Machine-Learning Analysis of Moisture Carryover in Boiling Water Reactors

Journal Article · 26 March 2019 · Nuclear Technology

DOI: https://doi.org/10.1080/00295450.2019.1583957 · OSTI ID:1559008

Wang, Haoyu ^[1]; Longman, Andrew ^[2]; Gruenwald, J. Thomas ^[2]; Tusar, James ^[3]; Vilim, Richard  ^[1]

---

1. Argonne National Lab. (ANL), Lemont, IL (United States)
2. Purdue Univ., West Lafayette, IN (United States); Blue Wave AI Labs, Celebration, FL (United States)
3. Exelon Generation, Kennett Square, PA (United States)

Moisture carryover (MCO) is modeled in the General Electric Type-4 boiling water reactor (BWR) using machine-learning methods and data from operating plants. Understanding MCO and the conditions that give rise to an elevated value is important since excessive MCO can damage critical turbine components, can result in elevated dose levels to on-site personnel, and can interfere with late-cycle power management. The analysis of MCO takes into account simplifying reactor symmetries and important geometric dependencies. The plant data are taken from several reactors and were collected over multiple years and multiple fuel cycles. A brief description of the origin of MCO in U.S. BWR plants is given. A machine-learning model is constructed from the data using applicable algorithms and data-reduction techniques. Matching model complexity with available data is one of the more challenging machine-learning tasks. Too many features and too little data will lead to overfitting. The data for each fuel cycle included over 6876 original features, 9 for each fuel bundle. Two approaches are used to reduce the data set into a manageable number of features. The first was an engineering analysis that resulted in the selection of steam quality Q and steam liquid phase velocity V_L as the main features driving MCO. Using a Q and a V_L for each fuel bundle gives 1528 Q and a V_L feature describing the reactor behavior. An analysis of different functional forms of these two variables led to the actual inputs to the neural network model. The second approach involved the use of statistical techniques such as Pearson’s correlation and k-means analysis. The identified groupings of bundles behaved similarly. Treating each grouping as a single feature further reduced the input variable set to a manageable number. Here, a model selection criterion is proposed, and results are presented along with a discussion of related issues.

• Research Organization: Argonne National Lab. (ANL), Argonne, IL (United States)
• Sponsoring Organization: USDOE Office of Nuclear Energy (NE)
• Grant/Contract Number: AC02-06CH11357
• OSTI ID: 1559008
• Journal Information: Nuclear Technology, Journal Name: Nuclear Technology Journal Issue: 8 Vol. 205; ISSN 0029-5450
• Publisher: Taylor & Francis - formerly American Nuclear Society (ANS)Copyright Statement
• Country of Publication: United States
• Language: English