The long-distance traditional belt conveyor driven by a single high-power motor has the problems of excessive tension increments and sharp fluctuations in speed and tension. This paper designs a distributed permanent magnet direct drive belt conveyor system. The dynamic model of the conveyor belt unit and the permanent magnet motor is analyzed. The multi-motor ring coupling control strategy and the double sliding film direct torque control strategy of the belt conveyor system are formulated. The mechanical-electrical coupling dynamic model of the belt conveyor system is built. Using MATLAB/Simulink modeling and simulation, the vector control strategy and electromechanical coupling dynamic behavior of the traditional belt conveyor system and the distributed permanent magnet direct drive belt conveyor system under light load start-up and local variable load operation conditions are studied. The results show that: the distributed permanent magnet direct drive belt conveyor system significantly reduces the peak of conveyor belt tension increment; the time spent under the starting light-load operation condition is shorter, and the fluctuation amplitude of speed and tension is smaller; it is possible to reduce the speed and tension fluctuation range of the conveying system and improve the robustness of the conveying system under local variable load conditions. Experiments have verified that increasing the number of drive motors in a conventional belt conveyor can suppress the disturbance caused by local load changes, and the distributed permanent magnet direct-drive belt conveyor has better dynamic regulation performance.

The power quality index is an important index in the power industry. Power quality disturbances (PQDs) have a great impact on the power grid. It is important to identify the type of PQDs accurately. However, it is difficult to analyze a large number of PQDs, especially in more complex power systems. Considering the limitations of the traditional time–frequency domain method and the complexity of the optimization algorithm in extracting features, a novel algorithm is proposed to classify the PQDs in this paper, which is based on the unscented Kalman filter (UKF) and the kernel extreme learning machine (KELM). The UKF is used to detect and process the original disturbances, and anti-noise detection performance is analyzed by tracking the amplitude change in voltage swell under different signal–noise ratios (SNRs). The amplitudes of the fundamental wave, third harmonic, fifth harmonic, seventh harmonic, and oscillatory wave are tracked in real time, and their minimum and peak indexes are taken as the optimal feature vector set. The feature vector set is classified by the KELM. The performance of the proposed method has also been evaluated with simulated and experimental results.