Automated anomaly detection and identification can signal equipment issues pinpoint causes in large-scale industrial systems. For systems with limited failure history, unsupervised machine learning methods be utilized as they do not require past failures. This study introduces the leave-one-variable-out (LOVO) model, which masks one variable at a time to predict others, underlying process correlations. Detection performance was assessed synthetic experimental data, while used only data due...

We present potential approaches for implementing secure embedded intelligence (SEI) and integrated state awareness (ISA) in advanced nuclear energy (NE) systems. A framework deliberate design operations of such systems is provided, risks, challenges impacts discussed. Activities that should be carried out research, development, demonstration (RD&D) opportunities are identified. Resulting implications operation 'smart systems', including remote operations, flexible predictive maintenance,...

An operator-in-the-loop study was conducted in support of control room modernization for a nuclear power plant. The featured benchmark comparison on glass-top simulator three variants turbine system (TCS): (1) the existing analog TCS, (2) proposed stand-alone digital TCS with two displays, and (3) addition third display consisting overview screen. prototypes were developed to allow formative evaluation operator preferences performance during realistic scenarios full-scope simulator. revealed...

The operations and maintenance monitoring of nuclear power plants (NPPs) in the United States is reliant on manual activities supplying information to a human decision-making process. Several manually collected labor-intensive processes generate that not typically used beyond intended target for collecting information. industry has recognized benefits both reducing tasks by automating them increasing fidelity enable advanced remote NPPs using data-driven decision making. This requires...

Achieving full decarbonization of all economic sectors remains a challenge, especially in niche markets. For example, remote communities and industrial or mining activities detached from the main electric grid heavily rely on fossil fuels, similar to urban microgrids with combined heat power needs. A combination renewables energy storage is often not suitable due cost, reliability, intermittency, large requirements. Small nuclear reactors flexible purpose could serve these applications....

This paper examines the potential of embedded intelligence (EI) and resultant implications secure EI (SEI) integrated state awareness (ISA) as disruptors in advanced nuclear energy systems market. To this end, it reviews state-of-the-art other industries; discusses design trends, benefits, challenges, opportunities; addresses rigorous development SEI-driven approaches for achieving ISA smart functionalities (e.g., remote, flexible, and/or autonomous operations). It also defines concepts such...

Xenon (Xe) is a noble gas with an isotope (Xe-135) that has extremely high absorption cross section of neutrons moving at thermal energies. Xe-135 produced through chain decay isotopes resulting from nuclear fission, in addition to directly fission. The results phase lag between concentration and the neutron flux or power reactor. oscillations several hours delay set response To enable rapid load following reactors maximum one change per hour, frequency 2.7 × 10 <sup...

Data-driven anomaly detection over time series data is studied from the perspective of separating anomalies—corresponding to sensor failures—from process anomalies—that arise equipment or operational failures. A semi-supervised approach proposed that utilizes two predictive models trained on non-anomalous using different groups as inputs, and a nested hypothesis test reliably classify anomalies. Conditions are derived choice guarantee reliable detection, case study presented demonstrate...

This paper presents data-driven methods to detect loss-of-coolant accidents (LOCAs) in the primary side of a pressurized water reactor. Process data for variety accident scenarios have been generated and collected using generic reactor simulator. The used train kernel density functions, which estimate nonparametric probability functions based on training data. These then with Bayesian hypothesis testing maximum likelihood estimation onset LOCAs identify where leaks occurred. able all tested...

As part of the ongoing efforts at U.S. Department Energy's Light Water Reactor Sustainability Program, Idaho National Laboratory is conducting several research projects in collaboration with nuclear industry to improve reliability, safety, and economics power industry, especially as plants extend their operating licenses 80 years. One these automated work package (AWP) project. An AWP an electronic intelligent interactive package. It uses plant condition, resources status, user progress...

During irradiation, the fuel-cladding interface of a nuclear fuel rod can experience significant mechanical and chemical interaction. In-situ measurement radial deformation cladding quantify extent this interaction state cladding. Existing capabilities to perform in-pile diameter measurements are limited by required contact an intrusive presence device near specimen. To overcome these limitations, researchers have developed evaluated electrical impedance based gauge using benchtop system....

The Nuclear Science User Facilities (NSUF) is the U.S. Department of Energy Office Energy's only designated nuclear energy user facility. Its mission to provide researchers access world-class capabilities and facilitate advancement science technology. This supported by providing state-of-the-art experimental irradiation testing, postirradiation examination facilities, high-performance computing capabilities, as well technical scientific assistance for design execution projects. As part an...