This study presents a framework for detecting mechanical damage in pipelines, focusing on generating simulated data and sampling to emulate distributed acoustic sensing (DAS) system responses. The workflow transforms simulated ultrasonic guided wave (UGW) responses into DAS or quasi-DAS system responses to create a physically robust dataset for pipeline event classification, including welds, clips, and corrosion defects. This investigation examines the effects of sensing systems and noise on classification performance, emphasizing the importance of selecting the appropriate sensing system for a specific application. The framework shows the robustness of different sensor number deployments to experimentally relevant noise levels, demonstrating its applicability in real-world scenarios where noise is present. Overall, this study contributes to the development of a more reliable and effective method for detecting mechanical damage to pipelines by emphasizing the generation and utilization of simulated DAS system responses for pipeline classification efforts. The results on the effects of sensing systems and noise on classification performance further enhance the robustness and reliability of the framework.
The fiber-optic distributed acoustic sensing (DAS) technique has increasingly become more attractive for structural health monitoring (SHM) and non-destructive evaluation (NDE) purposes. When it comes to traditional acoustic NDE methods, the presence of weldings can present a significant challenge as it can heavily scatter waves resulting in complex data analysis and interpretation. The present work aims to develop an improved understanding and interpretation framework in cases where welds play an important role in the signal with an emphasis on the steel shell of a canister, typically used for Dry Cask Storage Systems (DCSSs) that house spent nuclear waste fuel rods. We also introduce a promising approach in the use of guided ultrasonic waves along with fiber optic sensors that seeks to overcome the challenges that emerge when using traditional acoustic sensing based NDE techniques in welded structures. The study is conducted in a simulation theoretical manner, using a canister model constructed from a representative stainless-steel plate, with different configurations of weldings typically present for DCSS structure. Progressively increasing complexity of the weld physical representation is considered to fully incorporate in physics-based analysis. Furthermore, the acoustic response of these models is obtained from the simulations as a response of an assumed DAS or quasi-distributed acoustic sensing Q-DAS system network. The features originated from the welds are extracted and analyzed, and additional features associated with structure integrity associated with corrosion defects, etc. will also be explored for NDE inspection as in a traditional acoustic NDE approach.
Absence of a final repository for nuclear waste has increased attention on dry cask storage systems (DCSSs) which were originally intended for temporary storage, increasing the need for new structural health monitoring paradigms considering safety and environmental impacts. Current integrity inspection requirements consist of periodic manned inspections due in part to the difficulties with real-time monitoring of internal canister conditions without penetrating the canister surface. Here we overview a new approach to nuclear canister integrity structural health monitoring which combines both quasi-distributed fiber optic acoustic (and other) sensing modalities deployed external to the canister as well as physics-based modeling to enable real-time inference of internal canister conditions, including the identification, localization, and classification of various active or incipient failure conditions. More specifically, we overview the vision for the proposed monitoring approach and describe results to date in theoretical physics-based modeling and artificial intelligence-based analytics to accelerate the development of classification frameworks for rapid interpretation of quasi-distributed acoustic and other complementary fiber optic sensing responses. In addition, we describe early results obtained for a quasi-distributed fiber optic sensor network based upon multimode interferometer sensors using an experimental test bed established for dry-cask storage canister sensing experiments. Future work will be overviewed and discussed in the context of expanded scope of the proposed real-time monitoring system and planned field validations.
Distributed acoustic fiber optic sensors (DAS) enable spatially distributed monitoring of perturbations and contain rich multidimensional information that can be used in structural health monitoring. Machine learning based on physics-based simulations can make a breakthrough in traditional data analysis methods to improve their efficiency and performance, solving a series of problems such as huge data volume, low data processing speed, data signal-to-noise ratio, etc. Here, the relationship of DAS response and corrosion type are studied.First, we present a systematic theoretical study of the potential of direct coupling of quasi-distributed acoustic sensing (q-DAS) with guided ultrasound typically used for real-time pipeline health monitoring. To investigate properties of scattered acoustic waves and the performance of DAS and q-DAS in identifying defects, we use finite element analysis to simulate the response in a variety of pipeline structures including welds, clamps, defect types, and sensor installations representing various corrosion patterns expected in practice. A specific emphasis will be placed upon simulating and modeling pitting corrosion defects and contrasting with other types of corrosion observed in practice. We also aim to compare and analyze signal characteristics due to different kinds of corrosion types and structures, and to enhance machine learning algorithms for detection and size prediction of major pipeline structural changes and corrosion types. Ultimately, results of simulated DAS and q-DAS sensor networks are analyzed by a neural network-based machine learning algorithm for defect identification through supervised learning. To evaluate and improve effectiveness, we estimate model uncertainty and identify features of simulated results that contribute most to the model performance and efficacy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.