Subway foundation pit excavation risk identification method and device based on federated learning

Abstract

Embodiments of the invention disclose a subway foundation pit excavation risk identification method and device based on federated learning. The method comprises the following steps: each client node participating in federated learning acquires monitoring data of a subway foundation pit and obtains a standard sample; each client node performs encryption alignment processing on the local standard sample, and screens out a target data set from the encrypted standard sample; each client node trains a risk identification model based on the target data set to obtain local model parameters; a server node summarizes all local model parameters to obtain updated global model parameters, and feeds back the updated model global parameters to each client node; each client node continuously iterates, uploads and receives local parameters of the model until a loss function corresponding to the server node converges, and an optimized risk identification model is obtained; the optimized risk identification model is tested by adopting a verification set to obtain an optimal risk identification model; and a recognition result is determined by using the optimal risk recognition model. The method is higher in accuracy.

Description

technical field

[0001] The invention relates to the technical field of risk identification, in particular to a federated learning-based risk identification method and device for subway foundation pit excavation. Background technique

[0002] The identification of risk factors in subway foundation pit excavation is the key content of subway construction safety management, and it is also the premise to ensure the safety of subway foundation pit excavation. However, the traditional risk factor identification method mainly relies on manual experience investigation, expert on-site discussion, etc., which has a high degree of subjectivity; and as the construction environment becomes more and more complex, the types of risks are also increasing, and the traditional method can no longer Timely and comprehensive identification of risk factors. Therefore, there is an urgent need for a more objective, fast and intelligent risk identification method for the excavation of deep and large...

Images