Engineering Papers⌕ Search

Engineering topics

Huang, Dongli

Publications and source records attributed to Huang, Dongli.

Process Anomaly Detection for Sparsely Labeled Events in Nuclear Power Plants

An essential aspect of online monitoring, subtle anomaly detection increases the detection lead time for equipment failure and enables a nuclear power plant (NPP) to mitigate unexpected partial or full outages, resulting in significant cost saving to the plant. Once an anomaly is detected by plant staff, its cause and severity are investigated. Because the vast majority of anomalies require some level of investigation, including some that require time-consuming examination, before they are passed over to the engineering organization for further analysis, plants are often equipped with tools to assist the staff in performing anomaly detection. Those tools operate as a black box and are often based on statistical methods that establish sensor correlations using preconfigured mathematical models and flag correlation deviations as anomalies. Due to the number of anomalies detected at a given NPP on a daily basis, a significant number of flagged anomalies usually await examination for days or weeks. A primary cause of this backlog is that the methods used by the tools generate many false positives. Though this is usually attributed to oversensitive model settings due to very narrow normal operation bands, it can also be associated with the model development being inadequate for the process being monitored, or with missing model inputs that could have explained misclassified positives. The performance of anomaly detection tools impacts their plant acceptance and utilization, especially when the effort to address false positives generated by the tool depletes the value or cost saved by using that tool. Thus, means to advance anomaly detection performance have been investigated by the Department of Energy’s Light Water Reactor Sustainability program. Previous and ongoing efforts have targeted unsupervised machine-learning (ML) methods, which do not require the labeling of any data fed into the ML model. By contrast, in supervised anomaly detection methods, every data point is labeled as either a normal or abnormal process condition, and the model is trained to replicate the classification process. Supervised methods usually outperform unsupervised methods, due to the added value in differentiating normal from anomalous states of the monitored process. An NPP’s corrective action program requires it to track and document, via a dedicated report, the resolution of any issues that occur within the plant. Once created, each report is reviewed by a plant screening committee, and several classifications and decisions are made. Recently, a collaborating NPP developed an artificial intelligence and ML-based classifier to categorize a condition report (CR) into classes that can serve to label the data as normal or anomalous. Applying CRs as labels represents a semi-supervised use case. Semi-supervised ML assumes that labels exist for some data points (i.e., labeled anomalies, in this case) but not for the rest. In this effort, semi-supervised ML methods were used to fuse data from CRs with anomaly detection methods in order to test the hypothesis that partially labeled anomalies would improve the accuracy of the anomaly detection methods. Specifically, two methods were used. The first is the deep Semi-supervised Anomaly Detection (deep SAD) method, which can handle labels ranging from fully unsupervised to fully supervised cases. The second is a newly designed ML method developed specifically for this effort and referred to as the high-order feature (HOF)-based method. To evaluate these two methods in controlled environments, synthetic data generators were developed and used. The first datasets used a spring-mass-damper (SMD) system simulator commonly found in mechanical engineering references. This was used to create two use cases: a one- and a three-mass system. Anomalies were introduced by changing the spring and damper coefficients while the system was actuated by random forces. The second datasets used the commercial Dymola-Modelica software to build a simplified nuclear reactor model. Anomalies were added in the form of corrupted sensor readings and/or control commands. The deep SAD method was tested using the SMD system, while the HOF method was tested using both datasets. Application of the deep SAD semi-supervised ML method demonstrated that labels can generate increased confidence in detecting true anomalies. This helped increase the number of true positives and decrease the number of false negatives—something that would aid in addressing the backlog of possible anomalies. Application of the HOF method demonstrated that labels can aid in down selecting from a candidate set of features to a more optimal subset in order to better differentiate between normal and anomalous conditions.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Nuclear data uncertainty propagation and modeling uncertainty impact evaluation in neutronics core simulation

Uncertainty analysis is a critical requirement in reactor simulation as it is used to quantify the reliability of best-estimate calculation. A comprehensive uncertainty analysis should characterize all sources of uncertainties in a computationally-feasible and scientifically-defendable manner. Here we employ a well-established reduced order modeling (ROM) based uncertainty quantification methodology to propagate uncertainties throughout neutronic calculations. ROM relies on recent advances in randomized data mining techniques applied to large data streams. In our proposed implementation, the nuclear data uncertainties are first propagated from multi-group level through lattice physics calculation to generate few-group parameter uncertainties, described using a vector of mean values and a covariance matrix. Employing an ROM-based compression of the covariance matrix, the few-group uncertainties are then propagated through downstream core simulation in a computationally efficient manner. This straightforward approach, albeit efficient as compared to brute force forward and/or adjoint-based methods, often employs a number of assumptions that have been unquestioned in the literature of neutronic uncertainty analysis. This manuscript argues that these assumptions could introduce another source of uncertainty referred to as modeling uncertainties, whose magnitude needs to be quantified in tandem with nuclear data uncertainties. Thus, our primary goal is to explore the interactions between these two uncertainty sources in order to assess whether modeling uncertainties have an impact on parameter uncertainties. To explore this endeavor, the impact of a number of modeling assumptions on core attributes uncertainties is quantified. The study employs a CANDU reactor model, with Serpent and NEWT as lattice physics solvers and NESTLE-C as core simulator. The modeling assumptions investigated include those related with the uncertainty propagation method employed, e.g., deterministic vs. stochastic, the few-group energy structure employed to represent the cross-sections, the resonance treatment in lattice physics calculation, the reference values for the cross-section, and the number of samples employed to render ROM compression. Results indicate that some of the modeling assumptions could have a non-negligible impact on the core responses propagated uncertainties, highlighting the need for a more comprehensive approach to combine parameter and modeling uncertainties.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Verification of the sensitivity and uncertainty-based criticality safety validation techniques: ORNL’s SCALE case study

The use of sensitivity and uncertainty-based techniques has been well-developed in the neutronic community for criticality safety applications. Sensitivity techniques calculate the first-order relative variations in keff due to relative cross-section variations by isotope, reaction type, and incident neutron energy. The result is a vector of sensitivity coefficients which is folded with prior cross-section uncertainties to calculate the so-called similarity indices. Similarity indices are integral quantities which serve as useful mathematical measures for assessing the relevance of existing or new experiments to given application conditions, representing design systems for which the models are to be validated. Despite their importance for a wide range of validation activities, the peer-reviewed literature is non-existent on the development of rigorous verification analysis for their calculated values. Thus, this manuscript proposes a simple non-intrusive method to calculate similarity indices, serving as an independent verification tool for their evaluation. The manuscript derives the theoretical basis for the proposed verification analysis. Next, the verification analysis is applied to the ORNL’s SCALE code suite which employs adjoint-based methods to calculate similarity indices. Numerical experiments using a number of well-known benchmark experiments are employed to verify the calculation of the similarity indices.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Dimensionality reducibility for multi-physics reduced order modeling

Applications of reduced order modeling (ROM) to support analysis of complex reactor behavior using high fidelity simulations have developed rapidly in recent years. Reduction implies any computational approach aiming to reduce the cost of the simulation, especially for situations involving repeated executions such as probabilistic risk assessment and uncertainty quantification applications. This article presents a novel non-intrusive methodology to render reduction for multi-physics models by taking advantage of the combined reduction introduced by each sub-physics in the simulation. Next, a surrogate model is constructed in terms of the reduced dimensions. A key component of the proposed methodology is to upper-bound the errors resulting from the reduction to ensure its reliability for subsequent engineering applications. To implement and demonstrate the proposed ROM algorithm, the INL’s MAMMOTH environment is employed to analyze the level of reduction in the coupled radiation-thermal transport modeling of a 2D quarter fuel pin in a light water reactor spectrum. MAMMOTH couples the neutronics model of Rattlesnake module and the fuel performance model of BISON module. Here, the results show that the reduction obtained with coupled physics is more significant than that with individual sub-physics models.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Multi-Physics Surrogate Modeling with Dimensionality Reduction

This summary provides a new algorithm to construct surrogate models for multi-physics, nonlinear, high dimensional models which typically suffer from the curse of dimensionality. To deal with the high computational cost and difficult error estimation, we employ recent advances in reduced order modeling (ROM) techniques to do an error-preserving reduction for the number of influential model parameters, followed by a conventional surrogate construction process. To implement ROM for a multiphysics model, a range finding algorithm (RFA) is used to identify a linear transformation in which the number of influential parameters can be minimized and the errors resulting from the non-influential parameters can be upper-bounded. The proposed algorithm is applied to the MAMMOTH coupled code system developed at the Idaho National Laboratory. In particular, we investigate the reducibility of Rattlesnake and BISON codes and their multi-physics coupling. The most important result of this work is that the reduction obtained with coupled physics is more significant than that with individual physics models. This summary explores the application of ROM techniques on multi-physics coupling codes system. Concise methodology is provided and selected numerical results are provided to show that coupling system provides additional reduction at interfaces. Future work could be invested to determine the optimum surrogate model format. (authors)

97 MATHEMATICS AND COMPUTING↗

System Reliability Analysis Capability and Surrogate Model Application in RAVEN

This report collect the effort performed to improve the reliability analysis capabilities of the RAVEN code and explore new opportunity in the usage of surrogate model by extending the current RAVEN capabilities to multi physics surrogate models and construction of surrogate models for high dimensionality fields.

31274↗