Control method and system for direct-drive permanent magnet hydroelectric generation system on basis of fuzzy control, terminal and readable storage medium

Abstract

The invention discloses a control method and system for a direct-drive permanent magnet hydroelectric generation system on the basis of fuzzy control, a terminal and a readable storage medium. The control method aims at solving the problems that in the conventional maximum power tracking control process of a water turbine, the tracking speed is low, the steady-state precision is low, and the efficiency of the water turbine is reduced due to the fact that a large amount of energy is easily lost in the tracking process. A water turbine comprehensive characteristic curve is used for extracting power P, rotating speed n and flow Q data, BP (back propagation) neural network training is carried out on the power P, rotating speed n and flow Q data, and a neural network off-line model is obtained. According to the method, the neural network off-line model is used for evaluating the initial rotating speed, then the fuzzy control MPPT (maximum power point tracking) is used for tracking the maximum power, the combination of a neural network and a fuzzy controller is realized, in addition, the influence of the flow Q change is also considered, a new maximum power point is rapidly tracked, the power loss and the energy waste are reduced, and the efficiency of the water turbine is improved.

Description

technical field

[0001] The invention belongs to the technical field of hydroelectric power generation, and in particular relates to a control method, system, terminal and readable storage medium of a direct-drive permanent magnet hydroelectric power generation system based on fuzzy control. Background technique

[0002] Hydropower is recognized as a non-polluting and renewable energy source in the world. Compared with other traditional fossil energy sources, hydropower does not undergo chemical changes in the process of converting into electrical energy, does not emit harmful substances, and does not pollute the air and water. high-quality renewable energy. Among them, the constant speed and constant frequency system is limited by the frequency of the power grid, which greatly limits the output of the turbine, so the variable speed and constant frequency hydropower technology has been developed. Among them, the direct-drive permanent magnet hydroelectric power generation sy...

Examples

Embodiment 1

[0062] The focus of this embodiment is to use the fuzzy controller to realize maximum power tracking. The fuzzy controller constructed in this embodiment will be described below.

[0063] For a certain flow rate, the speed-power curve of the turbine is an approximate parabola, and the unique maximum power point is tracked by continuously changing the speed of the turbine. Therefore, the fuzzy controller constructed in this embodiment is a two-dimensional fuzzy controller. The input data of the fuzzy controller are the power variation Pe within the sampling time T and the rotational speed variation Sn-1 at the previous moment. The output data of the fuzzy control is The amount of speed change Sn at the current moment. Compared with the perturbation and observation method, using the fuzzy controller can change the speed step size in real time, and can speed up the tracking speed and reduce the steady-state oscillation at the maximum power point in the non-optimal operating regi...

Embodiment 2

[0077] Such as figure 1 As shown, in this embodiment, neural network and fuzzy control are combined to improve tracking efficiency and accuracy. The fuzzy control-based direct-drive permanent magnet hydroelectric power generation system control method provided in Embodiment 2 includes:

[0078] S1-1: Input the flow Q and power P of the water turbine into the neural network to predict the initial speed of the water turbine, wherein the neural network uses the comprehensive characteristic curve power P and flow Q of the water turbine as the training input data, and the speed n as the training output data and obtained through network training. Since the comprehensive characteristic curve data of the water turbine is used as the training data, the trained model can be approximated as the speed-power curve of the current water turbine, so the output speed n of the neural network is not necessarily the optimal speed of the actual water turbine operation, but in the most In the ran...

Embodiment 3

[0090] Such as figure 2 As shown, in this embodiment, it is considered that in actual working conditions, with the influence of weather or seasons, the flow rate that is easy to cause changes, therefore, this embodiment 3 provides a fuzzy control-based direct-drive permanent magnet hydropower system control The method is applied to the working condition of the variable flow rate of the water turbine, and the control method includes:

[0091] S2-1: Collect the power and calculate the variation Pe. If Pm>Pe>Ps, it means that due to the influence of weather or seasons, the flow Q changes greatly and the turbine deviates from the optimal speed. Step S2-2 is performed; if PcPm, the change of flow Q is large, and the current speed is far from the optimal speed, go to step S2-4. Among them, Pm and Ps are variable thresholds set for the power difference generated when the flow rate changes while the speed remains unchanged. That is, the power change threshold set based on this worki...

technical field

[0001] The invention belongs to the technical field of hydroelectric power generation, and in particular relates to a control method, system, terminal and readable storage medium of a direct-drive permanent magnet hydroelectric power generation system based on fuzzy control. Background technique

[0002] Hydropower is recognized as a non-polluting and renewable energy source in the world. Compared with other traditional fossil energy sources, hydropower does not undergo chemical changes in the process of converting into electrical energy, does not emit harmful substances, and does not pollute the air and water. high-quality renewable energy. Among them, the constant speed and constant frequency system is limited by the frequency of the power grid, which greatly limits the output of the turbine, so the variable speed and constant frequency hydropower technology has been developed. Among them, the direct-drive permanent magnet hydroelectric power generation sy...

Examples

Embodiment 1

[0062] The focus of this embodiment is to use the fuzzy controller to realize maximum power tracking. The fuzzy controller constructed in this embodiment will be described below.

[0063] For a certain flow rate, the speed-power curve of the turbine is an approximate parabola, and the unique maximum power point is tracked by continuously changing the speed of the turbine. Therefore, the fuzzy controller constructed in this embodiment is a two-dimensional fuzzy controller. The input data of the fuzzy controller are the power variation Pe within the sampling time T and the rotational speed variation Sn-1 at the previous moment. The output data of the fuzzy control is The amount of speed change Sn at the current moment. Compared with the perturbation and observation method, using the fuzzy controller can change the speed step size in real time, and can speed up the tracking speed and reduce the steady-state oscillation at the maximum power point in the non-optimal operating regi...

Embodiment 2

[0077] Such as figure 1 As shown, in this embodiment, neural network and fuzzy control are combined to improve tracking efficiency and accuracy. The fuzzy control-based direct-drive permanent magnet hydroelectric power generation system control method provided in Embodiment 2 includes:

[0078] S1-1: Input the flow Q and power P of the water turbine into the neural network to predict the initial speed of the water turbine, wherein the neural network uses the comprehensive characteristic curve power P and flow Q of the water turbine as the training input data, and the speed n as the training output data and obtained through network training. Since the comprehensive characteristic curve data of the water turbine is used as the training data, the trained model can be approximated as the speed-power curve of the current water turbine, so the output speed n of the neural network is not necessarily the optimal speed of the actual water turbine operation, but in the most In the ran...

Embodiment 3

[0090] Such as figure 2 As shown, in this embodiment, it is considered that in actual working conditions, with the influence of weather or seasons, the flow rate that is easy to cause changes, therefore, this embodiment 3 provides a fuzzy control-based direct-drive permanent magnet hydropower system control The method is applied to the working condition of the variable flow rate of the water turbine, and the control method includes:

[0091] S2-1: Collect the power and calculate the variation Pe. If Pm>Pe>Ps, it means that due to the influence of weather or seasons, the flow Q changes greatly and the turbine deviates from the optimal speed. Step S2-2 is performed; if PcPm, the change of flow Q is large, and the current speed is far from the optimal speed, go to step S2-4. Among them, Pm and Ps are variable thresholds set for the power difference generated when the flow rate changes while the speed remains unchanged. That is, the power change threshold set based on this worki...

Images