Fan Zhang

Leveraging robots to perform operation and maintenance (O&M) is a promising solution to reduce potential uncertainties in nuclear power plants (NPPs). Robots are reusable, perform consistently, and can cover a large-scale area, which makes them cost-efficient. This paper presents practical use cases for robot-assisted NPP O&M. The proposed method utilizes incident data from web databases of the International Atomic Energy Agency, the United States Nuclear Regulatory Commission, and the Operational Performance Information System for NPP of the Korea Institute of Nuclear Safety. It analyzes trends and critical maintenance tasks that robots can conduct for NPP O&M from insights from a customized domain-specific large language model named Intelligence for Advanced Nuclear Incident Analysis (iFAN-IA). Reading, studying, and analyzing all text data manually is time-consuming and subjective; however, iFAN-IA can rapidly read and analyze the text data objectively and quantitatively. Analyzing incident cases helps to identify risky or repetitive tasks and effectively find applicable use cases for robots. The proposed process not only contributes to developing practical use cases in robot-assisted NPP O&M but also is beneficial to other fields, such as cyber and physical attack scenario development.

Robotics has gained attention in the nuclear industry due to its precision and ability to automate tasks. However, there is a critical need for advanced simulation and control methods to predict robot behavior and optimize plant performance, motivating the use of digital twins. Most existing digital twins do not offer a total design of a nuclear power plant. Moreover, they are designed for specific algorithms or tasks, making them unsuitable for broader research applications. In response, this work proposes a comprehensive nuclear power plant digital twin designed to improve real-time monitoring, operational efficiency, and predictive maintenance. A full nuclear power plant is modeled in Unreal Engine 5 and integrated with a high-fidelity Generic Pressurized Water Reactor Simulator to create a realistic model of a nuclear power plant and a real-time updated virtual environment. The virtual environment provides various features for researchers to easily test custom robot algorithms and frameworks. • Provides a full-scale nuclear plant digital twin for robotics and AI research. • Supports a Python–Unreal bridge for robotic simulation and validation. • Features various tools for reinforcement learning and VR-based teleoperation.

Reducing greenhouse gas (GHG) emissions and fuel consumption remains a critical objective in courier fleet management. Dynamic routing, which continuously updates delivery routes in response to real-time conditions, offers a promising solution. However, its implementation is hindered by challenges in real-time data analytics and intelligent decision-making. This study addresses two underexplored, yet impactful, variables in dynamic fleet routing: (1) the changing weight of delivery trucks due to unloading at each stop and (2) traffic conditions on local roads, where most deliveries occur. We propose a machine learning-driven smart rerouting system that integrates real-time data analytics into a dynamic routing optimization framework focused on minimizing fuel consumption. Our approach consists of two key components. First, trucks are equipped to collect continuous real-time data on vehicle weight, which are analyzed using frequency domain techniques, and traffic conditions, which are interpreted via neural networks. Second, these data inform an optimization model that explicitly captures the relationship between fuel consumption, emissions, vehicle weight, and traffic dynamics. This model surpasses conventional capacitated vehicle routing approaches by embedding real-time reasoning into route planning. Extensive simulation studies demonstrate that the proposed system significantly reduces both GHG emissions and fuel consumption compared to traditional routing models, highlighting its potential for sustainable and cost-effective fleet operations.

In many industrial facilities, online monitoring systems have improved the reliability of key equipment, reducing the cost of operation and maintenance over recent decades. However, it often requires additional on-site inspection of target facilities due to limited information from installed sensors. To systematically automate such processes, an adaptive online fault diagnosis framework is required, which consecutively selects variables to measure and updates its inference with additional information at each measurement step. In this paper, adaptive online fault detection models-grafted composite decision trees-are proposed for such a framework. While conventional decision trees themselves can serve two required objectives of the framework, information from monitored variables can be less utilized because decision trees do not consider if required input variables are always monitored when the models are trained. On the other hand, the proposed grafted composite decision tree models are designed to fully utilize both monitored and robot-measured variables at any stage in a given measurement sequence by grafting two types of trees together: a prior-tree trained only with observed variables and sub-trees trained with robot-measurable variables. The proposed method was validated on a cooling water system in a nuclear power plant with multiple leak scenarios, in which improved measurement selection and increase in inference confidence in each measurement step are demonstrated. The performance comparison between the proposed models and the conventional decision tree model clearly illustrates how the acquired information is fully utilized for the best inference while providing the best choice of the next variable to measure, maximizing information gain at the same time.

Nuclear power plants (NPPs) require rigorous monitoring systems for their safety and efficiency, thus extensive data are acquired continuously from instrumentation and control systems. Anomaly detection is one of the most widely used machine learning approaches for monitoring data, especially when available data for model training are limited or imbalanced, as are data from NPPs.This research presents an anomaly detection system for centralized online monitoring in NPPs that is composed of two modules: data reconstruction and anomaly determination. Considering the large feature dimensions of the data, and leveraging their sequential characteristics in the time domain, four different autoencoder models for data reconstruction, long short-term memory, convolutional neural network, fully connected neural network, and principal component analysis are employed and compared.Two anomaly determination methods are presented and analyzed from the perspective of the characteristics of residuals from the data reconstruction models. The developed system is validated with simulation data containing 239 process variables (sensors) from different subsystems in a NPP.This paper highlights the effectiveness of simulations not only in overcoming the limited amount of data acquired from real plants in malfunctioning status, but also for evaluating the performance of the given models in a more quantitative way by comparing the performance at different malfunction levels. Weighted areas under the receiver operating characteristic curves are suggested as metrics for the validation of the given models and methods, and performance metrics, which can reflect engineers’ preferences, are demonstrated as well.

In order to solve the problems of key redundancy, transmission and storage security and the difficulty of realizing the one-time-secret mode in image encryption algorithm , this paper proposes a cloud dynamic public key information security scheme based on elliptic curve and primitive Pythagoras. The 6-D Lorentz hyperchaos system is used as the key generator, and the generated key is stored in the cloud key management center, which supports automatic update and dynamic change to further ensure the security of the key. The encryption key is selected by elliptic curve and primitive Pythagorean triplet. In the scrambling algorithm, according to the parity of random number and the parity of image pixel value coordinates, elliptic curve is used to reset the plaintext image. In the diffusion algorithm, the three-side rotation characteristic of the Rubik’s cube is simulated, the binary sequence of pixel values is stored at eight vertices of the cube, the cube is rotated according to the key value, and the changed 8 new binary numbers are XOR operated with the random sequence to obtain the new pixel value. The algorithm in this paper is applied to network transmission , which can effectively prevent data eavesdropping, tampering and forgery, ensure communication security.

Robotics has gained attention in the nuclear industry due to its precision and ability to automate tasks. However, there is a critical need for advanced simulation and control methods to predict robot behavior and optimize plant performance, motivating the use of digital twins. Most existing digital twins do not offer a total design of a nuclear power plant. Moreover, they are designed for specific algorithms or tasks, making them unsuitable for broader research applications. In response, this work proposes a comprehensive nuclear power plant digital twin designed to improve real-time monitoring, operational efficiency, and predictive maintenance. A full nuclear power plant is modeled in Unreal Engine 5 and integrated with a high-fidelity Generic Pressurized Water Reactor Simulator to create a realistic model of a nuclear power plant and a real-time updated virtual environment. The virtual environment provides various features for researchers to easily test custom robot algorithms and frameworks.

Instrumentation and control (I&C) systems in nuclear power plants (NPPs) are potential targets of cyberattacks and can prove deleterious for the safety of the NPPs. A Software Bill of Materials (SBOM) provides a detailed list of the various components and their dependencies in software, which helps in vulnerability and risk assessment for cyber hygiene and situational awareness. For an NPP, the process of generating an accurate SBOM report can be complex due to the legacy systems and firmware binaries involved. While most current SBOM tools are focused more on modern internet technology software, this research provides insights and guidelines for an NPP to generate an accurate and efficient SBOM. The paper proposes a new methodology to help NPPs categorize software and use appropriate tools to generate SBOMs for their digital I&C systems.

The transition from analog to digital instrumentation and control (I&C) systems introduces new threats caused by cyberattacks in the nuclear industry. This paper proposes a self-healing strategy to respond to a false data injection attack that targets digital I&C systems, which is a type of cyberattack commonly targeting nuclear power plants with the potential to cause serious physical impacts. This resilience strategy for self-healing control contains three components: (1) an anomaly detection model that can detect false data injection attacks, (2) a device-level control that utilizes inferred values to perform control under a detected false data injection, and (3) a system-level control that leverages another controller that is not under attack to lead the system back to a safe operation state when the device-level control is unavailable. Anomaly detection and device-level control use an autoencoder while system-level control utilizes reinforcement learning. The proposed self-healing resilience strategy is demonstrated with a generic pressurized water reactor (GPWR) simulator under false data injections, targeting the steam generator water level. The results show that the proposed strategy effectively leads the system back to a normal operation state under various false data injection cases.

As robot technologies are rapidly improving, an increasing number of new ideas on utilizing robots for automated operation and maintenance tasks in nuclear power plants (NPPs) are being studied. However, due to safety concerns, researchers hardly found opportunities to test their new robot solutions on physical NPPs. In that sense, an efficient and realistic simulation environment plays a vital role in the development of automation systems for an NPP. In this paper, we propose the design of a 3D digital twin system capable of simulating NPP in real-time. This system obtains the data from a full-scope NPP simulator to reproduce the operating conditions of the plant. In addition, a scenario of a team of robots performing inspection tasks like temperature and pressure measurements will highlight its usability. This system enables development of intelligent robot swarms to deploy for inspection and maintenance purposes. It will positively impact autonomous control and operations for many types of reactors by reducing uncertainty in autonomous control and providing the tools necessary for remote intervention.

Monitoring three-dimensional flux distribution in a nuclear reactor core is essential for improving safety and economics, which requires strategically placed in-core detectors. However, the deployment of these sensors is often constrained by physical, industrial, and economic limitations. This study treats optimizing the location of in-core detectors as a Markov decision process and develops a reinforcement learning (RL)–based framework to provide a solution for detector placement given a fixed number of detectors and available detector positions. The RL-based framework contains an environment consisting of a Proper Orthogonal Decomposition–based power reconstruction function paired with a novel reward function based on the power reconstruction error and a well-educated agent that updates the detector placement. Four RL algorithms including Proximal Policy Optimization, Deep Q-Network, Advantage Actor-Critic, and Monte Carlo Tree Search are investigated to optimize the detector placement and are analyzed. Genetic Algorithm (GA), a traditional optimization approach, is applied for comparison. The findings reveal that RL outperforms GA in terms of the quality of optimal solutions, demonstrating an inclination toward locating a global solution. Moreover, the flexible nature of RL enables the integration of developed novel reward functions from a specific reactor core into other reactors, considering the particular engineering requirements within the RL-based framework, thereby enhancing the optimization of in-core detector configurations.

Current preventative maintenance paradigms in nuclear power plants carry several costly risks and challenges associated with component downtime and the need for human data collection. Preventative maintenance may be enabled by an online monitoring system that accurately assesses component condition and identifies potential faults. We present an approach for autonomous online monitoring and multiagent planning for robotic data collection. Under the occurrence of a fault, we utilize a machine learning model to form an initial guess of its nature, which we then refine by selectively measuring certain variables to gain additional information via a situation-aware variable selection model. To generate a multi-robot plan to conduct these measurements, we develop a preference-based planning framework within a linear temporal logic–based planning approach that prioritizes collecting data from the most important features. Finally, we demonstrate our approach on a case study using a simulated nuclear power plant circulating water system, showing fault diagnostic performance as well as simulated robot data collection.