用3D打印叶片模型+机器学习，实现风力机叶片故障精准识别
Fault Diagnosis of 3D-Printed Scaled Wind Turbine Blades
- 结合仿真、实验与机器学习，从振动特征中识别裂纹
- 分类准确率达94%以上，模式3、4、6对损伤最敏感
- 适合风电结构健康监测研究者参考
本研究提出一种集成方法，通过3D打印的NREL 5MW叶片缩比模型，结合有限元分析、实验模态分析和机器学习技术实现风力机叶片故障检测。在关键位置人工引入裂纹，利用有限元模拟预测其对固有频率的影响，并通过可控锤击实验验证。提取时域与频域振动特征，采用ANOVA分析识别关键判别变量。支持向量机与K近邻分类器分类准确率超过94%。结果表明，第3、4、6阶振动模态对该叶片结构异常特别敏感。该方法证实了数值模拟与实验验证结合的可行性，为风电结构健康监测系统提供了新路径。
原文摘要 · Abstract (English)
This study presents an integrated methodology for fault detection in wind turbine blades using 3D-printed scaled models, finite element simulations, experimental modal analysis, and machine learning techniques. A scaled model of the NREL 5MW blade was fabricated using 3D printing, and crack-type damages were introduced at critical locations. Finite Element Analysis was employed to predict the impact of these damages on the natural frequencies, with the results validated through controlled hammer impact tests. Vibration data was processed to extract both time-domain and frequency-domain features, and key discriminative variables were identified using statistical analyses (ANOVA). Machine learning classifiers, including Support Vector Machine and K-Nearest Neighbors, achieved classification accuracies exceeding 94%. The results revealed that vibration modes 3, 4, and 6 are particularly sensitive to structural anomalies for this blade. This integrated approach confirms the feasibility of combining numerical simulations with experimental validations and paves the way for structural health monitoring systems in wind energy applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。