Abstract: In order to realize the precise control of the outer rotor coreless bearingless permanent magnet synchronous generator (ORC-BPMSG), a decoupling control strategy of ORC-BPMSG based on the least squares support vector machine (LS-SVM) inverse system optimized by the improved genetic algorithm (IGA) is proposed. First, based on the structure and working principle of the ORC-BPMSG, its mathematical model is deduced, and its reversibility is analyzed. Second, the LS-SVM regression equation is established, and IGA is used to optimize the performance parameters of LS-SVM, so as to train the inverse system. Then, the inverse system is concatenated with the original system to form a pseudo-linear system, which realizes the linearization and decoupling of the ORC-BPMSG. Finally, the proposed control method is compared with the traditional LS-SVM inverse system control method for simulation and experiments. The simulation and experimental results show that the proposed control strategy can better achieve the decoupling control among output voltage and suspension forces, as well as the decoupling control between the suspension forces of the ORC-BPMSG.