Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Decision-making based on Markov decision process in integrated artificial reasoning framework—Part I: Theory

Journal Article · · Nuclear Science and Technology Open Research
 [1];  [2];  [3];  [4];  [4];  [2];  [3]
  1. Rensselaer Polytechnic Inst., Troy, NY (United States); Idaho National Laboratory (INL), Idaho Falls, ID (United States)
  2. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
  3. Rensselaer Polytechnic Inst., Troy, NY (United States)
  4. Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
+ Show Author Affiliations

This paper presents a decision-making framework based on an integrated artificial reasoning framework and Markov decision process (MDP). The integrated artificial reasoning framework provides a physics-based approach that converts system information into state transition models, and the analysis result will be represented by the transition probabilities that can be used with an MDP to find a traceable and explainable optimal pathway. A dynamic Bayesian network (DBN) is well suited for representing the structure of an MDP. The causality information among process variables (or among subsystems) is mathematically represented in a DBN by the conditional probabilities of the node’s states provided different probabilities of the parent node’s states. To define node states in a physically understandable manner, we used multilevel flow modeling (MFM). An MFM follows the fundamental energy and mass conservation laws and supports the selection of process variables that represent the system of interest so that causal relations among process variables are properly captured. An MFM-based DBN supports developing state transition models in an MDP to capture the effect of process variables of system having physical relations. The operators of the target system can capture stochastic system dynamics as multiple subsystem state transitions based on their physical relations and uncertainties coming from component degradation or random failures. We analyzed a simplified exemplary system to illustrate an optimal operational policy using the suggested approach.

Research Organization:
Idaho National Laboratory (INL), Idaho Falls, ID (United States)
Sponsoring Organization:
USDOE Office of Nuclear Energy (NE), Nuclear Energy University Program (NEUP); USNRC
Grant/Contract Number:
NE0008873; AC07-05ID14517
OSTI ID:
2997527
Report Number(s):
INL/JOU--23-73256
Journal Information:
Nuclear Science and Technology Open Research, Journal Name: Nuclear Science and Technology Open Research Journal Issue: 64 Vol. 2; ISSN 2755-967X
Publisher:
F1000 Research LtdCopyright Statement
Country of Publication:
United States
Language:
English

References (11)

Machine Learning: Algorithms, Real-World Applications and Research Directions journal March 2021
Reinforcement learning for combinatorial optimization: A survey journal October 2021
Dynamic risk assessment with bayesian network and clustering analysis journal September 2020
System risk quantification and decision making support using functional modeling and dynamic Bayesian network journal November 2021
On the Theory of Dynamic Programming journal August 1952
Computer-Assisted Markov Failure Modeling of Process Control Systems journal April 1987
A Time-Temperature Relationship for Rupture and Creep Stresses journal July 1952
Trustworthy Autonomous System Development journal April 2023
Decision-making based on Markov decision process in integrated artificial reasoning framework—Part 2: Applications journal June 2024
Physics-Informed Machine Learning-Aided System Space Discretization
  • Kim, Junyung; Shah, Asad Ullah; Kang, Hyun
  • 12th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies (NPIC&HMIT 2021) https://doi.org/10.13182/T124-34648
conference January 2021
Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review journal May 2021

Similar Records

Related Subjects

Markov decision process
decision-making
dynamic Bayesian network
multilevel flow modeling
reinforcement learning