Data-Enabled Physics-Informed Machine Learning for Reduced-Order Modeling Digital Twin: Application to Nuclear Reactor Physics

Blockchain-based multi-authority revocable data sharing scheme in smart grid

In view of the problems of inefficient data encryption, non-support of malicious user revocation and data integrity checking in current smart grid data sharing schemes, this paper proposes a blockchain-based multi-authority revocable data sharing scheme in the smart grid. Using online/offline encryption technology with hybrid encryption technology enhances the encryption performance for the data owner. The use of user binary tree technology enables the traceability and revocability of malicious users. The introduction of multiple attribute authorization authorities eliminates the threat of collusive attacks that exist in traditional data-sharing schemes. In addition, the semi-honest problem of third-party servers is solved by uploading data verification credentials to the blockchain. The security analysis results show that the scheme can resist selective plaintext attacks and collusion attacks. The performance analysis results show that the proposed scheme has lower computational overhead and better functionality than similar schemes, which is suitable for secure data sharing in smart grids.

An intelligent fault detection approach for digital integrated circuits through graph neural networks

To quickly and accurately realize the fault diagnosis of analog circuits, this paper introduces the graph neural network method and proposes a fault diagnosis method for digital integrated circuits. The method filters the signals present in the digital integrated circuit to remove noise signals and redundant signals and analyzes the digital integrated circuit characteristics after the filtering process to obtain the digital integrated circuit leakage current variation. To the problem of the lack of a parametric model for Through-Silicon Via (TSV) defect modeling, the method of TSV defect modeling based on finite element analysis is proposed. The common TSV defects such as voids, open circuits, leakage, and unaligned micro-pads are modeled and analyzed by using industrial-grade FEA tools Q3D and HFSS, and the equivalent circuit model of resistance inductance conductance capacitance (RLGC) for each defect is obtained. Finally, the superior performance of this paper in fault diagnosis accuracy and fault diagnosis efficiency is verified by comparing and analyzing with the traditional graph neural network method and random graph neural network method for active filter circuits.

A review of the application of artificial intelligence to nuclear reactors: Where we are and what's next

As a form of clean energy, nuclear energy has unique advantages compared to other energy sources in the present era, where low-carbon policies are being widely advocated. The exponential growth of artificial intelligence (AI) technology in recent decades has resulted in new opportunities and challenges in terms of improving the safety and economics of nuclear reactors. This study briefly introduces modern AI algorithms such as machine learning, deep learning, and evolutionary computing. Furthermore, several studies on the use of AI techniques for nuclear reactor design optimization as well as operation and maintenance (O&M) are reviewed and discussed. The existing obstacles that prevent the further fusion of AI and nuclear reactor technologies so that they can be scaled to real-world problems are classified into two categories: (1) data issues: insufficient experimental data increases the possibility of data distribution drift and data imbalance; (2) black-box dilemma: methods such as deep learning have poor interpretability. Finally, this study proposes two directions for the future fusion of AI and nuclear reactor technologies: (1) better integration of domain knowledge with data-driven approaches to reduce the high demand for data and improve the model performance and robustness; (2) promoting the use of explainable artificial intelligence (XAI) technologies to enhance the transparency and reliability of the model. In addition, causal learning warrants further attention owing to its inherent ability to solve out-of-distribution generalization (OODG) problems.

An open time-series simulated dataset covering various accidents for nuclear power plants

Nuclear energy plays an important role in global energy supply, especially as a key low-carbon source of power. However, safe operation is very critical in nuclear power plants (NPPs). Given the significant impact of human-caused errors on three serious nuclear accidents in history, artificial intelligence (AI) has increasingly been used in assisting operators with regard to making various decisions. In particular, data-driven AI algorithms have been used to identify the presence of accidents and their root causes. However, there is a lack of an open NPP accident dataset for measuring the performance of various algorithms, which is very challenging. This paper presents a first-of-its-kind open dataset created using PCTRAN, a pre-developed and widely used simulator for NPPs. The dataset, namely nuclear power plant accident data (NPPAD), basically covers the common types of accidents in typical pressurised water reactor NPPs, and it contains time-series data on the status or actions of various subsystems, accident types, and severity information. Moreover, the dataset incorporates other simulation data (e.g., radionuclide data) for conducting research beyond accident diagnosis.

Parameter Flexible Wildfire Prediction Using Machine Learning Techniques: Forward and Inverse Modelling

Parameter identification for wildfire forecasting models often relies on case-by-case tuning or posterior diagnosis/analysis, which can be computationally expensive due to the complexity of the forward prediction model. In this paper, we introduce an efficient parameter flexible fire prediction algorithm based on machine learning and reduced order modelling techniques. Using a training dataset generated by physics-based fire simulations, the method forecasts burned area at different time steps with a low computational cost. We then address the bottleneck of efficient parameter estimation by developing a novel inverse approach relying on data assimilation techniques (latent assimilation) in the reduced order space. The forward and the inverse modellings are tested on two recent large wildfire events in California. Satellite observations are used to validate the forward prediction approach and identify the model parameters. By combining these forward and inverse approaches, the system manages to integrate real-time observations for parameter adjustment, leading to more accurate future predictions.