Neural Network-Based Direct Positioning Deviation Correction Method under the Condition of Array Amplitude and Phase Error

Abstract

The invention relates to a method for correcting direct positioning deviation based on a neural network under an array amplitude phase error condition. The method comprises the following steps: distributing a plurality of correction sources in a preset region, and acquiring a group of correction source estimated position and real position information aiming at each correction source; inputting theestimated position and real position information of all correction sources as a training set into a preset multi-layer perceptron neural network for training; acquiring the trained multi-layer perceptron neural network; and estimating a position with deviation caused by an array amplitude phase error according to a collected array signal including target position information, and inputting the position into the trained multi-layer perceptron neural network, so as to obtain the corrected target position. According to the method, the estimation of an array error matrix is omitted, and the correction of the target position is directly finished, so that the influence caused by the array amplitude phase error to the positioning precision can be inhibited to a certain extent, the positioning precision of a target under the amplitude phase error condition is improved, and the performance is stable, reliable and efficient.

Description

technical field [0001] The invention belongs to the technical field of radio signal positioning, in particular to a neural network-based direct positioning deviation correction method under the condition of array amplitude and phase errors. Background technique [0002] As we all know, radio signal positioning is of great significance for target discovery and situational awareness, and it is widely used in many engineering science fields such as communication signal reconnaissance, electronic information countermeasures, radio monitoring, telemetry and navigation. The traditional two-step positioning method, that is, each array observation station first estimates positioning parameters, such as time of arrival (Time of Arrival, TOA), angle of arrival (Direction of Arrival, DOA), etc., and then transmits these positioning parameters to the central station for For position calculation, its positioning performance is subject to the estimation accuracy of positioning parameters,...

AI Technical Summary

Problems solved by technology

At present, there are relatively few studies on the application of neural network methods to array deviation correction for direct positioning.

Images