Vol. 54,No. 3Mar 2020第54卷第3期
2020年3月原子能科学技术Atomic Energy Science and Technology 基于人工神经网络的压水堆燃料破损状态监测 时效处理设备肖维，尹楚轩，李宏轩，董冰，尹俊连，王德忠
(上海交通大学核科学与工程学院，上海200240$
摘要：为提升对核反应堆燃料棒包壳破损的预测能力，建立两个串联的人工神经网络分别判断燃料棒包 壳是否破损以及破损程度％通过改变沾污铀质量、增加数据扰动、改变运行功率和使用更少的特征核素 进行训练，对用于判断是否破损的神经网络模型和判断破损等级的神经网络进行了性能测试和分析％ 在沾污铀质量小于0. 5 g 、数据扰动在30%以内、单棒功率在77 kW 到120 kW 之间的条件下，第1个人 工神经网络能较好地判断出是否破损％第2个神经网络，对于考虑的5种破损程度，判断的精确性较 高％与传统的碘同位素比值法相比，神经网络方法响应更快，精度更高％结果表明，人工神经网络可用 于预测反应堆燃料包壳是否发生破损以及破损程度％ 关键词：燃料棒；神经网络；包壳破损；裂变产物
中图分类号:TM33 文献标志码:A 文章编号：1000-6931(2020)03-0481-07
doi ：10. 7538/yzk. 2019. youxian. 0258
连供系统PWR Fuel Failure Monitoring Based on Artificial Neural Network
XIAO Wei , YIN Chuxuan , LI Hongxuan , DONG Bing ,
YIN Junl7n , WANG Dezhong *CH3(CH2)6COOH
收稿日期：2019-04-08；修回日期：2019-06-03
基金项目：国家自然科学基金资助项目(11675105,11535009)
超滤器离子风机aryang作者简介：肖 维(1997—)男，广东韶关人，核工程与核技术专业
* 通信作者：王德忠，E-mail ： dzwang@sj t u . edu. cn
网络出版时间：2019-10-31；网络出版地址：http ：〃kns. cnki. net/kcms/detail/11. 2044. TL. 20191031. 1323. 014. html (.School of Nuclear Science and Engineering , Shanghai Jiao Tong University , Shanghai 200240, China )Abstract : In order to improve the accuracy of predicting the degree of the fuel defect , two serial artificial neural networks were established to determ动员剂
ine the fuel defect state and its degree. After changing the mass of tramp uranium , increasing data fluctuations , changingsinglerod power !and taking fewer characteristic nuclides as input vector ! performance tests and analysis were performed to evaluate the suitability of the neural network. The same analysis was performed to analyze the second network , which was t r ained t o determine the degree of the fuel defec t . Under the condition t h a t the mass of rampuraniumisless han0.5g heda afluc uaioniswihin30% and hesinglerod powerisbe ween77kWand120kW hefirs ar ificialneuralne workcanbe erde er- minewhe her hecladdingisdamaged.Thesecondneuralne workhasahigheraccuracy for hefivelevelsofdamage.Comparedwi h he radiionaliodineiso operaiome hod heneuralne workme hodisfas erandmoreaccura e.Theresul sshow ha hearifi-
豫公网安备41160202000603
站长QQ:729038198
关于我们
投诉建议