Decision-theoretic inspection planning using imperfect and incomplete data

Abstract

Attempts to formalize inspection and monitoring strategies in industry have struggled to combine evidence from multiple sources (including subject matter expertise) in a mathematically coherent way. The perceived requirement for large amounts of data are often cited as the reason that quantitative risk-based inspection is incompatible with the sparse and imperfect information that is typically available to structural integrity engineers. Current industrial guidance is also limited in its methods of distinguishing quality of inspections, as this is typically based on simplified (qualitative) heuristics. In this paper, Bayesian multi-level (partial pooling) models are proposed as a flexible and transparent method of combining imperfect and incomplete information, to support decision-making regarding the integrity management of in-service structures. This work builds on the established theoretical framework for computing the expected value of information, by allowing for partial pooling between inspection measurements (or groups of measurements). This method is demonstrated for a simulated example of a structure with active corrosion in multiple locations, which acknowledges that the data will be associated with some precision, bias, and reliability. Quantifying the extent to which an inspection of one location can reduce uncertainty in damage models at remote locations has been shown to influence many aspects of the expected value of an inspection. These results are considered in the context of the current challenges in risk based structural integrity management.

Multitask feature selection within structural datasets

“…In the context of modal analysis, Huang et al (2019) use hierarchical Bayesian models to learn multiple, correlated regression models. Di Francesco et al (2021) also use hierarchical models to build corrosion models from evidence at multiple locations, and Papadimas and Dodwell (2021) infer model parameters of material constitutive models. This paper focuses on the use of MTL to automate feature selection in SHM systems, which is often a manual process.…”

Sharing Information Between Machine Tools to Improve Surface Finish Forecasting

“…Although Bayesian hierarchical models have seen success in other parts of engineering [19][20][21],the benefits of these models have not yet reached machining and tool health monitoring. In this paper, the authors propose a random intercepts and slopes model to show the modelling improvements of hierarchical models specifically, for sparse datasets in machining.…”

Hierarchical Bayesian modeling for knowledge transfer across engineering fleets via multitask learning

“…A shared sparseness profile is inferred over all tasks and related measurement channels, improving damage detection and data recovery by considering the correlation between damage scenarios or adjacent sensors on the same structure. Some recent, related applications include Di Francesco et al (2021), who use hierarchical models to build corrosion models given evidence from multiple locations, and Papadimas and Dodwell (2021), where the results from a series of materials experiments (i.e., coupon samples) are combined to inform the estimation of material properties. Also, Dhada et al (2020) implement hierarchical Gaussian mixture models to cluster simulated data that represent novelty detection for asset management; the model parameters are interpretable in terms of the data distribution, rather than the application domain.…”

“…Some recent, related applications include Di Francesco et al. (2021), who use hierarchical models to build corrosion models given evidence from multiple locations, and Papadimas and Dodwell (2021), where the results from a series of materials experiments (i.e., coupon samples) are combined to inform the estimation of material properties. Also, Dhada et al.…”