使用基于Levenberg-Marquardt算法的人工神经网络对14.5MeV左右的(n,α)反应截面进行估算。
Estimations for (n,α) reaction cross sections at around 14.5MeV using Levenberg-Marquardt algorithm-based artificial neural network.
作者信息
Özdoğan Hasan, Üncü Yiğit Ali, Şekerci Mert, Kaplan Abdullah
机构信息
Antalya Bilim University, Vocational School of Health Services, Department of Medical Imaging Techniques, 07190, Antalya, Turkey.
Akdeniz University, Vocational School of Technical Sciences, Department of Biomedical Equipment Technology, 07070, Antalya, Turkey.
出版信息
Appl Radiat Isot. 2023 Feb;192:110609. doi: 10.1016/j.apradiso.2022.110609. Epub 2022 Dec 6.
Prediction of neutron-induced reaction cross-sections at around the 14.5 MeV neutron energy is crucial to calculate nuclear transmutation rates, nuclear heating, and radiation damage from gas formation in fusion reactor technology In this research, the new approach of (n,α) reaction cross-section is presented. It has been assessed by utilizing the artificial neural network (ANN) when compared to more advanced algorithms, the Levenberg-Marquardt algorithm-based ANN can be exceedingly fast. The correlation coefficients for a training R-value of 0.99283, a validation R-value of 0.991190, a testing R-value of 0.97337, and an overall R-value of 0.98515 demonstrate that Levenberg-Marquardt algorithm-based ANN is well suited for this purpose. . The obtained results were compared to theoretical calculations of TALYS 1.95 nuclear code. As a consequence, it has been demonstrated that the ANN model can be used to determine the systemic study for (n, α) reaction cross-sections.
预测14.5 MeV左右中子能量下的中子诱发反应截面对于计算聚变反应堆技术中的核嬗变速率、核加热以及气体形成导致的辐射损伤至关重要。在本研究中，提出了一种新的(n,α)反应截面方法。与更先进的算法相比，利用人工神经网络(ANN)对其进行了评估，基于Levenberg-Marquardt算法的ANN速度极快。训练R值为0.99283、验证R值为0.991190、测试R值为0.97337以及总体R值为0.98515的相关系数表明，基于Levenberg-Marquardt算法的ANN非常适合此目的。将所得结果与TALYS 1.95核代码的理论计算结果进行了比较。结果表明，ANN模型可用于确定(n,α)反应截面的系统研究。
Zotero 插件