Market Mechanisms and Regulation Strategies for Enhancing Wind Power Accommodation Capacity
风电机组故障诊断智能识别算法设计

摘要

随着风电技术发展，风电机组故障诊断是保障风电场安全运行的关键。针对机组故障类型多、特征难提取、传统诊断方法准确率低等问题，本文提出一种基于深度学习的智能故障诊断方法。首先依据齿轮箱、发电机、轴承、叶片等关键部件故障机理，建立故障特征库；再采用小波变换与经验模态分解结合，对振动信号进行预处理，获取时频特征。随后构建卷积神经网络与长短期记忆网络融合的深度学习模型，引入注意力机制优化特征权重，提升故障识别精度。基于某风电场实测数据验证，该方法对主要故障类型的识别准确率均超 95%，较传统支持向量机等方法分别提升 12% 和 8%，且实时性与鲁棒性优良，能在复杂工况下有效识别早期故障。该研究可为风电机组预防性维护提供支撑，有助于提高运维效率、降低运维成本。

Abstract

With the rapid development of wind power technology, fault diagnosis of wind turbines has become a key factor in ensuring the safe and stable operation of wind farms. In response to challenges such as diverse fault types, difficulty in feature extraction, and the relatively low accuracy of traditional diagnostic methods, this study proposes an intelligent fault diagnosis approach based on deep learning. First, a fault feature database is established according to the failure mechanisms of key components, including the gearbox, generator, bearings, and blades. Wavelet transform combined with empirical mode decomposition is then applied to preprocess vibration signals and extract time–frequency features. Subsequently, a deep learning model integrating convolutional neural networks (CNN) and long short-term memory networks (LSTM) is constructed, and an attention mechanism is introduced to optimize feature weighting and improve fault identification accuracy. The proposed method is validated using measured data from a wind farm. The results show that the recognition accuracy for major fault types exceeds 95%, representing improvements of 12% and 8% compared with traditional methods such as support vector machines. Moreover, the model demonstrates strong real-time performance and robustness, enabling effective identification of early-stage faults under complex operating conditions. This research provides technical support for predictive maintenance of wind turbines and contributes to improving operation and maintenance efficiency while reducing maintenance costs.