CN-116679793-B - Fan MPPT control method based on wind speed prediction and PID-DHDP

Abstract

The invention relates to the technical field of fan MPPT control, in particular to a fan MPPT control method based on wind speed prediction and PID-DHDP, and discloses a fan MPPT control method based on wind speed prediction and PID-DHDP. According to the fan MPPT control method based on wind speed prediction and PID-DHDP, wind speed is predicted through a GRU network, a wind speed prediction sequence value is obtained, a fan rotating speed reference value can be conveniently calculated through the wind speed prediction value and an optimal tip speed ratio, a deviation signal between the fan rotating speed reference value and an actual rotating speed value of the fan is used as an input signal of a PID-DHDP controller to form a closed-loop rotating speed control system, the fan rotating speed is stabilized at an optimal rotating speed, the fan outputs maximum power, and therefore fan MPPT control is achieved.

Inventors

• XIE XINGWANG
• WANG YOUHUI
• CHEN KANG
• LIAO XIANGYU
• TANG MIAO
• ZHANG MENGYAN
• ZHANG HAIYONG

Assignees

• 武昌理工学院

Dates

Publication Date

20260512

Application Date

20230713

Claims (1)

1. 1. The fan MPPT control method based on wind speed prediction and PID-DHDP is characterized by comprising the following steps: 1) Acquiring wind speed, temperature and humidity data in real time, and carrying out normalization processing on the data; 2) Optimizing GRU super parameters of the gate control circulation network by adopting a wolf swarm algorithm WPA; 3) The normalized data are used as input data of a GRU network, and the GRU network outputs a wind speed prediction sequence value; 4) Calculating a fan rotating speed reference value through a wind speed predicted value and an optimal tip speed ratio, taking a deviation signal between the fan rotating speed reference value and an actual fan rotating speed value as a controller input signal of PID-DHDP direct heuristic dynamic programming to form a closed-loop rotating speed control system, realizing that the fan rotating speed is stabilized at an optimal rotating speed, and outputting maximum power by the fan, thereby realizing MPPT control on the fan; the hidden layer in the GRU only comprises a reset gate and an update gate, wherein the reset gate and the update gate are used for controlling the degree of information transfer, and the input of the two gates is the input x t at the current moment and the hidden state h t-1 at the previous moment; The reset gate is responsible for determining how much memory information needs to be reserved, the input of the reset gate is formed by splicing the input x t at the current moment and the state h t-1 of the hidden layer at the previous moment, the reset gate outputs a number in a (0, 1) interval, the reserved proportion of the state h t-1 of the hidden layer at the previous moment is represented, and the output formula of the reset gate is as follows: (1) GRU discards and memorizes the input information through two gate structures, and calculates to obtain candidate hidden state value The calculation expression thereof is shown in the following formula (2): (2) Where f is the tanh activation function, x t represents the input at time t, h t-1 represents the hidden state at the last time, [ ] represents the two vectors connected, w h 、w r represents the weight matrix, Representing a sigmoid function; The input of the update gate is formed by splicing the input x t at the current moment and the state h t-1 of the hidden layer at the previous moment, the input of the update gate outputs a number in a (0, 1) interval, and the output formula of the update gate is shown as the formula (3): (3) After the tanh activation function obtains updated state information through the update gate, it creates vectors of all possible values according to the new input, calculates to obtain candidate hidden state values And then calculating the final state h t at the current moment through a network, wherein the calculation formula is shown in the formula (4): (4) According to the calculation formula, the GRU stores and filters information through two gates, important features are reserved through a gate function, dependency items are captured through learning, and then the optimal output value is obtained.

Description

Fan MPPT control method based on wind speed prediction and PID-DHDP Technical Field The invention relates to the technical field of fan MPPT control, in particular to a fan MPPT control method based on wind speed prediction and PID-DHDP. Background With the severe global warming and energy shortage situation, various countries are focusing on new energy industries, and at the same time, various new materials, new technologies and new processes are used for manufacturing fans, so that the performance of the fans is improved, and people, enterprises and governments are actively responding to low-carbon life and low-carbon economy, which greatly promotes the popularization of wind power generation. The wind wheel rotating speed of the wind driven generator is regulated, so that the tip speed ratio of the wind turbine is maintained near the optimal tip speed ratio in theory, and the maximum power tracking is realized, thereby fully utilizing the wind power and improving the economic and social benefits of wind farm enterprises. Because the wind speed is based on the characteristics of randomness, intermittence and volatility, how to improve the response tracking capability of the wind turbine to the rapid change of the wind speed and keep the fan working in the MPPT state as much as possible is a core problem. Disclosure of Invention (One) solving the technical problems Aiming at the defects of the prior art, the invention provides a fan MPPT control method based on wind speed prediction and PID-DHDP, which has the advantages of fan MPPT control and the like, and solves the problem of how to improve the response tracking capability of a wind turbine unit to rapid change of wind speed and keep the fan working in an MPPT state as far as possible because the wind speed is based on the characteristics of randomness, intermittence and fluctuation. (II) technical scheme In order to achieve the purpose of MPPT control of the fan, the invention provides the following technical scheme that the fan MPPT control method based on wind speed prediction and PID-DHDP comprises the following steps: 1) Acquiring data such as wind speed, temperature, humidity and the like in real time and carrying out normalization processing on the data; 2) Optimizing GRU super parameters of the gate control circulation network by adopting a wolf swarm algorithm WPA; 3) The normalized data are used as input data of a GRU network, and the GRU network outputs a wind speed prediction sequence value; 4) And calculating a fan rotating speed reference value through the wind speed predicted value and the optimal tip speed ratio, taking a deviation signal between the fan rotating speed reference value and the actual rotating speed value of the fan as a PID (proportion integration differentiation) namely proportional-integral-derivative control-DHDP direct heuristic dynamic programming controller input signal to form a closed loop rotating speed control system, realizing that the rotating speed of the fan is stabilized at the optimal rotating speed, and outputting the maximum power by the fan, thereby realizing MPPT control on the fan. Preferably, the hidden layer in the GRU only includes a reset gate and an update gate, where the reset gate and the update gate are used to control the degree to which information is transferred, and the inputs of the two gates are the input x t at the current time and the hidden state h t-1 at the previous time. Preferably, the reset gate is responsible for deciding how much memory information needs to be kept, and the input of the reset gate is composed of the input at the current momentAnd the state h t-1 of the hidden layer at the previous time is spliced, the number in a (0, 1) interval is output, the reserved proportion of the state h t-1 of the hidden layer at the previous time is represented, and the output formula of the reset gate is as follows: (1) GRU discards and memorizes the input information through two gate structures, and calculates to obtain candidate hidden state value The calculation expression thereof is shown in the following formula (2): (2) Wherein the method comprises the steps of For the tanh activation function, x t represents the input at time t, h t-1 represents the hidden state at the last time, [ ] represents the two vectors connected, w h、wr represents the weight matrix, σ () represents the sigmoid function. Preferably, the input of the update gate is composed of the input of the current momentAnd the state h t−1 of the hidden layer at the previous moment is spliced, and outputs a number in a (0, 1) interval, wherein the output of the update gate is shown as a formula (3): (3) After the tanh activation function obtains updated state information through the update gate, it creates vectors of all possible values according to the new input, calculates to obtain candidate hidden state values And then calculating the final state h t at the current moment through a network, wherein the calculatio