原子能科学技术
原子能科學技術
원자능과학기술
ATOMIC ENERGY SCIENCE AND TECHNOLOGY
2015年
6期
1026-1031
,共6页
彭星杰%李天涯%李庆%王侃
彭星傑%李天涯%李慶%王侃
팽성걸%리천애%리경%왕간
最小二乘支持向量机%功率分布重构%鲁棒性
最小二乘支持嚮量機%功率分佈重構%魯棒性
최소이승지지향량궤%공솔분포중구%로봉성
least square support vector machine%power distribution reconstruction%robustness
应用最小二乘支持向量机(LS‐SVM )进行了堆芯轴向功率分布重构的研究,通过6节堆内中子探测器的信号重构出堆芯轴向18个节块的功率。使用ACP‐100模块式小堆的7740套轴向功率分布对LS‐SVM重构算法进行了验证,实验结果表明:LS‐SVM算法的重构精度远优于交替条件期望(ACE)算法,且LS‐SVM算法具有良好的鲁棒性。
應用最小二乘支持嚮量機(LS‐SVM )進行瞭堆芯軸嚮功率分佈重構的研究,通過6節堆內中子探測器的信號重構齣堆芯軸嚮18箇節塊的功率。使用ACP‐100模塊式小堆的7740套軸嚮功率分佈對LS‐SVM重構算法進行瞭驗證,實驗結果錶明:LS‐SVM算法的重構精度遠優于交替條件期望(ACE)算法,且LS‐SVM算法具有良好的魯棒性。
응용최소이승지지향량궤(LS‐SVM )진행료퇴심축향공솔분포중구적연구,통과6절퇴내중자탐측기적신호중구출퇴심축향18개절괴적공솔。사용ACP‐100모괴식소퇴적7740투축향공솔분포대LS‐SVM중구산법진행료험증,실험결과표명:LS‐SVM산법적중구정도원우우교체조건기망(ACE)산법,차LS‐SVM산법구유량호적로봉성。
The application of the least square support vector machine (LS‐SVM ) to core axial power distribution reconstruction was researched ,and 18‐node powers were recon‐structed from six‐level in‐core detector signals .Axial power distributions of 7 740 cases of ACP‐100 modular reactor were used to verify the accuracy of the LS‐SVM reconstruction method .The results show that the LS‐SVM method performs much bet‐ter than the alternating conditional expectation (ACE) method and the LS‐SVM method has good robustness .