Small-Sample Transfer Learning Method for Aircraft Electrical Signal Classification and Recognition

Abstract

The invention relates to a migration learning method for classification and recognition of small-sample electrical signals of aircraft, comprising: collecting and transmitting source domain signals (102), sending them to a feature extraction basic module source domain multi-scale residual convolution module (103) and The maximum pooling layer (104) in the source domain sends the parameters in the basic module to the multi-scale residual convolution module (110) of the target domain and the maximum pooling layer (111) of the target domain. During the training process, the The global average pooling layer (112), the random dropout layer (113) of the target domain and the fully connected layer (114) of the target domain all need to perform backpropagation to update the network parameters (217) until the number of iteration steps is updated to meet the target domain iteration Step number judgment module condition (220), thereby finishes training (221). Through this method, the deep learning problem of small sample data in the actual test process is effectively solved, and the accuracy of aircraft signal classification and recognition is significantly improved.

Description

technical field [0001] The invention relates to a small-sample transfer learning method for classification and identification of aircraft electrical signals, which can be applied to the classification and identification of small-sample signals. Background technique [0002] In some areas of the aerospace field, few-shot learning is an important frontier direction in the field of deep learning. Since deep learning relies on a large amount of labeled data, the cost of time and money for the actual measurement experiment of the aircraft is extremely high, and a large amount of data cannot be collected. It is guaranteed that deep learning is prone to overfitting and it is difficult to extract enough features. However, small-sample transfer learning can effectively solve the problem of sample data volume and avoid over-fitting, and can use a small number of labeled samples to extract high-quality data features to achieve the purpose of signal classification and recognition. The...

AI Technical Summary

Problems solved by technology

Since deep learning relies on a large amount of labeled data, the cost of time and money for the actual measurement experiment of the aircraft is extremely high, and a large amount of data cannot be collected. Guaranteed, so deep learning is prone to overfitting and it is difficult to extract enough features

Images