Inversion Method for Multiple Nuclide Source Terms in Nuclear Accidents Based on Deep Learning Fusion Model

Abstract

During severe nuclear accidents, radioactive materials are expected to be released into the atmosphere. Estimating the source term plays a significant role in assessing the consequences of an accident to assist in actioning a proper emergency response. However, it is difficult to obtain information on the source term directly through the instruments in the reactor because of the unpredictable conditions induced by the accident. In this study, a deep learning-based method to estimate the source term with field environmental monitoring data, which utilizes the bagging method to fuse models based on the temporal convolutional network (TCN) and two-dimensional convolutional neural network (2D-CNN), was developed. To reduce the complexity of the model, the particle swarm optimization algorithm was used to optimize the parameters in the fusion model. Seven typical radionuclides (Kr-88, I-131, Te-132, Xe-133, Cs-137, Ba-140, and Ce-144) were set as mixed source terms, and the International Radiological Assessment System was used to generate model training data. The results indicated that the average prediction error of the fusion model for the seven nuclides in the test set was less than 10%, which significantly improved the estimation accuracy compared with the results obtained by TCN or 2D-CNN. Noise analysis revealed the fusion model to be robust, having potential applicability toward more complex nuclear accident scenarios.

Identification Method of Source Term Parameters of Nuclear Explosion Based on GA and PSO for Lagrange-Gaussian Puff Model

“…In existing studies of nuclear power plant accidents, the uncertainty of source term parameters is one of the main reasons for errors in the evaluation results [22][23][24]. To obtain more accurate source term parameters for nuclear accidents, techniques to invert the source term parameters of nuclear accidents based on monitoring data combined with artificial intelligence algorithms [25][26][27], or with swarm intelligence algorithms such as the cuckoo search algorithm [28], GA [29], and PSO [30] have been widely developed. The combination of these optimized algorithms and measured data can provide identification accuracy of source term parameters for accidents such as radioactive leaks in nuclear power plants of more than 95%, which provides a reference for research in the field of nuclear weapon explosions.…”