文献类型：期刊文献

中文题名：基于GAF-MACNN的风机叶片健康状态监测方法

英文题名：Wind Turbine Blade Health Monitoring Method Based on GAF-MACNN

作者：王裕祥[1,2];高阳[1];蒋恩超[2];董娜[2];陈旭东[2];彭凡[2];王立闻[1,2]

机构：[1]华东理工大学机械与动力工程学院,上海200237;[2]东方电气集团科学技术研究院有限公司,成都611731

年份：2026

卷号：62

期号：7

起止页码：139

中文期刊名：机械工程学报

外文期刊名：Journal of Mechanical Engineering

收录：;EI(收录号：20262120773047);北大核心:【北大核心2023】；

基金：国家自然科学基金资助项目(52275146)。

语种：中文

中文关键词：风电叶片;健康状态评估;格拉姆角场;卷积神经网络;多头注意力机制

外文关键词：wind turbine blades;assessment of health status;gramian angular field;convolutional neural network;multi-head attention

摘要：在风机运行过程中,叶片振动数据因不同工况环境呈现显著特征分布差异,且常受噪声干扰,致使故障特征提取困难、健康状态难以精准识别。为有效应对这一挑战,提出一种基于格拉姆角场与多头注意力机制卷积神经网络的叶片健康状态监测方法。首先,基于格拉姆角场的模态转换方法,将一维振动信号分别编码为格拉姆角差场(Gramian angular difference field,GADF)和格拉姆角和场(Gramian angular summation field,GASF)两种二维图像表征,通过极坐标映射有效保留时序信号的幅值与相位特征;其次,构建并行双通道卷积神经网络,分别提取GADF和GASF图像的空间特征,采用深度可分离卷积降低模型复杂度;最后,引入多头注意力机制进行跨通道特征融合,通过自适应权重分配强化关键故障特征的表达。为验证所提方法的有效性,本研究采用风电场叶片疲劳折损的实际数据进行试验验证,以确保方法在真实工况下的适用性和可靠性。试验结果表明,所提方法的诊断精度达到93.7%,显著优于其他对比方法,验证了其在实际应用中的有效性和优越性。
During the operation of wind turbines,blade vibration data exhibit significant differences in feature distributions under varying operating conditions and are often affected by noise,making fault feature extraction challenging and accurate health state identification difficult.To effectively address this challenge,this study proposes a blade health state monitoring method based on gramian angular field and multi-head attention convolutional neural network.First,a modal transformation approach based on Gramian Angular Field is employed to encode the one-dimensional vibration signal into two types of two-dimensional image representations:Gramian angular difference field(GADF)and gramian angular summation field(GASF).By using polar coordinate mapping,this method effectively preserves the amplitude and phase characteristics of the time-series signals.Second,a parallel dual-channel Convolutional Neural Network(CNN)is constructed to extract spatial features from GADF and GASF images separately,incorporating depthwise separable convolutions to reduce model complexity.Finally,a multi-head attention mechanism is introduced to perform cross-channel feature fusion,enhancing the expression of critical fault features through adaptive weight allocation.To verify the effectiveness of the proposed method,experimental validation is conducted using real-world data on blade fatigue damage from wind farms,ensuring its applicability and reliability in practical scenarios.The experimental results demonstrate that the proposed method achieves a diagnostic accuracy of 93.7%,significantly outperforming other comparative methods,thereby confirming its effectiveness and superiority in real-world applications.