innovatively addresses the challenges in wind energy system fault classification and detection, emphasising the integration of robust machine learning methodologies. Our study focuses on enhancing fault management through supervisory control and data acquisition (SCADA) systems, addressing imbalanced data representation issues and error vulnerabilities. A key innovation lies in applying particle swarm optimisation‐tuned extreme gradient boosting (XGBoost) on imbalanced SCADA datasets, combining resampled SCADA data with deep learning features produced by deep convolutional neural networks. The novel use of PSO‐XGBoost showcases effectiveness in optimising parameters and ensuring model robustness. Furthermore, our research contributes to supervised and unsupervised anomaly detection models using Seasonal‐Trend decomposition using locally estimated scatterplot smoothing and PSO‐XGBoost, presenting substantial advancements in fault classification and prediction metrics. Overall, the study offers a unique, integrated framework for fault management, demonstrating improved reliability in predictive maintenance architectures. Lastly, it highlights the transformative potential of advanced machine learning in enhancing sustainability within efficient and clean energy production.","PeriodicalId":33288,"journal":{"name":"IET Energy Systems Integration","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Wind energy system fault classification and detection using deep convolutional neural network and particle swarm optimization‐extreme gradient boosting\",\"authors\":\"Chun‐Yao Lee, Edu Daryl C. Maceren\",\"doi\":\"10.1049/esi2.12144\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Wind energy is crucial in the global shift towards a sustainable energy system. Thus, this research innovatively addresses the challenges in wind energy system fault classification and detection, emphasising the integration of robust machine learning methodologies. Our study focuses on enhancing fault management through supervisory control and data acquisition (SCADA) systems, addressing imbalanced data representation issues and error vulnerabilities. A key innovation lies in applying particle swarm optimisation‐tuned extreme gradient boosting (XGBoost) on imbalanced SCADA datasets, combining resampled SCADA data with deep learning features produced by deep convolutional neural networks. The novel use of PSO‐XGBoost showcases effectiveness in optimising parameters and ensuring model robustness. Furthermore, our research contributes to supervised and unsupervised anomaly detection models using Seasonal‐Trend decomposition using locally estimated scatterplot smoothing and PSO‐XGBoost, presenting substantial advancements in fault classification and prediction metrics. Overall, the study offers a unique, integrated framework for fault management, demonstrating improved reliability in predictive maintenance architectures. Lastly, it highlights the transformative potential of advanced machine learning in enhancing sustainability within efficient and clean energy production.\",\"PeriodicalId\":33288,\"journal\":{\"name\":\"IET Energy Systems Integration\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2024-03-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IET Energy Systems Integration\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1049/esi2.12144\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Energy Systems Integration","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1049/esi2.12144","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
Wind energy system fault classification and detection using deep convolutional neural network and particle swarm optimization‐extreme gradient boosting
Wind energy is crucial in the global shift towards a sustainable energy system. Thus, this research innovatively addresses the challenges in wind energy system fault classification and detection, emphasising the integration of robust machine learning methodologies. Our study focuses on enhancing fault management through supervisory control and data acquisition (SCADA) systems, addressing imbalanced data representation issues and error vulnerabilities. A key innovation lies in applying particle swarm optimisation‐tuned extreme gradient boosting (XGBoost) on imbalanced SCADA datasets, combining resampled SCADA data with deep learning features produced by deep convolutional neural networks. The novel use of PSO‐XGBoost showcases effectiveness in optimising parameters and ensuring model robustness. Furthermore, our research contributes to supervised and unsupervised anomaly detection models using Seasonal‐Trend decomposition using locally estimated scatterplot smoothing and PSO‐XGBoost, presenting substantial advancements in fault classification and prediction metrics. Overall, the study offers a unique, integrated framework for fault management, demonstrating improved reliability in predictive maintenance architectures. Lastly, it highlights the transformative potential of advanced machine learning in enhancing sustainability within efficient and clean energy production.