ABSTRACT
Fiber optic gyroscope has the advantages of simple structure, no moving parts, quick start, low power consumption, small volume, light weight, impact resistance, wide coverage of accuracy, large dynamic range. It has been widely used in the field of aviation, aerospace, weapons, oil exploration and geological prospecting.[1-2] Due to the core components of fiber, optic gyroscopes are more sensitive to temperature, so the change in temperature is one of the important factors aecting the performance of fiber-optic gyro. At present, many scholars at home and abroad put forward some modeling compensatory method through research on reasons of the temperature drift error of fiber optic gyro, such as polynomial model, neural network models, wavelet variance model [3], fuzzy model [4], controlled Markov chain model, etc. [5]. In recent years, the application of neural network for the temperature compensation for fiber optic gyro has become a research hot spot.
