An experimental investigation into passive acoustic damage detection for structural health monitoring of wind turbine blades
An experimental investigation into passive acoustic damage detection for structural health monitoring of wind turbine blades
复制标题
DOI：
10.1177/1475921719895588
复制
发表时间：
2020-01
期刊：
影响因子：
--
通讯作者：
Jaclyn Solimine;C. Niezrecki;M. Inalpolat
中科院分区：
文献类型：
--
作者：
Jaclyn Solimine;C. Niezrecki;M. Inalpolat
本文详细介绍了一种新的被动结构健康监测方法的实施，在风力涡轮机叶片损伤检测使用空气中的声音。该方法利用叶片内部麦克风来检测趋势，转变，或使用内部分布的机载声学传感器，自然发生的被动系统激励，和周期性的测量窗口的有限网络的叶片腔的声压级的尖峰。在进行疲劳测试的实用级风力涡轮机叶片上进行测试活动，以证明该方法用于结构健康监测应用的能力。初步的音频信号处理步骤中使用的研究，这是在语音处理应用程序中常用的那些方法的严重影响，进行了详细讨论。将主成分分析和K均值聚类应用于数据集的特征空间表示，以识别测量中的任何离群值（与风力涡轮机叶片的正常操作的偏差同义）。该系统的性能进行评估的基础上，它的能力，以检测这些结构事件的叶片，确定通过手动观察的测量。文章中提出的信号处理方法被证明是成功的，在检测结构和声学畸变经历了一个完整的风力涡轮机叶片进行疲劳测试。在对数据进行评估之后，给出了建议，以解决该方法在物理限制、信号处理技术和机器学习选项方面的未来发展。
This article details the implementation of a novel passive structural health monitoring approach for damage detection in wind turbine blades using airborne sound. The approach utilizes blade-internal microphones to detect trends, shifts, or spikes in the sound pressure level of the blade cavity using a limited network of internally distributed airborne acoustic sensors, naturally occurring passive system excitation, and periodic measurement windows. A test campaign was performed on a utility-scale wind turbine blade undergoing fatigue testing to demonstrate the ability of the method for structural health monitoring applications. The preliminary audio signal processing steps used in the study, which were heavily influenced by those methods commonly utilized in speech-processing applications, are discussed in detail. Principal component analysis and K-means clustering are applied to the feature-space representation of the data set to identify any outliers (synonymous with deviations from the normal operation of the wind turbine blade) in the measurements. The performance of the system is evaluated based on its ability to detect those structural events in the blade that are identified by making manual observations of the measurements. The signal processing methods proposed within the article are shown to be successful in detecting structural and acoustic aberrations experienced by a full-scale wind turbine blade undergoing fatigue testing. Following the assessment of the data, recommendations are given to address the future development of the approach in terms of physical limitations, signal processing techniques, and machine learning options.