@article{rivas_delipei_davis_bhongale_yang_hou_2024, title={A component diagnostic and prognostic framework for pump bearings based on deep learning with data augmentation}, volume={247}, ISSN={["1879-0836"]}, url={https://doi.org/10.1016/j.ress.2024.110121}, DOI={10.1016/j.ress.2024.110121}, abstractNote={To support the mission of providing safe electricity generation with a high capacity factor, a Predictive Maintenance (PdM) framework using Machine Learning Models (MLM) to optimize component maintenance operations is developed. Using sensor measurements to better predict the true component's Remaining Useful Life (RUL), the PdM framework has the potential to optimize maintenance costs by performing maintenance only when necessary. The PdM framework to pump bearings, the framework consists of a Convolutional Neural Network Autoencoder (CNN-AE) to detect component deviations from normality, a CNN to characterize component fault modes, and a Bayesian Neural Network (BNN) to estimate the component RUL with uncertainty. To increase the number of training samples, a synthetic data generation procedure was developed and includes procedures to recreate the fault-specific characteristic frequencies for diagnostics and the degradation trends for prognostics. The MLMs trained on the synthetic data are tested on the Center for Intelligent Maintenance Systems (IMS) dataset to showcase how well the synthetic data replicates measurement data. Utilizing this framework, the PdM was found to delay maintenance on average by a total of 8.92 years over 40 years and decrease the unexpected component failure rate from 10% to 0% when compared to traditional maintenance philosophies.}, journal={RELIABILITY ENGINEERING & SYSTEM SAFETY}, author={Rivas, Andy and Delipei, Gregory Kyriakos and Davis, Ian and Bhongale, Satyan and Yang, Jinan and Hou, Jason}, year={2024}, month={Jul} } @article{rivas_delipei_davis_bhongale_hou_2024, title={A system diagnostic and prognostic framework based on deep learning for advanced reactors}, volume={170}, ISSN={["1878-4224"]}, DOI={10.1016/j.pnucene.2024.105114}, abstractNote={To meet the projected energy demand in the next 30 years, advanced reactor designers are looking to maximize system capacity factor to increase economic competitiveness. To maximize capacity factor, operators must minimize the system downtime due to forced shutdowns from transients. To accomplish this, the objective of this work is to develop a System level Diagnostic/Prognostic (SDP) framework based on state-of-the-art Machine Learning Models (MLM) to support operators by detecting and diagnosing anomalous behaviors and predicting the onset of exceeding safety limits. This Accident Management Support Tool (AMST) consists of a Long Short Term Memory Autoencoder (LSTM-AE) model to identify if an anomaly is present, a Convolutional Neural Network (CNN) diagnostic model to characterize that anomaly, and a Long Short Term Memory Dense layered (LSTM-D) model to provide Remaining Useful Life (RUL) predictions. These models were trained on data from various system wide transients that occur at different power levels and at different rates using a digital twin of the Xe-100 Pebble-Bed High Temperature Gas Reactor (PB-HTGR) developed in SimuPACT. This framework’s capability is showcased with a water ingress constant reactivity insertion event that caused the reactor outlet temperature to exceed its safety threshold. This study showed that as the transient progresses, the LSTM-AE detects an anomaly within 20 s of event initiation, the CNN characterization stays steady throughout the transient with a 60 s delay, and the LSTM-D is able to accurately predict the time to threshold as the reactor outlet temperature approaches its safety threshold 720 s after fault initiation.}, journal={PROGRESS IN NUCLEAR ENERGY}, author={Rivas, Andy and Delipei, Gregory Kyriakos and Davis, Ian and Bhongale, Satyan and Hou, Jason}, year={2024}, month={May} } @article{faure_delipei_petruzzi_avramova_ivanov_2023, title={Fuel performance uncertainty quantification and sensitivity analysis in the presence of epistemic and aleatoric sources of uncertainties}, volume={11}, ISSN={["2296-598X"]}, DOI={10.3389/fenrg.2023.1112978}, abstractNote={Fuel performance modeling and simulation includes many uncertain parameters from models to boundary conditions, manufacturing parameters and material properties. These parameters exhibit large uncertainties and can have an epistemic or aleatoric nature, something that renders fuel performance code-to-code and code-to-measurements comparisons for complex phenomena such as the pellet cladding mechanical interaction (PCMI) very challenging. Additionally, PCMI and other complex phenomena found in fuel performance modeling and simulation induce strong discontinuities and non-linearities that can render difficult to extract meaningful conclusions form uncertainty quantification (UQ) and sensitivity analysis (SA) studies. In this work, we develop and apply a consistent treatment of epistemic and aleatoric uncertainties for both UQ and SA in fuel performance calculations and use historical benchmark-quality measurement data to demonstrate it. More specifically, the developed methodology is applied to the OECD/NEA Multi-physics Pellet Cladding Mechanical Interaction Validation benchmark. A cold ramp test leading to PCMI is modeled. Two measured quantities of interest are considered: the cladding axial elongation during the irradiations and the cladding outer diameter after the cold ramp. The fuel performance code used to perform the simulation is FAST. The developed methodology involves various steps including a Morris screening to decrease the number of uncertain inputs, a nested loop approach for propagating the epistemic and aleatoric sources of uncertainties, and a global SA using Sobol indices. The obtained results indicate that the fuel and cladding thermal conductivities as well as the cladding outer diameter uncertainties are the three inputs having the largest impact on the measured quantities. More importantly, it was found that the epistemic uncertainties can have a significant impact on the measured quantities and can affect the outcome of the global sensitivity analysis.}, journal={FRONTIERS IN ENERGY RESEARCH}, author={Faure, Quentin and Delipei, Gregory and Petruzzi, Alessandro and Avramova, Maria and Ivanov, Kostadin}, year={2023}, month={Mar} } @article{delipei_rouxelin_abarca_hou_avramova_ivanov_2022, title={CTF-PARCS Core Multi-Physics Computational Framework for Efficient LWR Steady-State, Depletion and Transient Uncertainty Quantification}, volume={15}, ISSN={["1996-1073"]}, url={https://doi.org/10.3390/en15145226}, DOI={10.3390/en15145226}, abstractNote={Best Estimate Plus Uncertainty (BEPU) approaches for nuclear reactor applications have been extensively developed in recent years. The challenge for BEPU approaches is to achieve multi-physics modeling with an acceptable computational cost while preserving a reasonable fidelity of the physics modeled. In this work, we present the core multi-physics computational framework developed for the efficient computation of uncertainties in Light Water Reactor (LWR) simulations. The subchannel thermal-hydraulic code CTF and the nodal expansion neutronic code PARCS are coupled for the multi-physics modeling (CTF-PARCS). The computational framework is discussed in detail from the Polaris lattice calculations up to the CTF-PARCS coupling approaches. Sampler is used to perturb the multi-group microscopic cross-sections, fission yields and manufacturing parameters, while Dakota is used to sample the CTF input parameters and the boundary conditions. Python scripts were developed to automatize and modularize both pre- and post-processing. The current state of the framework allows the consistent perturbation of inputs across neutronics and thermal-hydraulics modeling. Improvements to the standard thermal-hydraulics modeling for such coupling approaches have been implemented in CTF to allow the usage of 3D burnup distribution, calculation of the radial power and the burnup profile, and the usage of Santamarina effective Doppler temperature. The uncertainty quantification approach allows the treatment of both scalar and functional quantities and can estimate correlation between the multi-physics outputs of interest and up to the originally perturbed microscopic cross-sections and yields. The computational framework is applied to three exercises of the LWR Uncertainty Analysis in Modeling Phase III benchmark. The exercises cover steady-state, depletion and transient calculations. The results show that the maximum fuel centerline temperature across all exercises is 2474K with 1.7% uncertainty and that the most correlated inputs are the 238U inelastic and elastic cross-sections above 1 MeV.}, number={14}, journal={ENERGIES}, author={Delipei, Gregory K. and Rouxelin, Pascal and Abarca, Agustin and Hou, Jason and Avramova, Maria and Ivanov, Kostadin}, year={2022}, month={Jul} } @article{rivas_delipei_hou_2022, title={Predictions of component Remaining Useful Lifetime Using Bayesian Neural Network}, volume={146}, ISSN={["1878-4224"]}, url={http://dx.doi.org/10.1016/j.pnucene.2022.104143}, DOI={10.1016/j.pnucene.2022.104143}, abstractNote={The Machine Prognostics and Health Management (PHM) are concerned with the prediction of the Remaining Useful Lifetime (RUL) of assets. Accurate real-time RUL predictions are necessary when developing an efficient predictive maintenance (PdM) framework for equipment health assessment. If correctly implemented, a PdM framework can maximize the interval between maintenance operations, minimize the cost and number of unscheduled maintenance operations, and improve overall availability of the large facilities like nuclear power plants (NPPs). This is especially important for nuclear power facilities to maximize capacity factor and reliability. In this work, we propose a data-driven approach to make predictions of both the RUL and its uncertainty using a Bayesian Neural Network (BNN). The BNN utilizes the Bayes by backprop algorithm with variational inference to estimate the posterior distribution for each trainable parameter so that the model output is also a PDF from which one can draw the mean prediction and the associated uncertainty. To learn the correlations between various time-series sensor data measurements, a time window approach is implemented with a two-stage noise filtering process for incoming sensor measurements to enhance the feature extraction and overall model performance. As a proof of concept, the NASA Commercial Modular Aero Propulsion System Simulation (C-MAPPS) datasets are utilized to assess the performance of the BNN model. The modeled system can be treated as a surrogate for turbine generators used in NPPs due to the similar mode of operation, degradation, and measurable variables. Comparisons against other state-of-the-art algorithms on the same datasets indicate that the BNN model can not only make predictions with comparable level of accuracy, but also offer the benefit of estimating uncertainty associated with the prediction. This additional uncertainty, which can be continuously updated as more measurement data are collected, can facilitate the decision-making process with a quantifiable confidence level within a PdM framework. Additional advantages of the BNN are showcased, such as providing component maintenance ranges and model executing frequency, with an example of how the BNN estimated uncertainty can be used to support the continuous predictive maintenance. A PdM framework based on a BNN will allow for utilities to make more informed decisions on the optimal time for maintenance so that the loss of revenue can be minimized from planned and unplanned maintenance outages.}, journal={PROGRESS IN NUCLEAR ENERGY}, publisher={Elsevier BV}, author={Rivas, Andy and Delipei, Gregory Kyriakos and Hou, Jason}, year={2022}, month={Apr} } @article{delipei_hou_avramova_rouxelin_ivanov_2021, title={Summary of comparative analysis and conclusions from OECD/NEA LWR-UAM benchmark Phase I}, volume={384}, ISSN={["1872-759X"]}, url={http://dx.doi.org/10.1016/j.nucengdes.2021.111474}, DOI={10.1016/j.nucengdes.2021.111474}, abstractNote={In recent years, large efforts have been devoted to Light Water Reactor (LWR) Uncertainty Quantification (UQ). In 2006, the LWR Uncertainty Analysis in Modeling (UAM) benchmark was launched with an aim to investigate the uncertainty propagation in all modeling stages of the LWRs and guide uncertainty and sensitivity analysis methodology development. This article summarizes the benchmark activities for the standalone neutronics phase (Phase I), which includes three main exercises: Exercise I-1: “Cell Physics,” Exercise I-2: “Lattice Physics,” and Exercise I-3: “Core Physics.” A comparative analysis of the Phase I results is performed in this article for all the considered LWRs types: Three Mile Island – 1 Pressurized Water Reactor (PWR), Peach Bottom – 2 Boiling Water Reactor (BWR), Kozloduy – 6 Water - Water Energetic Reactor (VVER) and a Generation-III reactor. It was found, for all major exercises, that the predicted uncertainty of the system eigenvalue is highly dependent on the choice of the covariance libraries used in the UQ process and is less sensitive to the solution method, nuclear data library and UQ method. For all four reactor types, the observed relative standard deviation across all exercises is approximately 0.5% for the UO2 fuel. In the pin cell and lattice calculations with MOX fuel this uncertainty increases to 1%. The main reason is the larger Pu-239 nu-bar uncertainty compared to the U-235 nu-bar. The largest contributors to the eigenvalue uncertainties are the U-235 nu-bar and the U-238 capture in the UO2 fuel and the Pu-239 nu-bar in the MOX fuel. In the assembly lattice exercises, higher uncertainties are predicted for the fast group than the thermal group constants with differences up to one order of magnitude. This is attributed to the larger uncertainties of most cross-sections at high energies. The obtained correlation matrices share some common major trends but also exhibit strong differences in case by case comparisons indicating an impact of the selected neutronics modeling and nuclear data library. In the core exercises, the predicted relative standard deviation of the radial and axial power, for most of the cores, is below 10%. An exception is the radial power profile of the Generation-III core, when a mixture of UOX/MOX assemblies is considered. Finally, it is important to note that the bias in most of the studies is significant and up to the same order of the estimated uncertainty. This indicates a need for better quantification of the bias/variance through more code to code and code to experiments comparisons.}, journal={NUCLEAR ENGINEERING AND DESIGN}, publisher={Elsevier BV}, author={Delipei, Gregory Kyriakos and Hou, Jason and Avramova, Maria and Rouxelin, Pascal and Ivanov, Kostadin}, year={2021}, month={Dec} }