SEARCH · Engineering Papers

Results for “Fault Detection and Diagnostics”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17

All sources NASA NTRS DOE OSTI

NASA NTRS2007

NASA Glenn Research in Controls and Diagnostics for Intelligent Aerospace Propulsion Systems

With the increased emphasis on aircraft safety, enhanced performance and affordability, and the need to reduce the environmental impact of aircraft, there are many new challenges being faced by the designers of aircraft propulsion systems. The Controls and Dynamics Branch (CDB) at NASA (National Aeronautics and Space Administration) Glenn Research Center (GRC) in Cleveland, Ohio, is leading and participating in various projects in partnership with other organizations within GRC and across NASA, the U.S. aerospace industry, and academia to develop advanced controls and health management technologies that will help meet these challenges through the concept of Intelligent Propulsion Systems. This presentation describes the current CDB activities in support of the NASA Aeronautics Research Mission, with an emphasis on activities under the Integrated Vehicle Health Management (IVHM) and Integrated Resilient Aircraft Control (IRAC) projects of the Aviation Safety Program. Under IVHM, CDB focus is on developing advanced techniques for monitoring the health of the aircraft engine gas path with a focus on reliable and early detection of sensor, actuator and engine component faults. Under IRAC, CDB focus is on developing adaptive engine control technologies which will increase the probability of survival of aircraft in the presence of damage to flight control surfaces or to one or more engines. The technology development plans are described as well as results from recent research accomplishments.

Garg, Sanjay↗

DOE OSTI2020

Cell degradation quantification—a performance metric-based approach

A safe and reliable battery operation needs effective diagnostic tools. A quantitative failure analysis (FA) to enable cell qualification and quantify its effectiveness for reliable and safe operation of rechargeable Li batteries (RLB) is shown here. The method can identify and quantify potential failure based on the state of charge (SOC) under any operating conditions. A precise and accurate electrochemical analytic diagnosis (eCAD) of 14 rechargeable Li || NMC622 cells of the same build are used as an example. The FA by eCAD can quantitatively decipher good, bad and ugly cells in cycle aging. The cell qualification is based on thermodynamic SOC, not experimental conditions. The method provides a quantitative failure mode and effect analysis (FMEA) to reveal diverse “dead Li” formation that affects the reversibility of the Li anode and charge retention in the cell. This cell qualification method highlights the potential to improve cell quality for safe operation, with strong implications for early fault detection, FA, risk mitigation, state estimation and life prediction for reliable and safe RLB operations

25 ENERGY STORAGE↗

DOE OSTI2026

Automating Detection and Diagnosis of Faults, Failures, and Underperformance in PV Plants

The project developed hybrid physics-based and machine-learning methods for near-real-time detection of balance-of-system faults (e.g., string, combiner, and tracker outages) in utility-scale Photovoltaic plants, achieving over 50% true positive rates with under 10% false positives and significantly reducing engineering setup time. In the extended phase, the scope expanded to plant-level underperformance analysis and industry benchmarking through the SUPER.epri.com platform. SUPER standardizes data processing and performance metrics across more than 9 GWac and 120+ plants, enabling robust comparisons and insights into loss rates, inverter downtime, and capacity degradation.

14 SOLAR ENERGY↗

NASA NTRS2013

Vibration Based Sun Gear Damage Detection

Seeded fault experiments were conducted on the planetary stage of an OH-58C helicopter transmission. Two vibration based methods are discussed that isolate the dynamics of the sun gear from that of the planet gears, bearings, input spiral bevel stage, and other components in and around the gearbox. Three damaged sun gears: two spalled and one cracked, serve as the focus of this current work. A non-sequential vibration separation algorithm was developed and the resulting signals analyzed. The second method uses only the time synchronously averaged data but takes advantage of the signal/source mapping required for vibration separation. Both algorithms were successful in identifying the spall damage. Sun gear damage was confirmed by the presence of sun mesh groups. The sun tooth crack condition was inconclusive.

diagnostics↗

DOE OSTI2024

Power Module Precursors and Prognostics

This project focuses on finding and utilizing electrical properties (precursors) of power electronic devices and modules whose changes have strong correlations with different modes and levels of degradations in order to realize online and lightweight state of health evaluation and fault diagnosis. Results from this project will contribute to higher safety, reliability, and power density of power electronic components. The approaches mainly include reviewing academic literature and industry practices for state of the art precursor identification and extraction, accelerated life cycles (ALC) of various power modules to create different degradations in-house, and developing techniques for gate-driver-integratable precursor detection circuit. In FY24, the results includes two sets of definitively detected aging precursors (on-state resistance and gate threshold voltage) for two sets of power modules respectively, controlled accelerated lifetime cycling of multiple silicon carbide (SiC) metal-oxide-semiconductor field-effect transistor (MOSFET) modules, and the development and validation of a gate voltage detection system.

ADVANCED PROPULSION SYSTEMS↗

NASA NTRS2007

Hybrid Automated Diagnosis of Discrete/Continuous Systems

A recently conceived method of automated diagnosis of a complex electromechanical system affords a complete set of capabilities for hybrid diagnosis in the case in which the state of the electromechanical system is characterized by both continuous and discrete values (as represented by analog and digital signals, respectively). The method is an integration of two complementary diagnostic systems: (1) beacon-based exception analysis for multi-missions (BEAM), which is primarily useful in the continuous domain and easily performs diagnoses in the presence of transients; and (2) Livingstone, which is primarily useful in the discrete domain and is typically restricted to quasi-steady conditions. BEAM has been described in several prior NASA Tech Briefs articles: "Software for Autonomous Diagnosis of Complex Systems" (NPO-20803), Vol. 26, No. 3 (March 2002), page 33; "Beacon-Based Exception Analysis for Multimissions" (NPO-20827), Vol. 26, No. 9 (September 2002), page 32; "Wavelet-Based Real-Time Diagnosis of Complex Systems" (NPO-20830), Vol. 27, No. 1 (January 2003), page 67; and "Integrated Formulation of Beacon-Based Exception Analysis for Multimissions" (NPO-21126), Vol. 27, No. 3 (March 2003), page 74. Briefly, BEAM is a complete data-analysis method, implemented in software, for real-time or off-line detection and characterization of faults. The basic premise of BEAM is to characterize a system from all available observations and train the characterization with respect to normal phases of operation. The observations are primarily continuous in nature. BEAM isolates anomalies by analyzing the deviations from nominal for each phase of operation. Livingstone is a model-based reasoner that uses a model of a system, controller commands, and sensor observations to track the system s state, and detect and diagnose faults. Livingstone models a system within the discrete domain. Therefore, continuous sensor readings, as well as time, must be discretized. To reason about continuous systems, Livingstone uses monitors that discretize the sensor readings using trending and thresholding techniques. In development of the a hybrid method, BEAM results were sent to Livingstone to serve as an independent source of evidence that is in addition to the evidence gathered by Livingstone standard monitors. The figure depicts the flow of data in an early version of a hybrid system dedicated to diagnosing a simulated electromechanical system. In effect, BEAM served as a "smart" monitor for Livingstone. BEAM read the simulation data, processed the data to form observations, and stored the observations in a file. A monitor stub synchronized the events recorded by BEAM with the output of the Livingstone standard monitors according to time tags. This information was fed to a real-time interface, which buffered and fed the information to Livingstone, and requested diagnoses at the appropriate times. In a test, the hybrid system was found to correctly identify a failed component in an electromechanical system for which neither BEAM nor Livingstone alone yielded the correct diagnosis.

Park, Han↗

NASA NTRS2005

Instrumentation and Control Needs for Reliable Operation of Lunar Base Surface Nuclear Power Systems

As one of the near-term goals of the President's Vision for Space Exploration, establishment of a multi-person lunar base will require high-endurance power systems which are independent of the sun, and can operate without replenishment for several years. These requirements may be obtained using nuclear power systems specifically designed for use on the lunar surface. While it is envisioned that such a system will generally be supervised by humans, some of the evolutions required maybe semi or fully autonomous. The entire base complement for near-term missions may be less than 10 individuals, most or all of which may not be qualified nuclear plant operators and may be off-base for extended periods thus, the need for power system autonomous operation. Startup, shutdown, and load following operations will require the application of advanced control and health management strategies with an emphasis on robust, supervisory, coordinated control of, for example, the nuclear heat source, energy conversion plant (e.g., Brayton Energy Conversion units), and power management system. Autonomous operation implies that, in addition to being capable of automatic response to disturbance input or load changes, the system is also capable of assessing the status of the integrated plant, determining the risk associated with the possible actions, and making a decision as to the action that optimizes system performance while minimizing risk to the mission. Adapting the control to deviations from design conditions and degradation due to component failures will be essential to ensure base inhabitant safety and mission success. Intelligent decisions will have to be made to choose the right set of sensors to provide the data needed to do condition monitoring and fault detection and isolation because of liftoff weight and space limitations, it will not be possible to have an extensive set of instruments as used for earth-based systems. Advanced instrumentation and control technologies will be needed to enable this critical functionality of autonomous operation. It will be imperative to consider instrumentation and control requirements in parallel to system configuration development so as to identify control-related, as well as integrated system-related, problem areas early to avoid potentially expensive work-arounds . This paper presents an overview of the enabling technologies necessary for the development of reliable, autonomous lunar base nuclear power systems with an emphasis on system architectures and off-the-shelf algorithms rather than hardware. Autonomy needs are presented in the context of a hypothetical lunar base nuclear power system. The scenarios and applications presented are hypothetical in nature, based on information from open-literature sources, and only intended to provoke thought and provide motivation for the use of autonomous, intelligent control and diagnostics.

Turso, James↗

NASA NTRS2014

Embedded Data Acquisition Tools for Rotorcraft Diagnostic Sensors

Rotorcraft drive trains must withstand enormous pressure while operating continuously in extreme temperature and vibration environments. Captive components, such as planetary and spiral bevel gears, see enormous strain but are not accessible to fixed instrumentation, such as a piezoelectric transducer. Thus, it is difficult to directly monitor components that are most susceptible to damage. This innovation is a self-contained data processing unit within a specialized fixture that installs directly inside the rotating pinion gear in the gearbox. From this location, it detects and transmits high-resolution prognostic data to a fixed transceiver. The sensor is based on microelectromechanical systems (MEMS) technology and uses innovative circuit designs to capture high-bandwidth data and transmit it wirelessly from inside an operational helicopter transmission. With Ridgetop's advanced MEMS-based sensor, researchers have, for the first time, been able to extract high-resolution acoustic signatures wirelessly from sensors within the transmission that would otherwise be muffled by background gear noises. Ridgetop's innovative instrument will help researchers perform dynamic analysis of gear interaction and develop improved designs for gear components. In addition, data from this instrument can be used to validate new algorithms that detect and predict faults based on external acoustic signatures, for prognostic purposes. The result of this work will be an improvement in safety, performance, and cost for future generations of rotating components.

Wagoner, Robert↗

DOE OSTI2026

Real-Time Detection of Charge Jumps in Superconducting Qubits with a Convolutional Neural Network

Ionizing radiation from cosmic rays and gammas can induce discontinuous jumps in the environmental charge of superconducting qubits (charge jumps), causing correlated errors that challenge fault-tolerant quantum computing while simultaneously providing a detection signature for quantum sensing applications. Current detection methods operate offline, introducing latency incompatible with in-the-loop qubit control. In this paper, an online detector of charge jumps for superconducting qubits, based on a dilated causal convolutional neural network (DCCNN) designed for in-the-loop deployment on the Quantum Instrumentation Control Kit (QICK) platform, is presented. The network is trained on synthetic Ramsey tomography scans generated from qubit templates measured at the Northwestern Experimental Underground Site (NEXUS) at Fermilab, and translated to FPGA firmware via hls4ml with ap_fixed$\langle 16,6 \rangle$ quantization, reaching a per-inference latency of $6.19 μ$s on the Zynq UltraScale+ RFSoC ZCU216. At this operating point the DCCNN matches the detection efficiency of the established offline $χ^2$ algorithm ($0.843 \pm 0.022$ vs. $0.866 \pm 0.020$ on $|Δq| \in [0.1, 0.5] e$ at matched false-positive rate), while requiring no per-qubit hyperparameter tuning. This shifts charge-jump detection from a post-hoc diagnostic to a control-loop primitive, enabling adaptive protocols that respond to radiation-induced events in situ, with applications to quantum-computing error mitigation and to the use of superconducting qubits as particle detectors.

Gaytan-Villarreal, Daniel [Carnegie Mellon U.]↗

NASA NTRS2008

Instrumentation System Diagnoses a Thermocouple

An improved self-validating thermocouple (SVT) instrumentation system not only acquires readings from a thermocouple but is also capable of detecting deterioration and a variety of discrete faults in the thermocouple and its lead wires. Prime examples of detectable discrete faults and deterioration include open- and short-circuit conditions and debonding of the thermocouple junction from the object, the temperature of which one seeks to measure. Debonding is the most common cause of errors in thermocouple measurements, but most prior SVT instrumentation systems have not been capable of detecting debonding. The improved SVT instrumentation system includes power circuitry, a cold-junction compensator, signal-conditioning circuitry, pulse-width-modulation (PWM) thermocouple-excitation circuitry, an analog-to-digital converter (ADC), a digital data processor, and a universal serial bus (USB) interface. The system can operate in any of the following three modes: temperature measurement, thermocouple validation, and bonding/debonding detection. The software running in the processor includes components that implement statistical algorithms to evaluate the state of the thermocouple and the instrumentation system. When the power is first turned on, the user can elect to start a diagnosis/ monitoring sequence, in which the PWM is used to estimate the characteristic times corresponding to the correct configuration. The user also has the option of using previous diagnostic values, which are stored in an electrically erasable, programmable read-only memory so that they are available every time the power is turned on.

Perotti, Jose↗

NASA NTRS2015

Verification of Functional Fault Models and the Use of Resource Efficient Verification Tools

Functional fault models (FFMs) are a directed graph representation of the failure effect propagation paths within a system's physical architecture and are used to support development and real-time diagnostics of complex systems. Verification of these models is required to confirm that the FFMs are correctly built and accurately represent the underlying physical system. However, a manual, comprehensive verification process applied to the FFMs was found to be error prone due to the intensive and customized process necessary to verify each individual component model and to require a burdensome level of resources. To address this problem, automated verification tools have been developed and utilized to mitigate these key pitfalls. This paper discusses the verification of the FFMs and presents the tools that were developed to make the verification process more efficient and effective.

reliability↗

NASA NTRS2015

A Vehicle Management End-to-End Testing and Analysis Platform for Validation of Mission and Fault Management Algorithms to Reduce Risk for NASA's Space Launch System

The development of the Space Launch System (SLS) launch vehicle requires cross discipline teams with extensive knowledge of launch vehicle subsystems, information theory, and autonomous algorithms dealing with all operations from pre-launch through on orbit operations. The characteristics of these systems must be matched with the autonomous algorithm monitoring and mitigation capabilities for accurate control and response to abnormal conditions throughout all vehicle mission flight phases, including precipitating safing actions and crew aborts. This presents a large complex systems engineering challenge being addressed in part by focusing on the specific subsystems handling of off-nominal mission and fault tolerance. Using traditional model based system and software engineering design principles from the Unified Modeling Language (UML), the Mission and Fault Management (M&FM) algorithms are crafted and vetted in specialized Integrated Development Teams composed of multiple development disciplines. NASA also has formed an M&FM team for addressing fault management early in the development lifecycle. This team has developed a dedicated Vehicle Management End-to-End Testbed (VMET) that integrates specific M&FM algorithms, specialized nominal and off-nominal test cases, and vendor-supplied physics-based launch vehicle subsystem models. The flexibility of VMET enables thorough testing of the M&FM algorithms by providing configurable suites of both nominal and off-nominal test cases to validate the algorithms utilizing actual subsystem models. The intent is to validate the algorithms and substantiate them with performance baselines for each of the vehicle subsystems in an independent platform exterior to flight software test processes. In any software development process there is inherent risk in the interpretation and implementation of concepts into software through requirements and test processes. Risk reduction is addressed by working with other organizations such as S&MA, Structures and Environments, GNC, Orion, the Crew Office, Flight Operations, and Ground Operations by assessing performance of the M&FM algorithms in terms of their ability to reduce Loss of Mission and Loss of Crew probabilities. In addition, through state machine and diagnostic modeling, analysis efforts investigate a broader suite of failure effects and detection and responses that can be tested in VMET and confirm that responses do not create additional risks or cause undesired states through interactive dynamic effects with other algorithms and systems. VMET further contributes to risk reduction by prototyping and exercising the M&FM algorithms early in their implementation and without any inherent hindrances such as meeting FSW processor scheduling constraints due to their target platform - ARINC 653 partitioned OS, resource limitations, and other factors related to integration with other subsystems not directly involved with M&FM. The plan for VMET encompasses testing the original M&FM algorithms coded in the same C++ language and state machine architectural concepts as that used by Flight Software. This enables the development of performance standards and test cases to characterize the M&FM algorithms and sets a benchmark from which to measure the effectiveness of M&FM algorithms performance in the FSW development and test processes. This paper is outlined in a systematic fashion analogous to a lifecycle process flow for engineering development of algorithms into software and testing. Section I describes the NASA SLS M&FM context, presenting the current infrastructure, leading principles, methods, and participants. Section II defines the testing philosophy of the M&FM algorithms as related to VMET followed by section III, which presents the modeling methods of the algorithms to be tested and validated in VMET. Its details are then further presented in section IV followed by Section V presenting integration, test status, and state analysis. Finally, section VI addresses the summary and forward directions followed by the appendices presenting relevant information on terminology and documentation.

Trevino, Luis↗

NASA NTRSDate not supplied

Repurposing Drilling Control Diagnostics for Subsurface Edge Detection and Boundary Advisement During Planetary Drilling

Informed decision-making during lunar drilling and sampling missions will require data monitoring tools and specialized ground data systems. Accurate and updated situational awareness, with ongoing data monitoring, is critical for timely responses by to incoming science data. Traverse plans and scheduled activities may need to be flexibly changed in order to react to unexpected data or situations. Unlike (for example) Mars missions, the relative lightspeed closeness of the Moon allows for near-real-time ground processing of incoming mission and instrument data. An Apollo-class lunar regolith drill will in a sense “travel” a meter or two vertically at a given subsurface characterization site. As the drill penetrates into lunar regolith, it is likely to encounter a range of material densities, orientations, fracture toughness, and (perhaps) ice percentages. Lunar drill telemetry can provide science teams with a valuable first look into the subsurface structure, the regolith bulk properties, and constituents at each drilled site. Real-time AI-based recognition and reaction to downhole situations has been developed for automated deeper drilling on Mars and beyond. We can leverage the same knowledge bases and pattern-matching as areal-time interpreter of the subsurface, a situational awareness tool during drilling operations. We recently (Sept. 2019) demonstrated this AI drilling monitoring and analysis capability, in control of in-situ drilling and sampling operations, mounted on a KREX-2 rover in Chile’s Atacama Desert. Terrestrial automated drilling log analyses in oil exploration have used similar machine learning techniques in classifying and identifying features in drilling logs –but these typically are designed assuming a drilling fluid influencing downhole measurements and data (permeability, resistivity). Drilling models and existing AI software designed to detect and respond to drilling faults and hard materials can be repurposed, for near-real-time (ground-based) interpretation of drilling telemetry –a potentially valuable advisory tool for strata boundaries and changes in drilling parameters. On the Moon, this approach could be used to study the structure and to some extent the composition of lunar regolith vs. borehole depth, based on recognizable variations in fracture hardness, drilling energy and penetration rates while actively drilling. Since the early 2000s, a series of increasingly-capable real-time drilling telemetry interpretation and characterization software tools have been developed. These subsurface models and software tools have monitored the real-time drilling data received, and automatically identified changes in drill behavior (e.g., encountering a harder target layer, bit inclusions, drill choking due to infall downhole, and others) correlating these with subsurface structures and features. We discuss the mappings between drill borehole parameters, faults or events detected, and modeled changes in rock layer boundaries, in examples drawn from field testing at analog sites in an Arctic impact crater, Rio Tinto, and Chile’s Atacama Desert. These demonstrate how subsurface structural boundaries led to fault detections and responses by the software.

drilling advisor↗

DOE OSTI2024

A machine learning approach for particle accelerator errant beam prediction using spatial phase deviation

Particle accelerators are extremely complex systems that are expected to operate on high availability. Predicting impending failures only by utilizing data collected from diagnostic equipment already on board can help operators to avoid installing expensive sensors, unscheduled downtime and associated costs. For this purpose we explore the predictive power of Machine Learning algorithms to detect faulty beams prior to the failure. In this study, we propose a Machine Learning approach to model mapping from a pair of sensors located across the accelerator. While the model is trained to represent normal operation, we evaluate the predictive performance on known faulty beam pulses. We also investigate the model performance on unseen data through k-fold cross-validation. Then we recap the analysis with a neural architecture search and hyperparameter optimization study to fine tune our initial model. In conclusion, this paper will also introduce a sustainable framework that can standardize Machine Learning workflow applied to particle accelerators.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

NASA NTRS2026

AC and DC Fault Management for Megawatt Electrified Aircraft Electrical Powertrains Task 3: Lifetime and Reliability of Electrical Insulators

This research project was a collaborative investigation between researchers at the RTX Technology Research Center (RTRC) and the University of Texas at Austin and made a significant contribution to enabling electric aircraft. The transport of electric power between the points of generation and use requires power cables. These cables must be smaller, lighter and provide a more predictable life than power cables used in stationary applications. Consequently, this investigation provided heretofore unavailable information supporting the safety and reliability of smaller lighter power cables for electrified aircraft. In addition, the research identified key additional engineering data needed to support quantitative reliability assessments. Important advances included: • Demonstrated that at least one manufacturer can make a novel, smaller, lighter power cable that is free from serious defects. • Developed and published an appropriate analytical construct to describe the life of this novel cable. This is a necessary step for use in aviation where the understanding of remaining life is critical. • Demonstrated thermal-mechanical aging that suggested 1000+ flights before the thermal-mechanical processes produced defects large enough that the defect growth was accelerated electrically. • Showed that electrical aging took place at two rates. The first possibly lasting weeks to months and the second possibly days to weeks. If robust, this provides a good diagnostic for cable replacement. • Demonstrated that the traditional electrical testing of cable materials using manufactured voids can be misleading due to the size of the voids. Emerging laser drilling technology permitted demonstration that the physics of failure in realistically small voids is different from that in the unrealistically large voids used in earlier research, which is very important for high-quality, high-performance, small aircraft cables. Although this project represents a significant contribution to the specifics of cable aging in the aircraft environment, important additional research remains to be completed, including: • Non-uniform thermal cycling by applying the heat from the center conductor to maximize thermal stress next to the core area where the electric gradient is the strongest. This builds on the uniform thermal cycling that has been completed. • The augmentation of the thermal-mechanical failure rate by electrical processes. Better understanding of these time constants strongly affects the ability to predict life. • Termination design: Terminations provide not only electrical reflection potential, but a location for a series arc fault and an area where ozone can diffuse into the center conductor and negatively affect cable insulation. • The abrasion and ozone resistance of the cable jacket. • Pressure cycling as an accelerant of thermal, mechanical, and/or electrical aging. • Possible methods for online PD detection and offline PD localization

model↗

NASA NTRS1993

Knowledge From Pictures (KFP)

The old maxim goes: 'A picture is worth a thousand words'. The objective of the research reported in this paper is to demonstrate this idea as it relates to the knowledge acquisition process and the automated development of an expert system's rule base. A prototype tool, the Knowledge From Pictures (KFP) tool, has been developed which configures an expert system's rule base by an automated analysis of and reasoning about a 'picture', i.e., a graphical representation of some target system to be supported by the diagnostic capabilities of the expert system under development. This rule base, when refined, could then be used by the expert system for target system monitoring and fault analysis in an operational setting. Most people, when faced with the problem of understanding the behavior of a complicated system, resort to the use of some picture or graphical representation of the system as an aid in thinking about it. This depiction provides a means of helping the individual to visualize the bahavior and dynamics of the system under study. An analysis of the picture augmented with the individual's background information, allows the problem solver to codify knowledge about the system. This knowledge can, in turn, be used to develop computer programs to automatically monitor the system's performance. The approach taken is this research was to mimic this knowledge acquisition paradigm. A prototype tool was developed which provides the user: (1) a mechanism for graphically representing sample system-configurations appropriate for the domain, and (2) a linguistic device for annotating the graphical representation with the behaviors and mutual influences of the components depicted in the graphic. The KFP tool, reasoning from the graphical depiction along with user-supplied annotations of component behaviors and inter-component influences, generates a rule base that could be used in automating the fault detection, isolation, and repair of the system.

Truszkowski, Walt↗

DOE OSTI2021

Nuclear Power Fault Diagnostics and Preventative Maintenance Optimization NPIC presentation

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 primarily due to economic reasons, despite excellent safety records. Therefore, it is imperative to reduce costs in order to prevent these early closures. One of the contributors to these economic reasons is the large operations and maintenance costs. This paper showcases recent research on advanced fault diagnostics techniques and preventative maintenance optimization (PMO) for reducing NPP maintenance costs. Specifically, it 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 used to further differentiate the faulted data from the healthy data. Through a cross-validation procedure, support vectors machines were used to label other test sets of process data as either healthy or faulted. With relatively few faults identified in the BWR system, the potential for PMO opens up, since an unnecessary amount of PM leads to inflated maintenance costs. The steps for PMO are summarized, from component health determinations to recommendations for action. An example of PMO assessment is presented for condensate pumps, condensate booster pumps, and the respective motors that drive them.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2021

Performance Results for Sensor Assignment Problem as Solved on a Multi-Node Cluster

An earlier report described a procedure for optimal sensor set selection and its implementation on a computational cluster. This new and innovative capability was developed to facilitate a reduction in operations staffing levels to improve plant economics. By automating surveillance and maintenance tasks through early detection of degrading sensors and equipment, staff can be more efficiently deployed. The method uses automated reasoning and domain knowledge in the form of the conservation equations to infer from plant measurements the state of equipment health. Inclusion of domain knowledge addresses the problem that exists with pure data-driven methods that there are no rigorous guidelines for determining what constitutes an adequate sensor set. Formalizing the procedure for sensor set selection as we have done results in a more reliable and explainable diagnosis of plant equipment health. Importantly, from the standpoint of the plant owner, personnel are provided with an early and explicit diagnosis of an equipment problem. That in principle automates the process and eliminates having to send personnel into the plant to find the cause as typically occurs when a data-driven method detects an anomaly. In this report we describe first results obtained using a computational cluster to solve the sensor set selection problem as framed above. The case described addresses the problem of equipment health monitoring in the high-pressure (HP) feedwater system of a pressurized light water reactor as seen through the eyes of our collaborating utility partner. Maintenance of this system can amount to millions of dollars per year if equipment health issues go undiagnosed and lead to loss of function. On examining the potential that is inherent in the installed sensor set for diagnosing equipment health degradation, it was found that greater fault resolution capability can be achieved using a sensor set that is 20 percent fewer in number. The take-away is that compared to the installed sensor set there exists a more strategic assignment of sensors that will furnish better health monitoring capability and with fewer sensors. Where the problem defies solution by manual inspection, as is the case here, one can be found by an algorithm. The solution was obtained in four hours using 30 computational cores. The HP feedwater problem as posed above illustrates the added value of approaching the sensor selection problem as one amenable to algorithmic solution. This problem is of interest to advanced reactor designers and to utilities that are setting up remote monitoring and diagnostic centers.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗