Vector-controlled Permanent Magnet Synchronous Motor Drive Speed Identification Using General Regression Neural Network

Abstract

In this work, we established a speed identification scheme for the surface-mounted vectorcontrolled permanent magnet synchronous motor (PMSM) drive. The decoupled vectorcontrolled PMSM drive was developed using the stator current and voltage. The speed loop and two-axis stator current loops were designed in accordance with this decoupling mathematical model. Hall effect current sensors were used to detect the PMSM currents. A general regression neural network (GRNN) was used to develop the speed identification scheme, and smooth curve adaptation of the pattern layer was used in the modified particle swarm optimization (PSO) algorithm. The two-axis stator current controllers and speed controller were designed using the root locus and Bode plot. The MATLAB\Simulink ® toolbox was used to establish the simulation scheme and all control algorithms were realized using a TI DSP 6713-and-F2812 control card. Simulation and experimental results, including the estimated rotor speed, stator current, estimated electromagnetic torque, and the stator flux locus, confirmed the effectiveness of the proposed approach.

Application of Graph Convolutional Network in the Construction of Knowledge Graph for Higher Mathematics Teaching

“…The development of personalized teaching can be promoted, students' mathematical thinking and innovation abilities can be cultivated, and more intelligent and personalized solutions can be provided for future education. (23)(24)(25) Here, combined with the needs of GCN and mathematics disciplines, the construction and application of KGs of higher mathematics disciplines were carried out. Firstly, the relevant knowledge of higher mathematics in universities was collected and processed.…”