Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Predictive Maintenance”

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.

At least 145 records · Page 8

SAFARI - Secure Automation For Advanced Reactor Innovation (Final Technical Report)

The Secure Automation For Advanced Reactor Innovation (SAFARI) project was a pioneering initiative aimed at fundamentally changing how nuclear power plants are operated and maintained. Recognizing that current nuclear plants often rely on extensive manual procedures and large staffs, leading to higher costs compared to other energy sources like natural gas, SAFARI sought to introduce smart, automated technologies to make nuclear energy more efficient, cost-effective, and safer. This report details the research and development efforts of the SAFARI project, bringing us closer to a future where advanced nuclear reactors can operate more autonomously, adapt flexibly to energy demands, and predict their maintenance needs before issues arise. One of the key achievements of the SAFARI project is its contribution to our understanding of how Artificial Intelligence (AI) and sophisticated computer models, known as Digital Twins, can be effectively integrated with the complex physics of nuclear reactors.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Early Fault Detection in Particle Accelerator Power Electronics Using Ensemble Learning

Early fault detection and fault prognosis are crucial to ensure efficient and safe operations of complex engineering systems such as the Spallation Neutron Source (SNS) and its power electronics (high voltage converter modulators). Following an advanced experimental facility setup that mimics SNS operating conditions, the authors successfully conducted 21 early fault detection experiments, where fault precursors are introduced in the system to a degree enough to cause degradation in the waveform signals, but not enough to reach a real fault. Nine different machine learning techniques based on ensemble trees, convolutional neural networks, support vector machines, and hierarchical voting ensembles are proposed to detect the fault precursors. Although all 9 models have shown a perfect and identical performance during the training and testing phase, the performance of most models has decreased in the next test phase once they got exposed to realworld data from the 21 experiments. The hierarchical voting ensemble, which features multiple layers of diverse models, maintains a distinguished performance in early detection of the fault precursors with 95% success rate (20/21 tests), followed by adaboost and extremely randomized trees with 52% and 48% success rates, respectively. The support vector machine models were the worst with only 24% success rate (5/21 tests). The study concluded that a successful implementation of machine learning in the SNS or particle accelerator power systems would require a major upgrade in the controller and the data acquisition system to facilitate streaming and handling big data for the machine learning models. In addition, this study shows that the best performing models were diverse and based on the ensemble concept to reduce the bias and hyperparameter sensitivity of individual models.

43 PARTICLE ACCELERATORS↗

On the Formalization of Development and Assessment Process for Digital Twins in the Nearly Autonomous Management and Control System

In recent years, the autonomous control system has been encouraged in advanced reactors for restoring economic viability, simplifying the operation and maintenance, and enabling remote-site power generations [1]. Since the reactor is expected to be operated for a long period of time with a limited number of individuals onsite, it is recommended that the autonomous control system should have access to very realistic models of the state of processes in the whole lifecycle, together with these process behaviors in interaction with their environment in the real world. As a result, digital twin (DT) technology is suggested in autonomous control systems. DT is defined as a digital representation of a physical object or system, which contains a record for the histories of loads, operation and maintenance status, predictions for the near-term transient of important state variables, and decision-making process [2]. Since machine learning (ML) can recognize patterns within a complex system in real-time applications, it has been used to build DTs in the autonomous control systems for advanced reactors. Meanwhile, due to the rareness of operation data in accident scenarios, the development and assessment of DTs is expected to be mainly driven by simulations. Although the capability and feasibility of ML-based DTs are recognized in improving the safety and efficiency of reactor control, a major concern from the regulatory commission and the nuclear industry is whether the information from a DT is developed and assessed in accordance with expectation and requirements by the target decision. Such concerns not only affect the acceptance criteria for DTs, but also values that can be extracted from DTs and autonomous control system during operations. Inspired by the success of formal methods in improving the reliability and robustness of computer programming and software development, it is suggested that the development and assessment process (DAP) for both separate DTs and integral control system should be formalized in a transparent, consistent, and improvable manner. In this study, a digital-twin development and assessment process (DT-DAP) is proposed by adapting the evaluation model development and assessment process (EMDAP) [3] to requirements by the autonomous control system, ML algorithms, and DT technology. To demonstrate the framework, a baseline nearly autonomous management and control (NAMAC) system with ML-based DTs for diagnosis and prognosis is developed and assessed based on the framework. It is found that with selected testing methods and techniques, the DT-DAP can help identify errors in DTs and NAMAC which would otherwise be left unverified. Meanwhile, it is found that the DT-DAP can improve the DTs and NAMAC by continuously learning and iterating through different elements.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Low-cost Retrofit Kit for Integral Reciprocating Compressors (IRCs) to Reduce Emissions and Enhance Efficiency

Methane emissions from natural gas engines within the oil and gas industry pose a significant environmental challenge, contributing approximately 34.1 MMTCO2 eq to the total of 239 MMTCO2 eq of methane emissions in 2021, according to the EPA report. In response to this pressing issue, a collaborative effort involving the University of Oklahoma and key industry partners—WAGO Automation, Mid Continental Rental, Elipsa, and Perscient—has resulted in the development of a retrofit kit designed to reduce emissions from integral reciprocating compressors (IRCs), which are integrated compressors and engines. The retrofit kit developed comprises an Air Management System (AMS), Integrated Sensors, and a Cloud-Connected Control Unit with Graphical User Interface (GUI)/Human-Machine Interface (HMI). This solution enhances operational efficiency, reduces emissions, and expands the operational envelope of IRCs in the natural gas industry. The project successfully completed all tasks, including the installation of a full-size IRC at a designated site in Oklahoma, the development of an optimized AMS, integration of sensors, and implementation of a data acquisition system. Significant achievements include a notable reduction in CH 4 emissions, up to 84% at specific loads, and the successful deployment of the retrofit kit in diverse field conditions. The system's capabilities were enhanced through the creation of a feedback control algorithm for the AMS using a correlation matrix illustrating relationships between engine parameters, and the design of a predictive and preventive maintenance platform. The project concluded with the deployment of the entire retrofit kit to another location, confirming its effectiveness in reducing emissions and enhancing IRC performance. The comprehensive solution offers valuable benefits for IRCs, making them invaluable assets in the natural gas industry.

03 NATURAL GAS↗

Investigation of Multiple Data Streams for Gearbox Bearing Fault Prediction Through Machine-Learning Models

Operations and maintenance (O&M) cost of wind plant accounts up to 30% of total energy cost, which can be reduced through continuous monitoring and successfully detecting incipient wind turbine failures. To accomplish this, condition monitoring and predictive maintenance systems are being implemented in wind industry to support O&M decision making. A wide range of approaches for condition monitoring and fault prediction have been developed. These approaches generally use historical data of wind turbines collected by Supervisory Control and Data Acquisition (SCADA) system to identify patterns that lead to failure. These SCADA data show the overall condition of a wind turbine and can be leveraged to detect when the turbine's performance is degrading and to identify if a fault is developing. However, it becomes challenging to predict the failure of a specific wind turbine gearbox bearing, because the SCADA data are often not directly linked to the component. To bridge the gap, we have investigated features calculated from SCADA data using physics-based models and the gearbox design over the years. The damaged metric we used in the physics domain is frictional energy. Combining these physics domain variables with SCADA data as inputs to various machine learning models for gearbox bearing fault prediction, we have demonstrated the benefits of leveraging both physics and data domain models. It was an attempt to improve frictional-energy-based damage metric by adding data domain inputs, as we had learned that the frictional-energy-based damage metric alone is not sufficient to single out failed bearings from healthy. As condition monitoring data (either vibration or oil debris data) has become available at more and more wind plants, we would like to evaluate whether by adding the condition monitoring data can help further improve the performance of frictional-energy-based damage metric for gearbox bearing fault prediction. Both cases by modeling through various machine learning algorithms are discussed in this study along with some observations.

fault prediction↗

Regulatory Considerations for Nuclear Energy Applications of Digital Twin Technologies

Digital twins (DTs) in complex industrial and engineering applications have potential benefits that include increased operational efficiencies, enhanced safety and reliability, improved security engineering, reduced errors, faster information sharing, and better predictions. The interest in DT technologies continues to grow, and many of these advanced technologies are expected to experience rapid and wide industry adoption in the near future. Some of the potential application areas for DTs in the nuclear industry are design, licensing, plant construction, training simulators, predictive operations and maintenance, autonomous operation and control, failure and degradation prediction, physical protection modeling and simulation, and safety and reliability analyses. The Office of Nuclear Regulatory Research at the U.S. Nuclear Regulatory Commission (NRC) has initiated a future-focused research project to assess the regulatory viability of DTs for nuclear power plants and other NRC-regulated activities, such as fuel cycle facilities and operations. This report explores the potential impact of DT technologies in nuclear applications on NRC-regulated activities of interest. This report describes a nuclear DT system and its capabilities for nuclear power plant applications, followed by identification and discussion of some regulated activities that merit special consideration and present opportunities in implementing DT-enabling technologies and capabilities.

99 GENERAL AND MISCELLANEOUS↗

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (4th Annual Report)

Nuclear plant sites collect and store large volumes of data collected 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 and artificial intelligence technologies to provide diagnostic and prognostic capabilities within the nuclear power industry to reduce operating and maintenance costs. In this way, nuclear energy can become more economically competitive with other energy sources, and premature closures can be avoided. From a maintenance standpoint, savings can be achieved by leveraging machine learning and artificial intelligence technologies to develop data-driven algorithms to better diagnose and predict potential faults within the system. Improved model accuracy can lead to reductions in unnecessary maintenance and more efficient planning of future maintenance, thus lowering the costs associated with parts, labor, and unnecessary planned, forced, or extended outages. From an operations perspective, cost savings can be generated by shifting from route-based monitoring to wireless technologies for online monitoring, and by transitioning from onsite- to cloud-based computing and storage services. Wireless monitoring would reduce the 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 report summarizes this project’s effort to shift from costly, labor-intensive preventative maintenance to cheaper predictive maintenance.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

A survey on degradation modeling, prognosis, and prognostics-driven maintenance in wind energy systems

Wind energy generation proliferated over the past decades, introducing unique challenges and opportunities for failure prediction, operation and maintenance. Decision-makers are continuously looking into new methods to infer failure mechanisms and behaviors of wind turbine components to detect and intervene in the failures before they happen. Evidently, degradation modeling and prognosis become engaging topics for researchers and practitioners to prevent catastrophic failures. Prognostics-driven approaches predict the time of failure for the components (e.g., predicting remaining useful life), which provides significant insights for scheduling of operations and maintenance activities. Integrating these prognostics-driven insights into wind farm operations and maintenance presents a substantial challenge, demanding careful consideration of numerous factors such as accessibility, crew routing, and spare part logistics. This study provides state-of-the-art review for degradation modeling, prognosis, and prognostics-driven maintenance techniques for wind energy systems. The discussed techniques align with the United Nations' sustainable development goals, in particular Goal 7 (Affordable and Clean Energy), by enhancing effectiveness and sustainability of wind energy operations. This work also showcases open research questions related to degradation modeling, prognosis, and prognostics-driven maintenance.

Altinpulluk, Nur Banu↗

Hydrogen Component Leak Rate Quantification for System Risk and Reliability Assessment through QRA and PHM Frameworks: Preprint

The National Renewable Energy Laboratory's (NREL) Hydrogen Safety Research and Development (HSR&D) program in collaboration with the University of Maryland's Systems Risk and Reliability Analysis Laboratory (SyRRA) are working to improve reliability and reduce risk in hydrogen systems. This approach strives to use quantitative data on component leaks and failures, together with Prognosis and Health Management (PHM), and Quantitative Risk Assessment (QRA) to identify at-risk components, reduce component failures and downtime, and predict when components require maintenance. Hydrogen component failures increase facility maintenance cost, facility downtime, and reduce public acceptance of hydrogen technologies, ultimately increasing facility size and cost because of potentially overly conservative requirements. Leaks are a predominant failure mode for hydrogen components. However, uncertainties in the amount of hydrogen emitted from leaking components and the frequency of those failure events limit the understanding of the risks that they present under real-world operational conditions. NREL has deployed a test fixture, the Leak Rate Quantification Apparatus (LRQA), to quantify the mass flow rate of leaking gases from medium and high-pressure components that have failed while in service. Quantitative hydrogen leak rate data from this system could ultimately be used to better inform risk assessment and Regulation Codes and Standards (RCS). Parallel activity explores the use of PHM and QRA techniques to assess and reduce risk, thereby improving safety and reliability of hydrogen systems. The results of QRAs could further provide a systematic and science-based foundation for the design and implementation of RCS, as in the latest versions of the NFPA 2 code for gaseous hydrogen stations. Alternatively, data-driven techniques of PHM could provide new damage diagnosis and health-state prognosis tools. This research will help end users, station owners and operators, and regulatory bodies move towards risk-informed preventative maintenance versus emergency corrective maintenance, reducing cost and improving reliability. Predictive modelling of failures could improve safety and affect RCS requirements such as setback distances at liquid refuelling sites. The combination of leak rate quantification research, PHM, and QRA can lead to better informed models enabling data-based decision to be made for hydrogen system safety improvements.

codes and standards↗

Risk-informed Predictive Analytics To Achieve Cost-effective Condition-based Monitoring And Maintenance Strategy

The research involves developing risk-informed predictive analytic capabilities to achieve condition-based monitoring and maintenance strategies to reduce overall maintenance costs. The research utilizes data (real-time data, periodic data, and institutional knowledge) related to a particular plant asset from a specific nuclear plant site to develop risk-informed predictive analytic algorithms. The developed algorithms and codes are used to optimize the maintenance strategy and estimate/forecast generation costs based on the state of health of the plant asset. Developed codes specifically include 1. Parameter estimation code based on Bayesian inference 2. Statistical data analysis code 3. Feature engineering code 4. Health classifier code 5. Diagnosis code 6. Prognosis code 7. Hazard code 8. Generation risk code 9. Economic code

Agarwal, Vivek↗

Shot Planning and Analysis Tools

Shot planning and analysis tools (SPLAT) integrate components necessary to help achieve a high over-all operational efficiency of the National Ignition Facility (NIF) by combining near and long-term shot planning, final optics demand and supply loops, target diagnostics planning, and target fabrication requirements. Currently, the SPLAT project is comprised of two primary tool suites for shot planning and optics demand. The shot planning component provides a web-based interface to selecting and building a sequence of proposed shots for the NIF. These shot sequences, or 'lanes' as they are referred to by shot planners, provide for planning both near-term shots in the Facility and long-term 'campaigns' in the months and years to come. The shot planning capabilities integrate with the Configuration Management Tool (CMT) for experiment details and the NIF calendar for availability. Future enhancements will additionally integrate with target diagnostics planning and target fabrication requirements tools. The optics demand component is built upon predictive modelling of maintenance requirements on the final optics as a result of the proposed shots assembled during shot planning. The predictive models integrate energetics from a Laser Performance Operations Model (LPOM), the status of the deployed optics as provided by the online Final Optics Inspection system, and physics-based mathematical 'rules' that predict optic flaw growth and new flaw initiations. These models are then run on an analytical cluster comprised of forty-eight Linux-based compute nodes. Results from the predictive models are used to produce decision-support reports in the areas of optics inspection planning, optics maintenance exchanges, and optics beam blocker placement advisories. Over time, the SPLAT project will evolve to provide a variety of decision-support and operation optimization tools.

42 ENGINEERING↗

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (3 rd Annual Report)

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This report primarily focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 ± 0.014, 0.0026 ± 0, and 0.063 ± 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure. This report summarizes the Fiscal Year 2021 research progress encompassing the (1) data cleaning and feature selection necessary for ML applications; (2) development of short-term forecasting models to predict future plant process parameters for both single and multiple time steps ahead; and (3) validation of the feature selection methods and short-term forecasting models given new data from different systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗