ML21277A085
| ML21277A085 | |
| Person / Time | |
|---|---|
| Issue date: | 08/18/2021 |
| From: | Nathanael Hudson, Tehrani N, Peter Yarsky NRC/RES/DSA |
| To: | |
| Dennis M | |
| References | |
| Download: ML21277A085 (13) | |
Text
Autonomous Control Algorithms to Simulate Boiling Water Reactor Cycle Depletion NRC Team:
Nate Hudson, Ph.D. Nathanael.Hudson@nrc.gov Nazila Tehrani, Ph.D. Nazila.Tehrani @nrc.gov Peter Yarsky, Ph.D. Peter.Yarsky@nrc.gov
Regulatory Purpose NRC then NRC now
- Reactive
- Proactive
- Plant specific
- Generic model
- Traditional methods
- Advanced methods 9/8/2021 Data Sci/AI Reg Applications Workshop 2
NRC is exploring innovative tools
- Perform independent transients/accidents analysis
- Increase staff efficiency
- Identify/focus safety significant issues
- Boost confidence in licensee results
- uncertainty high
- margin low
- Address emergent issues 9/8/2021 Data Sci/AI Reg Applications Workshop 3
Motivation
- Automate LWR core/cycle design
- Create models not associated with any specific licensing action
- Use autonomous control methods 9/8/2021 Data Sci/AI Reg Applications Workshop 4
RES develops generic LWR TRACE models for accident/transient analysis Boiling water reactor Pressurized water reactor
- Peter Yarsky (Project Lead,
- Andy Bielen (Project Lead, Nuclear Senior Reactor Systems Engineer (Fuels/Neutronics), Fuel Engineer, Code And Reactor & Source Term Code Development Analysis Branch) Branch)
- Nate Hudson (Reactor
- Mike Rose (Reactor System Systems Engineer, Code And Engineer (Neutronics Analyst, Fuel Reactor Analysis Branch) & Source Term Code Development
- Nazila Tehrani (Reactor Branch)
Systems Engineer, Accident
- Alice Chung (Reactor System Analysis Branch) Engineer (Fuel Analyst), Fuel &
Source Term Code Development Branch) 9/8/2021 Data Sci/AI Reg Applications Workshop 5
BWR cores are complex to design
- burnable poisons Control excess
- control blades reactivity during cycle
- flow control windows
- meeting desired cycle energy
- maintaining safety margins Competing goals
- minimizing duty related fuel failures
- issues with symmetry High-dimensionality
- very large number of types of fuel elements of BWR cores 9/8/2021 Data Sci/AI Reg Applications Workshop 6
TRACE/PARCS models of PWR/BWR transients/accidents analysis
- Coupled neutronics/TH transient
- normal
- anticipated transients
- accident conditions
- current reactors
- advanced reactors
- 12 major plant types (5 BWR)
- Standard models
- Efficient confirmatory calculations 9/8/2021 Data Sci/AI Reg Applications Workshop 7
Necessity Traditional NRC Innovative NRC
- NRC used PARCS to simulate
- calculate cycle power and designs burnup distributions
- generate a BWR
- transient analyses need equilibrium cycle burnup-dependent - theoretical concept
- rod patterns - operate a typical plant
- flow rate - given fuel design
- EOC bundle shuffle sequence - over a long time 9/8/2021 Data Sci/AI Reg Applications Workshop 8
Autonomous control algorithms Literature review NRC goals
- Proposed micro-reactor
- PARCS models
- sense reactor conditions
- dynamically adjust
- sense reactor coolant system - fuel loading between cycles
- judge qualification of signals - control rod pattern
- flow rate during cycle
- evaluate current state of system
- yield all statepoint information over full cycle
- make decisions about actions
- implement actions for operation 9/8/2021 Data Sci/AI Reg Applications Workshop 9
Bayesian networks for dynamic (PRA)
Kim, et al.
Literature Review Annealing DNN to optimize core loading pattern for method BWR Hays and Turinsky Saleem, et al.
9/8/2021 Data Sci/AI Reg Applications Workshop 10
Literature Review Bayesian networks for DNNs to optimize core Annealing method loading pattern for BWR dynamic (PRA)
- DNNs trained against core simulator
- artificial reasoning makes
- studies evolution of
- use core simulator decisions about core risk during postulated
- use sampling of design loading patterns events choices similar to
- meeting power peaking
- makes decisions during particles distribution at a limits a transient for temperature reducing risk
- cycle energy demand
- iteratively lowering
- artificial reasoning rely temperature, algorithm
- reasonable computational on surrogate models finds optimal solution expense/accuracy
- NRC wants to create * ~100,000 core simulator
- used to find optimal surrogate models runs designs
- NRC wants to optimize * ~10,000 simulations to loading patterns train
- NRC wants to optimize loading patterns 9/8/2021 Data Sci/AI Reg Applications Workshop 11
Work to be Performed
- Autonomous control for BWR core/cycle design feasible?
- Apply combination of existing decision-making methods
- Bayesian
- Neural Networks
- etc.
- Approximate core loading design/control rod sequence
- Contingency (Traditional Methods)
- Need feedback 9/8/2021 Data Sci/AI Reg Applications Workshop 12
Definitions
- BWR: Boiling water reactor
- DNN: Deep neural networks
- EOC: End of cycle
- LWR: Light water reactor
- PARCS: NRC Reactor Kinetics code
- PWR: Pressurized water reactor
- RES: Office of Nuclear Regulatory Research
- TH: Thermal-Hydraulics
- TRACE: NRC Thermal-Hydraulics code 9/8/2021 Data Sci/AI Reg Applications Workshop 13