Uncertainty Quantification and Software Risk Analysis for Digital Twins in the Nearly Autonomous Management and Control Systems: A Review

01/28/2021

∙

A nearly autonomous management and control (NAMAC) system is designed to furnish recommendations to operators for achieving particular goals based on NAMAC's knowledge base. As a critical component in a NAMAC system, digital twins (DTs) are used to extract information from the knowledge base to support decision-making in reactor control and management during all modes of plant operations. With the advancement of artificial intelligence and data-driven methods, machine learning algorithms are used to build DTs of various functions in the NAMAC system. To evaluate the uncertainty of DTs and its impacts on the reactor digital instrumentation and control systems, uncertainty quantification (UQ) and software risk analysis is needed. As a comprehensive overview of prior research and a starting point for new investigations, this study selects and reviews relevant UQ techniques and software hazard and software risk analysis methods that may be suitable for DTs in the NAMAC system.

READ FULL TEXT

Uncertainty Quantification and Software Risk Analysis for Digital Twins in the Nearly Autonomous Management and Control Systems: A Review

Uncertainty Quantification and Sensitivity analysis for Digital Twin Enabling Technology: Application for BISON Fuel Performance Code

Leveraging Industry 4.0 – Deep Learning, Surrogate Model and Transfer Learning with Uncertainty Quantification Incorporated into Digital Twin for Nuclear System

Interpretable Uncertainty Quantification in AI for HEP

Non-Intrusive Uncertainty Quantification for U3Si2 and UO2 Fuels with SiC/SiC Cladding using BISON for Digital Twin-Enabling Technology

Uncertainty Quantification in the Road-level Traffic Risk Prediction by Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network(STZINB-GNN)

URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates

Uncertainty-aware Traffic Prediction under Missing Data

Uncertainty Quantification and Software Risk Analysis for Digital Twins in the Nearly Autonomous Management and Control Systems: A Review

Related Research

Uncertainty Quantification and Sensitivity analysis for Digital Twin Enabling Technology: Application for BISON Fuel Performance Code

Leveraging Industry 4.0 – Deep Learning, Surrogate Model and Transfer Learning with Uncertainty Quantification Incorporated into Digital Twin for Nuclear System

Interpretable Uncertainty Quantification in AI for HEP

Non-Intrusive Uncertainty Quantification for U3Si2 and UO2 Fuels with SiC/SiC Cladding using BISON for Digital Twin-Enabling Technology

Uncertainty Quantification in the Road-level Traffic Risk Prediction by Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network(STZINB-GNN)

URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates

Uncertainty-aware Traffic Prediction under Missing Data