JP2024036899A - Power generating system - Google Patents

Abstract

To provide a power generating system in which a voltage superimposition device controls a voltage applied by following changes in an AC voltage output by a generator.SOLUTION: A power generating system 100 includes a wind power generation device 10, a voltage superimposition device 30, a control device 40, and a prediction device 90. The voltage superimposition device 30 applies a voltage with a waveform of an opposite phase to a waveform of a noise component out of an AC voltage output by a generator 18 of the wind power generation device 10. The prediction device 90 stores mapping data 94A that defines a mapping M that outputs an output variable that indicates a prediction waveform of the noise component after a predetermined constant time by inputting a plurality of input variables. The mapping M is learned by machine learning in advance. The prediction device 90 executes acquiring processing for acquiring input variables, and calculation processing for outputting a value of the output variable by inputting the plurality of input variables to the mapping. The control device 40 controls a voltage applied by the voltage superimposition device 30 based on the prediction waveform shown by the output variable.SELECTED DRAWING: Figure 1

Description

The present invention relates to a power generation system.

The power generation system of Patent Document 1 includes a wind power generator, a sound collector, a speaker, and a control circuit. A wind power generation device includes a wind turbine and a generator. The sound collector captures the noise generated by the wind power generator. The control circuit converts the noise waveform acquired by the sound collector into a waveform with an opposite phase. Then, the control circuit outputs a sound with an opposite phase waveform from the speaker toward the wind power generator. As a result, part of the noise generated by the wind power generator is canceled out by the sound output from the speaker.

JP2014-227977A

In a power generation system such as Patent Document 1, when the wind speed of wind colliding with a wind turbine of a wind power generator changes, the rotation speed of the wind turbine and the rotation speed of the rotation shaft of the generator change thereafter. The waveform of the noise generated by the wind power generator changes depending on the rotational speed of the rotating shaft. If the waveform conversion processing performed by the control circuit cannot follow such changes in the noise waveform, there is a possibility that the noise generated by the wind power generator cannot be sufficiently suppressed.

A power generation system for solving the above problem includes a wind power generation device having a wind turbine and a generator, and applying a voltage with a waveform of an opposite phase to the waveform of the noise component of the AC voltage outputted by the generator. A power generation system comprising a voltage superimposition device, a control device that controls the voltage superimposition device, and a prediction device that predicts a waveform of the noise component, the prediction device including an execution device and a storage device. The storage device stores mapping data that defines a mapping that outputs an output variable indicating a predicted waveform of the noise component after a predetermined period of time by inputting a plurality of input variables. , the mapping is learned in advance by machine learning, the mapping includes a variable indicating the wind speed of the wind colliding with the wind turbine as one of the input variables, and the execution device and a calculation process of outputting the value of the output variable by inputting the plurality of input variables acquired by the acquisition process into the mapping, and the control device executes the calculation process of outputting the value of the output variable. The voltage applied by the voltage superimposition device is controlled based on the predicted waveform indicated by a variable.

According to the above configuration, by applying a voltage with a waveform that is opposite in phase to the waveform of the noise component of the AC voltage output from the generator, the AC voltage output from the generator approaches an ideal sine wave. . Therefore, the rotating shaft of the generator rotates smoothly, so the noise generated by the generator can be suppressed. The voltage having the opposite phase waveform is generated based on the predicted waveform of the noise component after a certain period of time. In this way, if the predicted waveform of the noise component after a certain period of time can be grasped, the voltage superimposition device can follow changes in the AC voltage output by the generator, even in situations where control delays may occur in the control device, for example. The applied voltage can be controlled.

FIG. 1 is a schematic configuration diagram of a power generation system. 3 is a flowchart showing predictive control.

<Schematic configuration of power generation system>
An embodiment of the present invention will be described below with reference to FIGS. 1 and 2. First, the schematic configuration of the power generation system 100 will be described.

As shown in FIG. 1, the power generation system 100 includes a wind power generation device 10, a voltage superimposition device 30, and a control device 40.
The wind power generation device 10 includes a tower 11, a nacelle 12, and a wind turbine 13. The wind power generation device 10 also includes a speed increaser 16, a brake device 17, a generator 18, and a power line 19. The windmill 13 is rotatable relative to the nacelle 12 due to the wind impinging on the windmill 13 . Nacelle 12 accommodates a speed increaser 16, a brake device 17, and a generator 18. The generator 18 includes a rotating shaft 18A. The rotating shaft 18A is connected to the wind turbine 13 via a speed increaser 16 and a brake device 17. Therefore, when the windmill 13 rotates, the speed of the rotation is increased by the speed increaser 16 and transmitted to the rotating shaft 18A. The power line 19 supplies the electric power generated by the generator 18 to electrical equipment (not shown). Note that the brake device 17 decelerates the windmill 13 when the rotational speed of the windmill 13 becomes excessive.

The voltage superimposition device 30 is located in the middle of the power line 19. The voltage superimposition device 30 applies a voltage having a waveform of an opposite phase to the waveform of the noise component of the AC voltage output by the generator 18 . The control device 40 and the voltage superimposing device 30 can communicate with each other. The control device 40 controls the voltage superimposing device 30 by outputting a control signal to the voltage superimposing device 30. Specifically, the control device 40 controls the voltage output by the voltage superimposition device 30 based on a predicted waveform of a noise component calculated by a prediction device 90 described later. Note that the control device 40 can detect the AC voltage on the power line 19 via the voltage superimposition device 30.

The power generation system 100 includes a wind speed sensor 51, a temperature sensor 52, a humidity sensor 53, a rotation axis angle sensor 54, and a communication device 57. The wind speed sensor 51 detects the wind speed SW, which is the flow speed of the wind colliding with the wind turbine 13. Temperature sensor 52 detects internal temperature TE, which is the temperature inside nacelle 12 . As an example, the temperature sensor 52 detects the temperature inside the nacelle 12 near the generator 18 as the internal temperature TE. Humidity sensor 53 detects internal humidity LH, which is the humidity inside nacelle 12 . As an example, the humidity sensor 53 detects the humidity inside the nacelle 12 near the generator 18 as the internal humidity LH. The rotating shaft angle sensor 54 detects the rotating shaft angle SR, which is the angular position of the rotating shaft 18A of the generator 18. The communication device 57 can acquire date information ID and time information IT by communicating with equipment external to the power generation system 100. Here, the date information ID is information that includes "month" and "day" as the current date. Further, the time information IT is information including "hour" and "minute" as the current time.

The power generation system 100 includes a prediction device 90. The prediction device 90 acquires signals indicating various values from the wind speed sensor 51 , temperature sensor 52 , humidity sensor 53 , rotation axis angle sensor 54 , and communication device 57 . Note that the prediction device 90 can detect the AC voltage on the power line 19 via the control device 40 and the voltage superimposition device 30. The prediction device 90 calculates the generator rotation speed NR, which is the rotation speed of the rotation shaft 18A, based on the rotation shaft angle SR.

The prediction device 90 predicts the noise component of the AC voltage output by the generator 18. Specifically, the prediction device 90 includes a CPU 91, a peripheral circuit 92, a ROM 93, a storage device 94, and a bus 95. The ROM 93 stores various programs in advance for the CPU 91 to execute various processes. The storage device 94 stores the above various values acquired by the prediction device 90. The storage device 94 stores in advance mapping data 94A that defines the mapping M learned by machine learning. The mapping M receives a plurality of input variables and outputs an output variable indicating a predicted waveform of the noise component after a predetermined period of time. Note that a specific explanation of the mapping M will be given later. In this embodiment, the CPU 91 and ROM 93 are execution devices. Further, the storage device 94 is a storage device. The peripheral circuit 92 includes a circuit that generates a clock signal that defines internal operations, a power supply circuit, a reset circuit, and the like.

<Predictive control>
Next, the predictive control executed by the predictive device 90 will be described. The prediction device 90 repeatedly executes predictive control, for example, on the condition that the generator rotational speed NR is greater than zero.

As shown in FIG. 2, when the CPU 91 starts predictive control, it executes the process of step S11. In step S11, the CPU 91 accesses the storage device 94 to obtain various values that are latest at the time of processing in step S11. Specifically, the CPU 91 acquires the wind speed SW, internal temperature TE, internal humidity LH, date information ID, time information IT, and generator rotational speed NR. In this embodiment, the process in step S11 is an acquisition process. After step S11, the CPU 91 advances the process to step S12.

In step S12, the CPU 91 generates the various values obtained in the process of step S11 as input variables x(1) to input variables x(6) to the mapping M. Specifically, the CPU 91 assigns the wind speed SW to the input variable x(1). The CPU 91 assigns the internal temperature TE to the input variable x(2). The CPU 91 assigns the internal humidity LH to the input variable x(3). The CPU 91 assigns the date information ID to the input variable x(4). The CPU 91 assigns the time information IT to the input variable x(5). The CPU 91 assigns the generator rotation speed NR to the input variable x(6). In this embodiment, the input variable x(1) is a variable indicating the wind speed SW, which is the flow speed of the wind that collides with the wind turbine 13. After step S12, the CPU 91 advances the process to step S13.

In step S13, the CPU 91 inputs the input variables x(1) to x(6) generated in the process of step S12 and the input variable x(0) as a bias parameter into the mapping M, thereby inputting the output variable y. Calculate the value of (i). Further, the CPU 91 calculates a predicted waveform indicated by the value of the output variable y(i). This predicted waveform is a predicted waveform of the noise component of the AC voltage output by the generator 18.

An example of the mapping M defined by the mapping data 94A is a function approximator, which is a fully connected forward propagation neural network with one intermediate layer. Specifically, in mapping M, input variables x(1) to input variables x(6) and input variable x(0) as a bias parameter are coefficients wFjk (j=1 to m, k=0 to 6). Each of the "m" values transformed by the linear mapping defined by is substituted into the activation function f. As a result, the values of the nodes in the middle layer are determined. In addition, each of the values obtained by converting the values of nodes in the intermediate layer by the linear mapping defined by the coefficient wSij (i = 1 to P) is assigned to the activation function g, so that the output variables y(1) to The output variable y(P) is determined. Note that the total of output variables in step S13 is written as "P". This "P" is defined as follows, for example. First, a lower limit value and an upper limit value of noise components that can be generated in the generator 18 are determined through experiments and simulations. Further, the frequency band from the lower limit value to the upper limit value of the determined noise component is divided into a plurality of frequency bands so as not to overlap. The number of divided frequency bands is defined as "P" which is the total of output variables. Note that an example of "P", which is the sum of output variables, is "10". Each of the output variables y(1) to y(P) is an output variable indicating a predicted waveform of the above noise component after a predetermined period of time. Here, after a certain period of time is, for example, several milliseconds to several tens of milliseconds after the current point in time. In this embodiment, an example of the activation function f is the ReLU function. Further, an example of the activation function g is a sigmoid function.

In this embodiment, the mapping M is generated as follows, for example. As a premise, in the wind power generator 10, when the wind speed SW colliding with the wind turbine 13 changes, the generator rotational speed NR changes thereafter. Then, the alternating current voltage output by the generator 18 changes. That is, when the wind speed SW etc. change, the noise component of the AC voltage output by the generator 18 changes after a certain period of time after the change. Therefore, in learning the mapping M, a plurality of test wind power generators 10 are prepared. In addition, while operating each wind power generation device 10 under various conditions, the wind speed SW, internal temperature TE, internal humidity LH, date information ID, time information IT, generator rotation speed NR, and the above-mentioned noise components are continuously acquired. . At this time, the wind speed SW, internal temperature TE, internal humidity LH, date information ID, time information IT, and generator rotational speed NR for a specific time and the noise component after a certain time from the specific time are combined into one set. Correlate as data. Then, for each set of data, input variables x(1) to input variables x(6) are generated based on the wind speed SW, etc., and output variables y(1) to output variable y(P ) is generated. In addition, by inputting input variables x(1) to input variables x(6) as training data and output variables y(1) to output variables y(P) as teacher data into the mapping M, machine learning The mapping M is learned by

In the present embodiment, the processing in steps S12 and S13 is a calculation process that outputs an output variable that indicates the predicted waveform of the noise component after a predetermined period of time. After step S13, the CPU 91 ends the current predictive control.

<Action of this embodiment>
In the power generation system 100, the voltage superimposition device 30 generates a waveform with an opposite phase to the waveform of the noise component of the AC voltage output by the generator 18 for each frequency band corresponding to "P" which is the sum of output variables. voltage is applied. Therefore, the alternating current voltage output by the generator 18 approaches an ideal sine wave. As a result, the rotating shaft 18A of the generator 18 rotates smoothly, so the noise generated by the generator 18 is suppressed.

<Effects of this embodiment>
(1) In the present embodiment, the voltage having the opposite phase waveform is generated based on the predicted waveform of the noise component after a certain period of time predicted by the prediction device 90. If the predicted waveform of the noise component after a certain period of time can be grasped in this way, even in situations where the noise component changes due to changes in the wind speed SW, for example, the voltage superimposition device can be adjusted to match the predicted waveform of the noise component after a certain period of time. The voltage applied by 30 is controlled. As a result, even in a situation where a control delay or the like may occur in the control device 40, for example, the voltage applied by the voltage superimposition device 30 can be controlled to follow the change in the alternating current voltage output by the generator 18.

(2) In the present embodiment, the prediction device 90 takes into account the internal temperature TE, internal humidity LH, date information ID, time information IT, and generator rotational speed NR in addition to the wind speed SW, and calculates the Predict the predicted waveform of the noise component. Thereby, the prediction accuracy of the predicted waveform of the noise component after a certain period of time can be improved.

<Example of change>
This embodiment can be implemented with the following modifications. This embodiment and the following modified examples can be implemented in combination with each other within a technically consistent range.

- In the above embodiment, as long as the mapping M includes the wind speed SW as an input variable, other input variables may be omitted or changed. For example, the internal temperature TE, internal humidity LH, date information ID, time information IT, and generator rotational speed NR may be omitted as input variables.

- In the above embodiment, further learning of the mapping M may be performed.
For example, when the wind power generation device 10 is operating, the prediction device 90 acquires the AC voltage on the power line 19 via the control device 40 and the voltage superimposition device 30. Further, while the wind power generation device 10 is operating, the prediction device 90 acquires a signal indicating the sound pressure of noise from a sound collection device such as a microphone. The prediction device 90 then extracts a noise component when the sound pressure of the noise is equal to or higher than a predetermined threshold. Furthermore, the prediction device 90 specifies the wind speed SW and the like a certain period of time before the time when the noise component is extracted. The prediction device 90 may further learn the mapping M using the same procedure as in the above embodiment by associating the extracted noise component and the identified wind speed SW etc. as one set of data. According to this configuration, it can be expected that the prediction accuracy of noise components that cause noise will be improved.

- For example, when the wind power generator 10 is operating, the prediction device 90 acquires the AC voltage on the power line 19 via the control device 40 and the voltage superimposition device 30. Furthermore, while the wind power generator 10 is operating, the prediction device 90 acquires a signal indicating vibration from the vibration sensor. The prediction device 90 then extracts a noise component when the vibration is greater than or equal to a predetermined threshold. Furthermore, the prediction device 90 specifies the wind speed SW and the like a certain period of time before the time when the noise component is extracted. The prediction device 90 may further learn the mapping M using the same procedure as in the above embodiment by associating the extracted noise component and the identified wind speed SW etc. as one set of data. According to this configuration, it can be expected that the prediction accuracy of noise components that cause vibrations will be improved.

M... Mapping, 10... Wind power generation device, 30... Voltage superimposition device, 40... Control device, 90... Prediction device, 91... CPU, 92... Peripheral circuit, 93... ROM, 94... Storage device, 94A... Mapping data, 95 ...Bus, 100...Power generation system.

Claims (1)

A wind power generation device having a windmill and a generator;
a voltage superimposition device that applies a voltage with a waveform of an opposite phase to a waveform of a noise component of the AC voltage output by the generator;
a control device that controls the voltage superimposition device;
A power generation system comprising: a prediction device that predicts a waveform of the noise component;
The prediction device includes an execution device and a storage device,
The storage device stores mapping data that defines a mapping that outputs an output variable indicating a predicted waveform of the noise component after a predetermined period of time by inputting a plurality of input variables,
The mapping is learned in advance by machine learning,
The mapping includes, as one of the input variables, a variable indicating the wind speed of the wind impinging on the windmill;
The execution device includes:
an acquisition process for acquiring the input variable;
performing a calculation process of outputting the value of the output variable by inputting the plurality of input variables acquired by the acquisition process into the mapping;
The power generation system, wherein the control device controls the voltage applied by the voltage superimposition device based on the predicted waveform indicated by the output variable.

Images