Research on the application and compensation for startup process of FOG based on RBF neural network

As the core components of Fiber Optic Gyroscope (FOG) are sensitive to temperature, there is a certain temperature drift error in the working process of FOG. In particular, during the period from supplying power to achieving the nominal precision, the temperature drift of FOG is much higher. In this paper, for reducing the drift in the startup process of FOG and shortening the time of FOG startup, a scheme based on Radial Basis Function (RBF) neural networks is designed to compensate the drift in the startup process of FOG. The RBF neural network use the two inputs and single output scheme that use the temperature of FOG and the temperature change rate as the inputs and use the drift of FOG as the output. In the room temperature, the RBF neural network is used to compensate for the startup process of FOG, and the results show that the method can effectively reduce the drift and startup time of the FOG. This method is used in a certain type of FOG North Finder and can greatly reduce the North Finder preparation time and improve the north-seeking accuracy.