Heterogeneous federated learning mine electromagnetic radiation trend tracking method based on SVD algorithm

Abstract

The invention discloses a heterogeneous federated learning mine electromagnetic radiation intensity trend tracking method based on an SVD algorithm, and the method comprises: firstly proposing a heterogeneous model federated learning algorithm for the problem of data imbalance in a federated learning client, and setting a heterogeneous central model in a server for the client to select, so as to improve the precision of a local model; aiming at the problem of uploading communication cost of local model parameters, providing an efficient communication algorithm that an SVD algorithm is firstlyused for decomposing a parameter matrix to obtain a corresponding singular value matrix, and then the singular value matrix is uploaded to a central server for aggregation updating; and finally, usingthe updated local model by each client to extract local data features, and using the features and real data values by each client to train the ESN and then to execute trend tracking. According to theinvention, trend tracking of electromagnetic radiation intensity acquired by multiple sensors can be realized on the premise of protecting data privacy, the trend tracking precision of each client can be improved, and the communication cost required by a framework is reduced.

Description

technical field [0001] The invention belongs to the technical field of coal mine safety early warning, and in particular relates to a heterogeneous federated learning mine electromagnetic radiation intensity trend tracking method based on the SVD algorithm. Background technique [0002] At present, there are two main types of coal-rock dynamic disaster prediction methods at home and abroad, one is the conventional method, which uses static indicators such as stress measurement method, drilling cuttings volume, initial velocity of drilling gas gushing out and drilling cuttings gas desorption index Forecasting and forecasting, because coal-rock dynamic disasters are a process of continuous change in the dynamic characteristics of coal-rock mass, simply selecting the properties of coal-rock mass at a certain moment cannot fully reflect its changing characteristics. The other is the use of geophysical methods for forecasting. For example, the electromagnetic radiation method, ac...

AI Technical Summary

Problems solved by technology

However, in the current research on FL, in order to facilitate the aggregation of relevant parameters in the central server, it is assumed that each client uses the same learner model, and the difference of the model when processing sensory data with different sampling frequencies is not considered.

Images