ANN-based MPPT algorithm for solar PMSM drive system fed by direct-connected PV array

作者：Deniz Erkan^*

来源：Neural Computing & Applications, 2017, 28(10): 3061-3072.

DOI：10.1007/s00521-016-2326-4

• Maximum power point tracking (MPPT)
• Artificial neural network (ANN)
• Low-voltage PMSM
• Vector control
• Kyocera KD205GX-LP

In this paper, artificial neural network (ANN) based on a maximum power point tracking (MPPT) algorithm is developed for a solar permanent magnet synchronous motor (PMSM) drive system used without a boost converter and batteries. The discontinuous space vector PWM technique is used to drive two-level inverter which is directly fed by three parallel-connected Kyocera KD205GX-LP PV modules. The ANN-based MPPT algorithm estimates the voltages and currents corresponding to maximum powers produced by PV array at the maximum power point (MPP) for swiftly changing situations such as solar radiance and temperature. These maximum powers are given as input signal to vector control algorithm of PMSM. The PMSM is designed by using Infolytica/MotorSolve software so that the phase-to-phase maximum value of its operating voltage is 20 V. The use of three-phase PMSM presents more efficient solutions to the trading solar systems with dc motor or induction motor. Thus, an effective solar system is achieved. The performance of developed ANN-based MPPT algorithm, designed PMSM, vector-controlled driver and solar system is analyzed by using MATLAB/SimPowerSystems blocks under the rapidly changing environmental conditions.

• 出版日期2017-10