Abstract
Given the insufficient early warning capacity of nuclear cold source biological disasters, this paper explores prediction methods for biomass caused by nuclear cold source disasters based on deep learning. This paper also uses the correlation analysis method to determine the main environmental factors. The adaptive particle swarm optimization method was used to optimize the depth confidence network model of the Gaussian continuous constrained Boltzmann machine (APSO-CRBM-DBN). To train the model, the marine environmental factors were used as the main input factors and the biomass after a period of time was used as the output for training. Optimal prediction results were obtained, and thus, the prediction model of biomass caused by the nuclear cold source disaster was established. The model provides an accurate scientific basis for the early warning of cold source disasters in nuclear power plants and has important practical significance for solving the problem of biological blockage at the inlet of cold source water in nuclear power plants.