SEARCH · Search NASA

Results for “Cause identification”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

All sources NASA NTRS DOE OSTI

DOE OSTI2020

Cause identification of electromagnetic transient events using spatiotemporal feature learning

This paper presents a spatiotemporal feature learning method for cause identification of electromagnetic transient events in power grids. The proposed method is formulated based on the availability of time-synchronized high-frequency measurements and using the convolutional neural network as the spatiotemporal feature representation along with softmax function for the classification. Despite the existing threshold-based, or energy-based events analysis methods, such as support vector machine autoencoder, and tapered multi-layer perceptron neural network, the proposed feature learning is carried out with respect to both time and space. The effectiveness of the proposed feature learning and the subsequent cause identification is validated through the Electromagnetic Transients Program (EMTP) simulation of different events such as line energization, capacitor bank energization, lightning, fault, and high-impedance fault in the IEEE 30-bus, and the real-time digital simulation of the Western System Coordinating Council (WSCC) 9-bus system.

42 ENGINEERING↗

DOE OSTI2022

Integrated Issues and Risk Management: A Theoretical Framework Overview

The contractor requirements document for DOE O 226.1B, Implementation of Department of Energy Oversight Policy, requires DOE/NNSA contractors to establish an assurance system that includes, among other things, “Rigorous, risk-informed, and credible self-assessment and feedback and improvement activities. Assessment programs must be risk-informed, formally described and documented, and appropriately cover potentially high consequence activities” and “Contains an issues management process that is capable of categorizing the significance of findings based on risk and priority and other appropriate factors….” However, the term “risk-informed” is not defined in this or any other DOE order, and no formal guidance on how to integrate the two concepts currently exists. The Risk Management Guide for Defense Programs released by NA-18, Office of Systems Engineering and Integration (SE&I), states it is “a framework and general guidance to program office personnel on the effective management of program risks and issues”, however it then defines issues as “events with 100% likelihood of affecting program objectives” and states “unless specified otherwise, the term “risk” will also serve to represent issues for the remainder of this plan,” severally limiting its ability to provide adequate guidance on this topic. Outside of DOE scope, the U.S. Nuclear Regulatory Commission (U.S. NRC) imposes similar requirements. ASME NQA-1-2015 Requirement 16 states “Conditions adverse to quality shall be identified promptly and corrected as soon as practicable. In the case of a significant condition adverse to quality, the cause of the condition shall be determined, and corrective action taken to preclude recurrence. The identification, cause, and corrective action for significant conditions adverse to quality shall be documented and reported to appropriate levels of management. Completion of corrective actions shall be verified”. The purpose of this document is to provide a best-in-class framework for an integrated risk and issues management process. This process would provide a robust feedback loop between risk management and issues management to: Enhance risk identification and characterization, use risk handling principles to improve corrective action planning, and ensure regulatory compliance.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2025

Case Report: Differential diagnosis of hematuria in the emergency department: emphasizing double J stent-inferior vena cava fistula

Introduction Hematuria, a common clinical indicator of genitourinary tract pathology, arises from diverse etiologies including calculi, infections, malignancies, trauma, and iatrogenic causes. Initial evaluation requires hemodynamic assessment, identification of underlying causes, and urinary drainage optimization. This report highlights a rare case of iatrogenic hematuria secondary to double-J stent migration into the inferior vena cava. Case presentation A Chinese male presented with acute left flank pain and gross hematuria persisting for 4 h. Diagnostic imaging revealed a left ureteral stone, prompting double-J stent placement at a local hospital. Despite intervention, hematuria worsened, necessitating abdominal CT. Imaging identified proximal migration of the left double-J stent into the inferior vena cava, with no evidence of vascular injury. Due to concerns regarding inadequate drainage and infection risk, conservative management without catheter clamping was initiated prior to referral. Definitive treatment involved ureteroscopic stent removal under direct visualization at our institution, resulting in rapid symptom resolution. Conclusion This case emphasizes three critical clinical insights: (1) Persistent postoperative hematuria warrants consideration of iatrogenic causes, particularly following urologic device placement. (2) Imaging modalities, especially CT, are indispensable for detecting atypical stent migration. (3) Comprehensive history-taking must include prior urologic interventions to guide differential diagnosis. While double-J stent migration into major vessels remains exceptionally rare, its recognition prevents delayed management of potentially life-threatening complications. Clinicians should maintain heightened vigilance for device-related hematuria in patients with refractory symptoms post-procedurally, ensuring prompt imaging evaluation and multidisciplinary intervention when indicated.

Qi, Wenqi↗

DOE OSTI2020

Systematic identification of cis -regulatory variants that cause gene expression differences in a yeast cross

Sequence variation in regulatory DNA alters gene expression and shapes genetically complex traits. However, the identification of individual, causal regulatory variants is challenging. Here, we used a massively parallel reporter assay to measure the cis-regulatory consequences of 5832 natural DNA variants in the promoters of 2503 genes in the yeast Saccharomyces cerevisiae. We identified 451 causal variants, which underlie genetic loci known to affect gene expression. Several promoters harbored multiple causal variants. In five promoters, pairs of variants showed non-additive, epistatic interactions. Causal variants were enriched at conserved nucleotides, tended to have low derived allele frequency, and were depleted from promoters of essential genes, which is consistent with the action of negative selection. Causal variants were also enriched for alterations in transcription factor binding sites. Models integrating these features provided modest, but statistically significant, ability to predict causal variants. This work revealed a complex molecular basis for cis-acting regulatory variation.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

Analyzing Potential Failures and Effects in a Pilot-Scale Biomass Preprocessing Facility for Improved Reliability

This study demonstrates a failure identification methodology applied to a preprocessing facility generating conversion-ready feedstocks from biomass meeting conversion process critical quality attribute (CQA) specifications. Failure Modes and Effects Analysis (FMEA) was used as an industrially relevant risk analysis approach to evaluate a logging residue preprocessing system to prepare feedstock for pyrolysis conversion. Risk evaluations considered both system-level and operation unit-level assessments considering process efficiency, product quality, cost, sustainability, and safety. Key outputs included estimations of semi-quantitative risk scores for each failure, identification of the failure impacts, identification of failure causes associated with material attributes and process parameters, ranking success rates of failure detection methods, and speculation of potential mitigation strategies for decreasing failure risk scores. Results showed that deviations from moisture specifications had cascading consequences for other CQAs along with process safety implications. Failures linked to fixed carbon specifications carried the highest risk scores for product quality and process efficiency impacts. As increased throughput can be inversely related to meeting product quality specifications; achieving throughput and other material-based CQAs simultaneously will likely require system optimization or prioritization based on system economics. Ultimately, this work successfully demonstrates FMEA as a risk analysis approach for other bioenergy process systems.

09 BIOMASS FUELS↗

DOE OSTI2023

Anomaly Detection and Identification Using a Leave-One-Variable-Out Method

At nuclear power plants (NPPs), anomaly detection and identification (i.e., determining the causes of anomalies) are important tasks for ensuring the safe and efficient operation of NPPs. These tasks are currently labor-intensive and costly, and are made more difficult by the size and complexity of NPP systems. An alternative approach to conducting these tasks is to automate them, such as via the reconstruction-based contribution method, which is a well-researched unsupervised machine learning method that uses a data-driven model of anomaly-free behavior to detect events and then identify each variable’s contributions to those events. The present effort developed a novel contribution approach that utilized a leave-one-variable-out (LOVO) model, with which each variable is predicted using all the other variables. The novelty lay in transforming this model into a reconstruction model and modifying the identification algorithm to work with the new reconstruction model. To evaluate this method in a controlled environment, a synthetic dataset based on spring-mass-damper (SMD) systems (commonly found in mechanical engineering references) was used, with known anomalies introduced into the system. The proposed method successfully detected the anomalies and afforded insights into their causes, thus enabling the appropriate identifications to be made.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2020

Microbial Community Composition in Deep‐Subsurface Reservoir Fluids Reveals Natural Interwell Connectivity

Abstract The identification of natural fractures and the wells they connect is crucial for the development of geological reservoirs because it may have an important impact on reservoir model construction and hydraulic fracture propagation. In this study we investigated the use of a novel data source, the microbial community composition in the reservoir formation fluids, for identification of interwell connectivity caused by natural fractures. We verified this concept at a newly developed mesoscale enhanced geothermal system (EGS) field testbed located 4,850 ft (1,478 m) beneath ground surface at the Sanford Underground Research Facility in Lead, SD. Fluids produced at or near the EGS testbed were sampled and subjected to high‐throughput 16S rRNA gene amplicon sequencing to analyze the microbial community profile therein. Despite the typically substantial heterogeneity across the community profiles of samples spatially distributed (10 m to 1.9 km apart) throughout the site, samples from two wells at the EGS testbed showed highly similar microbial community composition, suggesting the two wells intersected the same natural fracture. This evidence of natural connectivity between the two wells at the EGS testbed was later corroborated by core log analysis and sewer camera surveys into the boreholes. Besides the field case described in this study, microbial community composition as a reservoir diagnostic tool would be applicable in a much broader context such as unconventional hydrocarbon exploitation, groundwater reservoir characterization, and environmental remediation, adding valuable “hard” data capable of pinpointing the origins of fluids unambiguously.

Zhang, Yuran↗

DOE OSTI2024

Technical Language Processing of Nuclear Power Plants Equipment Reliability Data

Operating nuclear power plants (NPPs) generate and collect large amounts of equipment reliability (ER) element data that contain information about the status of components, assets, and systems. Some of this information is in textual form where the occurrence of abnormal events or maintenance activities are described. Analyses of NPP textual data via natural language processing (NLP) methods have expanded in the last decade, and only recently the true potential of such analyses has emerged. So far, applications of NLP methods have been mostly limited to classification and prediction in order to identify the nature of the given textual element (e.g., safety or non-safety relevant). In this paper, we target a more complex problem: the automatic generation of knowledge based on a textual element in order to assist system engineers in assessing an asset’s historical health performance. The goal is to assist system engineers in the identification of anomalous behaviors, cause–effect relations between events, and their potential consequences, and to support decision-making such as the planning and scheduling of maintenance activities. “Knowledge extraction” is a very broad concept whose definition may vary depending on the application context. In our particular context, it refers to the process of examining an ER textual element to identify the systems or assets it mentions and the type of event it describes (e.g., component failure or maintenance activity). In addition, we wish to identify details such as measured quantities and temporal or cause–effect relations between events. This paper describes how ER textual data elements are first preprocessed to handle typos, acronyms, and abbreviations, then machine learning (ML) and rule-based algorithms are employed to identify physical entities (e.g., systems, assets, and components) and specific phenomena (e.g., failure or degradation). A few applications relevant from an NPP ER point of view are presented as well.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Development of Analysis Methods that Integrate Numeric and Textual Equipment Reliability Data

Within the Light Water Reactor Sustainability (LWRS) program, the Risk-Informed Systems Analysis (RISA) Pathway is performing collaborative research on the development and deployment of technologies designed to assist operating nuclear power plants (NPPs) to reduce operating costs improve plant reliability and availability. One of the RISA research areas is focusing on the development of methods and tools designed to optimize plant operations (e.g., maintenance/replacement schedules, optimal maintenance postures for plant structures, systems, and components [SSCs]) in a manner that is more cost effective than current approaches and makes better use of available SSC health data. The Risk-Informed Asset Management (RIAM) project targets this research area by creating a direct bridge between component equipment reliability (ER) data and system engineer decision making regarding maintenance activity scheduling and component aging management. In this respect, one challenge that NPP system engineers are facing is that the amount of ER data being continuously generated is not only extremely large in size, but it comes in different forms: textual (e.g., condition or maintenance reports) and numeric (e.g., generated by monitoring systems). All these data elements provide them with valuable insights and information regarding: 1) the discovery of anomalous behaviors or degradation trends, 2) the identification of the possible causes behind such behaviors/trends, and 3) the prediction of their direct consequences. However, several challenges have proved to be roadblocks to this process. While some of these challenges are technical in nature (i.e., data are often distributed over several physical servers/databases), others are conceptual in nature: data elements come in different formats (e.g., numeric or textual), and measured values have different scales (e.g., vibration spectra and oil temperature). The activities performed by the RIAM project during FY23 directly tackles the need to simultaneously integrate the analysis of ER data in all its forms, numeric and textual. Note that such task has never been performed before due to the complexity of the systems under consideration but, most importantly, because of the technical challenges behind the harmonization of ER data formats and the lack of adequate computational methods to analyze them. Our approach borrows ideas and concepts from the medical field where integration of several data sources is vital to assist medical practitioners to perform correct diagnosis and indicate optimal treatments. In our view a NPP asset is equivalent to a patient in a medical context. The main difference is the complexity of a human body is a magnitude more complex when compared to typical assets commonly present in NPPs (e.g., centrifugal pumps, or motor operated valves). This simplifies our first requirement when analyzing heterogenous ER data formats: to put data into “context”. Context is here intended as the additional piece of information that is needed by ER data analysis tools to understand what these data elements are referring to, i.e., which king of knowledge they are generating. In our context, this knowledge can be translated into models that capture the form and functional architecture of assets/systems, their dependencies, and how they interact. These models actually emulate the knowledge that that NPP system engineers possess about assets and systems; this is their key of success when analyzing ER data, their challenge is ability to handle large amount of data. Here, we employ model-based system engineering (MBSE) models of systems and assets to represent and capture their architecture and functional, i.e. cause-effect, relations. Then, ER data elements are processed by identifying first of all which elements of the developed MBSE elements they are referring to. For numeric ER data this task is fairly easy since it is possible to precisely pinpoint what MBSE elements the corresponding sensor are observing (e.g., bearing temperature of a centrifugal pump). Task is much harder for textual data since the information contained in issue or maintenance reports needs to “be understood” by a computational tool. Here we called this process as “knowledge extraction”. Once again, we borrow the experience in the medical field where methods to extract knowledge from textual data have been developed in the past decade. The missing element for us is the availability of a complete dictionary of NPP related concepts (in addition to the MBSE models presented earlier) that can put “text into context”. In FY23, such dictionary has been developed along with all the computational elements required for knowledge extraction. Lastly, once numeric and textual ER data elements have been processed and “understood”, then the last step is the discovery of possible cause-effect relations among them. This is performed by observing if a logical connection through the MBSE models exists, and if the

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Model-Based Approaches to Generate Knowledge from Data in a Plant Reliability Context

One challenge that nuclear power plant system engineers are facing is that the amount of equipment reliability (ER) data being continuously generated are extremely large. These data elements come in different forms: textual (e.g., condition reports) and numeric (e.g., generated by monitoring systems) and they provide system engineers with valuable insights and information regarding the discovery of anomalous behaviors or degradation trends, the identification of the possible causes behind such behaviors and trends, and the prediction of their direct consequences. This paper directly targets the generation of knowledge from ER data by putting “data into context”. Here, we employ model-based system engineering (MBSE) models of systems and assets to represent and capture their architecture and functional (i.e., cause-effect) relations. ER data elements are processed by identifying first which elements of the developed MBSE elements they are referring to. This task is much harder for textual data since the information contained in issue or maintenance reports needs to “be understood” by a computational tool. Here we called this process “knowledge extraction” where our methods to extract knowledge from textual data. Lastly, once numeric and textual ER data elements have been processed and “understood”, we discover possible cause-effect relations among them. This is performed by observing if a logical connection through the MBSE models exists, and if there is a temporal relation among them. The logic and temporal are the two main ingredients to perform “machine reasoning” from ER data.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Feedstock-Conversion Interface Consortium: Failure Mode and Effects Analysis Summary Report (FY2022)

This report provides an overview of the development of failure modes and effects analysis (FMEA) and its implementation as a systematic criticality and risk assessment tool supporting a quality by design (QbD) approach for FCIC research. This report also provides a high-level overview of the results for the FMEA evaluation of two feedstock preprocessing system configurations: (1) generation of pine residue materials for high-temperature pyrolysis conversion and (2) generation of corn stover materials for low-temperature conversion using deacetylation and disc mechanical refining pretreatment for fermentation to hydrocarbons. For the results presented in this report, our FMEA interviews included two approaches. The first approach was to perform FMEA interviews for the entire system of unit operations giving a wholistic system level view. The second approach consisted of detailed interviews for each individual unit operation within the system allowing for a “deep dive” into the specific failures for the individual components within the configuration. These two approaches provide different resolutions of information. The FMEA results of this report were focused on failures associated with meeting critical quality attributes (CQAs) identified for the target conversion processes for each processed feedstock type. The information gathered through the FMEA interviews include estimations of risk scores for meeting each given CQA specification, identification of the impacts for not meeting a CQA specification, capturing causes associated with material attributes and process parameters for each failure, identification of current detection methods, and speculation of potential mitigation strategies for decreasing a failure’s risk score. The complete results of all FMEA interviews are provided in the Appendices of this report.

09 BIOMASS FUELS↗

DOE OSTI2023

Failure Mode and Effects Analysis Summary Report

conversion↗

DOE OSTI2023

Failure Modes and Effects Analysis of Biorefinery Pathways

This talk provides an overview of failure modes and effects analysis (FMEA) development and implementation as a systematic criticality and risk assessment tool for biorefinery pathways within the FCIC. This supports a quality by design (QbD) approach, and this talk provides a high-level overview of the results for the FMEA evaluation focused on the generation of pine residue materials for high-temperature pyrolysis conversion. the FMEA interviews included two approaches. The first approach was based around the entire system of unit operations giving a wholistic system level view. The second approach used detailed interviews from individual unit operation within the system allowing for specific failures for individual system components. These two approaches provide different resolutions of information about the reliability and risk. The FMEA results focused on failures associated with meeting critical quality attributes (CQAs) identified for the high temperature conversion of loblolly pine residues and were supplemented with experimental data supporting process upsets and reliability also collected within the consortium. Estimations of risk scores for meeting each given CQA specification, identification of the impacts for not meeting a CQA specification, capturing causes associated with material attributes and process parameters for each failure, identification of current detection methods, and speculation of potential mitigation strategies for decreasing a failure’s risk score were gathered through the FMEA interviews, and were combined to understand the overall process risk metrics and where technology, process, and knowledge improvements are needed in order to de-risk emerging biorefineries.

09 BIOMASS FUELS↗

DOE OSTI2020

Iodine interstitials as a cause of nonradiative recombination in hybrid perovskites

The identification of deep-level defects that act as detrimental nonradiative recombination centers is critical for optimizing the optoelectronic performance of hybrid perovskites. Although extensive studies have been devoted to revealing the nature of deep-level defects in hybrid perovskites, it is still unclear what defects are responsible for the experimentally observed nonradiative recombination rates. Employing first-principles approaches, we quantitatively show that the iodine interstitial is a dominant nonradiative recombination center in methylammonium-lead iodide. Finally, this important insight points to a target for defect engineering in order to further improve the performance of hybrid perovskites.

36 MATERIALS SCIENCE↗

DOE OSTI2022

Hypothesis-Agnostic Network-Based Analysis of Real-World Data Suggests Ondansetron is Associated with Lower COVID-19 Any Cause Mortality

Background: The COVID-19 pandemic generated a massive amount of clinical data, which potentially hold yet undiscovered answers related to COVID-19 morbidity, mortality, long-term effects, and therapeutic solutions.Objectives: The objectives of this study were (1) to identify novel predictors of COVID-19 any cause mortality by employing artificial intelligence analytics on real-world data through a hypothesis-agnostic approach and (2) to determine if these effects are maintained after adjusting for potential confounders and to what degree they are moderated by other variables.Methods: A Bayesian statistics-based artificial intelligence data analytics tool (bAIcis®) within the Interrogative Biology® platform was used for Bayesian network learning and hypothesis generation to analyze 16,277 PCR+ patients from a database of 279,281 inpatients and outpatients tested for SARS-CoV-2 infection by antigen, antibody, or PCR methods during the first pandemic year in Central Florida. This approach generated Bayesian networks that enabled unbiased identification of significant predictors of any cause mortality for specific COVID-19 patient populations. These findings were further analyzed by logistic regression, regression by least absolute shrinkage and selection operator, and bootstrapping.Results: We found that in the COVID-19 PCR+ patient cohort, early use of the antiemetic agent ondansetron was associated with decreased any cause mortality 30 days post-PCR+ testing in mechanically ventilated patients.Conclusions: The results demonstrate how a real-world COVID-19-focused data analysis using artificial intelligence can generate unexpected yet valid insights that could possibly support clinical decision making and minimize the future loss of lives and resources.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

Generation of macro- and microplastic databases by high-throughput FTIR analysis with microplate readers

Abstract FTIR spectral identification is today’s gold standard analytical procedure for plastic pollution material characterization. High-throughput FTIR techniques have been advanced for small microplastics (10–500 µm) but less so for large microplastics (500–5 mm) and macroplastics (> 5 mm). These larger plastics are typically analyzed using ATR, which is highly manual and can sometimes destroy particles of interest. Furthermore, spectral libraries are often inadequate due to the limited variety of reference materials and spectral collection modes, resulting from expensive spectral data collection. We advance a new high-throughput technique to remedy these problems using FTIR microplate readers for measuring large particles (> 500 µm). We created a new reference database of over 6000 spectra for transmission, ATR, and reflection spectral collection modes with over 600 plastic, organic, and mineral reference materials relevant to plastic pollution research. We also streamline future analysis in microplate readers by creating a new particle holder for transmission measurements using off-the-shelf parts and fabricating a nonplastic 96-well microplate for storing particles. We determined that particles should be presented to microplate readers as thin as possible due to thick particles causing poor-quality spectra and identifications. We validated the new database using Open Specy and demonstrated that additional transmission and reflection spectra reference data were needed in spectral libraries. Graphical abstract

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2020

Jefferson Laboratory C100 Superconducting Radio-Frequency Cavity Fault Data, 2020

The dataset was created to train machine learning models for the task of identifying the (1) cavity and (2) fault type from C100-type cryomodules at the Thomas Jefferson National Accelerator Facility (Jefferson Lab), thereby replacing the time-consuming efforts of a subject matter expert. Superconducting radio-frequency (SRF) cavity trips represent a significant source of accelerator downtime. Real-time – rather than post-mortem – identification of the offending cavity and classification of the fault type would give control room operators valuable feedback for corrective action planning. The anticipated benefit is increased beam-on-target time for users and provides performance metrics that can be used to improve future cavity designs. A series of 17 RF signals are recorded for each of the 8 cavities in a C100 cryomodule every time a cavity trips. These time-series signals are written to file using a specially designed data acquisition system. The dataset represents fault events recorded during Continuous Electron Beam Accelerator Facility (CEBAF) beam operations between January 18, 2019 and March 9, 2020. The following filtering steps were applied to collected data; (1) only 4 of the 17 signals per cavity are retained (GMES, GASK, CRFP, DETA2) (2) only events with data from each of the eight cavities in the cryomodule are kept, (3) only events that were sampled at 5 kHz were kept, (4) events from cryomodule 0L04 were neglected, (5) events occurring between February 4, 3PM and February 5, 12PM were neglected. As a result of preprocessing, the dataset is comprised of 2,375 unique events. The full dataset is comprised of three files: features.csv, cavity_labels.csv, fault_labels.csv. Each instance in faults.csv includes a timestamp (“date_time”), a label for the cryomodule which experienced the trip (“zone_label”), and 192 features (“feature_1”, “feature_2”... “feature_192”). The features correspond to 6 autoregressive features for each of 4 signals per cavity for each of the 8 cavities (6 × 4 signals/cavity × 8 cavities/cryomodule = 192). To deal with the large variation of signal amplitudes, time-series standardization via the z-score (standard score) function was applied prior to computing the features. For each instance, there is an associated label for the (1) cavity which faulted first (cavity_labels.csv) and (2) the type of fault that caused the trip (fault_labels.csv). The cavity identification can take values of [0, 1, 2, 3, 4, 5, 6, 7, 8] and the fault type can take values of [‘Microphonics’, ‘Quench_100ms’, ‘Controls_Fault’, ‘E_Quench’, ‘Quench_3ms’, ‘Single_Cav_Turn_Off’ , ‘Heat_Riser_Choke’, ‘Multi_Cav_Turn_Off’].

43 PARTICLE ACCELERATORS↗

DOE OSTI2025

Unsupervised Process Anomaly Detection and Identification Using the Leave-One-Variable-Out Approach

Automated anomaly detection and identification can signal equipment issues and pinpoint causes in large-scale industrial systems. For systems with limited failure history, unsupervised machine learning methods can be utilized as they do not require past failures. This study introduces the leave-one-variable-out (LOVO) model, which masks one variable at a time to predict the others, learning underlying process correlations. Detection performance was assessed with synthetic and experimental data, while identification performance used only synthetic data due to its ability to generate labeled anomaly types. For detection using synthetic data, the LOVO model generally outperformed comparative models; while using experimental data, the comparative methods outperformed the LOVO model. However, the comparative methods required selecting a latent size, and these conclusions pertain to using the optimal size. In practice, it would not be feasible to always select the optimal value, and incorrect selections impacted performance. In contrast, the LOVO model does not require a latent space. For identification using synthetic data, the LOVO model was slightly outperformed in interpretability and repeatability but still demonstrated impressive results. These outcomes suggest that the LOVO model is an effective model and may be more easily implemented without the challenging tuning process of selecting a latent size.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗