基于BP神经网络的堆芯三维功率重构方法研究
|
摘要
堆芯功率分布包含了堆芯内的大量信息,由于在反应堆运行过程中无法直接测量堆芯内所有位置的功率,因此需通过其他方法得到堆芯三维功率分布的情况。本文以秦山一期工程为对象,利用堆外中子探测器在不同棒位和不同功率下的计数及BP神经网络对堆芯三维功率分布进行重构计算,并利用REMARK程序对该计算结果进行验证。结果表明,该功率重构方法能在反应堆运行的50%～100%功率范围内,较好地呈现堆芯三维功率分布。
The in-core power distribution contains plenty of informations in the core.Because the power distribution of all the parts of the core can not be directly measured when the reactor is operating,it is necessary to obtain the in-core power distribution by other ways.A method was proposed to calculate 3D power distribution of Qinshan project by using of ex-core neutron detecting system and BP neural network.The results were compared with those obtained by REMARK core physics real-time simulation program.It is shown that this BP reconstruction method can reconstruct the 3D distribution of reactor core power well in 50%-100% power range.
The in-core power distribution contains plenty of informations in the core.Because the power distribution of all the parts of the core can not be directly measured when the reactor is operating,it is necessary to obtain the in-core power distribution by other ways.A method was proposed to calculate 3D power distribution of Qinshan project by using of ex-core neutron detecting system and BP neural network.The results were compared with those obtained by REMARK core physics real-time simulation program.It is shown that this BP reconstruction method can reconstruct the 3D distribution of reactor core power well in 50%-100% power range.
引文
[1]刘国发.核电站测量仪表与控制原理[M].深圳:大亚湾核电运营管理公司培训中心,2008:125-129.
[2]赵强,张志俭,曹欣荣.反应堆堆外核测量系统的实时仿真[J].核动力工程,2005,26(5):484-487.ZHAO Qiang,ZHANG Zhijian,CAO Xinrong.Real-time simulation of ex-core nuclear instrumentation system[J].Nuclear Power Engineering,2005,26(5):484-487(in Chinese).
[3]李富.重构堆芯通量分布的谐波综合法及其诊断应用[D].北京:清华大学,1994.
[4]李富,周旭华,王登营,等.采用堆芯外探测器监测堆内功率分布[J].核动力工程,2010,31(S2):92-95.LI Fu,ZHOU Xuhua,WANG Dengying,et al.Monitoring of in-core power distribution by excore detectors[J].Nuclear Power Engineering,2010,31(S2):92-95(in Chinese).
[5] EVANS T M,DAVIDSON G G,SLAYBAUGH R N.Three-dimensional full core power calculations for pressurized water reactors[J].Journal of Physics:Conference Series,2010,68:367-379.
[6]李茁,吴宏春,曹良志,等.基于谐波展开法的压水堆堆芯功率分布在线监测[J].核动力工程,2015,36(5):165-168.LI Zhuo,WU Hongchun,CAO Liangzhi,et al.A PWR power distribution on-line monitoring based on harmonics expansion method[J].Nuclear Power Engineering,2015,36(5):165-168(in Chinese).
[7]李伟.基于堆外计数的堆芯功率分布重构方法研究[D].哈尔滨:哈尔滨工程大学,2009.
[8]夏虹,李彬,刘建新.基于RBF神经网络的压水堆堆芯三维功率分布方法研究[J].原子能科学技术,2014,48(4):698-702.XIA Hong,LI Bin,LIU Jianxin.Research on3Dpower distribution of PWR reactor core based on RBF neural network[J].Atomic Energy Science and Technology,2014,48(4):698-702(in Chinese).
[9] DIAS A M,SILVA F C.Determination of the power density distribution in a PWR reactor based on neutron flux measurements at fixed reactor incore detectors[J].Annals of Nuclear Energy,2016,90:148-156.
[10]刘建新.压水堆核电站负荷跟踪反应堆功率智能控制研究[D].哈尔滨:哈尔滨工程大学,2012.
[11]欧阳予.秦山核电工程[M].北京:原子能出版社,2000:258-259.
[12]刘天舒.BP神经网络的改进研究及应用[D].哈尔滨:东北农业大学,2011.
[13]HECHT-NIELSEN R.Theory of the backpropagation neural network[J].Neural Networks,1988,1(1):593-605.
[14]宋梅村,蔡琦.基于BP神经网络的反应堆功率预测[J].原子能科学技术,2011,45(10):1 242-1 246.SONG Meicun,CAI Qi.Reactor power prediction based on bp neural network[J].Atomic Energy Science and Technology,2011,45(10):1 242-1 246(in Chinese).
[15]KUMARGOEL A,SAXENA S C,BHANOT S.A fast learning algorithm for training feed forward neural networks[J].International Journal of Systems Science,2006,37(10):709-722.
[16]王炳萱.LM优化算法和神经网络预测控制在非线性系统中的研究[D].太原:太原理工大学,2016.
[2]赵强,张志俭,曹欣荣.反应堆堆外核测量系统的实时仿真[J].核动力工程,2005,26(5):484-487.ZHAO Qiang,ZHANG Zhijian,CAO Xinrong.Real-time simulation of ex-core nuclear instrumentation system[J].Nuclear Power Engineering,2005,26(5):484-487(in Chinese).
[3]李富.重构堆芯通量分布的谐波综合法及其诊断应用[D].北京:清华大学,1994.
[4]李富,周旭华,王登营,等.采用堆芯外探测器监测堆内功率分布[J].核动力工程,2010,31(S2):92-95.LI Fu,ZHOU Xuhua,WANG Dengying,et al.Monitoring of in-core power distribution by excore detectors[J].Nuclear Power Engineering,2010,31(S2):92-95(in Chinese).
[5] EVANS T M,DAVIDSON G G,SLAYBAUGH R N.Three-dimensional full core power calculations for pressurized water reactors[J].Journal of Physics:Conference Series,2010,68:367-379.
[6]李茁,吴宏春,曹良志,等.基于谐波展开法的压水堆堆芯功率分布在线监测[J].核动力工程,2015,36(5):165-168.LI Zhuo,WU Hongchun,CAO Liangzhi,et al.A PWR power distribution on-line monitoring based on harmonics expansion method[J].Nuclear Power Engineering,2015,36(5):165-168(in Chinese).
[7]李伟.基于堆外计数的堆芯功率分布重构方法研究[D].哈尔滨:哈尔滨工程大学,2009.
[8]夏虹,李彬,刘建新.基于RBF神经网络的压水堆堆芯三维功率分布方法研究[J].原子能科学技术,2014,48(4):698-702.XIA Hong,LI Bin,LIU Jianxin.Research on3Dpower distribution of PWR reactor core based on RBF neural network[J].Atomic Energy Science and Technology,2014,48(4):698-702(in Chinese).
[9] DIAS A M,SILVA F C.Determination of the power density distribution in a PWR reactor based on neutron flux measurements at fixed reactor incore detectors[J].Annals of Nuclear Energy,2016,90:148-156.
[10]刘建新.压水堆核电站负荷跟踪反应堆功率智能控制研究[D].哈尔滨:哈尔滨工程大学,2012.
[11]欧阳予.秦山核电工程[M].北京:原子能出版社,2000:258-259.
[12]刘天舒.BP神经网络的改进研究及应用[D].哈尔滨:东北农业大学,2011.
[13]HECHT-NIELSEN R.Theory of the backpropagation neural network[J].Neural Networks,1988,1(1):593-605.
[14]宋梅村,蔡琦.基于BP神经网络的反应堆功率预测[J].原子能科学技术,2011,45(10):1 242-1 246.SONG Meicun,CAI Qi.Reactor power prediction based on bp neural network[J].Atomic Energy Science and Technology,2011,45(10):1 242-1 246(in Chinese).
[15]KUMARGOEL A,SAXENA S C,BHANOT S.A fast learning algorithm for training feed forward neural networks[J].International Journal of Systems Science,2006,37(10):709-722.
[16]王炳萱.LM优化算法和神经网络预测控制在非线性系统中的研究[D].太原:太原理工大学,2016.