CN115357065B

CN115357065B - Remote intelligent dehumidification control system and method for offshore wind turbine

Info

Publication number: CN115357065B
Application number: CN202211036246.5A
Authority: CN
Inventors: 黄力哲; 王力军; 陈思; 徐峰; 王洪兴; 刘荣波; 郝蛟蛟; 吕胜波
Original assignee: Huaneng Renewables Corp Ltd; Beijing Huaneng Xinrui Control Technology Co Ltd
Current assignee: Huaneng Renewables Corp Ltd; Beijing Huaneng Xinrui Control Technology Co Ltd
Priority date: 2022-08-27
Filing date: 2022-08-27
Publication date: 2024-04-12
Anticipated expiration: 2042-08-27
Also published as: CN115357065A

Abstract

The application relates to the field of intelligent dehumidification control of an offshore wind turbine, and particularly discloses a remote intelligent dehumidification control system of the offshore wind turbine and a method thereof. In this way, the dynamic change characteristics of the moisture brought by wind data are introduced into the dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range.

Description

Remote intelligent dehumidification control system and method for offshore wind turbine

Technical Field

The invention relates to the field of intelligent dehumidification control of offshore fans, in particular to a remote intelligent dehumidification control system and a method thereof of an offshore fan.

Background

The offshore wind turbine works in a high-humidity and high-salt environment for a long time. The metal equipment and facilities in the fan are easy to corrode. In general, the critical point of the relative humidity of metal corrosion is 45% -50%, corrosion occurs beyond the limit, the corrosion speed is increased along with the increase of the relative humidity, and once condensation occurs on steel, the corrosion process is more rapid.

Currently, each fan is equipped with a dehumidifier, and in the existing operation mode of the dehumidifier, the dehumidifier is operated in a fixed power mode and a predetermined operation time, and this control mode not only causes the dehumidifier to generate a great deal of ineffective operation (for example, when the dryness of the fan is low, the fan still works), but also expects that the dehumidifier can perform adaptive adjustment of the operation power according to specific conditions, rather than still operate in a preset power, if the humidity in the offshore fan suddenly increases.

Thus, an optimized intelligent dehumidification control scheme is desired.

Disclosure of Invention

The present application has been made in order to solve the above technical problems. The embodiment of the application provides a remote intelligent dehumidification control system and a remote intelligent dehumidification control method for an offshore wind turbine, which utilize a multiscale neighborhood feature extraction module to respectively and dynamically extract implicit features of humidity values, wind data and working power of a dehumidifier at a plurality of time points by adopting an artificial intelligent control technology, and utilize Bayes to fuse data features to conduct real-time dynamic regulation and control of the power of the dehumidifier. In this way, the dynamic change characteristics of the moisture brought by wind data are introduced into the dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range.

According to one aspect of the present application, there is provided a remote intelligent dehumidification control system of an offshore wind turbine, comprising:

the environment data acquisition module is used for acquiring humidity values of a plurality of preset time points in a preset time period acquired by the hygrometer and wind data of the preset time points acquired by the wind speed station, wherein the wind data comprises a wind speed value and a wind direction, and the wind direction is represented by a sine value or a cosine value of an angle;

the working state data acquisition module is used for acquiring the working power of the dehumidifier at a plurality of preset time points;

the single-point wind data coding module is used for enabling wind data of each preset time point in the wind data of the preset time points to pass through the full connection layer so as to obtain a plurality of wind characteristic vectors corresponding to each preset time point;

the wind data multi-scale neighborhood coding module is used for arranging the wind feature vectors corresponding to each preset time point into one-dimensional feature vectors and then obtaining multi-scale wind feature vectors through the first multi-scale neighborhood feature extraction module;

the humidity data multiscale neighborhood coding module is used for enabling the humidity values of the preset time points to pass through the second multiscale neighborhood feature extraction module so as to obtain multiscale humidity feature vectors;

The power data multiscale neighborhood coding module is used for enabling the working power of the dehumidifier at a plurality of preset time points to pass through the third multiscale neighborhood feature extraction module so as to obtain multiscale power feature vectors;

the Bayesian inference module is used for fusing the multiscale power feature vector, the multiscale humidity feature vector and the multiscale wind feature vector by using a Bayesian probability model to obtain a posterior probability feature vector, wherein the multiscale power feature vector is an prior probability vector, the multiscale humidity feature vector is an event probability vector and the multiscale wind feature vector is an evidence probability vector;

the posterior distribution correction module is used for correcting the characteristic values of all positions in the posterior probability characteristic vector based on the inverse of the average value of the characteristic values of all positions in the posterior probability characteristic vector so as to obtain a corrected posterior probability characteristic vector; and

and the control result generation module is used for passing the corrected posterior probability feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the power value of the dehumidifier at the current time point should be increased, kept or reduced.

In the remote intelligent dehumidification control system of the offshore wind turbine, the single-point wind data encoding module is further configured to: arranging wind data of each preset time point in the wind data of the preset time points into an input vector according to a time dimension; and performing full-join encoding on the input vector by using the full-join layer to extract high-dimensional implicit features of feature values of each position in the input vector to obtain the wind feature vectors corresponding to each predetermined time point, wherein the formula is as follows:wherein X is the input vector, Y is the output vector, W is the weight matrix, B is the bias vector, < >>Representing a matrix multiplication.

In the remote intelligent dehumidification control system of the offshore wind turbine, the wind data multi-scale neighborhood coding module comprises: the first convolution unit is used for inputting the one-dimensional feature vector into a first convolution layer of the first multi-scale neighborhood feature extraction module to obtain a first neighborhood scale wind feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length; a second convolution unit, configured to input the one-dimensional feature vector into a second convolution layer of the first multi-scale neighborhood feature extraction module to obtain a second neighborhood-scale wind feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and the cascading unit is used for cascading the first neighborhood scale wind characteristic vector and the second neighborhood scale wind characteristic vector to obtain the multi-scale wind characteristic vector.

In the remote intelligent dehumidification control system of the offshore wind turbine, the first convolution unit is further used for; performing one-dimensional convolution encoding on the one-dimensional feature vector by using a first convolution layer of the first multi-scale neighborhood feature extraction module according to the following formula to obtain a first neighborhood scale wind feature vector;

wherein, the formula is:

wherein a is the width of the first convolution kernel in the X direction, F is a first convolution kernel parameter vector, G is a local vector matrix calculated by a convolution kernel function, w is the size of the first convolution kernel, and X represents a tension input vector.

In the remote intelligent dehumidification control system of an offshore wind turbine, the second convolution unit is further configured to: performing one-dimensional convolution coding on the one-dimensional feature vector by using a second convolution layer of the first multi-scale neighborhood feature extraction module according to the following formula to obtain a second neighborhood scale wind feature vector;

wherein, the formula is:

wherein b is the width of the second convolution kernel in the X direction, F is a second convolution kernel parameter vector, G is a local vector matrix calculated by a convolution kernel function, m is the size of the second convolution kernel, and X represents a tension input vector.

In the remote intelligent dehumidification control system of an offshore wind turbine, the bayesian inference module is further configured to: fusing the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector using a bayesian probability model in the following formula to obtain the posterior probability feature vector;

wherein, the formula is:

qi＝pi*ai/bi

where pi is the eigenvalue of each position in the multi-scale power eigenvector, ai and bi are the eigenvalues of each position in the multi-scale humidity eigenvector and the multi-scale wind eigenvector, respectively, and qi is the eigenvalue of each position in the posterior probability eigenvector.

In the remote intelligent dehumidification control system of the offshore wind turbine, the posterior distribution correction module is further configured to: correcting the characteristic values of all positions in the posterior probability characteristic vector according to the following formula based on the inverse of the average value of the characteristic values of all positions in the posterior probability characteristic vector to obtain the corrected posterior probability characteristic vector;

wherein, the formula is:

wherein V represents the posterior probability feature vector,indicating the inverse of the mean of the eigenvalues at all positions in the posterior probability eigenvector, and as such, indicates multiplication by position.

In the remote intelligent dehumidification control system of an offshore wind turbine, the control result generation module is further configured to: processing the corrected posterior probability feature vector using the classifier to obtain the classification result with the following formula: softmax { (W) _n ,B _n ):…:(W ₁ ,B ₁ ) X, where W ₁ To W _n Is a weight matrix, B ₁ To B _n And X is the corrected posterior probability feature vector for the bias vector.

According to another aspect of the present application, a remote intelligent dehumidification control method of an offshore wind turbine, comprising:

acquiring humidity values of a plurality of preset time points in a preset time period acquired by a hygrometer and wind data of the preset time points acquired by a wind speed station, wherein the wind data comprises a wind speed value and a wind direction, and the wind direction is represented by a sine value or a cosine value of an angle;

acquiring the working power of the dehumidifier at a plurality of preset time points;

passing wind data of each predetermined time point in the wind data of the plurality of predetermined time points through the fully connected layer to obtain a plurality of wind feature vectors corresponding to each predetermined time point;

the wind feature vectors corresponding to the preset time points are arranged into one-dimensional feature vectors and then pass through a first multi-scale neighborhood feature extraction module to obtain multi-scale wind feature vectors;

The humidity values of the preset time points are passed through a second multiscale neighborhood feature extraction module to obtain multiscale humidity feature vectors;

working power of the dehumidifier at a plurality of preset time points is processed through a third multi-scale neighborhood feature extraction module to obtain multi-scale power feature vectors;

fusing the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector by using a Bayesian probability model to obtain a posterior probability feature vector, wherein the multi-scale power feature vector is an priori probability vector, the multi-scale humidity feature vector is an event probability vector and the multi-scale wind feature vector is an evidence probability vector;

correcting the characteristic values of all positions in the posterior probability characteristic vector based on the inverse of the average value of the characteristic values of all positions in the posterior probability characteristic vector to obtain a corrected posterior probability characteristic vector; and

the corrected posterior probability feature vector is passed through a classifier to obtain a classification result indicating that the power value of the dehumidifier at the current point in time should be increased, should be maintained, or should be decreased.

Far distance of the above-mentioned offshore wind turbine In the intelligent dehumidification control method, wind data of each preset time point in the wind data of the preset time points is passed through a full connection layer to obtain a plurality of wind characteristic vectors corresponding to each preset time point, and the intelligent dehumidification control method comprises the following steps: arranging wind data of each preset time point in the wind data of the preset time points into an input vector according to a time dimension; and performing full-join encoding on the input vector by using the full-join layer to extract high-dimensional implicit features of feature values of each position in the input vector to obtain the wind feature vectors corresponding to each predetermined time point, wherein the formula is as follows:wherein X is the input vector, Y is the output vector, W is the weight matrix, B is the bias vector, < >>Representing a matrix multiplication.

In the above remote intelligent dehumidification control method of an offshore wind turbine, the steps of arranging the wind feature vectors corresponding to each preset time point into one-dimensional feature vectors, and then obtaining the multi-scale wind feature vectors through a first multi-scale neighborhood feature extraction module include: inputting the one-dimensional feature vector into a first convolution layer of the first multi-scale neighborhood feature extraction module to obtain a first neighborhood scale wind feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length; inputting the one-dimensional feature vector into a second convolution layer of the first multi-scale neighborhood feature extraction module to obtain a second neighborhood-scale wind feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and cascading the first neighborhood-scale wind feature vector and the second neighborhood-scale wind feature vector to obtain the multi-scale wind feature vector.

In the above remote intelligent dehumidification control method of an offshore wind turbine, inputting the one-dimensional feature vector into a first convolution layer of the first multi-scale neighborhood feature extraction module to obtain a first neighborhood scale wind feature vector includes: performing one-dimensional convolution encoding on the one-dimensional feature vector by using a first convolution layer of the first multi-scale neighborhood feature extraction module according to the following formula to obtain a first neighborhood scale wind feature vector;

wherein, the formula is:

In the above remote intelligent dehumidification control method of an offshore wind turbine, inputting the one-dimensional feature vector into a second convolution layer of the first multi-scale neighborhood feature extraction module to obtain a second neighborhood scale wind feature vector, including: performing one-dimensional convolution coding on the one-dimensional feature vector by using a second convolution layer of the first multi-scale neighborhood feature extraction module according to the following formula to obtain a second neighborhood scale wind feature vector;

wherein, the formula is:

In the above remote intelligent dehumidification control method of an offshore wind turbine, a bayesian probability model is used to fuse the multiscale power feature vector, the multiscale humidity feature vector and the multiscale wind feature vector to obtain a posterior probability feature vector, wherein the multiscale power feature vector is an prior probability vector, the multiscale humidity feature vector is an event probability vector, and the multiscale wind feature vector is an evidence probability vector, and the remote intelligent dehumidification control method comprises the following steps: fusing the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector using a bayesian probability model in the following formula to obtain the posterior probability feature vector;

wherein, the formula is:

qi＝pi*ai/bi

In the above remote intelligent dehumidification control method of an offshore wind turbine, correcting the feature values of each position in the posterior probability feature vector based on the inverse of the average value of the feature values of all positions in the posterior probability feature vector to obtain a corrected posterior probability feature vector includes: correcting the characteristic values of all positions in the posterior probability characteristic vector according to the following formula based on the inverse of the average value of the characteristic values of all positions in the posterior probability characteristic vector to obtain the corrected posterior probability characteristic vector;

wherein, the formula is:

In the remote intelligent dehumidification control method of the offshore wind turbine, the corrected posterior probability feature vector is passed through a classifier to obtain a classification result, and the classification result is used for indicating that the power value of the dehumidifier at the current time point should be increased and should be keptHolding or should be reduced, including: processing the corrected posterior probability feature vector using the classifier to obtain the classification result with the following formula: softmax { (W) _n ,B _n ):…:(W ₁ ,B ₁ ) X, where W ₁ To W _n Is a weight matrix, B ₁ To B _n And X is the corrected posterior probability feature vector for the bias vector.

Compared with the prior art, the remote intelligent dehumidification control system and the method for the offshore wind turbine, provided by the application, utilize the multiscale neighborhood feature extraction module to respectively and dynamically extract implicit features of humidity values, wind data and working power of the dehumidifier at a plurality of time points by adopting an artificial intelligent control technology, and utilize Bayes to fuse data features to conduct real-time dynamic regulation and control of the power of the dehumidifier. In this way, the dynamic change characteristics of the moisture brought by wind data are introduced into the dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range.

Drawings

The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.

Fig. 1 is an application scenario diagram of a remote intelligent dehumidification control system of an offshore wind turbine according to an embodiment of the application.

FIG. 2 is a block diagram of a remote intelligent dehumidification control system of an offshore wind turbine according to an embodiment of the application.

Fig. 3 is a flowchart of a remote intelligent dehumidification control method of an offshore wind turbine according to an embodiment of the application.

Fig. 4 is a schematic architecture diagram of a remote intelligent dehumidification control method of an offshore wind turbine according to an embodiment of the application.

Detailed Description

Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.

Scene overview

As previously mentioned, offshore wind turbines operate in high humidity, high salt environments for long periods of time. The metal equipment and facilities in the fan are easy to corrode. In general, the critical point of the relative humidity of metal corrosion is 45% -50%, corrosion occurs beyond the limit, the corrosion speed is increased along with the increase of the relative humidity, and once condensation occurs on steel, the corrosion process is more rapid.

Currently, each fan is equipped with a dehumidifier, and in the existing operation mode of the dehumidifier, the dehumidifier is operated in a fixed power mode and a predetermined operation time, and this control mode not only causes the dehumidifier to generate a great deal of ineffective operation (for example, when the dryness of the fan is low, the fan still works), but also expects that the dehumidifier can perform adaptive adjustment of the operation power according to specific conditions, rather than still operate in a preset power, if the humidity in the offshore fan suddenly increases. Thus, an optimized intelligent dehumidification control scheme is desired.

Accordingly, the inventor considers that because the humidity in the offshore wind turbine at each time point has implicit characteristic association information, and the change of the humidity also causes the change of the working power of the dehumidifier, if the power of the dehumidifier is to be dynamically regulated and controlled in real time according to the actual condition of the humidity in the wind turbine, deep implicit association characteristic excavation needs to be performed on the humidity value at each time point and the working power value of the dehumidifier. And the inventor also considers that wind brings more moisture, so that the dynamic change characteristic of the moisture brought by wind data is introduced into a dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range.

Specifically, in the technical solution of the present application, first, for the acquisition of environmental data, humidity values at a plurality of predetermined time points within a predetermined period of time are acquired by a hygrometer disposed in a wind turbine, and wind data at the plurality of predetermined time points are acquired by a wind speed station, the wind data including a wind speed value and a wind direction, the wind direction being represented by a sine value or a cosine value of an angle. Then, for the collection of the working state data of the dehumidifier, the working power of the dehumidifier at a plurality of preset time points is obtained through a power detector.

Further, for the wind data of the plurality of preset time points, the wind data of each preset time point in the wind data of the plurality of preset time points is processed through the fully-connected layer so as to extract high-dimensional implicit characteristics of the wind data of each preset time point, and therefore a plurality of wind characteristic vectors corresponding to each preset time point are obtained.

Then, the wind feature vectors corresponding to the respective predetermined time points are arranged in a time dimension as one-dimensional feature vectors to facilitate subsequent feature mining. It should be appreciated that convolutional neural networks were originally models applied in the image domain, but the concept of local feature extraction can be equally applied to time series data analysis. For example, a time series convolution structure with a convolution kernel size of 3, for time series data input, the convolution kernel is shifted in the time dimension in the form of a sliding window and outputs a weighted sum of the data within each time series segment. Each convolution unit stacks a plurality of convolution kernels to output a multi-dimensional feature. The large convolution kernel extracts features from the large-scale time sequence neighborhood, wherein the influence of each numerical value in the neighborhood is smaller, so that fluctuation of input data is weakened, and the influence of noise points on the output features is lightened. However, the large-scale convolution kernel weakens the difference of numerical variation, and easily causes the problem of smooth transition, so that the output characteristics lose the discrimination capability. In contrast, small scale convolution kernels are better able to preserve information in the input data, but are also more susceptible to interference from noise therein. Therefore, the characteristics of convolution of different scales are considered, and the convolution units of different sizes are used in combination to extract the characteristics of different time sequence scales. And then, finishing feature fusion by adopting a feature splicing mode, thereby obtaining the multi-scale neighborhood features.

That is, in the technical solution of the present application, further, a one-dimensional convolution encoding is performed on the one-dimensional feature vectors by using a convolution layer of a first multi-scale neighborhood feature extraction module, where the convolution layer has one-dimensional convolution kernels with different scales, and then the obtained feature vectors corresponding to the two one-dimensional convolution kernels with different scales are cascaded to obtain the multi-scale wind feature vector. In particular, by the method, the dynamic change implicit characteristic information of the wind data can be extracted, the output characteristics not only comprise the smoothed characteristics, but also preserve the original input characteristics, so that the information is prevented from being lost, and the accuracy of the subsequent classification is further improved. In other examples of the present application, the multi-scale neighborhood feature extraction module may further include a greater number of one-dimensional convolution layers, which use one-dimensional convolution kernels of different lengths to perform intra-neighborhood correlation feature extraction of different scales, which is not limited by the present application.

Similarly, for the humidity values of the plurality of preset time points and the working power of the dehumidifier, after the humidity values of the plurality of preset time points are arranged as humidity input vectors and the working power of the dehumidifier of the plurality of preset time points is arranged as power input vectors, one-dimensional convolution coding is carried out in a convolution layer with one-dimensional convolution kernels of different scales of the multi-scale neighborhood feature extraction module, and then the obtained feature vectors corresponding to the two one-dimensional convolution kernels of different scales are cascaded to obtain the multi-scale humidity feature vector and the multi-scale power feature vector respectively. Therefore, the humidity value and the dynamic change characteristic information of the working power of the dehumidifier in the time dimension can be extracted.

It should be appreciated that, considering the use of the multi-scale power feature vector as a priori probability, the objective in the technical solution of the present application is to update the a priori probability to obtain a posterior probability when new evidence is present, i.e. when there is new moisture carried by the wind data. Then, according to a bayesian formula, the posterior probability is the prior probability multiplied by the event probability divided by the evidence probability, so in the technical scheme of the application, a bayesian probability model is used to fuse the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector to obtain the posterior probability feature vector, wherein the multi-scale power feature vector is the prior probability vector, the multi-scale humidity feature vector is the event probability vector and the multi-scale wind feature vector is the evidence probability vector. In this way, the dynamic change characteristics of the humidity brought by the wind data can be introduced into the dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range. Then, the posterior probability feature vector is passed through a classifier to obtain a classification result that the power value of the dehumidifier indicating the current point in time should be increased, maintained or decreased.

However, the bayesian probability model is used to calculate the fusion of the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector by location, that is, each location of the posterior probability feature vector corresponds to the posterior probability under different time sequence features and has a certain phase attribute. However, the classification of the classifier is typically location independent, which results in possible bias in classification results.

Therefore, in the technical solution of the present application, the vectors for further performing phase sensing on the posterior probability feature vector are aggregated by position, that is:

Here, the optimized phase perception representation of the posterior probability feature vector V' introduces a real-value-like virtual representation of amplitude-phase, and performs position-wise splicing and unfolding of the real-value vector by using a principle based on an euler formula to perform position-wise aggregation in a multi-layer phase perception manner, so that a possible induced deviation caused when the posterior probability feature vector V is subjected to a real-value classification task without position attribute is compensated, and accuracy of a classification result is improved.

Based on this, this application provides a remote intelligent dehumidification control system of marine fan, and it includes: the environment data acquisition module is used for acquiring humidity values of a plurality of preset time points in a preset time period acquired by the hygrometer and wind data of the preset time points acquired by the wind speed station, wherein the wind data comprises a wind speed value and a wind direction, and the wind direction is represented by a sine value or a cosine value of an angle; the working state data acquisition module is used for acquiring the working power of the dehumidifier at a plurality of preset time points; the single-point wind data coding module is used for enabling wind data of each preset time point in the wind data of the preset time points to pass through the full connection layer so as to obtain a plurality of wind characteristic vectors corresponding to each preset time point; the wind data multi-scale neighborhood coding module is used for arranging the wind feature vectors corresponding to each preset time point into one-dimensional feature vectors and then obtaining multi-scale wind feature vectors through the first multi-scale neighborhood feature extraction module; the humidity data multiscale neighborhood coding module is used for enabling the humidity values of the preset time points to pass through the second multiscale neighborhood feature extraction module so as to obtain multiscale humidity feature vectors; the power data multiscale neighborhood coding module is used for enabling the working power of the dehumidifier at a plurality of preset time points to pass through the third multiscale neighborhood feature extraction module so as to obtain multiscale power feature vectors; the Bayesian inference module is used for fusing the multiscale power feature vector, the multiscale humidity feature vector and the multiscale wind feature vector by using a Bayesian probability model to obtain a posterior probability feature vector, wherein the multiscale power feature vector is an prior probability vector, the multiscale humidity feature vector is an event probability vector and the multiscale wind feature vector is an evidence probability vector; the posterior distribution correction module is used for correcting the characteristic values of all positions in the posterior probability characteristic vector based on the inverse of the average value of the characteristic values of all positions in the posterior probability characteristic vector so as to obtain a corrected posterior probability characteristic vector; and a control result generation module for passing the corrected posterior probability feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the power value of the dehumidifier at the current time point should be increased, should be kept or should be reduced.

Fig. 1 illustrates an application scenario diagram of a remote intelligent dehumidification control system of an offshore wind turbine according to an embodiment of the application. As shown in fig. 1, in this application scenario, first, humidity values at a plurality of predetermined time points within a predetermined period of time are acquired by a hygrometer (e.g., H as illustrated in fig. 1) disposed in a wind turbine (e.g., F as illustrated in fig. 1) and wind data at the plurality of predetermined time points, including a wind speed value and a wind direction, which is represented by a sine value or a cosine value of an angle, are acquired by a power detector (e.g., P as illustrated in fig. 1), and operating power of a dehumidifier (e.g., T as illustrated in fig. 1) at the plurality of predetermined time points is acquired by a wind speed station (e.g., W as illustrated in fig. 1). Then, the acquired humidity values, wind data, and operating power of the dehumidifier at a plurality of predetermined time points within the predetermined time period are input into a server (e.g., a cloud server S as illustrated in fig. 1) where a remote intelligent dehumidification control algorithm of the offshore wind turbine is deployed, wherein the server is capable of processing the humidity values, the wind data, and the operating power of the dehumidifier at a plurality of predetermined time points within the predetermined time period with the remote intelligent dehumidification control algorithm of the offshore wind turbine to generate a classification result indicating that the power value of the dehumidifier at the current time point should be increased, should be maintained, or should be decreased.

Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.

Exemplary System

FIG. 2 illustrates a block diagram of a remote intelligent dehumidification control system of an offshore wind turbine in accordance with an embodiment of the disclosure. As shown in fig. 2, a remote intelligent dehumidification control system 200 of an offshore wind turbine according to an embodiment of the application includes: an environmental data collection module 210, configured to obtain humidity values at a plurality of predetermined time points within a predetermined time period collected by a hygrometer and wind data at the plurality of predetermined time points collected by a wind speed station, where the wind data includes a wind speed value and a wind direction, and the wind direction is represented by a sine value or a cosine value of an angle; the working state data acquisition module 220 is configured to acquire working powers of the dehumidifier at the plurality of predetermined time points; a single-point wind data encoding module 230, configured to pass wind data of each predetermined time point in the wind data of the plurality of predetermined time points through the full connection layer to obtain a plurality of wind feature vectors corresponding to each predetermined time point; the wind data multi-scale neighborhood coding module 240 is configured to arrange the wind feature vectors corresponding to each predetermined time point into one-dimensional feature vectors, and then obtain multi-scale wind feature vectors through the first multi-scale neighborhood feature extraction module; the humidity data multiscale neighborhood encoding module 250 is configured to pass the humidity values of the plurality of predetermined time points through the second multiscale neighborhood feature extraction module to obtain multiscale humidity feature vectors; the power data multi-scale neighborhood coding module 260 is configured to pass the working powers of the dehumidifiers at the plurality of predetermined time points through the third multi-scale neighborhood feature extraction module to obtain multi-scale power feature vectors; the bayesian inference module 270 is configured to fuse the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector to obtain a posterior probability feature vector by using a bayesian probability model, where the multi-scale power feature vector is an a priori probability vector, the multi-scale humidity feature vector is an event probability vector, and the multi-scale wind feature vector is an evidence probability vector; the posterior distribution correction module 280 is configured to correct the feature values of each position in the posterior probability feature vector based on the inverse of the average value of the feature values of all positions in the posterior probability feature vector to obtain a corrected posterior probability feature vector; and a control result generating module 290 for passing the corrected posterior probability feature vector through a classifier to obtain a classification result indicating that the power value of the dehumidifier at the current time point should be increased, should be maintained or should be decreased.

Specifically, in the embodiment of the present application, the environmental data collection module 210 and the working state data collection module 220 are configured to obtain humidity values of a plurality of predetermined time points in a predetermined period of time collected by a hygrometer and wind data of the plurality of predetermined time points collected by a wind speed station, where the wind data includes a wind speed value and a wind direction, and the wind direction is represented by a sine value or a cosine value of an angle, and obtain working powers of the dehumidifier at the plurality of predetermined time points. As described above, in the technical solution of the present application, considering that there is implicit characteristic correlation information due to humidity in the offshore wind turbine at each time point, and the change of the humidity may also cause the change of the working power of the dehumidifier, if the power of the dehumidifier is to be dynamically regulated in real time according to the actual humidity situation in the wind turbine, deep implicit correlation feature mining needs to be performed on the humidity value at each time point and the working power value of the dehumidifier. And further, more moisture is brought by wind, so that in the technical scheme of the application, the moisture dynamic change characteristics brought by wind data are introduced into a dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range.

That is, specifically, in the technical solution of the present application, first, for the acquisition of environmental data, humidity values at a plurality of predetermined time points within a predetermined period of time are acquired by a hygrometer disposed in a wind turbine and wind data including a wind speed value and a wind direction, which is represented by a sine value or a cosine value of an angle, are acquired by a wind speed station. Then, for the collection of the working state data of the dehumidifier, the working power of the dehumidifier at a plurality of preset time points is obtained through a power detector.

Specifically, in the embodiment of the present application, the single-point wind data encoding module 230 is configured to pass wind data of each predetermined time point among the wind data of the plurality of predetermined time points through the fully-connected layer to obtain a plurality of wind feature vectors corresponding to each predetermined time point. That is, in the technical solution of the present application, further, for the wind data at the plurality of predetermined time points, the wind data at each predetermined time point in the wind data at the plurality of predetermined time points is processed through the fully-connected layer, so as to extract high-dimensional implicit features of the wind data at each predetermined time point, thereby obtaining a plurality of wind feature vectors corresponding to each predetermined time point.

More specifically, in an embodiment of the present application, the single-point wind data encoding module is further configured to: arranging wind data of each preset time point in the wind data of the preset time points into an input vector according to a time dimension; and performing full-join encoding on the input vector by using the full-join layer to extract high-dimensional implicit features of feature values of each position in the input vector to obtain the wind feature vectors corresponding to each predetermined time point, wherein the formula is as follows:wherein X is the input vector, Y is the output vector, W is the weight matrix, B is the bias vector, < >>Representing a matrix multiplication.

Specifically, in the embodiment of the present application, the wind data multi-scale neighborhood encoding module 240 is configured to arrange the wind feature vectors corresponding to each predetermined time point into one-dimensional feature vectors, and then obtain multi-scale wind feature vectors through the first multi-scale neighborhood feature extraction module. That is, in the technical solution of the present application, the plurality of wind feature vectors corresponding to each predetermined time point are further arranged into one-dimensional feature vectors according to a time dimension so as to facilitate subsequent feature mining. It should be appreciated that convolutional neural networks were originally models applied in the image domain, but the concept of local feature extraction can be equally applied to time series data analysis. For example, a time series convolution structure with a convolution kernel size of 3, for time series data input, the convolution kernel is shifted in the time dimension in the form of a sliding window and outputs a weighted sum of the data within each time series segment. Each convolution unit stacks a plurality of convolution kernels to output a multi-dimensional feature. The large convolution kernel extracts features from the large-scale time sequence neighborhood, wherein the influence of each numerical value in the neighborhood is smaller, so that fluctuation of input data is weakened, and the influence of noise points on the output features is lightened. However, the large-scale convolution kernel weakens the difference of numerical variation, and easily causes the problem of smooth transition, so that the output characteristics lose the discrimination capability. In contrast, small scale convolution kernels are better able to preserve information in the input data, but are also more susceptible to interference from noise therein. Therefore, the characteristics of convolution of different scales are considered, and the convolution units of different sizes are used in combination to extract the characteristics of different time sequence scales. And then, finishing feature fusion by adopting a feature splicing mode, thereby obtaining the multi-scale neighborhood features.

More specifically, in an embodiment of the present application, the wind data multi-scale neighborhood encoding module includes: the first convolution unit is used for inputting the one-dimensional feature vector into a first convolution layer of the first multi-scale neighborhood feature extraction module to obtain a first neighborhood scale wind feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length. Accordingly, in one specific example, the one-dimensional feature vector is one-dimensionally convolutionally encoded using a first convolution layer of the first multi-scale neighborhood feature extraction module to obtain the first neighborhood-scale wind feature vector with the following formula;

Wherein, the formula is:

wherein a is the width of the first convolution kernel in the X direction, F is a first convolution kernel parameter vector, G is a local vector matrix calculated by a convolution kernel function, w is the size of the first convolution kernel, and X represents a tension input vector. And the second convolution unit is used for inputting the one-dimensional feature vector into a second convolution layer of the first multi-scale neighborhood feature extraction module to obtain a second neighborhood scale wind feature vector, wherein the second convolution layer is provided with a second one-dimensional convolution kernel with a second length, and the first length is different from the second length. Accordingly, in one specific example, the one-dimensional feature vector is one-dimensionally convolutionally encoded using a second convolution layer of the first multi-scale neighborhood feature extraction module to obtain the second neighborhood-scale wind feature vector with the following formula;

wherein, the formula is:

wherein b is the width of the second convolution kernel in the X direction, F is a second convolution kernel parameter vector, G is a local vector matrix calculated by a convolution kernel function, m is the size of the second convolution kernel, and X represents a tension input vector. And the cascading unit is used for cascading the first neighborhood scale wind characteristic vector and the second neighborhood scale wind characteristic vector to obtain the multi-scale wind characteristic vector.

Specifically, in this embodiment of the present application, the humidity data multiscale neighborhood encoding module 250 and the power data multiscale neighborhood encoding module 260 are configured to pass the humidity values of the multiple predetermined time points through a second multiscale neighborhood feature extraction module to obtain multiscale humidity feature vectors, and pass the working power of the dehumidifier of the multiple predetermined time points through a third multiscale neighborhood feature extraction module to obtain multiscale power feature vectors. It should be understood that in the technical solution of the present application, similarly, for the humidity values at the plurality of predetermined time points and the working power of the dehumidifier, after the humidity values at the plurality of predetermined time points are arranged as humidity input vectors and the working power of the dehumidifier at the plurality of predetermined time points is arranged as power input vectors, one-dimensional convolution encoding is performed in the convolution layer with one-dimensional convolution kernels of different scales through the multi-scale neighborhood feature extraction module, and then the obtained feature vectors corresponding to the two one-dimensional convolution kernels of different scales are cascaded to obtain the multi-scale humidity feature vector and the multi-scale power feature vector, respectively. Therefore, the humidity value and the dynamic change characteristic information of the working power of the dehumidifier in the time dimension can be extracted.

Specifically, in the embodiment of the present application, the bayesian inference module 270 is configured to use a bayesian probability model to fuse the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector to obtain a posterior probability feature vector, where the multi-scale power feature vector is an a priori probability vector, the multi-scale humidity feature vector is an event probability vector, and the multi-scale wind feature vector is an evidence probability vector. It should be appreciated that, considering the use of the multi-scale power feature vector as a priori probability, the objective in the technical solution of the present application is to update the a priori probability to obtain a posterior probability when new evidence is present, i.e. when there is new moisture carried by the wind data. Then, according to a bayesian formula, the posterior probability is the prior probability multiplied by the event probability divided by the evidence probability, so in the technical scheme of the application, a bayesian probability model is used to fuse the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector to obtain the posterior probability feature vector, wherein the multi-scale power feature vector is the prior probability vector, the multi-scale humidity feature vector is the event probability vector and the multi-scale wind feature vector is the evidence probability vector. In this way, the dynamic change characteristics of the humidity brought by the wind data can be introduced into the dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range.

More specifically, in an embodiment of the present application, the bayesian inference module is further configured to: the bayesian inference module is further configured to: fusing the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector using a bayesian probability model in the following formula to obtain the posterior probability feature vector;

wherein, the formula is:

qi＝pi*ai/bi

Specifically, in the embodiment of the present application, the posterior distribution correction module 280 is configured to correct the eigenvalues of each position in the posterior probability eigenvector based on the inverse of the average of the eigenvalues of all positions in the posterior probability eigenvector to obtain a corrected posterior probability eigenvector. It should be understood that, in the technical solution of the present application, after the posterior probability feature vector is obtained, the posterior probability feature vector is passed through a classifier to obtain a classification result that the power value of the dehumidifier for representing the current time point should be increased, should be maintained or should be decreased. However, the bayesian probability model is used to calculate the fusion of the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector by location, that is, each location of the posterior probability feature vector corresponds to the posterior probability under different time sequence features and has a certain phase attribute. However, the classification of the classifier is typically location independent, which results in possible bias in classification results. Therefore, in the technical scheme of the application, vectors for further performing phase sensing on the posterior probability feature vectors are aggregated by position.

More specifically, in an embodiment of the present application, the posterior distribution correction module is further configured to: correcting the characteristic values of all positions in the posterior probability characteristic vector according to the following formula based on the inverse of the average value of the characteristic values of all positions in the posterior probability characteristic vector to obtain the corrected posterior probability characteristic vector;

wherein, the formula is:

wherein V represents the posterior probability feature vector,indicating the inverse of the mean of the eigenvalues at all positions in the posterior probability eigenvector, and as such, indicates multiplication by position. It should be appreciated that, here, the phase-aware representation of the optimized posterior probability feature vector V' introduces a magnitude-phase quasi-real-value-imaginary representation, by performing a position-wise stitching expansion of the real-valued vectors based on the principle of the euler equation, to perform a position-wise aggregation in the form of a multi-layer phase-aware compensation for the possible guidance in performing a position-attribute-free real-valued classification task on the posterior probability feature vector VThe induced deviation improves the accuracy of the classification result.

Specifically, in the embodiment of the present application, the control result generating module 290 is configured to pass the corrected posterior probability feature vector through a classifier to obtain a classification result, where the classification result is used to indicate that the power value of the dehumidifier at the current time point should be increased, should be maintained, or should be decreased. Accordingly, in one specific example, the corrected posterior probability feature vector is processed using the classifier to obtain the classification result with the following formula: softmax { (W) _n ,B _n ):…:(W ₁ ,B ₁ ) X, where W ₁ To W _n Is a weight matrix, B ₁ To B _n And X is the corrected posterior probability feature vector for the bias vector.

In summary, the remote intelligent dehumidification control system 200 of the offshore wind turbine according to the embodiment of the application is illustrated, which adopts an artificial intelligence control technology to dynamically extract implicit characteristics of humidity values, wind data and working power of the dehumidifier at a plurality of time points by using a multi-scale neighborhood characteristic extraction module, and utilizes bayes to fuse data characteristics to perform real-time dynamic regulation and control of the dehumidifier power. In this way, the dynamic change characteristics of the moisture brought by wind data are introduced into the dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range.

As described above, the remote intelligent dehumidification control system 200 of an offshore wind turbine according to an embodiment of the present application may be implemented in various terminal devices, for example, a server of a remote intelligent dehumidification control algorithm of an offshore wind turbine, or the like. In one example, the remote intelligent dehumidification control system 200 of an offshore wind turbine according to embodiments of the present application may be integrated into a terminal device as a software module and/or hardware module. For example, the remote intelligent dehumidification control system 200 of the offshore wind turbine may be a software module in the operating system of the terminal device or may be an application developed for the terminal device; of course, the remote intelligent dehumidification control system 200 of the offshore wind turbine can also be one of a plurality of hardware modules of the terminal device.

Alternatively, in another example, the remote intelligent dehumidification control system 200 of the offshore wind turbine and the terminal device may be separate devices, and the remote intelligent dehumidification control system 200 of the offshore wind turbine may be connected to the terminal device through a wired and/or wireless network and transmit the interaction information in a agreed data format.

Exemplary method

FIG. 3 illustrates a flow chart of a remote intelligent dehumidification control method of an offshore wind turbine. As shown in fig. 3, the remote intelligent dehumidification control method of the offshore wind turbine according to the embodiment of the application comprises the following steps: s110, acquiring humidity values of a plurality of preset time points in a preset time period acquired by a hygrometer and wind data of the preset time points acquired by a wind speed station, wherein the wind data comprises a wind speed value and a wind direction, and the wind direction is represented by a sine value or a cosine value of an angle; s120, acquiring the working power of the dehumidifier at a plurality of preset time points; s130, enabling wind data of each preset time point in the wind data of the preset time points to pass through a fully-connected layer to obtain a plurality of wind characteristic vectors corresponding to each preset time point; s140, arranging the wind feature vectors corresponding to the preset time points into one-dimensional feature vectors, and then obtaining multi-scale wind feature vectors through a first multi-scale neighborhood feature extraction module; s150, passing the humidity values of the plurality of preset time points through a second multi-scale neighborhood feature extraction module to obtain a multi-scale humidity feature vector; s160, working power of the dehumidifier at the plurality of preset time points is processed through a third multi-scale neighborhood feature extraction module to obtain multi-scale power feature vectors; s170, fusing the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector by using a Bayesian probability model to obtain a posterior probability feature vector, wherein the multi-scale power feature vector is an prior probability vector, the multi-scale humidity feature vector is an event probability vector and the multi-scale wind feature vector is an evidence probability vector; s180, correcting the characteristic values of all positions in the posterior probability characteristic vector based on the inverse of the average value of the characteristic values of all positions in the posterior probability characteristic vector to obtain a corrected posterior probability characteristic vector; and S190 of passing the corrected posterior probability feature vector through a classifier to obtain a classification result indicating that the power value of the dehumidifier at the current point in time should be increased, should be maintained or should be decreased.

Fig. 4 illustrates an architecture schematic diagram of a remote intelligent dehumidification control method of an offshore wind turbine according to an embodiment of the application. As shown in fig. 4, in the network architecture of the remote intelligent dehumidification control method of an offshore wind turbine, first, wind data of each predetermined time point of the obtained wind data of the plurality of predetermined time points (e.g., P1 as illustrated in fig. 4) is passed through a fully connected layer (e.g., FC as illustrated in fig. 4) to obtain a plurality of wind feature vectors (e.g., V1 as illustrated in fig. 4) corresponding to each predetermined time point; next, the plurality of wind feature vectors corresponding to respective predetermined time points are arranged into one-dimensional feature vectors (e.g., V2 as illustrated in fig. 4) and then passed through a first multi-scale neighborhood feature extraction module (e.g., MS1 as illustrated in fig. 4) to obtain multi-scale wind feature vectors (e.g., VF1 as illustrated in fig. 4); then, passing the humidity values (e.g., P2 as illustrated in fig. 4) at the plurality of predetermined time points through a second multi-scale neighborhood feature extraction module (e.g., MS2 as illustrated in fig. 4) to obtain a multi-scale humidity feature vector (e.g., VF2 as illustrated in fig. 4); next, passing the operating power (e.g., P3 as illustrated in fig. 4) of the dehumidifier for the plurality of predetermined time points through a third multi-scale neighborhood feature extraction module (e.g., MS3 as illustrated in fig. 4) to obtain a multi-scale power feature vector (e.g., VF3 as illustrated in fig. 4); then, fusing the multi-scale power feature vector, the multi-scale humidity feature vector, and the multi-scale wind feature vector using a bayesian probability model (e.g., BPM as illustrated in fig. 4) to obtain a posterior probability feature vector (e.g., VP1 as illustrated in fig. 4); then, based on the inverse of the average of the eigenvalues of all the positions in the posterior eigenvector, correcting the eigenvalues of each position in the posterior eigenvector to obtain a corrected posterior eigenvector (e.g., VP2 as illustrated in fig. 4); and finally, passing the corrected posterior probability feature vector through a classifier (e.g., circle S as illustrated in fig. 4) to obtain a classification result indicating that the power value of the dehumidifier at the current point in time should be increased, should be maintained, or should be decreased.

More specifically, in step S110 and step S120, humidity values at a plurality of predetermined time points within a predetermined period of time acquired by a hygrometer and wind data at the plurality of predetermined time points acquired by a wind speed station are acquired, the wind data including a wind speed value and a wind direction, the wind direction being represented by a sine value or a cosine value of an angle, and operating powers of dehumidifiers at the plurality of predetermined time points are acquired. That is, in the technical solution of the present application, considering that there is implicit characteristic association information due to humidity in the offshore wind turbine at each time point, and the change of the humidity may also cause the change of the working power of the dehumidifier, if the power of the dehumidifier is to be dynamically regulated in real time according to the actual humidity in the wind turbine, deep implicit association feature mining needs to be performed on the humidity value at each time point and the working power value of the dehumidifier. And further, more moisture is brought by wind, so that in the technical scheme of the application, the moisture dynamic change characteristics brought by wind data are introduced into a dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range.

More specifically, in step S130 and step S140, the wind data of each predetermined time point in the wind data of the plurality of predetermined time points is passed through the fully connected layer to obtain a plurality of wind feature vectors corresponding to each predetermined time point, and the plurality of wind feature vectors corresponding to each predetermined time point are arranged into one-dimensional feature vectors and then passed through the first multi-scale neighborhood feature extraction module to obtain multi-scale wind feature vectors. That is, in the technical solution of the present application, further, for the wind data at the plurality of predetermined time points, the wind data at each predetermined time point in the wind data at the plurality of predetermined time points is processed through the fully-connected layer, so as to extract high-dimensional implicit features of the wind data at each predetermined time point, thereby obtaining a plurality of wind feature vectors corresponding to each predetermined time point.

Further, the wind feature vectors corresponding to the respective predetermined time points are arranged into one-dimensional feature vectors according to the time dimension so as to facilitate subsequent feature mining. It should be appreciated that convolutional neural networks were originally models applied in the image domain, but the concept of local feature extraction can be equally applied to time series data analysis. For example, a time series convolution structure with a convolution kernel size of 3, for time series data input, the convolution kernel is shifted in the time dimension in the form of a sliding window and outputs a weighted sum of the data within each time series segment. Each convolution unit stacks a plurality of convolution kernels to output a multi-dimensional feature. The large convolution kernel extracts features from the large-scale time sequence neighborhood, wherein the influence of each numerical value in the neighborhood is smaller, so that fluctuation of input data is weakened, and the influence of noise points on the output features is lightened. However, the large-scale convolution kernel weakens the difference of numerical variation, and easily causes the problem of smooth transition, so that the output characteristics lose the discrimination capability. In contrast, small scale convolution kernels are better able to preserve information in the input data, but are also more susceptible to interference from noise therein. Therefore, the characteristics of convolution of different scales are considered, and the convolution units of different sizes are used in combination to extract the characteristics of different time sequence scales. And then, finishing feature fusion by adopting a feature splicing mode, thereby obtaining the multi-scale neighborhood features.

More specifically, in step S150 and step S160, the humidity values at the plurality of predetermined time points are passed through a second multi-scale neighborhood feature extraction module to obtain a multi-scale humidity feature vector, and the working power of the dehumidifier at the plurality of predetermined time points is passed through a third multi-scale neighborhood feature extraction module to obtain a multi-scale power feature vector. It should be understood that in the technical solution of the present application, similarly, for the humidity values at the plurality of predetermined time points and the working power of the dehumidifier, after the humidity values at the plurality of predetermined time points are arranged as humidity input vectors and the working power of the dehumidifier at the plurality of predetermined time points is arranged as power input vectors, one-dimensional convolution encoding is performed in the convolution layer with one-dimensional convolution kernels of different scales through the multi-scale neighborhood feature extraction module, and then the obtained feature vectors corresponding to the two one-dimensional convolution kernels of different scales are cascaded to obtain the multi-scale humidity feature vector and the multi-scale power feature vector, respectively. Therefore, the humidity value and the dynamic change characteristic information of the working power of the dehumidifier in the time dimension can be extracted.

More specifically, in step S170, the multi-scale power feature vector, the multi-scale humidity feature vector, and the multi-scale wind feature vector are fused using a bayesian probability model to obtain a posterior probability feature vector, where the multi-scale power feature vector is an a priori probability vector, the multi-scale humidity feature vector is an event probability vector, and the multi-scale wind feature vector is an evidence probability vector. It should be appreciated that, considering the use of the multi-scale power feature vector as a priori probability, the objective in the technical solution of the present application is to update the a priori probability to obtain a posterior probability when new evidence is present, i.e. when there is new moisture carried by the wind data. Then, according to a bayesian formula, the posterior probability is the prior probability multiplied by the event probability divided by the evidence probability, so in the technical scheme of the application, a bayesian probability model is used to fuse the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector to obtain the posterior probability feature vector, wherein the multi-scale power feature vector is the prior probability vector, the multi-scale humidity feature vector is the event probability vector and the multi-scale wind feature vector is the evidence probability vector. In this way, the dynamic change characteristics of the humidity brought by the wind data can be introduced into the dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range. More specifically, in step S180, the feature values of the respective positions in the posterior feature vector are corrected based on the inverse of the average value of the feature values of all the positions in the posterior feature vector to obtain a corrected posterior feature vector. It should be understood that, in the technical solution of the present application, after the posterior probability feature vector is obtained, the posterior probability feature vector is passed through a classifier to obtain a classification result that the power value of the dehumidifier for representing the current time point should be increased, should be maintained or should be decreased. However, the bayesian probability model is used to calculate the fusion of the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector by location, that is, each location of the posterior probability feature vector corresponds to the posterior probability under different time sequence features and has a certain phase attribute. However, the classification of the classifier is typically location independent, which results in possible bias in classification results. Therefore, in the technical scheme of the application, vectors for further performing phase sensing on the posterior probability feature vectors are aggregated by position.

More specifically, in step S190, the corrected posterior probability feature vector is passed through a classifier to obtain a classification result indicating that the power value of the dehumidifier at the current point in time should be increased, should be maintained, or should be decreased.

In summary, the remote intelligent dehumidification control method of the offshore wind turbine according to the embodiment of the application is explained, by adopting an artificial intelligence control technology, a multiscale neighborhood feature extraction module is utilized to respectively and dynamically extract implicit features of humidity values, wind data and working power of a dehumidifier at a plurality of time points, and bayes are utilized to fuse data features to perform real-time dynamic regulation and control of the power of the dehumidifier. In this way, the dynamic change characteristics of the moisture brought by wind data are introduced into the dehumidifier power control model, so that the power control of the dehumidifier is prospective and predictive, and the humidity of the offshore wind turbine in a future time period can be kept within a preset reasonable range.

The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not intended to be limited to the details disclosed herein as such.

The block diagrams of the devices, apparatuses, devices, systems referred to in this application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.

It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent to the present application.

The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.

Claims

1. Remote intelligent dehumidification control system of marine fan, its characterized in that includes:

2. The remote intelligent dehumidification control system of an offshore wind turbine of claim 1, wherein the single point wind data encoding module is further configured to: arranging wind data of each preset time point in the wind data of the preset time points into an input vector according to a time dimension; and performing full-join encoding on the input vector by using the full-join layer to extract high-dimensional implicit features of feature values of each position in the input vector to obtain the wind feature vectors corresponding to each predetermined time point, wherein the formula is as follows:wherein X is the input vector, Y is the output vector, W is the weight matrix, B is the bias vector, < >>Representing a matrix multiplication.

3. The remote intelligent dehumidification control system of an offshore wind turbine of claim 2, wherein the wind data multi-scale neighborhood encoding module comprises:

the first convolution unit is used for inputting the one-dimensional feature vector into a first convolution layer of the first multi-scale neighborhood feature extraction module to obtain a first neighborhood scale wind feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length;

A second convolution unit, configured to input the one-dimensional feature vector into a second convolution layer of the first multi-scale neighborhood feature extraction module to obtain a second neighborhood-scale wind feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and

and the cascading unit is used for cascading the first neighborhood scale wind characteristic vector and the second neighborhood scale wind characteristic vector to obtain the multi-scale wind characteristic vector.

4. The remote intelligent dehumidification control system of an offshore wind turbine of claim 3, wherein the first convolution unit is further configured to; performing one-dimensional convolution encoding on the one-dimensional feature vector by using a first convolution layer of the first multi-scale neighborhood feature extraction module according to the following formula to obtain a first neighborhood scale wind feature vector;

wherein, the formula is:

5. The remote intelligent dehumidification control system of an offshore wind turbine of claim 4, wherein the second convolution unit is further to: performing one-dimensional convolution coding on the one-dimensional feature vector by using a second convolution layer of the first multi-scale neighborhood feature extraction module according to the following formula to obtain a second neighborhood scale wind feature vector;

Wherein, the formula is:

6. The remote intelligent dehumidification control system of an offshore wind turbine of claim 5, wherein the bayesian inference module is further to: fusing the multi-scale power feature vector, the multi-scale humidity feature vector and the multi-scale wind feature vector using a bayesian probability model in the following formula to obtain the posterior probability feature vector;

wherein, the formula is:

qi＝pi*ai/bi

7. The remote intelligent dehumidification control system of an offshore wind turbine of claim 6, wherein the posterior distribution correction module is further to: correcting the characteristic values of all positions in the posterior probability characteristic vector according to the following formula based on the inverse of the average value of the characteristic values of all positions in the posterior probability characteristic vector to obtain the corrected posterior probability characteristic vector;

Wherein, the formula is:

8. The remote intelligent dehumidification control system of an offshore wind turbine of claim 7, wherein the control result generation module is further configured to: using the classifier to correct the posterior for the correction with the following formulaProcessing the probability feature vector to obtain the classification result, wherein the formula is as follows: softmax { (W) _n ,B _n ):…:(W ₁ ,B ₁ ) X, where W ₁ To W _n Is a weight matrix, B ₁ To B _n And X is the corrected posterior probability feature vector for the bias vector.

9. The remote intelligent dehumidification control method of the offshore wind turbine is characterized by comprising the following steps of:

10. The remote intelligent dehumidification control method of an offshore wind turbine of claim 9, wherein passing wind data of each of the plurality of predetermined time points through a fully connected layer to obtain a plurality of wind feature vectors corresponding to each of the predetermined time points comprises:

arranging wind data of each preset time point in the wind data of the preset time points into an input vector according to a time dimension; and

performing full-join encoding on the input vector by using the full-join layer to extract high-dimensional implicit features of feature values of each position in the input vector to obtain the wind feature vectors corresponding to each predetermined time point, wherein the formula is as follows:wherein X is the input vector, Y is the output vector, W is the weight matrix, B is the bias vector, < >>Representing a matrix multiplication.