Kernel recursive least squares algorithm-based adaptive aircraft robust control method

The invention provides a kernel recursive least squares algorithm-based adaptive aircraft robust control method. According to the technical scheme of the invention, an offline identifier and an online controller form a feedback adjusting system for realizing the adaptive adjustment. The offline identifier identifies a model equivalent to a measured system based on the recursive least squares algorithm on the basis of the input and output data of an aircraft actual model. The output quantity of the online controller is adjusted in the online manner based on the recursive least squares algorithm according to the input and output data of the system on the premise that the aircraft actual model is precisely identified. Therefore, the adaptive robust control is realized. The kernel recursive least squares algorithm is improved based on the characteristic value extraction, and the orthogonal decomposition of a kernel matrix is conducted based on the principal component analysis and the singular value decomposition