Non-affine system optimal fault-tolerant control method based on reinforced learning

The invention relates to a non-affine system optimal fault-tolerant control method, in particular to a non-affine system optimal fault-tolerant control method based on reinforced learning. The non-affine system optimal fault-tolerant control method comprises the following steps of: 1, converting a non-affine system into an affine system by using a system conversion technology; 2, designing a fixed time sliding mode observer; and 3, designing a fault-tolerant tracking controller. The optimal fault-tolerant controller under a performance index can be designed based on a reinforced learning technology, and the fault-tolerant control scheme can still enable the output of the system to well track a given reference value after a fault occurs; a non-affine system control design scheme is provided; the designed fixed-time sliding-mode observer can quickly and accurately estimate an unknown function; and the optimal fault-tolerant tracking controller under infinite time domain performance indexes is designed by using