Operation and Maintenance (O&M) costs for nuclear power plants (NPPs) are very large. The nuclear industry is beginning to see reactors shut down-even after their operating licenses have been extended-because they are not economically competitive with other energy sources. These early closures happen due to economic reasons, despite excellent safety records. Therefore, it is imperative to reduce costs in order to prevent these early closures. This paper showcases recent research on advanced fault diagnostics techniques and preventative maintenance optimization (PMO) for reducing NPP maintenance costs. This report focuses on the feedwater and condensate system (FWCS) for both pressurized-and boiling-water reactor (BWR) systems. The computerized maintenance management system (CMMS), which contains the plant's digital record of all corrective maintenance (CM) and preventative maintenance (PM) work orders, provided the ground truth for locating potential faults and labeling the process data as either healthy or faulted. Various feature extraction techniques were utilized to further differentiate the faulted data from the healthy data. Through a cross-validation procedure, support vectors machines (SVMs) were used to label other test sets of process data as either healthy or faulted. Similar faults were not found within the BWR system, thus opening up the potential for PMO, since an unnecessary amount of PM leads to inflated maintenance costs. This paper summarizes the steps for PMO, from component health determinations to recommendations for action. An example of PMO assessment is presented for condensate pumps (CPs), condensate booster pumps (CBPs), and the respective motors that drive them.
The research and development reported here is part of the Technology Enabled Risk-Informed Maintenance Strategy project sponsored by the U.S. Department of Energy's Light Water Reactor Sustainability program. The primary objective of the research presented in this report is to produce a technical basis for developing explainable and trustable artificial intelligence (AI) and machine learning (ML) technologies. The technical basis will lay the foundation for addressing the technical and regulatory adoption challenges of AI/ML technologies across plant assets and the nuclear industry at scale and to achieve seamless cost-effective automation without compromising plant safety and reliability.The technical basis ensuring wider adoption of AI/ML technologies presented in this report was developed by Idaho National Laboratory (INL), in collaboration with Public Service Enterprise Group (PSEG) Nuclear, LLC. To develop the initial technical basis, the circulating water system (CWS) at the PSEG-owned plant sites was selected as the identified plant asset. Specifically, the issue of waterbox fouling diagnosis in the CWS using different types of CWS data is presented to address the said challenge. The approach presented in this report is based on the closed-loop forward-backward process that tries to capture the advancements in data science addressing the explainability of AI/ML outcomes, user-centric interpretability of those outcomes, and how user interpretation can be used as feedback to further simplify the process. A prototype interface is developed to present a focused component-level display of the ML model outputs in a usable and digestible form.
Nuclear plant sites collect and store large volumes of data gathered from various equipment and systems. These datasets typically include plant process parameters, maintenance records, technical logs, online monitoring data, and equipment failure data. The collection of such data affords an opportunity to leverage data-driven machine learning (ML) and artificial intelligence (AI) technologies to provide diagnostic and prognostic capabilities within the nuclear power industry, thus reducing operations and maintenance (O&M) costs. In this way, nuclear energy can become more economically competitive with other energy sources, and premature plant closures can be avoided. From a maintenance standpoint, savings can be achieved by leveraging ML and AI technologies to develop data-driven algorithms that better diagnose and predict potential faults within the system. Improved model accuracy can help reduce unnecessary maintenance and foster more efficient planning of future maintenance, thereby lowering the costs associated with parts, labor, and costly planned, forced, or extended outages. From an operations perspective, cost savings can be generated by shifting from routine-based monitoring to online monitoring by taking advantage of advancements in sensors and wireless communication technologies. Advancements in data storage, mapping, management, and analytics would inform the transition from onsite- to cloud-based computing and storage services. Online monitoring would reduce the number of operator manhours required for taking routine measurements, while cloud computing services would generate cost savings by reducing the amount of hardware needing to be purchased and maintained all while scaling to both computational and storage demands. This paper summarizes an end state vision of how to shift from costly, labor-intensive preventative maintenance to cost-effective predictive maintenance.
Wind energy is growing increasingly popular in the United States, so it is imperative to make it as cost competitive as possible. Operations and Maintenance (O&M) make up 20-25% of the total cost of onshore wind projects. Unplanned maintenance contributes approximately 75% of the total maintenance costs (WWEA, 2012). Condition-based maintenance strategies intend to maximize the uptime by reducing to the amounts of unplanned maintenance. This should result in an overall decrease in the cost of maintenance. Wind turbines produce an interesting challenge, because their main shaft rotation is both slow and nonstationary. Through the use of adaptive resampling and order tracking, both of these challenges were combated as the bearing fault was identified in the order spectrum then tracked as it progressed. The fault was identified as an outer race defect on the main bearing that initiated sometime during or before installation. The total energy in the order spectrum around the bearing fault rate was identified as a potential front-runner for a prognostic parameter. This paper presents a case study application to operational wind turbine bearing data to demonstrate the ease and intuitiveness of combining adaptive resampling and order tracking to diagnose faults for slow, nonstationary bearings. Prognosis of remaining useful life is proposed with features extracted from the order spectrum, but additional data are needed to develop and demonstrate this analysis.
For economic reasons, the nuclear industry is witnessing premature closure of nuclear power plants, despite excellent safety records. Operations and maintenance activities are some of the largest costs in operating legacy lightwater plants. By reducing operations and maintenance costs, nuclear energy can become more economically competitive with other energy sources. This can be achieved in part by leveraging machine-learning and artificial intelligence technologies to develop data-driven algorithms to better diagnose potential faults within the system. The improved accuracy of the models can lead to a reduction in unnecessary maintenance, thus reducing costs associated with parts, labor, and unnecessary planned, forced, or extended outages.To address these challenges, the goal of this project is to perform research and development in the area of digital monitoring (i.e., the application of advanced sensor technologies, particularly wireless sensor technologies, and data-science-based analytic capabilities) to advance online monitoring and predictive maintenance in nuclear plants and improve plant performance (efficiency gain and economic competitiveness). This report summarizes the Fiscal Year 2020 research progress encompassing the (1) different wireless vibration sensor and data indicators used to assess the health of a plant asset; (2) development of diagnostic models for fault detection; and (3) development of prognostic models for estimating the health of the system up to 7 days ahead.
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.