Magnetic suspension vertical-axis wind power unit control method based on neural network model prediction control

A neural network model, predictive control technology, applied in neural network algorithms, control generators, wind turbine combinations, etc., can solve the problem of little research on neural network model predictive control applications
CN110345013AActive Publication Date: 2019-10-18三零六零实验室(北京)科技有限公司
5 Cites 7 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
三零六零实验室(北京)科技有限公司
Publication Date
2019-10-18

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a magnetic suspension vertical-axis wind power unit control method based on neural network model prediction control, and belongs to the technical field of wind power. The method comprises the steps that a neural network model prediction control strategy is adopted for conducting real-time steady control over a magnetic suspension vertical-axis wind power unit; when the wind speed reaches the cut-in wind speed, a suspension converter adopts a PID control algorithm and the neural network model prediction control strategy to control the suspension current, so that a generator rotating body rises and keeps at a suspension balance point; when the wind speed is between the cut-in wind speed and the rated wind speed, the suspension converter ensures that the rotating bodyis kept at a balance point in the rotating process; and meanwhile, a unit-side converter and a rotor-side converter adopt neural network model prediction control and zero-d axis current control strategies for conducting MPPT control over the wind power unit; and when the wind speed is larger than the rated wind speed and is smaller than the cut-out wind speed, the suspension converter carries outrotary damping control, and the unit-side converter carries out constant-power control. According to the magnetic suspension vertical-axis wind power unit control method, the control is easy and convenient to achieve, and low-wind-speed starting and high-power output can be realized.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a control method, in particular to a control method for a maglev vertical axis wind turbine based on neural network model predictive control, and belongs to the technical field of wind power. Background technique

[0002] At present, the mainstream products of high-power wind turbines are horizontal axis wind turbines. However, horizontal-axis wind turbines have inherent defects such as the need to yaw against the wind, large starting resistance torque, complex and difficult control, inconvenient installation, and high cost, which affect their healthy development, especially difficult to meet the low wind speed start-up requirements of weak wind wind farms.

[0003] Because there is no mechanical friction, the maglev vertical axis wind turbine greatly reduces the starting resistance torque, so it can further reduce the starting wind speed. It has the advantages of low starting wind speed, easy installation, and no yaw device. ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More