On multi-site damage identification using single-site training data
On multi-site damage identification using single-site training data
复制标题
DOI：
10.1016/j.jsv.2017.07.038
复制
发表时间：
2017-11-24
影响因子：
4.7
通讯作者：
Worden, K.
中科院分区：
文献类型：
--
作者：
Barthorpe, R. J.;Manson, G.;Worden, K.
本文提出了一种开发工程结构多点损伤定位系统的方法，该系统可以仅使用单点损伤状态数据进行训练。该方法包括基于单点损伤数据训练一系列二元分类器，并将所开发的分类器组合成一个鲁棒的多类损伤定位器。这样，多点损伤识别问题就可以分解为一系列二值决策。本文采用支持向量分类器作为二元决策的手段。所提出的方法代表了多点损伤识别领域的一项进步，该领域需要：(1)从单点和多点损伤案例中获得完整的损伤状态数据，或者(2)开发基于物理的模型来进行多点模型预测。所提出的方法的潜在好处是，为了训练一个多站点损伤定位器，而无需求助于基于物理的模型预测，可能需要显著减少记录的损伤状态的数量。本文首先证明了支持向量分类是一种适用于多点损伤定位问题的方法，并讨论了结合二值分类器的方法。接下来，通过将所提出的方法应用于实际工程结构（Piper Tomahawk教练机机翼）进行演示和评估，并将其性能与使用完整损坏状态数据集训练的分类器进行比较。(C) 2017年作者。Elsevier Ltd.出版。
This paper proposes a methodology for developing multi-site damage location systems for engineering structures that can be trained using single-site damaged state data only. The methodology involves training a sequence of binary classifiers based upon single-site damage data and combining the developed classifiers into a robust multi-class damage locator. In this way, the multi-site damage identification problem may be decomposed into a sequence of binary decisions. In this paper Support Vector Classifiers are adopted as the means of making these binary decisions. The proposed methodology represents an advancement on the state of the art in the field of multi-site damage identification which require either: (1) full damaged state data from single- and multi-site damage cases or (2) the development of a physics-based model to make multi-site model predictions. The potential benefit of the proposed methodology is that a significantly reduced number of recorded damage states may be required in order to train a multi-site damage locator without recourse to physics-based model predictions. In this paper it is first demonstrated that Support Vector Classification represents an appropriate approach to the multi-site damage location problem, with methods for combining binary classifiers discussed. Next, the proposed methodology is demonstrated and evaluated through application to a real engineering structure - a Piper Tomahawk trainer aircraft wing - with its performance compared to classifiers trained using the full damaged-state dataset. (C) 2017 The Authors. Published by Elsevier Ltd.