Wind turbine generator fault simulation method

Through high-resolution environmental simulation, virtual reality, deep learning and digital twin technology, the lack of simulation authenticity and data accuracy in the wind turbine fault simulation method is solved, and more accurate fault prediction and more efficient fault diagnosis are achieved. With repair training, it has improved global cooperation and innovation capabilities.

CN119089764APending Publication Date: 2024-12-06GUODIAN POWER GUANGXI WIND POWER DEV CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410987255.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing wind turbine fault simulation methods have shortcomings in simulation authenticity and data accuracy, and cannot fully reproduce the operating status of wind turbines in complex natural environments. The fault simulation depends on historical data, resulting in inaccurate simulation results.

Method used

Adopting high-resolution environmental simulation and real-time climate monitoring, virtual reality and augmented reality technology, adaptive simulation models based on deep learning, digital twin technology and open data sharing and crowdsourcing platform, combining AI technology, convolutional neural networks and loops Neural networks build accurate virtual environments and models to realize real-time data synchronization and failure simulation.

Benefits of technology

Significantly improves the accuracy of fault prediction and operation reaction time, provides more intuitive and real-time teaching support, reduces trial and error costs, and provides a higher data resource library through global information integration and data quality control, which promotes Global collaborative researcher and generation of innovative solutions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089764A_ABST
    Figure CN119089764A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of wind turbine generator fault simulation, and discloses a wind turbine generator fault simulation method. The system comprises the application of a high-resolution environment simulation and real-time climate monitoring, virtual reality and augmented reality technology, an adaptive simulation model based on deep learning, digital twin technology application and an open data sharing and crowdsourcing platform. According to the wind turbine generator fault simulation method, through application of augmented reality (AR) and virtual reality (VR) technologies, an operator can be fully trained without directly facing a high-risk environment, so that the training safety is improved, more intuitive and real-time teaching support is provided, and the training efficiency is improved. The training of fault diagnosis and repair is more efficient and realistic, artificial intelligence, a convolutional neural network (CNN) and a recurrent neural network (RNN) are utilized to help a simulation system to learn a large amount of historical operation data and fault cases, and future possible fault modes are predicted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of wind turbine fault simulation, in particular to a wind turbine fault simulation method. Background Art

[0002] Wind turbine fault simulation is a technical method that uses computer programs and hardware equipment to reproduce the process of wind turbine failure under various operating and environmental conditions. Its core purpose is to better understand the mechanism of fault formation, predict possible fault development trends, and test the effectiveness of various prevention and maintenance strategies. However, the existing wind turbine fault simulation methods have insufficient simulation authenticity and lack of data accuracy during use. The simulation technology cannot fully reproduce the actual operating status of wind turbines in various complex natural environments, including extreme climate impacts and non-standard operating conditions. At the same time, fault simulation relies heavily on historical fault data and operating data. If the data collection is not comprehensive or the accuracy is not high, the simulation results may not be accurate enough. Summary of the invention

[0003] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A wind turbine fault simulation method, which includes high-resolution environmental simulation and real-time climate monitoring, virtual reality and augmented reality technology applications, deep learning-based adaptive simulation models, digital twin technology applications, and an open data sharing and crowdsourcing platform.

[0006] As a further solution of the present invention: in the high-resolution environmental simulation and real-time climate monitoring, it is necessary to accurately simulate the natural environment where the actual wind turbine is located, including detailed geographical features and weather changes, as follows:

[0007] Deploy high-precision weather stations to collect weather data at specific locations in real time;

[0008] Combining satellite imagery with Earth system science models to achieve 3D modeling of wind farm microclimate and surrounding atmospheric conditions;

[0009] Use AI technology to analyze past and real-time data to predict future environmental changes.

[0010] As a further solution of the present invention: In the application of virtual reality and augmented reality technology, it is necessary to reproduce the operation and fault conditions of wind turbines in a specific environment in a virtual environment, and provide an immersive learning and testing platform, which specifically includes:

[0011] Use VR technology to build a panoramic simulation environment to simulate the interaction between operators and crews;

[0012] Use AR technology to overlay fault information and repair instructions in the real world to assist technicians in fault diagnosis and troubleshooting training.

[0013] As a further solution of the present invention: in the adaptive simulation model based on deep learning, a simulation model capable of self-learning and optimization is created to improve the accuracy and adaptability of the simulation, as follows:

[0014] Collect and organize a large amount of operating data and fault case library;

[0015] Use deep learning algorithms, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), to learn failure patterns and predict future failures;

[0016] Achieve continuous optimization and updating of the model and enhance its predictive ability through feedback loops.

[0017] As a further solution of the present invention: in the application of the digital twin technology, a virtual copy of the wind turbine is constructed to achieve real-time data synchronization and fault simulation, as follows:

[0018] Create a digital twin model on the cloud platform to map the structure and operating status of the actual wind turbine in real time;

[0019] Combined with Internet of Things (IoT) technology, the unit’s operating data is collected and the status of the digital twin is updated in a timely manner;

[0020] Simulate failures in the digital twin and test the effectiveness of different repair solutions.

[0021] As a further solution of the present invention: the open data sharing and crowdsourcing platform needs to integrate and utilize data resources around the world to improve the breadth and accuracy of simulation results, as follows:

[0022] Build an open access platform to encourage researchers, technicians and enterprises around the world to share wind turbine operation data and failure cases;

[0023] Establish data quality control and security mechanisms to ensure data accuracy and security;

[0024] Leverage crowdsourcing to solve specific problems or develop new fault diagnosis algorithms.

[0025] As a further solution of the present invention: in the wind turbine fault simulation method, the specific algorithm formulas of applying convolutional neural network (CNN) and recurrent neural network (RNN) are as follows:

[0026] Convolutional Neural Networks (CNN)

[0027] Convolutional layer In the convolutional layer, the main operation is the convolution operation, the purpose of which is to extract the features of the input data. For one-dimensional data (such as wind turbine time series data), the convolution formula is:

[0028]

[0029] where yk[i] is the output of the kth filter at position i, and b k is the bias term of the kth filter, W k is the weight of the kth filter, x[ij] is the value of the input data at position ij, and f is the size of the filter;

[0030] Activation function: A non-linear activation function, such as ReLU, is applied after each convolution step:

[0031] z[i]=max(0,y[i]);

[0032] Among them, y[i] is the output of the convolution layer, and z[i] is the output after activation;

[0033] Pooling layer: used to reduce data dimension and enhance the generalization ability of the model, maximum pooling operation:

[0034]

[0035] As a further solution of the present invention: in the wind turbine fault simulation method, the specific algorithm formula of the recurrent neural network (RNN) is as follows:

[0036] Hide status update:h t =σ(W hh ·h t-1 +W hx ·x t +b h );

[0037] Among them, h t is the hidden state at time t, h t-1 is the hidden state at time t-1, x t is the input data at time t, W hh is the weight matrix of the hidden state, W hx is the weight matrix of the input data, b his the bias term, σ is the activation function, usually tanh or sigmoid;

[0038] Output prediction: o t =W ho ·h t +b o ;

[0039] Among them, ot: output at time t, Who: output layer weight matrix, bo: output layer bias.

[0040] As a further solution of the present invention: the AI ​​technology in the high-resolution environmental simulation and real-time climate monitoring adopts time series prediction, which is as follows:

[0041] Autoregressive Integrated Moving Average (ARIMA) model:

[0042] Y t =μ+φ1Y t-1 +...+φ p Y t-p +∈ t +θ1∈ t-1 +...+θ q ∈ t-q ;

[0043] Where Yt is the target variable at time t, μ is the model constant, φi is the autoregressive parameter, θj is the moving average parameter, and ∈t is the error term.

[0044] As a further solution of the present invention: the Internet of Things (IoT) technology specifically includes:

[0045] Data collection: Use sensors installed at key locations of wind turbines, including temperature sensors, vibration sensors, and speed sensors, to collect real-time operating data;

[0046] Data communication: Through the Internet of Things technology, these data are transmitted to the cloud platform in real time and used to update the status of the digital twin model to ensure that the model can accurately reflect the actual operating conditions of the unit.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] Through the application of augmented reality (AR) and virtual reality (VR) technologies, operators can be fully trained without having to face high-risk environments directly. This not only increases the safety of training, but also provides more intuitive and real-time teaching support, making fault diagnosis and repair training more efficient and realistic. Using artificial intelligence, convolutional neural networks (CNN) and recurrent neural networks (RNN), the simulation system can learn a large amount of historical operating data and fault cases, and predict possible future fault modes. This method significantly improves the accuracy of fault prediction and the response time of operations. By building an accurate virtual copy of the wind turbine, real-time monitoring and simulation of the actual equipment status can be achieved, which not only helps real-time fault detection, but also can test different maintenance strategies in a simulated environment to find the optimal solution and reduce the trial and error costs in actual operations. At the same time, through the integration of global information and combined with data quality control, a more extensive and accurate data resource library is provided. Such a platform can also promote cooperation between researchers around the world, increase the generation of innovative solutions, and help to quickly solve complex problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 The figure is a schematic diagram of the method steps of a wind turbine fault simulation method. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the specific implementation modes of the present invention are described in detail below in conjunction with the accompanying drawings.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0052] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0053] Example 1

[0054] See also Figure 1 , which is the first embodiment of the present invention, and provides a method for simulating wind turbine faults, which is specifically for simulating wind turbine faults in coastal areas, and the steps are as follows:

[0055] Step 1: High-resolution environmental simulation and real-time climate monitoring: Deploy multiple high-precision meteorological stations in coastal areas to collect real-time data on wind speed, wind direction, air pressure, humidity, and salt spray concentration. Combined with satellite images and marine meteorological models, three-dimensional 3D modeling is performed based on the unique microclimate characteristics of the coastal areas.

[0056] Step 2: Application of virtual reality and augmented reality technology: Use VR technology to build a panoramic simulation environment under specific geographical and meteorological conditions, simulate wind turbine operation under extreme conditions such as strong winds and salt spray erosion, and use AR technology to display real-time fault diagnosis data and quick repair guidance using head-mounted devices at the actual wind turbine site;

[0057] Step 3: Adaptive simulation model based on deep learning: Gather the operation data and fault case library of wind turbines in coastal areas, use deep learning algorithms (CNN and RNN), and train the model specifically to learn the failure modes caused by salt spray and erosion, and predict similar failures that may occur in the future;

[0058] Step 4: Application of digital twin technology: Create a digital twin model of a specific wind turbine, synchronize the structure and operation status of coastal wind turbines in real time, and use the Internet of Things technology to collect real-time operation data, including data generated by extreme weather, to achieve instant status updates;

[0059] Step 5. Open data sharing and crowdsourcing platform: Establish an open data platform focusing on coastal wind turbines, strengthen the research and sharing of wind turbine data under such specific environmental conditions worldwide, set strict data quality control standards to ensure the provision of high-quality and reliable data, and use crowdsourcing to solve specific technical challenges.

[0060] Example 2

[0061] See also Figure 1 , which is the second embodiment of the present invention, specifically for wind turbine fault simulation in mountainous areas, the method steps are as follows:

[0062] Step 1: High-resolution environmental simulation and real-time climate monitoring: Deploy high-precision meteorological stations in mountainous areas to measure wind speed, temperature, humidity, etc. Considering the changeable weather conditions and terrain influence in mountainous areas, use topographic maps and climate models to simulate the special climate conditions and geographical influences of mountainous wind farms;

[0063] Step 2: Application of virtual reality and augmented reality technologies: Build a VR simulation platform for mountainous environments, simulate operation scenarios under high altitude, low oxygen and complex terrain, and apply AR technology on site to provide real-time fault diagnosis support and operation guides, especially for equipment operation under high altitude and low temperature conditions;

[0064] Step 3: Adaptive simulation model based on deep learning: Collect the unique operating data and fault information of wind turbines in mountainous areas, and apply deep learning technology, especially for the fault mode analysis of frequent shutdown and startup problems caused by terrain;

[0065] Step 4: Application of digital twin technology: Establish a digital twin model based on mountain wind turbines, simulate and analyze the impact of various extreme natural environments in actual operation, and combine IoT to collect real-time data feedback in extreme weather events to enhance the dynamic update capability of digital twins;

[0066] Step 5. Open data sharing and crowdsourcing platform: Create a data sharing platform for wind turbine operations in mountainous areas, strengthen the understanding and research of the operating characteristics of high-altitude wind turbines, encourage global researchers to share data, especially data on high-altitude wind power stations, and establish high-standard safety and quality assurance mechanisms.

[0067] The experimental data table is as follows:

[0068]

[0069]

[0070] In summary, through the application of augmented reality (AR) and virtual reality (VR) technologies, operators can be fully trained without having to face high-risk environments directly. This not only increases the safety of training, but also provides more intuitive and real-time teaching support, making fault diagnosis and repair training more efficient and realistic. Using artificial intelligence, convolutional neural networks (CNN) and recurrent neural networks (RNN), the simulation system can learn a large amount of historical operation data and fault cases, and predict possible future fault modes. This method significantly improves the accuracy of fault prediction and the response time of operation. By building an accurate virtual copy of the wind turbine, real-time monitoring and simulation of the actual equipment status can be achieved, which not only helps real-time fault detection, but also can test different maintenance strategies in a simulated environment to find the optimal solution and reduce the trial and error costs in actual operations. At the same time, through the integration of global information and combined with data quality control, a more extensive and accurate data resource library is provided. Such a platform can also promote cooperation between researchers around the world, increase the generation of innovative solutions, and help to quickly solve complex problems.

[0071] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., the size, scale, structure, shape and proportion of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. In the claims, any "device plus function" clause is intended to cover the structure of performing the function described herein, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the invention is not limited to a specific embodiment, but extends to several modifications still falling within the scope of the appended claims.

[0072] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0073] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0074] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A wind turbine fault simulation method, Features: Its simulation methods include high-resolution environmental simulation and real-time climate monitoring, application of virtual reality and augmented reality technologies, adaptive simulation models based on deep learning, application of digital twin technology, and open data sharing and crowdsourcing platforms.

2. A wind turbine fault simulation method according to claim 1, Features: In the high-resolution environmental simulation and real-time climate monitoring, it is necessary to accurately simulate the natural environment where the actual wind turbine is located, including detailed geographical features and weather changes, as follows: Deploy high-precision weather stations to collect weather data at specific locations in real time; Combining satellite imagery with Earth system science models to achieve 3D modeling of wind farm microclimate and surrounding atmospheric conditions; Use AI technology to analyze past and real-time data to predict future environmental changes.

3. A wind turbine fault simulation method according to claim 1, Features: In the application of virtual reality and augmented reality technology, it is necessary to reproduce the operation and fault conditions of wind turbines in a specific environment in a virtual environment and provide an immersive learning and testing platform, including: Use VR technology to build a panoramic simulation environment to simulate the interaction between operators and crews; Use AR technology to overlay fault information and repair instructions in the real world to assist technicians in fault diagnosis and troubleshooting training.

4. A wind turbine fault simulation method according to claim 1, Features: In the adaptive simulation model based on deep learning, a simulation model capable of self-learning and optimization is created to improve the accuracy and adaptability of the simulation, as follows: Collect and organize a large amount of operating data and fault case library; Use deep learning algorithms, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), to learn failure patterns and predict future failures; Achieve continuous optimization and updating of the model and enhance its predictive ability through feedback loops.

5. A wind turbine fault simulation method according to claim 1, Features: In the application of digital twin technology, a virtual copy of the wind turbine is constructed to achieve real-time data synchronization and fault simulation, as follows: Create a digital twin model on the cloud platform to map the structure and operating status of the actual wind turbine in real time; Combined with Internet of Things (IoT) technology, the unit’s operating data is collected and the status of the digital twin is updated in a timely manner; Simulate failures in the digital twin and test the effectiveness of different repair solutions.

6. A wind turbine fault simulation method according to claim 1, Features: The open data sharing and crowdsourcing platform needs to integrate and utilize data resources around the world to improve the breadth and accuracy of simulation results, as follows: Build an open access platform to encourage researchers, technicians and enterprises around the world to share wind turbine operation data and failure cases; Establish data quality control and security mechanisms to ensure data accuracy and security; Leverage crowdsourcing to solve specific problems or develop new fault diagnosis algorithms.

7. A wind turbine fault simulation method according to claim 4, Features: In the wind turbine fault simulation method, the specific algorithm formulas of applying convolutional neural network (CNN) and recurrent neural network (RNN) are as follows: Convolutional Neural Networks (CNN) Convolutional layer In the convolutional layer, the main operation is the convolution operation, the purpose of which is to extract the features of the input data. For one-dimensional data (such as wind turbine time series data), the convolution formula is: where yk[i] is the output of the kth filter at position i, and b k is the bias term of the kth filter, W k is the weight of the kth filter, x[ij] is the value of the input data at position ij, and f is the size of the filter; Activation function: A non-linear activation function, such as ReLU, is applied after each convolution step: z[i]=max(0,y[i]); Among them, y[i] is the output of the convolution layer, and z[i] is the output after activation; Pooling layer: used to reduce data dimension and enhance the generalization ability of the model, maximum pooling operation:

8. A wind turbine fault simulation method according to claim 4, Features: In the wind turbine fault simulation method, the specific algorithm formula of the recurrent neural network (RNN) is as follows: Hide status update:h t =σ(W hh ·h t-1 +W hx ·x t +b h ); Among them, h t is the hidden state at time t, h t-1 is the hidden state at time t-1, x t is the input data at time t, W hh is the weight matrix of the hidden state, W hx is the weight matrix of the input data, b h is the bias term, σ is the activation function, usually tanh or sigmoid; Output prediction: o t =W ho ·h t +b o ; Among them, ot: output at time t, Who: output layer weight matrix, bo: output layer bias.

9. A wind turbine fault simulation method according to claim 1, Features: The AI ​​technology used in the high-resolution environmental simulation and real-time climate monitoring adopts time series prediction, which is as follows: Autoregressive Integrated Moving Average (ARIMA) model: Y t =μ+φ 1 Y t-1 +...+φ p Y t-p +∈ t +θ 1 ∈ t-1 +...+θ q ∈ t-q ; Where Yt is the target variable at time t, μ is the model constant, φi is the autoregressive parameter, θj is the moving average parameter, and ∈t is the error term.

10. A wind turbine fault simulation method according to claim 1, Features: The Internet of Things (IoT) technology specifically includes: Data collection: Use sensors installed at key locations of wind turbines, including temperature sensors, vibration sensors, and speed sensors, to collect real-time operating data; Data communication: Through the Internet of Things technology, these data are transmitted to the cloud platform in real time and used to update the status of the digital twin model to ensure that the model can accurately reflect the actual operating conditions of the unit.