Summary of Ai Enabled Neutron Flux Measurement and Virtual Calibration in Boiling Water Reactors, by Anirudh Tunga et al.
AI Enabled Neutron Flux Measurement and Virtual Calibration in Boiling Water Reactors
by Anirudh Tunga, Jordan Heim, Michael Mueterthies, Thomas Gruenwald, Jonathan Nistor
First submitted to arxiv on: 25 Sep 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Machine learning (ML) models are being used to solve challenges in accurately capturing three-dimensional power distribution within reactor cores. Offline, neutronics simulators estimate power, moderator, void, and flow distributions, while online, local power range monitors (LPRMs) capture neutron flux information. However, problems with measurement, calibration, and power adaptation pose challenges to operators, limiting the ability to design reload cores economically. To address these issues, ML models are being trained from deep neural network (DNN) architectures, such as SurrogateNet and LPRMNet, which demonstrate testing errors of 1 percent and 3 percent, respectively. These models can be applied to virtual sensing for bypassed or malfunctioning LPRMs, on-demand calibration of detectors, accurate nuclear end-of-life determinations, and reduced bias between measured and predicted power distributions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning (ML) is being used to help ensure the safe and economical operation of reactor cores. Currently, it’s hard to accurately measure power distribution within these cores, which can make it difficult to design new fuel cores. ML models are being trained to solve this problem by using information from neutronics simulators and local power range monitors (LPRMs). These models can help reduce errors in measuring power distribution and even allow for virtual sensing if an LPRM is broken or not working properly. This technology has the potential to make it easier to design new fuel cores and improve the overall safety and efficiency of reactor operations. |
Keywords
* Artificial intelligence * Machine learning * Neural network
