Unmanned aerial vehicle aeromagnetic holoaxial gradient magnetic disturbance compensation method based on feedforward network

Abstract

The invention provides an unmanned aerial vehicle aeromagnetic holoaxial gradient magnetic disturbance compensation method based on a feedforward network. The method includes the steps that calibrated flight data is subjected to preprocessing operation of wavelet transform and normalization, normalized feedforward network input vectors are transmitted into the established feedforward network to be trained, a regularized cost function is adopted, stable feedforward network parameters are iteratively obtained through an error back-propagating algorithm, and a finally convergent network serves as a compensation network; exploration flight data is subjected to identical preprocessing operation and transmitted to the obtained compensation network to be calculated, estimation of an airplane disturbing magnetic field is obtained, and magnetic disturbance compensation is obtained. The stable network parameters are obtained by training the feedforward network, the network serves as the compensation network for compensating for the exploration flight data, the problems of inverse matrix instability and over-fitting in a least squares algorithm are effectively avoided, the generalization performance of the feedforward network is expanded, and unmanned aerial vehicle aeromagnetic holoaxial gradient magnetic disturbance compensation is achieved.

Description

technical field [0001] The invention belongs to the field of geophysical aeromagnetic exploration, and relates to a method for compensating unmanned aerial vehicle aeromagnetic full-axis gradient magnetic interference based on a feedforward network. Background technique [0002] As an important means of airborne geophysical prospecting, aeromagnetic prospecting has been widely used in the field of geophysics. The traditional aeromagnetic prospecting platform is mainly manned and manned. In the past ten years, with the development of UAV technology, UAVs have been It is widely used in the field of airborne magnetic prospecting. Compared with manned aircraft, unmanned aerial vehicles have significant advantages such as low cost, high efficiency, and safety. However, due to the characteristics of small aircraft size and short baseline between probes, unmanned aerial vehicles interfere with the magnetic field in the acquired aeromagnetic gradient data. The impact is very signif...

AI Technical Summary

Problems solved by technology

[0004] The compensation method based on the least squares algorithm is easy to cause overfitting, and the generalization performance of the algorithm is limited. There is a problem of complex collinearity in the traditional aeromagnetic compensation algorithm model. When using the least squares algorithm to invert the characteristic matrix , the inverse matrix is ​​unstable because the condition number is too large, and this problem cannot be solved well; , yaw and other maneuvering flight, so the calibration flight designed for manned aircraft cannot be applied to common UAVs

Images