论文标题
通过配对和外壳效果的人工神经网络对核$α$ decay Energy的研究
Study on nuclear $α$-decay energy by an artificial neural network with pairing and shell effects
论文作者
论文摘要
我们基于实验性$α$ -Decay Energy（$q_α$）数据来构建和训练人工神经网络模型（ANN）。除了父母核和子核之间的基础状态之间的衰变外，还包括从父核的基础状态腐烂到子核的激发状态。这样，样本的数量大大增加。 ANN模型计算得出的结果以良好的精度重现了实验数据。相对于实验数据的根平方（RMS）为0.105 meV。研究了不同输入的影响。发现壳效应或配对效应会导致ANN模型的预测能力明显提高，并且壳效应起着更重要的作用。可以同时考虑壳和配对效应，因此可以获得最佳结果。 ANN模型在预测$α$ -DECAY ENergy中的应用显示了中子魔法数量为$ n = 184 $，并且在超核Nuclei区域中可能存在$ n = 174 $或176的子壳差距。
We build and train the artificial neural network model (ANN) based on the experimental $α$-decay energy ($Q_α$) data. Besides decays between the ground states of parent and daughter nuclei, decays from the ground state of parent nuclei to the excited state of daughter nuclei are also included. By this way, the number of samples are increased dramatically. The results calculated by ANN model reproduce the experimental data with a good accuracy. The root-mean-square (rms) relative to the experiment data is 0.105 MeV. The influence of different input is investigated. It is found that either the shell effect or the pairing effect results in an obvious improvement of the predictive power of ANN model, and the shell effect plays a more important role. The optimal result can be obtained as both the shell and pairing effects are considered simultaneously. Application of ANN model in prediction of the $α$-decay energy shows the neutron magic number at $N=184$, and a possible sub-shell gap around $N=174$ or 176 in the superheavy nuclei region.
