Wind power plant construction management method and system based on Internet of Things

Abstract

The invention relates to the technical field of wind power plants, in particular to a wind power plant construction management method and system based on the Internet of Things, and the method mainly comprises the steps: carrying out the recognition of site construction image data, obtaining the target image data of a current target construction object, and obtaining the target image data of the current target construction object; and comparing the current image data with the completed image data of the target building, analyzing the equipment data through the fault diagnosis model, and outputting a result indicating whether the current equipment has a fault or not. By means of the method, various data in the construction process are obtained and analyzed, whether the current information is consistent with the actual construction progress or not is confirmed, whether the current summarized content has problems or not is found in time, workers can obtain the effective and accurate data and information in time, and meanwhile, the working efficiency is improved. Based on the judgment of the equipment in the current construction project, a reference basis is provided for a worker to schedule or not.

Description

Technical Field

[0001] The present invention relates to the technical field of wind farms, and more particularly, to a method and system for managing the construction of a wind farm based on the Internet of Things. Background Art

[0002] The Internet of Things refers to the ubiquitous end devices and facilities, which are connected through various wireless and / or wired long-distance and / or short-distance communication networks to realize interconnection and interoperability, application integration, and SaaS operation models based on cloud computing. In the intranet, private network, and / or Internet environment, appropriate information security protection mechanisms are adopted to provide management and service functions such as secure and controllable or even personalized real-time online monitoring, positioning and tracing, alarm linkage, dispatching and command, pre-plan management, remote control, security prevention, and remote maintenance, so as to achieve the "efficient, energy-saving, safe, and environmentally friendly" "management, control, and operation" integration of "all things".

[0003] In the current management of wind farm construction based on the Internet of Things, for the construction situation of the wind farm, the steps of direct collection, summary, and upload are generally adopted, without analyzing the data provided by the current wind farm construction. The obtained judgment results are not accurate enough, and the current construction situation of the wind farm is not comprehensively analyzed from multiple perspectives, resulting in the staff not being able to obtain effective and relatively accurate information in a timely manner. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for managing the construction of a wind farm based on the Internet of Things to solve the above problems of the prior art.

[0005] The present invention is achieved through the following technical solutions:

[0006] In a first aspect, the present invention provides a method for managing the construction of a wind farm based on the Internet of Things, including:

[0007] Obtain real-time construction data of the wind farm, collect and transmit it based on the Internet of Things, and classify the real-time construction data, including equipment operation data and progress data;

[0008] Obtain progress data, where the progress data includes reported construction progress data and site construction image data, identify the site construction image data, obtain the target image data of the current target building, and compare the current image data with the completed image data of the target building to obtain the actual construction progress data;

[0009] Compare the actual construction progress data with the reported construction progress data, set an error threshold, and determine whether it is within the error threshold range. If so, no processing is performed. If not, an error alarm is issued;

[0010] Obtain the device operation data and device historical operation data of the construction project that issues error alerts, establish a device fault diagnosis model based on the device historical operation data, analyze the device data through the fault diagnosis model, and output the result of whether the current device is faulty;

[0011] If a fault occurs, send a signal that the current construction project needs to accept external scheduling. If no fault occurs, no processing is performed.

[0012] Preferably, the collection and transmission based on the Internet of Things include:

[0013] Filter, denoise, and remove redundancy from the real-time construction data of the wind farm, and select a transmission protocol;

[0014] Summarize the collected real-time construction data of the wind farm, encrypt it, and transmit the encrypted data to the cloud platform to be processed.

[0015] Preferably, the encryption includes:

[0016] Divide the real-time construction data of the wind farm into blocks, and fill the data that is less than one block:

[0017] Generate an AES key, encrypt the AES key using the RSA public key, and encrypt the real-time construction data of the wind farm using AES to obtain ciphertext;

[0018] And send the ciphertext and the encrypted AES key to the receiving end. The receiving end decrypts the AES key using the RSA public key and decrypts the ciphertext using the decrypted AES key.

[0019] Preferably, the encryption of the real-time construction data of the wind farm using AES includes:

[0020] C = E AES (P, K AES , IV)

[0021] The encryption of the AES key using the RSA public key includes:

[0022]

[0023] AES where C is the ciphertext, E AES is the encryption function, P is the real-time construction data of the wind farm, IV is the initialization vector, K key is the AES key, C

[0024] Preferably, the recognition of the site construction image data includes:

[0025] The image data of the site construction is grayscaled, and the denoising process and normalization are performed on the grayscaled image to obtain the image to be recognized;

[0026] Feature extraction is performed on the image to be recognized, and feature dimensionality reduction is performed on the image after feature extraction;

[0027] A first neural network model is constructed to classify and recognize the image according to the features and output the recognition result.

[0028] Preferably, the denoising process of the image includes:

[0029] Calculating the average value of the pixels in the local area using a convolution kernel and replacing the central pixel value with the average value;

[0030]

[0031] In the formula, I′(x, y) is the value of the filtered image at the pixel position (x,y), W is the normalization factor, G s (i,j) is the spatial weight, G r (I(x+i, y+j),I(x,y)) is the pixel value difference weight, k is the filter kernel size, x and y are pixel coordinates, and i and j are the offsets of the filter kernel relative to the central pixel.

[0032] Preferably, the establishment of the equipment fault diagnosis model includes:

[0033] Dividing the historical operation data of the equipment into data sets, including a training set and a validation set, and performing normalization on the historical operation data of the equipment to establish a second neural network model;

[0034] The second neural network model includes:

[0035]

[0036] In the formula, P d is the model output value, is the input sample, σ is the activation function, λ is the regularization coefficient, w ij is the input from the i-th input layer to the j-th hidden layer, is the bias of the j-th input layer, k nm is the input from the n-th hidden layer to the m-th output layer, χ j is the bias of the j-th hidden layer, κ ij is the connection weight from the i-th input layer to the j-th hidden layer, η nm is the connection weight from the n-th hidden layer to the m-th output layer, ζ l is the output of the output layer, μ is the learning rate, and N is the number of samples for each training;

[0037] When -1 ≤ P d ≤ 0, output a signal indicating the current device failure. When 0 < P d ≤ 1, output a signal indicating that the current device is not faulty.

[0038] In a second aspect, the present invention also provides a construction management system for a wind farm based on the Internet of Things, including:

[0039] A data acquisition module, configured to acquire real-time construction data of the wind farm, collect and transmit it based on the Internet of Things, and classify the real-time construction data, including equipment operation data and progress data;

[0040] A first warning module, configured to acquire progress data, where the progress data includes reported construction progress data and site construction image data, identify the site construction image data to obtain target image data of the current target building, compare the current image data with the completed image data of the target building to obtain actual construction progress data; compare the actual construction progress data with the reported construction progress data, and set an error threshold to determine whether it is within the error threshold range. If so, no processing is performed. If not, an error warning is issued;

[0041] A second warning module, configured to acquire the equipment operation data and equipment historical operation data of the construction project that issues an error warning, establish an equipment failure diagnosis model based on the equipment historical operation data, analyze the equipment data through the failure diagnosis model, and output the result of whether the current equipment is faulty; if a fault occurs, issue a signal indicating that the current construction project needs to accept external scheduling. If no fault occurs, no processing is performed;

[0042] A main control module, connected to the data acquisition module, the first warning module, and the second warning module, for executing the above-mentioned construction management method for a wind farm based on the Internet of Things.

[0043] The technical solution of the present invention has at least the following advantages and beneficial effects:

[0044] The method provided by the present invention mainly includes identifying the image data of the site construction, obtaining the target image data of the current target building, comparing the current image data with the completed image data of the target building to obtain the actual construction progress data, comparing the actual construction progress data with the reported construction progress data, analyzing the equipment data through a fault diagnosis model, and outputting the result of whether the current equipment is faulty. Through the above method, various data in the construction process are obtained, and various data are analyzed to confirm whether the current information is consistent with the actual construction progress, so as to timely discover whether there are problems in the current summary content, enabling the staff to obtain effective and relatively accurate data and information in a timely manner. At the same time, based on the judgment of the equipment in the current construction project, it provides a reference basis for whether the staff needs to carry out scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0046] Figure 1 It is a schematic flow chart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0048] The division of modules in this application is a logical division. In actual implementation, there may be other division methods. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0049] The independently described modules or sub-modules may or may not be physically separated: they can be implemented by software or hardware. And part of the modules or sub-modules can be implemented by software, and the functions of this part of the modules or sub-modules are called by the processor through the software, while other parts of the modules or sub-modules are implemented by hardware, such as through a hardware circuit. In addition, part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this application.

[0050] Please refer toFigure 1 , a method for managing the construction of a wind farm based on the Internet of Things provided by the present invention includes:

[0051] S101: Obtain the real-time construction data of the wind farm, collect and transmit it based on the Internet of Things, and classify the real-time construction data, including equipment operation data and progress data;

[0052] The real-time construction data of the wind farm mainly includes the following aspects: equipment installation progress, such as the number, model, and installation status of wind turbines; construction progress, including the installation of foundation works, tower bodies, and blades; electrical connection status, involving the construction of substations and transmission lines; weather conditions, environmental factors affecting construction; resource utilization, involving wind speed and climate data; the matching of progress and budget, monitoring the time and cost control of the project. These data help improve construction efficiency and safety management.

[0053] In this embodiment, the analysis mainly starts from the operation conditions of the equipment and the progress data of the construction.

[0054] S102: Obtain the progress data, where the progress data includes the reported construction progress data and the site construction image data. Identify the site construction image data to obtain the target image data of the current target building, and compare the current image data with the completed image data of the target building to obtain the actual construction progress data;

[0055] Among them, the site construction image data is mainly obtained through on-site monitoring. Of course, it can also be obtained by controlling drones to obtain real-time data from multiple angles to improve the accuracy of the final analysis and set the flight route of the drones.

[0056] Among them, the ratio between the current image data and the completed image data of the target building can be used to obtain a specific data, which can intuitively reflect the current construction progress.

[0057] S103: Compare the actual construction progress data with the reported construction progress data, and set an error threshold to determine whether it is within the error threshold range. If so, no processing is required; if not, an error warning is issued;

[0058] Among them, the error threshold can be set according to specific circumstances. Generally, an error within 1%-3% can be set.

[0059] S104: Obtain the equipment operation data and equipment historical operation data of the construction project for which the error warning is issued. Establish an equipment fault diagnosis model based on the equipment historical operation data, analyze the equipment data through the fault diagnosis model, and output the result of whether the current equipment is faulty;

[0060] S105: If a fault occurs, send a signal that the current construction project needs to receive external scheduling. If no fault occurs, no action is taken.

[0061] This embodiment also takes into account the operating status of the equipment. Projects with false alarms need further attention. If the actual construction progress data is greater than the reported construction progress data, it will not have an impact on the follow-up. If the actual construction progress data is less than the reported construction progress data, it will have a greater impact on the follow-up. Therefore, it is necessary to further analyze the equipment situation to assist the staff in determining whether external assistance is needed.

[0062] The method provided by the present invention mainly includes identifying the site construction image data, obtaining the target image data of the current target building, comparing the current image data with the completed image data of the target building to obtain the actual construction progress data, comparing the actual construction progress data with the reported construction progress data, analyzing the equipment data through a fault diagnosis model, and outputting the result of whether the current equipment is faulty. Through the above method, various data in the construction process are obtained and analyzed to confirm whether the current information is consistent with the actual construction progress, so as to timely discover whether there are problems in the current summary content, enabling the staff to obtain effective and relatively accurate data and information in a timely manner. At the same time, based on the judgment of the equipment in the current construction project, it provides a reference basis for the staff to determine whether to perform scheduling.

[0063] An exemplary implementation manner of the present invention for collection and transmission based on the Internet of Things includes:

[0064] Filter, denoise, and remove redundancy from the real-time construction data of the wind farm, and select a transmission protocol;

[0065] Summarize the collected real-time construction data of the wind farm, encrypt it, and transmit the encrypted data to the cloud platform to be processed.

[0066] Specifically, the encryption includes:

[0067] Divide the real-time construction data of the wind farm into blocks, and fill in the data that is less than one block:

[0068] Generate an AES key, encrypt the AES key using the RSA public key, and encrypt the real-time construction data of the wind farm using AES to obtain ciphertext;

[0069] Send the ciphertext and the encrypted AES key to the receiving end. The receiving end decrypts the AES key using the RSA public key and decrypts the ciphertext using the decrypted AES key.

[0070] An exemplary embodiment of the present invention uses AES to encrypt real-time construction data of a wind farm, including:

[0071] C = E AES (P, K AES , IV)

[0072] The encryption of the AES key using the RSA public key includes:

[0073]

[0074] Wherein, C is the ciphertext, E AES is the encryption function, P is the real-time construction data of the wind farm, IV is the initialization vector, K AES is the AES key, C key is the encrypted AES key, n is the RSA modulus, and e is the encryption exponent.

[0075] An exemplary embodiment of the present invention for identifying site construction image data includes:

[0076] Performing grayscale processing on the site construction image data, and performing denoising processing and normalization on the image after grayscale processing to obtain the image to be recognized;

[0077] Performing feature extraction on the image to be recognized, and performing feature dimensionality reduction on the image after feature extraction;

[0078] Constructing a first neural network model to classify and recognize the image according to the features, and outputting the recognition result.

[0079] An exemplary embodiment of the present invention for denoising an image includes:

[0080] Calculating the average value of pixels in a local area using a convolution kernel, and replacing the central pixel value with the average value;

[0081]

[0082] Wherein, I′(x, y) is the value of the filtered image at the pixel position (x, y), W is the normalization factor, G s (i, j) is the spatial weight, G r (I(x + i, y + j), I(x, y)) is the pixel value difference weight, k is the filter kernel size, x and y are pixel coordinates, and i and j are the offsets of the filter kernel relative to the central pixel.

[0083] An exemplary embodiment of the present invention for establishing a device fault diagnosis model includes:

[0084] Divide the device historical operation data into data sets, including a training set and a validation set, normalize the device historical operation data, and establish a second neural network model;

[0085] The second neural network model includes:

[0086]

[0087] Where P d is the model output value, is the input sample, σ is the activation function, λ is the regularization coefficient, w ij is the input from the i-th input layer to the j-th hidden layer, is the bias of the j-th input layer, k nm is the input from the n-th hidden layer to the m-th output layer, χ j is the bias of the j-th hidden layer, κ ij is the connection weight from the i-th input layer to the j-th hidden layer, η nm is the connection weight from the n-th hidden layer to the m-th output layer, ζ l is the output of the output layer, μ is the learning rate, and N is the number of samples for each training;

[0088] When -1 ≤ P d ≤ 0, output a signal of the current device failure. When 0 < P d ≤ 1, output a signal that the current device is not faulty.

[0089] In a second aspect, the present invention also provides an Internet of Things-based wind farm construction management system, including:

[0090] A data acquisition module, configured to acquire real-time wind farm construction data, collect and transmit it based on the Internet of Things, and classify the real-time construction data, including device operation data and progress data;

[0091] A first warning module, configured to acquire progress data, where the progress data includes reported construction progress data and site construction image data, identify the site construction image data to obtain target image data of the current target construction, compare the current image data with the completed image data of the target building to obtain actual construction progress data; compare the actual construction progress data with the reported construction progress data, set an error threshold, and determine whether it is within the error threshold range. If so, no processing is performed. If not, an error warning is issued;

[0092] The second warning module is configured to obtain the device operation data and the device historical operation data of the construction project that issues an error warning, establish a device fault diagnosis model based on the device historical operation data, analyze the device data through the fault diagnosis model, and output the result of whether the current device is faulty; if a fault occurs, it sends a signal that the current construction project needs to accept external scheduling, and if no fault occurs, no processing is performed.

[0093] The main control module is connected to the data acquisition module, the first warning module and the second warning module, and is used to execute the above-mentioned wind farm construction management method based on the Internet of Things.

[0094] In addition, in each embodiment of the present invention, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0095] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present invention. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs and other various media that can store program codes.

[0096] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for managing the construction of a wind farm based on the Internet of Things, characterized in that Including: Obtain the real-time construction data of the wind farm, collect and transmit it based on the Internet of Things, and classify the real-time construction data, including equipment operation data and progress data; Obtain the progress data, where the progress data includes reported construction progress data and site construction image data, identify the site construction image data, obtain the target image data of the current target building, and compare the current image data with the completed image data of the target building to obtain the actual construction progress data; Compare the actual construction progress data with the reported construction progress data, set an error threshold, and determine whether it is within the error threshold range. If so, no processing is performed. If not, an error warning is issued; Obtain the equipment operation data and equipment historical operation data of the construction project with an error warning issued, establish an equipment fault diagnosis model based on the equipment historical operation data, analyze the equipment data through the fault diagnosis model, and output the result of whether the current equipment is faulty; If a fault occurs, a signal that the current construction project needs to accept external scheduling is issued. If no fault occurs, no processing is performed.

2. The method for managing the construction of a wind farm based on the Internet of Things according to claim 1, wherein, The collection and transmission based on the Internet of Things includes: Filter, denoise, and remove redundancy from the real-time construction data of the wind farm, and select a transmission protocol; Summarize the collected real-time construction data of the wind farm, encrypt it, and transmit the encrypted data to the cloud platform to be processed.

3. The method for managing the construction of a wind farm based on the Internet of Things according to claim 2, wherein The encryption includes: Divide the real-time construction data of the wind farm into blocks, and fill the data that is less than one block; Generate an AES key, encrypt the AES key using the RSA public key, and encrypt the real-time construction data of the wind farm using AES to obtain ciphertext; And send the ciphertext and the encrypted AES key to the receiving end, where the receiving end decrypts the AES key using the RSA public key and decrypts the ciphertext using the decrypted AES key.

4. The method for managing the construction of a wind farm based on the Internet of Things according to claim 3, wherein The encryption of the real-time construction data of the wind farm using AES includes: C = E AES (P, K AES , IV) The encryption of the AES key using the RSA public key includes: Where C is the ciphertext, E AES is the encryption function, P is the real-time construction data of the wind farm, IV is the initialization vector, K AES is the AES key, C key is the encrypted AES key, n is the RSA modulus, and e is the encryption exponent.

5. The method for managing the construction of a wind farm based on the Internet of Things according to claim 4, wherein, The identification of the site construction image data includes: Perform grayscale processing on the site construction image data, and perform denoising processing and normalization on the image after grayscale processing to obtain the image to be identified; Extract features from the image to be identified, and perform feature dimensionality reduction on the image after feature extraction; Construct a first neural network model to classify and identify the image according to the features, and output the identification result.

6. The method for managing the construction of a wind farm based on the Internet of Things according to claim 5, wherein, The denoising processing of the image includes: Calculate the average value of the pixels in the local area using a convolution kernel, and replace the central pixel value with the average value; Where, I′(x, y) is the value of the filtered image at the pixel position (x, y), W is the normalization factor, G s (i, j) is the spatial weight, G r (I(x + i, y + j), I(x, y)) is the pixel value difference weight, k is the filter kernel size, x and y are pixel coordinates, and i and j are the offsets of the filter kernel relative to the central pixel.

7. The method for managing the construction of a wind farm based on the Internet of Things according to claim 6, wherein, The establishment of the equipment fault diagnosis model includes: Divide the equipment historical operation data into data sets, including a training set and a validation set, perform normalization processing on the equipment historical operation data, and establish a second neural network model; The second neural network model includes: Wherein, P d is the model output value, is the input sample, σ is the activation function, λ is the regularization coefficient, w ij is the input from the input layer of the i-th layer to the hidden layer of the j-th layer, is the bias of the input layer of the j-th layer, k nm is the input from the hidden layer of the n-th layer to the output layer of the m-th layer, χ j is the bias of the hidden layer of the j-th layer, κ ij is the connection weight from the input layer of the i-th layer to the hidden layer of the j-th layer, η nm is the connection weight from the hidden layer of the n-th layer to the output layer of the m-th layer, ζ l is the output of the output layer, μ is the learning rate, and N is the number of samples for each training; When - 1 ≤ P d ≤ 0, output a signal indicating the current device failure. When 0 < P d ≤ 1, output a signal indicating that the current device is not faulty.

8. The wind farm construction management system based on the Internet of Things is characterized in that Including: A data acquisition module configured to obtain the real-time construction data of the wind farm, collect and transmit it based on the Internet of Things, and classify the real-time construction data, including equipment operation data and progress data; The first warning module is configured to obtain progress data, where the progress data includes reported construction progress data and site construction image data, identify the site construction image data to obtain the target image data of the current target building, compare the current image data with the completed image data of the target building to obtain the actual construction progress data; compare the actual construction progress data with the reported construction progress data, set an error threshold, and determine whether it is within the error threshold range. If so, no processing is performed. If not, an error warning is issued; The second warning module is configured to obtain the device operation data and device historical operation data of the construction project that issues an error warning, establish a device fault diagnosis model based on the device historical operation data, analyze the device data through the fault diagnosis model, and output the result of whether the current device is faulty; If a fault occurs, a signal that the current construction project needs to accept external scheduling is issued. If no fault occurs, no processing is performed; The main control module is connected to the data acquisition module, the first warning module, and the second warning module, and is used to execute the method for managing the construction of a wind farm based on the Internet of Things according to any one of claims 1-7.

Images