Temperature Compensation of MEMS-Gyro Based on Improving Cuckoo Search and Support Vector Machines

Aiming at the problem that the zero bias of an MEMS gyro is greatly influenced by temperature, a gyro zero bias temperature compensation method based on the combination of the cuckoo search (CS) algorithm and the support vector machine (SVM) is proposed. Firstly, the smoothed gyro data is taken as the sample point. The SVM method based on the radial basis kernel function is used to construct the drift model, and the data is mapped from the low dimensional space to the high dimensional space for linear fitting. Then, the cuckoo algorithm is used to optimize the penalty vector, kernel function parameters and insensitivity coefficient of the SVM, avoid the blindness of the artificially selected parameters, and improve the accuracy of the established model. The experimental results show that the gyro output accuracy is higher after CS compensation and vector machine algorithm compensation. Compared with the least-squares segmented fitting method and the BP neural network method, the gyro output data variances decrease by 63.2% and 43.4%, respectively, and the maximum errors decrease by an average of 71.63% and 48.3%, respectively. © 2019, Editorial Dept. of JA. All right reserved.