Multi-sensor data fusion method based on deep migration network

Abstract

The invention discloses a multi-sensor data fusion method based on a deep migration network. The multi-sensor data fusion method comprises the following steps of performing data preprocessing on acquired source domain data and target domain data of a plurality of sensors; constructing training data and test data; training a feature coding network and a classifier by using a deep neural network; calculating the maximum mean error loss and the corresponding classification loss of each coding network, calculating the inconsistent loss of all classifiers to the target domain sample output, optimizing the data classification, the maximum mean difference and the total loss generated by the classifier output, and obtaining an overall loss function; and inputting the target domain test data into each coding network to extract features, and outputting a final data fusion result. According to the fusion method, redundant and complementary information of different position sensors is effectively utilized, and a stable fusion result and high diagnosis precision are obtained. Meanwhile, the distribution difference between the test data and the training data can be effectively reduced.

Description

technical field [0001] The invention relates to data fusion technology, in particular to a multi-sensor data fusion method based on a deep migration network. Background technique [0002] With the continuous progress of today's science and technology, high-tech has been applied in many heavy equipment. On the one hand, various performances of the device are greatly improved; on the other hand, the technical and structural complexity of the device is significantly increased, which brings severe challenges to the diagnosis of the device. This has become a hot topic of current research. How to perfectly fuse the data of multiple sensors has become a problem that scholars need to consider. [0003] Sensor data fusion is divided into three layers: data layer, feature layer and decision layer. At present, the methods for sensor data fusion usually include: 1. Classical estimation methods, such as Kalman filtering, maximum likelihood estimation, etc.; 2. Classical traditional me...

AI Technical Summary

Problems solved by technology

However, the data layer fusion method needs to process a large amount of data, and the processing efficiency is low.

Images