Diffusion Partition Consensus: Diffusion-Aided Time-of-Flight Estimates, Anomaly Detection, and Localization for Ultrasonic Nondestructive Evaluation Data
Diffusion partition consensus is a novel generative AI-based technique for time-series anomaly detection and data imputation in the presence of outliers. To illustrate the method, an implementation with design choices tailored for well-structured time series typical of single probe ultrasonic nondes...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Instrumentation and Measurement |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10734664/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536145613127680 |
|---|---|
| author | Nick Torenvliet John S. Zelek |
| author_facet | Nick Torenvliet John S. Zelek |
| author_sort | Nick Torenvliet |
| collection | DOAJ |
| description | Diffusion partition consensus is a novel generative AI-based technique for time-series anomaly detection and data imputation in the presence of outliers. To illustrate the method, an implementation with design choices tailored for well-structured time series typical of single probe ultrasonic nondestructive evaluation (NDE) datasets is proposed. The technique relies on cross-talk between a conditional score-based diffusion model, and two well-chosen Savitzky-Golay filters. Testing and evaluation are performed on a series of progressively information rich synthetic datasets, and on real-world ultrasonic NDE datasets taken from a Canada Deuterium Uranium nuclear reactor pressure tube and calibration fixture. The iterative technique is a blend of stochastic and deterministic methods that uses confidence and consensus of target parameter estimates to update several data classifying partitions over the dataset, which in turn allows a new set of estimates and confidence measures to be established. Data classification induces a progressive bias in the training datasets allowing a diffusion model to identify the prevalent distribution. Methods for fault diagnosis support the efficacious inclusion of a human in the loop making the technique suitable for use in safety-critical applications. The main advantages of the technique are that it is unsupervised—in that it does not require labeled datasets or significant data preprocessing, does not rely on out-of-distribution generalization, provides means for fault diagnosis without recourse to ground truth, converges with stability, and naturally includes a human in the loop. The quality of results, the checks and balances provided by the fault diagnosis mechanism, and the opportunity to include a human in the loop, support the case for usage in safety-critical contexts such as NDE at a nuclear power facility. |
| format | Article |
| id | doaj-art-f7d8c7862a364febaee7bf7c46e5712b |
| institution | Kabale University |
| issn | 2768-7236 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Instrumentation and Measurement |
| spelling | doaj-art-f7d8c7862a364febaee7bf7c46e5712b2025-01-15T00:04:28ZengIEEEIEEE Open Journal of Instrumentation and Measurement2768-72362024-01-01311110.1109/OJIM.2024.348571110734664Diffusion Partition Consensus: Diffusion-Aided Time-of-Flight Estimates, Anomaly Detection, and Localization for Ultrasonic Nondestructive Evaluation DataNick Torenvliet0https://orcid.org/0009-0006-9923-7092John S. Zelek1https://orcid.org/0000-0002-8138-3546Department of Systems Design Engineering, University of Waterloo, Waterloo, ON, CanadaDepartment of Systems Design Engineering, University of Waterloo, Waterloo, ON, CanadaDiffusion partition consensus is a novel generative AI-based technique for time-series anomaly detection and data imputation in the presence of outliers. To illustrate the method, an implementation with design choices tailored for well-structured time series typical of single probe ultrasonic nondestructive evaluation (NDE) datasets is proposed. The technique relies on cross-talk between a conditional score-based diffusion model, and two well-chosen Savitzky-Golay filters. Testing and evaluation are performed on a series of progressively information rich synthetic datasets, and on real-world ultrasonic NDE datasets taken from a Canada Deuterium Uranium nuclear reactor pressure tube and calibration fixture. The iterative technique is a blend of stochastic and deterministic methods that uses confidence and consensus of target parameter estimates to update several data classifying partitions over the dataset, which in turn allows a new set of estimates and confidence measures to be established. Data classification induces a progressive bias in the training datasets allowing a diffusion model to identify the prevalent distribution. Methods for fault diagnosis support the efficacious inclusion of a human in the loop making the technique suitable for use in safety-critical applications. The main advantages of the technique are that it is unsupervised—in that it does not require labeled datasets or significant data preprocessing, does not rely on out-of-distribution generalization, provides means for fault diagnosis without recourse to ground truth, converges with stability, and naturally includes a human in the loop. The quality of results, the checks and balances provided by the fault diagnosis mechanism, and the opportunity to include a human in the loop, support the case for usage in safety-critical contexts such as NDE at a nuclear power facility.https://ieeexplore.ieee.org/document/10734664/Diffusiongenerativenondestructive testingultrasonicunsupervised |
| spellingShingle | Nick Torenvliet John S. Zelek Diffusion Partition Consensus: Diffusion-Aided Time-of-Flight Estimates, Anomaly Detection, and Localization for Ultrasonic Nondestructive Evaluation Data IEEE Open Journal of Instrumentation and Measurement Diffusion generative nondestructive testing ultrasonic unsupervised |
| title | Diffusion Partition Consensus: Diffusion-Aided Time-of-Flight Estimates, Anomaly Detection, and Localization for Ultrasonic Nondestructive Evaluation Data |
| title_full | Diffusion Partition Consensus: Diffusion-Aided Time-of-Flight Estimates, Anomaly Detection, and Localization for Ultrasonic Nondestructive Evaluation Data |
| title_fullStr | Diffusion Partition Consensus: Diffusion-Aided Time-of-Flight Estimates, Anomaly Detection, and Localization for Ultrasonic Nondestructive Evaluation Data |
| title_full_unstemmed | Diffusion Partition Consensus: Diffusion-Aided Time-of-Flight Estimates, Anomaly Detection, and Localization for Ultrasonic Nondestructive Evaluation Data |
| title_short | Diffusion Partition Consensus: Diffusion-Aided Time-of-Flight Estimates, Anomaly Detection, and Localization for Ultrasonic Nondestructive Evaluation Data |
| title_sort | diffusion partition consensus diffusion aided time of flight estimates anomaly detection and localization for ultrasonic nondestructive evaluation data |
| topic | Diffusion generative nondestructive testing ultrasonic unsupervised |
| url | https://ieeexplore.ieee.org/document/10734664/ |
| work_keys_str_mv | AT nicktorenvliet diffusionpartitionconsensusdiffusionaidedtimeofflightestimatesanomalydetectionandlocalizationforultrasonicnondestructiveevaluationdata AT johnszelek diffusionpartitionconsensusdiffusionaidedtimeofflightestimatesanomalydetectionandlocalizationforultrasonicnondestructiveevaluationdata |