Neural network-based zero offset temperature compensation method and device for fiber-optic gyroscope and storage medium

Abstract

The invention provides a zero offset temperature compensation method and device for a fiber-optic gyroscope based on a neural network, and a storage medium. The method comprises the following steps: preprocessing a collected training sample to obtain a preprocessed training sample, and training the neural network to obtain a zero offset temperature compensation model; optimizing the zero offset temperature compensation model based on target FPGA performance in the fiber-optic gyroscope to obtain an optimized zero offset temperature compensation model; the optimized zero offset temperature compensation model is deployed on the basis of resources of the target FPGA; and when the fiber-optic gyroscope is initialized, collecting the current temperature and a plurality of historical temperatures of the fiber-optic gyroscope, preprocessing the current temperature and the plurality of historical temperatures, inputting the current temperature and the plurality of historical temperatures into the optimized zero offset temperature compensation model on the target FPGA, and outputting a compensation temperature value to compensate the zero offset temperature of the fiber-optic gyroscope. According to the method, the current temperature and a plurality of historical temperatures of the fiber-optic gyroscope and the specially designed loss function are used, so that the temperature compensation precision of the fiber-optic gyroscope is improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence and fiber optic gyroscopes, in particular to a method, device and storage medium for compensating fiber optic gyroscope zero bias temperature based on neural network. Background technique [0002] Fiber optic gyroscope is an all-solid-state angular rate sensor based on the principle of Sagnac effect. It has the advantages of small size, light weight, fast startup, large dynamic range, overload resistance and shock resistance, etc. It has gradually become a research hotspot of inertial devices at home and abroad. [0003] Since the core of the fiber optic gyroscope, the fiber optic ring, is temperature-sensitive, thermal conduction or ambient temperature changes will cause the non-reciprocity of the fiber optic gyroscope, which will bring a large temperature drift to the fiber optic gyroscope. From the actual situation, when the ambient temperature changes, the scale factor, misali...

AI Technical Summary

Problems solved by technology

It is only to optimize the parameters of the neural network, and the compensation accuracy is not high. Therefore, how to improve the temperature compensation accuracy of the fiber optic gyroscope is a technical challenge for engineers and technicians.

Images