Towards Population-Based Structural Health Monitoring, Part VII: EOV Fields – Environmental Mapping

Abstract

In a population-based structural health monitoring setting, data from one structure in a population, where the health state is known, may be used to make inferences about the health state in any nominally-identical structure. Any deviation from the learned 'healthy response' potentially indicates damage. However, as in standard applications of structural health monitoring, the healthy response from different structures also varies with the changes in environmental conditions across the population. This paper investigates the modelling of the change in environment across a population of structures located in one geographical region, such as a wind turbine farm. A data-driven mapping method (based on Gaussian process regression) will be introduced that aims to quantify and normalise variation stemming from the environment, such that the remaining response is only sensitive to damage or performance anomalies. The way in which environmental maps are constructed and implemented is demonstrated via a case study from an offshore wind farm. The ideas introduced here will constitute a field in the framework of population-based structural health monitoring presented elsewhere in the conference.

Towards Population-Based Structural Health Monitoring, Part I: Homogeneous Populations and Forms

“…In consequence, if a framework can transfer this missing information between groups of similar structures, it should bring significant advantages to practical applications of SHM. This issue of missing information motivates a population-based approach to SHM [1,2,3,4,5,6,7]. The aim of this new technology is to facilitate the transfer of valuable knowledge between groups of similar systems, i.e.…”

“…Importantly, this paper is the first in a series [2,5,6,7] introducing various methods for population-based SHM. While this work focusses on the most uniform case -the application of a population form to model nominally-identical systems -papers [2,4,5] concern more involved technologies, of a different nature.…”

A mapping method for anomaly detection in a localized population of structures

“…Population-based structural health monitoring (PBSHM) allows the health monitoring of a structure to be improved or enabled by using data from other structures within the same population (Worden et al, 2015; Bull et al, 2020; Gardner and Worden, 2020; Gosliga et al, 2020a,b; Lin et al, 2020b; Worden, 2020; Wickramarachchi et al, 2021). A wind farm demonstrates a localized homogeneous population , where a population of nominally identical structures is located in close vicinity to each other, allowing them to share the same environment.…”

Towards Population-Based Structural Health Monitoring, Part IV: Heterogeneous Populations, Transfer and Mapping

“…The concept of PBSHM is to incorporate the feature and label data from each aeroplane to generate a machine learning-based approach that generalises across the complete fleet for all damage scenarios, especially when many members of the fleet have no labelled data associated with them. This work is Part IV of a series of papers on PBSHM [2,3,4,5,6], where for an overview of PBSHM and further motivation the reader is referred to earlier parts [2,3,4].…”