Research on Judgment of Supercritical Water Heat Transfer Deterioration Based on Machine Learning
-
摘要: 为了进一步提高超临界水堆的安全稳定性，避免超临界水传热恶化的发生，在已有的超临界水传热实验数据基础之上，利用几种主要的机器学习算法，对超临界水的实验参数状态点是否发生了传热恶化进行分类判断和预测精度分析。研究表明：随机森林算法对于测试数据的平均预测精度最高，达到了97.8%左右；K近邻（KNN）分类算法的平均预测精度最低，但是也达到了90%以上。同时对各种不同的影响参数对传热恶化的选取重要度的分析可知，与传热恶化判定关系最重要的参数是比焓，其次为传热系数；与传热恶化重要度选择关系最小的是管径。Abstract: In order to further improve the safety and stability of supercritical water reactors, avoid the occurrence of the heat transfer deterioration in supercritical water, based on the existing experimental data of supercritical water heat transfer, using several main machine learning algorithms, the classification and judgment and prediction accuracy analysis of the experimental parameter state points of supercritical water were made to determine the occurrence of the heat transfer deterioration. The research results show that the random forest algorithm has the highest average prediction accuracy for the test data, reaching about 97.8%. The average prediction accuracy of the K-nearest neighbor algorithm is the lowest, but it also reaches about 91%. At the same time, the importance of various influence parameters on the selection of heat transfer deterioration was analyzed.The most important parameter related to the heat transfer deterioration judgment is the specific enthalpy, and the second important parameter is the heat transfer coefficient. The third important parameter with contribution to the heat transfer deterioration is the pipe diameter.
-
表 1 超临界水实验数据参数范围
Table 1. Parameter Range of Supercritical Water Experimental Data
名称 比焓/(kJ·kg−1) 管径/mm 流量/(kg·m−2·s−1) 热流密度/(kW·m−2) 压力/MPa 换热系数/(kW·m−2·K−1) 最大值 3162.846 38.1 3000 2960 31 171.0758 最小值 451.3 0.7 203 166 22.5 1.0443 平均值 1996.529 11.83538 1000.091 567.3809 24.56971 16.90726 
下载: 导出CSV
-
[1] PIORO I L, DUFFEY R B. Experimental heat transfer in supercritical water flowing inside channels (survey)[J]. Nuclear Engineering and Design, 2005, 235(22): 2407-2430. doi: 10.1016/j.nucengdes.2005.05.034 [2] DUFFEY R B, PIORO I L. Experimental heat transfer of supercritical carbon dioxide flowing inside channels (survey)[J]. Nuclear Engineering and Design, 2005, 235(8): 913-924. doi: 10.1016/j.nucengdes.2004.11.011 [3] WEN Q L, GU H Y. Numerical investigation of acceleration effect on heat transfer deterioration phenomenon in supercritical water[J]. Progress in Nuclear Energy, 2011, 53(5): 480-486. doi: 10.1016/j.pnucene.2011.02.012 [4] PODILA K, RAO Y F. CFD analysis of flow and heat transfer in Canadian supercritical water reactor bundle[J]. Annals of Nuclear Energy, 2015(75): 1-10. doi: 10.1016/j.anucene.2014.07.039 [5] HUANG D, WU Z, SUNDEN B, et al. A brief review on convection heat transfer of fluids at supercritical pressures in tubes and the recent progress[J]. Applied Energy, 2016(162): 494-505. doi: 10.1016/j.apenergy.2015.10.080 [6] VIKHREV Y V, BARULIN Y D, KON’KOV A S. A study of heat transfer in vertical tubes at supercritical pressures[J]. Therm Eng., 1967, 14(9): 116-119. [7] MOKRY S, PIORO I, FARAH A, et al. Development of supercritical water heat-transfer correlation for vertical bare tubes[J]. Nuclear Engineering and Design, 2011, 241(4): 1126-1136. doi: 10.1016/j.nucengdes.2010.06.012 [8] WANG H, BI Q C, YANG Z D, et al. Experimental and numerical investigation of heat transfer from a narrow annulus to supercritical pressure water[J]. Annals of Nuclear Energy, 2015(80): 416-428. doi: 10.1016/j.anucene.2015.02.029 [9] 潘杰,杨冬,董自春,等. 垂直上升光管内超临界水的传热特性试验研究[J]. 核动力工程,2011, 32(1): 75-80. [10] 王飞,杨珏,顾汉洋,等. 垂直管内超临界水传热实验研究[J]. 原子能科学技术,2013, 47(6): 933-939. doi: 10.7538/yzk.2013.47.06.0933 [11] 徐峰,郭烈锦,毛宇飞,等. 超临界压力下水在垂直加热管内传热特性的实验研究[J]. 西安交通大学学报,2005, 39(5): 468-471. doi: 10.3321/j.issn:0253-987X.2005.05.007 [12] MÜLLER A C, GUIDO S. Python机器学习基础教程[M]. 张亮, 译. 北京: 人民邮电出版社, 2018 -
图(6) / 表(1)
计量
- 文章访问数: 220
- HTML全文浏览量: 104
- PDF下载量: 40
- 被引次数: 0
