Development of AgeAlert. A Predictive Maintenance Sensor for Electrical Insulation Systems in Nuclear Power Applications
Explore the source record for details and available documents.
SEARCH · Engineering Papers
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.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
Methods, systems and apparatuses for early fault detection of a power generator are provided. An alternator output power parameter is received and a fuel flow input measurement is received. An estimated engine efficiency value is determined in response to the alternator output power parameter and the fuel flow input measurement. The estimated engine efficiency value may be transmitted to a monitoring device.
Poster to explain app that we are presenting at the conference
Maintenance activities in the United States nuclear power industry are mainly centered on preventive and corrective maintenance. Predictive maintenance, which is a variable time basis maintenance strategy that is dependent on the condition of the equipment, is less utilized but potentially more effective. In the current maintenance practices, the nuclear power plants rely on manual processes to supply information to a human decision making process. The plants have several processes that generate information that is not typically used beyond the intended target for collecting that information. This information is a source of data that is manually collected by labor intensive tasks. The data is therefore expensive to collect, yet limited in use. The industry has realized the opportunity present in reducing the labor intensive tasks by automating them and increasing the uses of the data collected by either developing advanced predictive maintenance methods using data-driven decision making that could span from trending to machine learning and artificial intelligence. This shift in maintenance strategy may result in high cost saving impact. In addition to reducing labor requirements and frequency of maintenance activities, this shift in strategy will reduce the materials portion of the operations and maintenance cost as well. The aim of this specific effort is to focus on the automation of data collection process. It is part of a series of planned efforts to target multiple elements of migrating the current preventive maintenance approach in nuclear power plants to a data-driven approach. These elements include data collection, management, analysis, visualization, in addition to value analysis and change enabling. The other five elements of migration were not considered because they are planned to be explicitly studied in multiple parallel efforts. Challenges including regulations requirements or limitations are planned in a future effort that focuses on change enabling. The risk and benefit/cost of the approach shift is planned in another effort targeted towards value. The storage, communication, computational power, data architecture, and protection are part of the information infrastructure and are planned in dedicated data management effort. The best means to present the data for assisted human decision making is planned in a data visualization effort. The data interpretation and patterns recognition for machine decision making is planned through multiple efforts in data analytics over the following years. This work identified seventeen data sources collection methods in nuclear power plants that could be automated for an integrated data platform that enables comprehensive and informed decision making. For each of the identified seventeen data sources, the base, modern, and state of the art states were described. The current state of data collection used by most utilities was identified as the "base state". The current achievable state was identified as the "modern state", a state that has either been achieved by at least some US utilities or in other industries. The future state that requires research and development to reach was identified as the "state of the art" state. The described states used an out-of-the-box thinking approach. This effort found that there is a hug potential for task automation and data fidelity improvements by evolving the current industry data collection methods. The majority of the processes analyzed were found to be manual and labor intensive and fell in the base state. As a result, the modern state often targeted reducing the manual logging efforts by using electronic and semi-intelligent means or complementing the work with sensors and mobile or fixed technologies that can reduce the demand of labor activities. The state of the art state involved applications advanced methods of data correlation, data mining, and machine learning along with increasing the spatial distribution and fidelity of data, coupling multiple data sources, and enabling the use of sophisticated mobile devices and machine comprehension methods.
In order to reduce operation and maintenance (O&M) costs, nuclear power plants (NPPs) are moving from corrective and periodic maintenance to predictive maintenance strategies. Such transition requires changes on the data that needs to be retrieved and on the type of decision processes to be employed. Advanced monitoring and data analysis technologies are essential to support predictive strategies. They can in fact provide precise information about health of a component, track its degradation trends, and provide information of its expected failure time. With such information, maintenance operations for a component can be performed right before its expected failure time. This dynamic context of O&M operations requires new methods to analyze data, propagate component health information from the component to the system level, and optimize plant resources. In this respect, the risk informed asset management (RIAM) project has been tasked to develop and test this new class of methods into a risk analytics toolset. This toolset consists of data analytics tools coupled with reliability methods designed to manage plant assets and performances in a predictive maintenance context. This report shows the latest improvements on such development and the initial testing of our methods on the three main research areas that the RIAM project is focusing on. These areas are the following: equipment reliability data analytics, system reliability modeling, and plant resources optimization methods. We show how the methods developed in these areas can support predictive maintenance strategies by: 1) analyzing equipment reliability data (either in numeric and textual form), 2) assessing component and system health through an innovative margin-based reliability approach, and 3) identifying the most critical components and set optimal maintenance schedule based on plant economic and operational constraints.
Representing complex systems as graphs enables use of mathematical tools to identify faults or predict failures. Graph nodes correspond to individual modules or subsystems, and edges link coupled system parts. ‘Probes’ measure the node outputs, monitoring the system health for unexpected behavior. Assuming one cannot probe every point, within a system, the fault correlates to a region—not necessarily the specific location. Bayesian networks trained to understand fault patterns can accurately identify the source. The diagnostic tool described aides debugging by pinpointing system failure causes. For predictive maintenance, probe data develop probability distribution functions describing subsystem mean time to failure. Unit lifetime can be estimated through these probability distributions. Two approaches include using Bayesian classifiers to infer the system failure source and developing maintenance schedules by treating systems as collections of random variables. When failure behavior does not follow a closed form function, use of similarity models is proposed.
Inverter reliability remains one of the most persistent challenges limiting the performance, availability, and economic viability of utility‑scale photovoltaic (PV) plants. Industry data consistently show that inverters account for the highest share of corrective maintenance events and unplanned outages across PV fleets. These failures result in energy losses, increased O&M costs, and reduced confidence in long‑term solar asset performance. Motivated by these challenges, this project—Extending Component Lifetime and Improving Inverter Reliability (ECLAIIR)—was undertaken to systematically investigate inverter degradation and failure mechanisms, develop predictive maintenance capabilities, and establish data‑driven pathways to improve service life and reduce the Levelized Cost of Energy (LCOE) for large‑scale PV systems. The primary goal of the project was to identify pre‑failure signatures in string inverters using both lab‑based accelerated lifetime testing and field‑based data and to develop predictive maintenance algorithms that can anticipate inverter faults before they occur. Through collaboration with inverter testing laboratory, solar PV plant owner, and failure‑analysis experts, the project advanced the technical understanding of inverter reliability. By instrumenting inverters with thermistors, humidity sensors, power‑quality meters, and acoustic sensors, the research established how multiple sensing modalities can reliably detect deviations from normal behavior hours to days before failure. These findings substantially enhance scientific understanding of inverter failure kinetics and provide the PV industry with the most comprehensive cross‑OEM characterization of early‑stage failure indicators reported to date. Technically, the project demonstrated the effectiveness of predictive maintenance by developing and validating the PreDICT (Predictive Diagnostics of PV Inverters Using Condition Monitoring and Trend Analysis) framework—a multi‑layer diagnostic architecture combining peer‑to‑peer analytics, historical trend modeling, and advanced machine‑learning techniques such as the Sequential Conditional Variational Autoencoder (SCVAE). This predictive model achieved more than 90% accuracy in detecting pre‑failure conditions and provided up to four days of lead time before inverter failure in field scenarios. Economically, the project’s LCOE analysis showed that predictive maintenance can reduce lifetime energy losses and minimize corrective maintenance interventions. Modeling indicated that, depending on inverter failure rates and replacement timelines, predictive maintenance can significantly reduce LCOE impacts associated with inverter downtime: from as high as 19.4% under conventional maintenance strategies to 0.1%–10.17% when predictive analytics are adopted. These results confirm that predictive maintenance is both technically feasible and economically advantageous for utilities and plant operators. The project’s findings also have broad public benefit. By improving inverter reliability and reducing downtime, predictive maintenance directly increases electricity generation from existing PV assets. Enhanced reliability lowers operational costs for utilities, which can translate over time into lower energy costs for consumers. Furthermore, the project’s technical publications, conference presentations, and industry workshops ensure that knowledge gained is shared broadly across the solar industry, supporting workforce development and enabling utilities of all sizes to adopt modern asset‑health monitoring practices. The retrofitting case study and service‑life prediction framework further support informed decision‑making for aging PV fleets, helping operators extend system life and reduce electronic waste. In summary, the ECLAIIR project significantly advanced the state of knowledge on inverter degradation, demonstrated the technical and economic value of predictive maintenance, and delivered actionable tools and insights that support more reliable, cost‑effective, and sustainable PV plant operation. The outcomes of this project will continue to inform utility practices, guide inverter design improvements, and strengthen the long‑term performance of solar assets nationwide.
Advanced computational tools and techniques such as artificial intelligence and machine learning (AI/ML) can transform the nuclear power industry. This is necessary given that the economic viability of the existing fleet is in jeopardy and its labor-centric approach to operations and maintenance. Currently, AI/ML research is being undertaken for reactor system design and analysis including fault and accident prognosis, nuclear risk analysis such as plant safety and security evaluation, and plant operations and maintenance including predictive maintenance. Applications include both existing and advanced reactor technologies with the aim of improving operational and business efficiencies. Most every aspect of the organization can benefit, from instrumentation and control, to work planning, to human-machine interactions and business management. AI/ML in nuclear can simplify complex problems and produce more effective decision-making. Nonetheless, careful consideration must be given to the implementation of an AI/ML initiative. The aims of this research are to 1) review barriers to AI/ML adoption within the nuclear power industry, and 2) suggest potential solutions. These barriers are organized along five distinct categories (Figure 1) that are interconnected. The first are historical barriers that track the industry’s development over the decades including worldwide nuclear events that shaped public perceptions. The resulting federal scrutiny and intense safety culture that emerged are discussed. Technical barriers to AI/ML adoption are considerable, and include data privacy concerns, data governance, and the current lack of AI/ML expert knowledge at the plants. The main business case barrier remains cost, but an absence of an industry-wide vision and wide-scale adoption also produces reluctance. Stakeholder readiness is reviewed with special attention given to regulatory readiness. The 5-year strategic plan for AI readiness recently published by the U.S. Nuclear Regulatory Commission is highlighted. Last, adoption barriers at the user level are addressed including the importance of user experience and explainable AI. The AI adoption barriers described here are inter-related and ideally should be addressed in a holistic fashion.
Hot Labs are used in the nuclear industry for various purposes: maintenance of nuclear reactor, sampling and testing of fuel, inspection activities and decommissioning. Despite their vast use, their current designs and operations do not meet entirely today's needs and requirements of the operations nor tomorrow's. This paper will give an overview of the research and investigations performed around Hot Cells design and concept in order to integrate new operability modes and functions. The overall idea is to bring modularity, flexibility and adaptability to the Hot Lab nuclear industry. Taking the key principles of Model Based System Engineering, an interoperable data model, the most advanced digital technologies (Building Information Modelling - BIM, Virtual Reality / Augmented Reality, Artificial Intelligence), and looking at all the life-cycle of such a facility, a concept design of a new type of Hot Lab has been developed. Four mains aspects are implemented during this study: Implement the principles of the Industry 4.0; use modular and flexible solutions; explore the concept of in service maintenance and predictive maintenance; optimise the decommissioning and dismantling process by taking into account the entire life-cycle of the facility. The design was developed as a case study taking several assumptions to adapt to any project. The design developed demonstrates that modularity and flexibility can be brought in without compromising the core safety functions of such a facility. This Hot Lab concept brings the current Hot Lab to the next level as the design has been adapted to meet the current operational needs, implement novel ideas and consider its entire life-cycle. This paper will demonstrate how decommissioning and dismantling operations can become more efficient and safer with such a concept. In addition, the Model Based System Engineering approach used from the beginning of the design phase allows to have an optimum architecture during its entire lifetime. It also allowed to flag new topics to be further developed for the benefit of the nuclear industry as a whole. A first example would be the development of the Control System using digital tools and artificial intelligence to run remotely controlled equipment inside the Hot Lab. Assystem is an international engineering group. As a key participant in the nuclear industry for over 50 years, the Group supports its clients in managing their capital expenditure throughout their asset life-cycles. Assystem can offer support in project management, design, digital engineering, industrial control systems, security and safety and industrial digitalisation. Assystem's Imagine program is an internal program intending to serve as an incubator for the development of innovations. The Innovative Hot Lab project integrates one of the four innovation projects Assystem choose to develop and invest in. (authors)
System-level prognostics is crucial for ensuring reliability and enabling predictive maintenance in complex systems with interconnected components. This study presents a framework that integrates data-driven methods to predict the remaining useful life (RUL) of a subsystem under multiple and concurrent faults within a nuclear power plant system with explainable artificial intelligence (XAI). A nuclear power plant (NPP) operation was simulated to model the degradation behavior of NPP components, and four machine learning models—Gradient Boosting Regressor (GBR), Support Vector Regressor (SVR), Fully Connected Neural Network (FCNN), and Long Short-Term Memory (LSTM)—were evaluated for prognostics with a novel system RUL parameter. The LSTM model demonstrated potential superior repeatability, while SHAP (SHapley Additive exPlanations) for explainability provided consistent and trustworthy global explanations. In contrast, LIME (Local Interpretable Model-agnostic Explanations) offered localized interpretability but showed reduced stability for sequential data. Key findings include the interplay between component-level degradation and system-wide performance, with LSTM effectively capturing these dynamics through sequence-level predictions. The XAI techniques enhanced transparency by identifying critical features influencing model predictions and aligning with domain knowledge. Furthermore, this framework has significant implications for improving trust and understanding in predictive maintenance, particularly in safety-critical industries like nuclear energy.
The project delivers a well-integrated and validated simulation platform for cycling operation analysis in coal-fired power plant. Two critical mechanical components of the boiler island were analyzed through mechanical integrity assessment and economic benefit analysis. The current phase of the project focuses on the development of the integrated simulation infrastructure and prove its feasibility and effectiveness using two typical use cases. This integrated platform can help save a lot of engineering efforts for model development and simulation analysis. Through the real simulation scenarios in this document, it was demonstrated that using this platform, an analysis can be completed in approximately 2 days, while it could cost several weeks before using this platform. Going forward, the platform built in this project can be used for more boiler service applications, and it can be further enhanced with more functions/features to maximize its usage and benefits. 1) Extend component-level analysis with more use cases to cover all the major critical components of boiler island under cycling operations. A library of critical components can be developed and validated for typical pulverized coal-fired subcritical boiler units. 2) Develop predictive maintenance features based on the integrated models (Digital Twins) and engineering analysis procedures. Predictive maintenance enables each asset to be serviced based on forecast on life consumption and cost profile for replacing/welding the critical mechanical parts of the boiler. This minimizes the chance of unscheduled shutdowns and emergency services at much higher costs and prevent the fatal accidents in unit operations. 3) Develop and maintain a standard library for critical component analysis under flexible plant operations, which will include libraries of: process models, MI models for typical pressure parts, and economic models with typical plant operating data and ISO power trade data.
This paper summarizes research that integrates condition monitoring and prognostics with decision making for nuclear power plant operations and maintenance. As part of this research, we have developed an online asset management tool to help reduce life-cycle maintenance and repair costs. Using the latest advancements in condition monitoring, supply chain analytics, and deep reinforcement learning, we have created a predictive maintenance tool that can optimize the maintenance and spare-part management of a repairable nuclear system. To demonstrate these methods, preliminary studies were conducted on a simple, representative maintenance system undergoing a stochastic degradation process that requires repairs or replacement to continue operation. Through Monte Carlo simulations, we were able to reduce maintenance spending by approximately 50% compared to optimized, time-based maintenance strategies. Not only does the decision maker reduce the average life-cycle costs, it also minimizes the chance of high cost scenarios, lowering the variance of the expected cost distributions, and reducing overall financial risk. Furthermore, this work also studies the ability of the decision maker to handle various levels of noise from observation uncertainty. By introducing uncertainty into the decision-making process, we have quantified the robustness and resiliency of the decision maker, as well as identified necessary levels of observability to demonstrate cost effectiveness.
One of the major contributors to the total operating costs of domestic nuclear fleet of reactors today is the operation and maintenance (O&M) costs. These include labor-intense preventive maintenance programs involving manually-performed inspection, calibration, testing, and maintenance of plant assets at periodic frequency and time-based replacement of assets at periodic frequency, irrespective of their conditions. This has resulted in a labor-centric business model to achieve high capacity factors. To build an optimal maintenance program, it’s time to transition from this labor-centric business model to a technology-centric business model. Fortunately, there are technologies (advanced sensor, data analytics, and risk assessment methodologies) that will support this transition. The technology-centric business model will result in significant plant life extension and reduction of time-based maintenance activities. This will drive down O&M costs as labor is a rising cost and technology is a declining cost. This approach will lay the foundation for real-time condition assessment of plant assets, allowing condition-based maintenance to enhance plant safety, reliability, and economics of operation. The goal of this project is to address challenges in the area of digital monitoring, i.e., the application of advanced sensor technologies (particularly wireless sensor technologies) and science-based data analytic capabilities to advance online monitoring and predictive maintenance in nuclear plants to improve plant performance (efficiency gain and economic competitiveness). To achieve the project goal, in partnership with Exelon Generating Company (Exelon), researchers from Idaho National Laboratory (INL) and Oak Ridge National Laboratory (ORNL) are performing research and development (R&D) to demonstrate application of wireless sensors using the distributed antenna system and advanced data analytics to achieve predictive maintenance. In the report, wireless vibration sensors, vibration data and its indicator are described. The wireless vibration sensors presented in this report support three types of wireless communication, namely, Wi-Fi, cellular, and 900 MHz. These wireless vibration sensors are considered by partner plant site for installation on plant asset to enable online vibration monitoring to replace periodic measurements. These vibration data along with other plant process data will be utilized to develop diagnostic and prognostic models.
This report describes the research results to date to identify regulatory implications of DT technologies and their uses. Specifically, this report reviews current regulatory guidance relevant to the application of predictive maintenance DTs, artificial intelligence (AI), and automation. The focus of this review included determination of constraints on the application of DT technology, identification of any regulatory gaps or uncertainties, and clarification of anticipated technical basis information likely to be important for regulatory acceptance of these technologies. The research included review of topical reports and other submissions to the US Nuclear Regulatory Commission (NRC) on technologies relevant to using DTs for predictive maintenance, NRC safety evaluation (SE) reports, and other relevant literature to identify specific regulatory concerns.
Accurate drive mode classification is essential for enhancing the reliability and predictive maintenance of heavy-duty electric trucks. This study proposes a novel fuzzy logic-based framework, DriveSense, for real-time drive mode classification, addressing key challenges such as sensor noise, transitional behaviors, and computational efficiency. The proposed approach integrates a two-stage filtering pipeline, combining adaptive outlier removal and a dynamic Kalman filter to enhance data quality. A fuzzy inference system with smoothened trapezoidal membership functions is then applied to classify driving modes into standstill, constant speed, acceleration, and deceleration while mitigating the effects of noise and edge cases. Performance evaluation using real-world and simulated drive cycles demonstrates significant improvements in classification accuracy (up to 97.8%), F1-score (up to 0.97), and robustness against noise, while reducing false positives. Comparative analysis against baseline models, demonstrates DriveSense’s superior accuracy and generalizability across diverse driving patterns. The framework’s lightweight and interpretable fuzzy inference engine operates with low computational latency, ensuring compatibility with real-time embedded systems typical of heavy-duty electric trucks. Moreover, DriveSense models transitional behaviors through overlapping fuzzy sets and adaptive borderline classification logic, enabling smooth identification of subtle shifts such as rolling stops or gradual deceleration. These results highlight DriveSense’s potential to enhance predictive maintenance strategies, reduce downtime, and support scalable, fleet-wide diagnostics.
The US Department of Energy’s SunShot goals look to reduce the cost of Concentrating Solar Power (CSP) technology to 5¢/kWh for baseload plants. This is about a 50% reduction from current costs. To achieve this cost target, a significant reduction in operation and maintenance (O&M) costs of 40 to 50% is likely needed. Advances are needed in the O&M practices of CSP plants if the technology is to achieve the SunShot cost goals. Digitization of plant performance and O&M data has become a new best practice in the world of renewable energy asset management. Owners and operators of large photovoltaic and wind power plants are working to digitize performance and O&M data at their existing assets, to improve their management of the facilities, to increase performance, reduce O&M costs, and lower the overall life cycle cost of ownership. CSP power plants are behind the curve of other technologies on the digitization of plant information to aid in the plant asset management. This project directly addresses the objective of digitizing the O&M data of the solar field, focusing on three areas: 1) creating a framework for sharing data and information, 2) creating a system for monitoring and managing the maintenance of the solar field collectors, and 3) developing analytic tools to identify issues in the solar field. According to the NREL CSP Best Practices Study, the current practice at many CSP plants is to rely on paper lists, spreadsheets, and email for monitoring and managing problems and maintenance in the solar field. The key element to digitize solar field O&M is the creation of a centralized data archive that all users and systems can interface with. This project developed a centralized relational database framework that allows users and applications to access and share data. Conventional power plants utilize Computerized Maintenance Management Systems (CMMSs) to track the corrective, preventive (scheduled), and predictive maintenance of equipment and subsystems in the power plant. CSP plants use these systems in the power block, but while these systems specialize at tracking maintenance on up to thousands of pieces of equipment, they are not well suited for tracking the tens or hundreds of thousands of components in large commercial CSP or photovoltaic solar fields. In this project we developed a new software application referred to as FieldStatus (TM). This is a specialized database program that is used to track the status of each collector and its components. This application is designed to complement the existing CMMS to enable improved tracking and management of maintenance activities in the solar field. One of the major maintenance tasks for solar fields is maintaining the cleanliness of the mirrors. Although seemingly a relatively straight forward task, it has often proven challenging to maintain high levels of cleanliness in an efficient and cost-effective manner. This project developed new tools and metrics for monitoring and optimizing solar field cleaning resources and overall solar field cleanliness.