Maglev systems using reluctance actuators (RAs) are increasingly being used in ultra-precision motion platforms due to the non-contact feature of the guide rails. However, because the control system of RAs suffers from strong nonlinearity and uncertainty, it is challenging to realize the high-precision position control of RAs. In this paper, a fractional-order sliding mode control with adaptive neural network (ANN-FSMC) approach is proposed to achieve high-precision position control of RAs. Based on the basic sliding mode control (SMC) approach, the proposed ANN-FSMC introduces the sliding surface with the term of fractional-order calculus. It guarantees that the state converges to the sliding manifold with fast response and small overshoot, and enhances the positioning precision of RAs. Besides, the radial basis function (RBF) neural network is utilized to compensate for the lumped disturbances including magnetic flux leakage, fringe flux, eddy currents, and uncompleted hysteresis compensation, etc. The stability of ANN-FSMC is analyzed and proved according to the Lyapunov Theorem. Finally, experiments are conducted on an RA-based maglev-guided system, and results show that ANN-FSMC can improve the position control performance and disturbance suppression capability of RAs more effectively than the conventional SMC method combined with RBF neural networks.