Abstract A recent investigation proposed a simulated radioactive particle tracking (RPT) system using eight scintillator detectors in order to predict instantaneous positions of a radioactive particle inside a concrete mixer using an artificial neural network as a location algorithm. In the context of RPT, the aim of the present study is to propose an optimization in the number of detectors in a single-phase flow RPT system. The new detection geometry consists of an array of six NaI(Tl) detectors, a 137Cs point source with isotropic emission of gamma-rays (radioactive particle) and a polyvinyl chloride mixer filled with concrete made with Portland cement as a homogenous flow regime. Another feature of this study is the use of MCNP6 code, which is based on Monte Carlo Method. In addition, three feed-forward multilayer perceptron networks with different configuration are tested as a location algorithm. All three networks showed good statistical results and the root mean square error is 1.18 in the worst scenario. The results also showed an agreement with previous study, which indicates that this methodology reducing two detectors works satisfactorily and maintain a good accuracy in position prediction.

中文翻译：

---

使用MCNP6代码和人工智能方法优化单相流中放射性粒子跟踪方法

摘要 最近的一项研究提出了一种使用八个闪烁体探测器的模拟放射性粒子跟踪 (RPT) 系统，以使用人工神经网络作为定位算法来预测混凝土搅拌机内放射性粒子的瞬时位置。在 RPT 的背景下，本研究的目的是提出对单相流 RPT 系统中检测器数量的优化。新的探测几何结构由六个 NaI(Tl) 探测器阵列、一个具有各向同性发射伽马射线（放射性粒子）的 137Cs 点源和一个聚氯乙烯混合器组成，该混合器中填充了由波特兰水泥制成的混凝土作为均匀流动状态。本研究的另一个特点是使用了基于蒙特卡罗方法的 MCNP6 代码。此外，测试了具有不同配置的三个前馈多层感知器网络作为定位算法。所有三个网络都显示出良好的统计结果，最坏情况下的均方根误差为 1.18。结果还表明与之前的研究一致，这表明这种减少两个探测器的方法工作令人满意，并保持了良好的位置预测精度。