Identification of Flow Regime of Boiling Flow in a Vertical Annulus with Unsupervised Machine Learning
-
摘要: 研究流动沸腾两相流动形态对封闭反应堆安全分析程序关键本构模型具有重要意义。本文基于非监督机器学习流型识别方法，提出将两相流物理知识融入数据驱动的机器学习模型，并构建输入特征的挑选原则：①机器学习在输入特征中捕捉到的应为流型相关信息；②机器学习的聚类准则应包络该流型下输入特征的所有可能性。依据挑选原则分析电导探针信号生成的汽泡分布特征，确定汽泡弦长累积分布函数数据可用于非监督机器学习流型判断。依据流型识别结果，获得了竖直环形流道内流动沸腾的二维局部流型特性，发现高位局部流型出现在流道中心位置并偏向内加热壁面；并判别了流道截面的全局流型，结果表明流动沸腾泡状流至弹状流的流型转变出现在空泡份额约为0.14位置。Abstract: Accurate flow regime identification of the boiling flow is of great significance for using closure correlations in thermal-hydraulic system codes. The flow regime identification is achieved by the unsupervised machine learning (ML) approach, and the current work integrates the data-driven ML model with the two-phase-flow domain knowledge. Two requirements are established to determine whether the feed-in data type is appropriate or not: ①the information captured by the unsupervised ML should be regime-relevant features for distinguishing flow regimes;②the cluster criterion for a flow regime should cover all the possible feed-in features of the regime. Feed-in data types generated by the conductivity probe are examined; among them, only the bubble chord length Cumulative Distribution Function (CDF) fulfills the two requirements. With the feed-in data of chord length CDF, the two-dimensional local flow regimes are identified and analyzed for a boiling dataset conducted in an internally heated vertical annulus. The results show that the higher-rank regimes appear at the channel’s center leaning toward the inner-heated wall. The global flow regime map is obtained with the local regimes, and a new flow regime transition criterion between the bubbly and slug flow is developed as the void fraction equals 0.14.
-
Key words:
- Two-phase flow /
- Flow regime /
- Bubble size distribution /
- Machine learning /
- Feed-in feature
-
图 2 基于知识-数据融合型非监督机器学习方法的流型识别流程
xn—特征数据
Figure 2. Workflow of Flow Regime Identification Using the Physics-data-integrated Unsupervised Machine Learning
图 3 用于流型识别的机器学习方法输入特征
Figure 3. Feed-in Features for the Machine Learning to Identify Flow Regimes
图 4 使用归一化汽泡时延频数数据得出的流型识别结果
Figure 4. Flow Regime Identification Results Using the Normalized Bubble Duration Frequency
图 5 使用汽泡弦长累积分布函数斜率数据得出的流型识别结果示例
Figure 5. Flow Regime Identification Results Using the Bubble Chord Length CDFs’ Slope Data
图 6 使用汽泡弦长CDF得出的局部流型识别结果
Figure 6. LFR Identification Results Using the Bubble Chord Length CDF
图 7 使用汽泡弦长累积分布函数得出的全局流型识别结果及特征
Figure 7. GFR Identification Results and Features Using the Bubble Chord Length CDF
-
[1] U. S. NRC. RELAP5/MOD3.3 code manual Vol. 1: Code structure, system models, and solution methods. Nuclear safety analysis division Office of Nuclear Regulatory Research U. S. Nuclear Regulatory Commission: RELAP5/MOD3.3 Code Manual: NUREG/CR-5535[R]. Rockville: Information Systems Laboratories, Inc. , 2001. [2] TRACE. TRACE V5.0 Theory Manual[Z]. U. S.: Nuclear Regulatory Commission, 2010. [3] SEKOGUCHI K, INOUE K, IMASAKI T. Void signal analysis and gas-liquid two-phase flow regime determination by a statistical pattern recognition method: fluids engineering[J]. JSME International Journal, 1987, 30(266): 1266-1273. doi: 10.1299/jsme1987.30.1266 [4] MI Y, ISHII M, TSOUKALAS L H. Flow regime identification methodology with neural networks and two-phase flow models[J]. Nuclear Engineering and Design, 2001, 204(1-3): 87-100. doi: 10.1016/S0029-5493(00)00325-3 [5] 孙斌,周云龙. 基于支持向量机和小波包能量特征的气液两相流流型识别方法[J]. 中国电机工程学报,2005, 25(17): 93-99. doi: 10.3321/j.issn:0258-8013.2005.17.019 [6] 孙斌,周云龙,赵鹏,等. 基于奇异值分解和最小二乘支持向量机的气-液两相流流型识别方法[J]. 核动力工程,2007, 28(6): 62-66. doi: 10.3969/j.issn.0258-0926.2007.06.015 [7] 乔守旭,钟文义,谭思超,等. 基于PCA-GA-SVM的竖直下降两相流流型预测[J]. 核动力工程,2022, 43(3): 85-93. doi: 10.13832/j.jnpe.2022.03.0085 [8] OOI Z J, ZHU L X, BOTTINI J L, et al. Identification of flow regimes in boiling flows in a vertical annulus channel with machine learning techniques[J]. International Journal of Heat and Mass Transfer, 2022, 185: 122439. doi: 10.1016/j.ijheatmasstransfer.2021.122439 [9] BOTTINI J L, ZHU L X, OOI Z J, et al. Experimental study of boiling flow in a vertical heated annulus with local two-phase measurements and visualization[J]. International Journal of Heat and Mass Transfer, 2020, 155: 119712. [10] LEE J Y, ISHII M, KIM N S. Instantaneous and objective flow regime identification method for the vertical upward and downward co-current two-phase flow[J]. International Journal of Heat and Mass Transfer, 2008, 51(13-14): 3442-3459. doi: 10.1016/j.ijheatmasstransfer.2007.10.037 [11] KOHONEN T. The self-organizing map[J]. Proceedings of the IEEE, 1990, 78(9): 1464-1480. doi: 10.1109/5.58325 [12] CONG T L, SU G H, QIU S Z, et al. Applications of ANNs in flow and heat transfer problems in nuclear engineering: A review work[J]. Progress in Nuclear Energy, 2013, 62: 54-71. doi: 10.1016/j.pnucene.2012.09.003 [13] JULIÁ J E, LIU Y, PARANJAPE S, et al. Upward vertical two-phase flow local flow regime identification using neural network techniques[J]. Nuclear Engineering and Design, 2008, 238(1): 156-169. doi: 10.1016/j.nucengdes.2007.05.005 [14] HERNÁNDEZ L, JULIÁ J E, CHIVA S, et al. Fast classification of two-phase flow regimes based on conductivity signals and artificial neural networks[J]. Measurement Science and Technology, 2006, 17(6): 1511-1521. doi: 10.1088/0957-0233/17/6/032 [15] MISHIMA K, ISHII M. Flow regime transition criteria for upward two-phase flow in vertical tubes[J]. International Journal of Heat and Mass Transfer, 1984, 27(5): 723-737. doi: 10.1016/0017-9310(84)90142-X [16] KELESSIDIS V C, DUKLER A E. Modeling flow pattern transitions for upward gas-liquid flow in vertical concentric and eccentric annuli[J]. International Journal of Multiphase Flow, 1989, 15(2): 173-191. doi: 10.1016/0301-9322(89)90069-4 [17] DAS G, DAS P K, PUROHIT N K, et al. Flow pattern transition during gas liquid upflow through vertical concentric annuli—Part I: experimental investigations[J]. Journal of Fluids Engineering, 1999, 121(4): 895-901. doi: 10.1115/1.2823552 [18] WU B, FIROUZI M, MITCHELL T, et al. A critical review of flow maps for gas-liquid flows in vertical pipes and annuli[J]. Chemical Engineering Journal, 2017, 326: 350-377. doi: 10.1016/j.cej.2017.05.135 [19] OZAR B, JEONG J J, DIXIT A, et al. Flow structure of gas–liquid two-phase flow in an annulus[J]. Chemical Engineering Science, 2008, 63(15): 3998-4011. doi: 10.1016/j.ces.2008.04.042 -
下载:
计量
- 文章访问数: 1869
- HTML全文浏览量: 73
- PDF下载量: 67
- 被引次数: 0
