An operator-in-the-loop study was conducted in support of control room modernization for a nuclear power plant. The study featured a benchmark comparison on a glass-top simulator of three variants of a turbine control system (TCS): (1) the existing analog TCS, (2) a proposed stand-alone digital TCS with two displays, and (3) the digital TCS with the addition of a third display consisting of a system overview screen. TCS prototypes were developed to allow formative evaluation of operator preferences and performance during realistic turbine scenarios in the full-scope simulator. The study revealed that completion of turbine startup was several minutes faster with the digital TCS variants than with the conventional analog TCS. Eye-tracking fixations were more widely distributed in the overview versus stand-alone TCS condition, suggesting the overview screen was cueing reactor operators to verify values across the boards. There was no significant difference in workload or situation awareness across the three interfaces. Reviewing key plant parameters showed smoother transitions during load-following for the digital-versus-analog TCS. Despite some performance advantages for the digital TCS variants, operators preferred the existing analog TCS. Open-ended responses suggested this finding may be more an artifact of familiarity than a reflection of dissatisfaction with the new TCS. The study provides compelling evidence that the new digital TCS was used successfully by the operators, suggesting high usability for the digital TCS design. Further advantages were realized through the addition of the system overview screen to provide crews with at-a-glance indicators of key turbine parameters.

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

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

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 information that is not typically used beyond the intended target for collecting that information. The industry has recognized the benefits of both reducing labor-intensive tasks by automating them and increasing the fidelity of the information collected to enable advanced remote monitoring of NPPs using data-driven decision making. This requires developing new means to acquire data from the various data sources of an NPP. While some sources already exist in a digital form, others are collected manually, summarized through conclusive statements, or not collected at all. This paper describes 15 sources of data at an NPP and methods to migrate the data collection from a manual and analog data form to an automated and digital data form that increases the data fidelity in time and space. Three states of data collection methods are described for each data source. The states describe a base state for how the data are currently being collected, a modern state for a more efficient method of collecting data that has not yet been implemented, and a state of the art for an advanced method of collecting data that is not yet ready for deployment.

To facilitate the automated online monitoring of power plants, a systematic and qualitative strategy for anomaly detection is presented. This strategy is essential to provide credible reasoning on why and when an empirical versus hybrid (i.e., physics-supported) approach should be used and to determine the ideal mix of these two approaches for a defined anomaly detection scope. Empirical methods are usually based on pattern, statistical, and causal inference. Hybrid methods include the use of physics models to train and test data methods, reduce data dimensionality, reduce data-model complexity, augment data, and reduce empirical uncertainty; hybrid methods also include the use of data to tune physics models. The presented strategy is driven by key decision points related to data relevance, simple modeling feasibility, data inference, physics-modeling value, data dimensionality, physics knowledge, method of validation, performance, data availability, and suitability for training and testing, cause-effect, entropy inference, and model fitting. The strategy is demonstrated through a pilot use case for the application of anomaly detection to capture a valve packing leak at the high-pressure coolant injection system of a nuclear power plant.