基于改进UNet模型的截断脉冲高度估计器

Truncated pulse height estimator based on an improved UNet model

针对测量系统本身导致的脉冲截断给脉冲高度分析带来的挑战,本研究提出一种复合神经网络模型,用于预测产生了截断的脉冲高度。该模型将长短期记忆模型(Long and Short-term Memory,LSTM)嵌入UNet结构,采用模拟脉冲数据集对模型进行训练,使用相对误差指标对模型性能进行评估。结果显示:在对模拟脉冲序列进行脉冲高度估计时,UNet-LSTM模型的平均相对误差约为2.31%,相较于传统的梯形成形算法的平均相对误差降低了1.91%;在粉末铁矿样品和粉末岩石样品的实际测量中,不同截断率的实测脉冲序列也进一步验证了UNet-LSTM模型的脉冲高度估计性能,在两种样品、8组离线脉冲序列的高度估计中得到的平均相对误差为2.36%,表明该模型可以准确估计截断脉冲的高度。

[Background]Generally,pulse truncation events caused by measurement systems often present challenges to pulse height analysis in the field of spectroscopy and radiometry,resulting in spectral distortion.[Purpose]This study aims to propose a composite neural network model for accurately estimating the heights of truncated pulses.[Methods]Firstly,a long and short-term memory(LSTM)network was embedded into the UNet structure to construct a composite neural network model(LSTM-UNet).Then,the model was trained for height estimation of truncated pulses output by silicon drift detectors using a simulated pulse dataset for which the pulse amplitude matrix superimposed with noise was taken as input signal while the output signal was a set of expanded pulse heights.Finally,the performance of the model using relative error indicators was evaluated by analyses of powder iron ore and powder rock samples.[Results]The average relative error of the UNet-LSTM model for pulse height estimation analysis on simulated pulse sequences is approximately 2.31%,which is 1.91%lower than the average relative error of traditional trapezoidal shaping algorithms.Verification results of the UNet-LSTM model on measured pulse sequences with different degrees of truncation show that the average relative error obtained during the height estimation of two samples and eight sets of offline pulse sequences is 2.36%.[Conclusions]The results reveal that the proposed model can accurately estimate truncated pulse heights.