论文部分内容阅读
利用前馈神经网络对激光等离子体打靶实验中所得的X光光谱数据进行处理，可以方便地求出等离子体的电子温度和电子密度等参数。在对网络的训练时采用误差信号反向传输算法，训练后的神经网络能够有效地对X光光谱数据进行处理。文中给出了用此法算出的Mg等离子体电子温度和电子密度的空间分布轮廓，与用传统方法所得的结果完全吻合。
By using the feedforward neural network to process the X-ray spectrum data obtained from laser plasma target experiment, parameters such as electron temperature and electron density of the plasma can be conveniently obtained. In the training of the network using error signal reverse transmission algorithm, the trained neural network can effectively deal with the X-ray spectrum data. The spatial distribution profile of electron temperature and electron density of Mg plasma calculated by this method is completely consistent with the results obtained by the traditional method.