Quantifying the Value of Information Transfer in Population-Based SHM

Population-based structural health monitoring (PBSHM) seeks to address some of the limitations associated with data scarcity that arise in traditional structural health monitoring (SHM). A tenet of the population-based approach to SHM is that information can be shared between sufficiently similar structures in order to improve predictive models. Transfer learning techniques, such as domain adaptation, have been shown to be a highly useful technology for sharing information between structures when developing statistical classifiers for PBSHM. Nonetheless, transfer learning techniques are not without their pitfalls. In some circumstances, for example, if the data distributions associated with the structures within a population are dissimilar, applying transfer learning methods can be detrimental to classification performance—this phenomenon is known as negative transfer. When considered in the context of operation and maintenance decision processes, negative transfer has significant implications. Deterioration in classification performance could translate to unnecessary inspections or repairs, and even critical maintenance interventions being missed entirely. Such changes in operation and maintenance strategy would result in additional costs being incurred and could undermine the integrity and safety of structures. Given the potentially severe consequences of negative transfer, it is prudent for engineers to ask the question “when, what, and how should one transfer between structures”.The current chapter aims to demonstrate a transfer-strategy decision process for a classification task for a population of simulated structures in the context of a representative SHM maintenance problem, supported by domain adaptation. The transfer decision framework is based on the concept of the expected value of information transfer. In order to compute the expected value of information transfer, predictions must be made regarding the classification (and decision performance) in the target domain following information transfer. In order to forecast the outcome of transfers, a probabilistic regression is used here to predict classification performance from a proxy for structural similarity based on the modal assurance criterion.