In this paper, an intelligent fuzzy sliding mode control system, which cooperates with a new learning approach called modulus genetic algorithm, is proposed. Furthermore, it is applied to a high precision table positioning system for verifying its practicability. Fuzzy sliding mode controller (FSMC) is a special type of fuzzy controller with certain attractive advantages than the conventional fuzzy controller. The learning and stability issues of FSMC are discussed in the paper. Furthermore, to overcome the encoding/decoding procedure that leads to considerable numeric errors in conventional genetic algorithm, this paper proposes a new algorithm called modulus genetic algorithm (MGA). The MGA uses the modulus operation such that the encoding/decoding procedure is not necessary. It has the following advantages: (1) the evolution can be speeded up; (2) the numeric truncation error can be avoided; (3) the precision of solution can be increased. For verifying the practicability of the proposed approach, the MGA-based FSMC is applied to design a position controller for a high precision table. The experimental results show the proposed approach can achieve submicro positioning precision.
International Journal of Intelligent Systems 16(12), pp.1333-1356