基于Transformer的风电机组故障预测  

Transformer based fault prediction for wind turbines

作　　者：朱彦民 李忠虎[1] 王金明[1] 杨立清[1] 张鑫宇[2] Zhu Yanmin;Li Zhonghu;Wang Jinming;Yang Liqing;Zhang Xinyu(School of Automation and Electrical Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,China;School of Mechanical Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,China)

机构地区：[1]内蒙古科技大学自动化与电气工程学院,包头014010 [2]内蒙古科技大学机械工程学院,包头014010

出　　处：《电子测量技术》2024年第13期45-52,共8页Electronic Measurement Technology

基　　金：内蒙古自治区科技计划项目(2021GG0433)资助。

摘　　要：为了研究基于SCADA数据的风电机组故障预测方法,将一台2000 kW双馈风电机组14个月的SCADA数据作为研究对象,首先对数据进行预处理,保证数据的可用性,其次,考虑到传统Transformer模型存在模型结构复杂且模型参数设置多等问题,通过引入线性解码器结构构建Transformer模型,并使用该模型对风电机组故障进行预测研究。研究表明:所构建的算法模型具备长期使用稳定性,模型可以消除误预测现象,可以提前6天时间做出故障预测,为避免因故障恶化而引起突然停机提供了保障。To study fault prediction methods for wind turbines based on SCADA data,the SCADA data of a 2000 kW doubly-fed wind turbine over 14 months is used as the research subject.First,the data is preprocessed to ensure its usability.Considering the issues with the traditional Transformer model,such as complex structure and numerous parameter settings,a Transformer model is constructed by introducing a linear decoder structure.This model is then used for fault prediction research on wind turbines.The study shows that the constructed algorithm model has long-term stability,can eliminate false predictions,and can predict faults 6 days in advance,providing a safeguard to prevent sudden shutdowns due to fault deterioration.

关 键 词：风电机组 深度学习 数据分析 SCADA系统 故障预测 

分 类 号：TM315[电气工程—电机] TN03[电子电信—物理电子学]