Search

Over the last decades, the rising number of aging infrastructures has progressively fueled much interest toward the field of structural health monitoring. Following the increasing popularity of artificial intelligence algorithms, an autoencoder‐based damage detection technique within the context of unsupervised learning is proposed in this paper to provide support for practical engineering applications. The developed methodology uses the autoencoder to reconstruct raw acceleration sequences of user‐defined length collected from a healthy structure. To quantify the errors between the original input and the reconstructed output, which may be representative of damage occurrence, two indexes of reconstruction loss are selected as damage‐sensitive features. To support damage detection, a selected number of short‐time sequences are finally grouped into a unique macrosequence. The novel procedure can effectively both work at the single sensor level, as well as combine the predictive models using an ensemble learning strategy. Avoiding system identification, results obtained in the Z24 bridge demonstrate that the proposed method is quite effective for local damage detection with limited computational effort and using a limited number of sensors, thereby suitable to be easily applicable in the context of real‐time bridge assessment. [ABSTRACT FROM AUTHOR]

Data-driven machine-learning algorithms generally suffer from a lack of labelled health-state data, mainly those referring to damage conditions. To address such an issue, population-based structural health monitoring seeks to enrich the original dataset by transferring knowledge from a population of monitored structures. Within this context, this paper presents a transfer learning approach, based on domain adaptation, to leverage information from completely-labelled bridge structure data to accurately predict new instances of an unknown target domain. Since intrinsic structural differences may cause distribution shifts, domain adaptation attempts to minimise the distance between the domains and to learn a mapping within a shared feature space. Specifically, the methodology involves the long-term acquisition of natural frequencies from several structural scenarios. Such damage-sensitive features are then aligned via domain adaptation so that a machine-learning algorithm can effectively utilise the labelled source domain data and generalise well to the unlabelled target-domain data. The described procedure is applied to two case studies, including the Z24 and the S101 benchmark bridges and their finite element models, respectively. The results demonstrate the successful exchange of health-state labels to identify the damage class within a population of bridges equipped with SHM systems, showing potential to reduce computational efforts and to deal with scarce or poor data sets in application to bridge network monitoring. • A data-based domain adaptation framework is applied to bridge monitoring. • Domain Adaptation aligns and transform damage-sensitive features into a shared feature space. • Joint Domain Adaptation and Normal Condition Alignment are compared and discussed. • The KNN algorithm uses the transformed features to perform damage detection and classification. • The method is applied to transfer health-state labels across real bridges and finite element models. [ABSTRACT FROM AUTHOR]

The development of long-term structural health monitoring systems is recently receiving a growing scientific interest in the field of Civil Engineering. In the context of unsupervised learning processes, deviations of dynamic parameters from their normal conditions can allow damage detection. However, due to the fact that modal properties are highly sensitive to environmental and operational factors, it is extremely important to remove such effects in order to obtain suitable damage sensitive features. In this regard, the selection of a proper multivariate statistical data analysis method for removing environmental effects is a key issue, heavily affecting the distribution of the residuals, the control chart and therefore the damage detection. However, specific criteria guiding the optimal definition of such statistical methods are yet to be established. In order to bridge this research gap, an original methodology is proposed in the present paper, based on Receiver Operating Characteristic (ROC) curves in combination with Precision-versus-Recall (PR) curves. Specifically, ROC and PR curves are computed and compared for a variety of statistical methods for data normalization and different damage scenarios and the model selection strategy is formulated as an optimization problem. The proposed approach is exemplified by application in two case studies of continuously monitored structures: the Z24 Bridge in Switzerland and the Consoli Palace, a mediaeval masonry building in Italy. The results highlight that the combined use of both ROC and PR curves represents a suitable tool for defining the most effective statistical data analysis method and the optimal damage threshold, in order to minimize the occurrence of false alarms and missing alarms. • A method to select the best technique for data cleansing in SHM is proposed. • The evaluation of model's performance is crucial for a reliable damage detection. • ROC and PR curves give a complete quantification of damage classification errors. • The model selection strategy is formulated as an optimization problem. • The optimal threshold is defined by minimizing false alarms and missing alarms. [Display omitted] [ABSTRACT FROM AUTHOR]