A wind farm power transmission equipment monitoring system

Abstract

The application provides a kind of wind farm power transmission equipment monitoring system, it is related to wind farm equipment monitoring technical field, including data acquisition module, data processing module, fault early warning module, intelligent inspection module, data fusion module, digital twin module and management decision module, the data acquisition module utilizes high-precision sensor real-time acquisition wind farm power transmission equipment's operating state data, and through intelligent perception camera collects field image data;The application integrates multiple modules, realizes the comprehensive monitoring of wind farm power transmission equipment, including digital twin technology, high-precision sensor technology, big data analysis technology, machine learning technology, AI intelligent inspection technology etc., constructs the integration and interoperation system of interdisciplinary knowledge model, improves the technical advancement and comprehensive monitoring capability of system, realizes the comprehensive grasp of the overall operating state of wind farm power transmission equipment.

Description

Technical Field

[0001] This invention relates to the field of wind farm equipment monitoring technology, and in particular to a wind farm transmission equipment monitoring system. Background Technology

[0002] In the wind power industry, the stable operation of wind farm transmission equipment is crucial to the reliability and security of the entire power system. However, existing monitoring technologies for wind farm transmission equipment have many shortcomings:

[0003] On the one hand, traditional monitoring systems often only monitor single devices or single parameters, such as relying solely on SCADA data for wind turbine fault warnings. They lack comprehensive monitoring and collaborative analysis of multiple types of equipment, including substations and transmission / transformation equipment, making it difficult to achieve a complete understanding of the overall operating status of wind farm transmission equipment. On the other hand, in terms of fault warning, existing technologies are mostly based on simple data threshold comparisons or single algorithm models, lacking the ability to identify complex equipment fault modes, easily leading to false alarms or missed alarms. For example, in transmission / transformation equipment fault warning, traditional methods cannot fully utilize the large amounts of data collected by high-precision sensors, combined with expert knowledge and machine learning algorithms for in-depth analysis, resulting in insufficient accuracy and timeliness of fault prediction. Furthermore, existing monitoring systems have deficiencies in data fusion and intelligent decision-making, failing to effectively integrate advanced technologies such as digital twin technology and AI intelligent inspection systems. This makes it difficult to achieve real-time, accurate monitoring, remote operation, and intelligent decision-making for transmission equipment, thus affecting the operating efficiency and equipment management level of wind farms, increasing operating and maintenance costs. Therefore, this invention proposes a wind farm transmission equipment monitoring system to address the problems existing in the prior art. Summary of the Invention

[0004] To address the aforementioned issues, this invention proposes a wind farm transmission equipment monitoring system. This system integrates multiple modules to achieve comprehensive monitoring of wind farm transmission equipment, including digital twin technology, high-precision sensor technology, big data analysis technology, machine learning technology, and AI intelligent inspection technology. It constructs an integrated and interoperable system of interdisciplinary knowledge models, enhancing the system's technological advancement and comprehensive monitoring capabilities, and enabling a complete grasp of the overall operating status of wind farm transmission equipment.

[0005] To achieve the objectives of this invention, the invention is implemented through the following technical solution: a wind farm transmission equipment monitoring system, comprising a data acquisition module, a data processing module, a fault early warning module, an intelligent inspection module, a data fusion module, a digital twin module, and a management decision-making module, characterized in that: the data acquisition module utilizes high-precision sensors to collect real-time operating status data of the wind farm transmission equipment and collects on-site image data through intelligent sensing cameras; the data processing module is used to process and analyze the collected data using big data analysis algorithms and machine learning algorithms;

[0006] The fault early warning module provides fault warnings based on the processed data; the intelligent inspection module processes on-site image data and identifies defects to generate alarm information; the data fusion module collects multi-source data and establishes the integration and interoperability of interdisciplinary knowledge models; the digital twin module constructs digital twins of wind turbines and substations; and the management decision module provides decision support for users.

[0007] A further improvement is that the high-precision sensors in the data acquisition module include a temperature sensor, a vibration sensor, a voltage sensor, and a current sensor, which are used to acquire the temperature, vibration, voltage, and current parameters of the device, respectively.

[0008] A further improvement is made in the data processing module, where a big data analysis algorithm is used to extract the patterns and characteristics of equipment operation. This algorithm includes a time series analysis (TSA) algorithm and a year-on-year / month-on-month (YOA) analysis algorithm. The formula for the time series analysis (TSA) algorithm is as follows:

[0009] X t =T t +S t +R t

[0010] Where: X t The device status parameters collected at time t; T t The trend component represents the long-term trend of equipment status over time; S t The seasonal component represents a periodic pattern of change; R t For random error components, representing unpredictable random fluctuations;

[0011] In the year-on-year and month-on-month analysis algorithm (YOA), the formula for calculating the year-on-year growth rate is as follows:

[0012]

[0013] The formula for calculating the month-on-month growth rate is:

[0014]

[0015] Where: YGR t MGR is the year-on-year growth rate at time t. t X represents the month-on-month growth rate at time t; t This refers to the device status data collected in the current cycle; X t-n This provides equipment status data for the same period last year at n-period intervals; X t-1 This is the equipment status data from the previous cycle.

[0016] A further improvement is that the machine learning algorithm is used to train a fault prediction model on historical fault data of the equipment, and the machine learning algorithm includes a support vector machine (SVM) model, a random forest (RF) model, and a long short-term memory network (LSTM) model. The decision function of the support vector machine (SVM) model is:

[0017]

[0018] Where f(x) is the equipment fault prediction result, 1 represents fault and 0 represents normal; W is the weight vector of the feature space; is the nonlinear feature mapping function for the input data x; b is the bias term of the classification hyperplane;

[0019] The random forest (RF) model consists of K decision trees. Composition, and the final prediction result is:

[0020]

[0021] In the formula: is the predicted value for the equipment fault type; C is the fault type category; I(·) is the indicator function, which takes the value 1 when the condition is true and 0 otherwise; Tk(x) is the prediction result of the k-th decision tree for the input data x;

[0022] The cell state update equation of the Long Short-Term Memory (LSTM) network model is as follows:

[0023]

[0024] Among them, f t The output of the forget gate controls the cell state C. t-1 The degree of forgetting; i t The input gate outputs control new information. Write level; C t The current state of the cell; o t Output gate output, controls the hidden state h t The output of W; f W i W C W ob is the weight matrix for each gate; f ,b i ,b C ,b o These are the bias vectors for each gate; sigmoid is the activation function, and tanh is the hyperbolic tangent activation function; This represents element-wise multiplication.

[0025] Further improvements include: the fault early warning module includes a diagnostic model and an expert system. The diagnostic model is used to retrieve diagnostic information according to region, unit, and time range, and the expert system provides fault early warning and maintenance suggestions based on expert knowledge and experience.

[0026] A further improvement lies in the following: the algorithm model of the intelligent inspection module includes a target detection algorithm and an image classification function, used to process and annotate on-site image data to identify actual defects. The coordinates of the detection box of the target detection algorithm are represented as follows:

[0027]

[0028] In the formula: (b x ,b y (b) represents the coordinates of the detection box center. w ,b h ) represents the width and height of the detection frame; (c x ,c y (p) represents the coordinates of the top-left corner of the current grid; w ,p h ) represents the width and height of the prior bounding box; (t) x ,t y ,t w ,t h ) represents the offset and scaling factor predicted by the network; This is the sigmoid function, used to map coordinate offsets to the grid area.

[0029] Further improvements include: the data fusion module collects multi-source data including substation data, generator unit data, energy management system data, wind power prediction system data, fire alarm system data, and video surveillance data, and employs a cross-modal data fusion algorithm to integrate numerical sensor data D... s With image-based inspection data D i Merge into a unified feature vector F:

[0030] F = Concat(f) s (D s ),f i (D i ))

[0031] Where: fs (·) represents the sensor data feature extraction function; f i (·) is the image data feature extraction function; Concat(·) represents the feature vector concatenation operation.

[0032] Further improvements include: the wind turbine twin of the digital twin module enables intelligent monitoring, optimized operation, and predictive maintenance of the wind turbine, while the substation digital twin achieves a one-to-one simulation of the real substation.

[0033] Further improvements include: the management decision module displays the status of the site camera equipment, alarm images, alarm data analysis, equipment operating status, fault warning information, and digital twin simulation results through visual charts.

[0034] Further improvements include: a hardware integration module that uses hardware integration technology to enable collaborative work between different types of computing nodes, achieve data sharing and communication through high-speed networks and shared storage systems, and use load balancing and task scheduling technologies to achieve efficient utilization and management of computing resources.

[0035] The beneficial effects of this invention are as follows:

[0036] 1. This invention integrates multiple modules to achieve comprehensive monitoring of wind farm transmission equipment, including digital twin technology, high-precision sensor technology, big data analysis technology, machine learning technology, AI intelligent inspection technology, etc. It constructs an integrated and interoperable system of interdisciplinary knowledge models, improves the system's technological advancement and comprehensive monitoring capabilities, and enables a comprehensive understanding of the overall operating status of wind farm transmission equipment.

[0037] 2. This invention has a variety of fault early warning mechanisms. By combining diagnostic models, expert systems, time series analysis algorithms, and year-on-year and month-on-month analysis algorithms, it improves the accuracy and timeliness of fault early warning and can detect and prevent faults from occurring in advance.

[0038] 3. The intelligent inspection module of this invention adopts edge computing and multiple image acquisition methods, combined with advanced algorithm models for image processing and defect identification, realizing intelligent inspection of power transmission equipment on site, and improving inspection efficiency and reliability.

[0039] 4. The data fusion module of this invention realizes efficient fusion of multi-source data and integration of interdisciplinary knowledge models, providing a stable and reliable data foundation for the digital twin module and management decision-making module, and supporting intelligent monitoring and decision-making of wind farm transmission equipment. Attached Figure Description

[0040] Figure 1 This is a schematic diagram illustrating the technical points of the present invention;

[0041] Figure 2 This is a schematic diagram of the intelligent inspection module of the present invention;

[0042] Figure 3 This is a functional diagram of the hardware integration module of the present invention. Detailed Implementation

[0043] To enhance understanding of the present invention, the present invention will be further described in detail below with reference to embodiments. These embodiments are only used to explain the present invention and do not constitute a limitation on the scope of protection of the present invention.

[0044] Example 1

[0045] according to Figure 1 , 2 As shown in Figure 3, this embodiment proposes a wind farm transmission equipment monitoring system, including a data acquisition module, a data processing module, a fault early warning module, an intelligent inspection module, a data fusion module, a digital twin module, and a management decision module. The system is characterized in that: the data acquisition module uses high-precision sensors to collect real-time operating status data of the wind farm transmission equipment and acquires on-site image data through intelligent sensing cameras; the data processing module uses big data analysis algorithms and machine learning algorithms to process and analyze the collected data.

[0046] The fault early warning module provides fault warnings based on the processed data; the intelligent inspection module processes on-site image data and identifies defects to generate alarm information; the data fusion module collects multi-source data and establishes the integration and interoperability of interdisciplinary knowledge models; the digital twin module constructs digital twins of wind turbines and substations; and the management decision module provides decision support for users.

[0047] The data acquisition module includes high-precision sensors such as a temperature sensor, a vibration sensor, a voltage sensor, and a current sensor, which are used to acquire the temperature, vibration, voltage, and current parameters of the equipment, respectively. Through Internet of Things (IoT) technology, the sensors are connected to the power transmission and transformation equipment to achieve remote monitoring and management of the equipment.

[0048] In the data processing module, big data analysis algorithms are used to extract the patterns and characteristics of equipment operation. These algorithms include a time series analysis algorithm (TSA) and a year-on-year / month-on-month analysis algorithm (YOA). The formula for the time series analysis algorithm (TSA) is as follows:

[0049] X t =T t +S t +R t

[0050] Where: X t The device status parameters collected at time t; Tt The trend component represents the long-term trend of equipment status over time; S t The seasonal component represents a periodic pattern of change; R t For random error components, representing unpredictable random fluctuations;

[0051] In the year-on-year and month-on-month analysis algorithm (YOA), the formula for calculating the year-on-year growth rate is as follows:

[0052]

[0053] The formula for calculating the month-on-month growth rate is:

[0054]

[0055] Where: YGR t MGR is the year-on-year growth rate at time t. t X represents the month-on-month growth rate at time t; t This refers to the device status data collected in the current cycle; X t-n This provides equipment status data for the same period last year at n-period intervals; X t-1 This is the equipment status data from the previous cycle.

[0056] The machine learning algorithm is used to train a fault prediction model on historical fault data of the equipment. The machine learning algorithm includes a Support Vector Machine (SVM) model, a Random Forest (RF) model, and a Long Short-Term Memory (LSTM) network model. The decision function of the Support Vector Machine (SVM) model is:

[0057]

[0058] Where f(x) is the equipment fault prediction result, 1 represents fault and 0 represents normal; W is the weight vector of the feature space; is the nonlinear feature mapping function for the input data x; b is the bias term of the classification hyperplane;

[0059] The random forest (RF) model consists of K decision trees. Composition, and the final prediction result is:

[0060]

[0061] In the formula: is the predicted value for the equipment fault type; C is the fault type category; I(·) is the indicator function, which takes the value 1 when the condition is true and 0 otherwise; Tk(x) is the prediction result of the k-th decision tree for the input data x;

[0062] The cell state update equation of the Long Short-Term Memory (LSTM) network model is as follows:

[0063]

[0064] Among them, f t The output of the forget gate controls the cell state C. t-1 The degree of forgetting; i t The input gate outputs control new information. Write level; C t The current state of the cell; o t Output gate output, controls the hidden state h t The output of W; f W i W C W o b is the weight matrix for each gate; f ,b i ,b C ,b o These are the bias vectors for each gate; sigmoid is the activation function, and tanh is the hyperbolic tangent activation function; This represents element-wise multiplication.

[0065] The fault early warning module includes a diagnostic model and an expert system. The diagnostic model is used to retrieve diagnostic information according to region, unit, and time range. The expert system provides fault early warning and maintenance suggestions based on expert knowledge and experience.

[0066] The intelligent inspection module's algorithm model includes a target detection algorithm and image classification functionality, used to process and annotate on-site image data to identify actual defects. The target detection algorithm's bounding box coordinates are represented as follows:

[0067]

[0068] In the formula: (b x ,b y (b) represents the coordinates of the detection box center. w ,b h ) represents the width and height of the detection frame; (c x ,c y (p) represents the coordinates of the top-left corner of the current grid; w ,p h ) represents the width and height of the prior bounding box; (t) x ,t y ,t w ,t h ) represents the offset and scaling factor predicted by the network; This is the sigmoid function, used to map coordinate offsets to the grid area.

[0069] The data fusion module collects multi-source data including substation data, generator unit data, energy management system data, wind power prediction system data, fire alarm system data, and video surveillance data. It also employs a cross-modal data fusion algorithm to integrate numerical sensor data (D...). s With image-based inspection data D i Merge into a unified feature vector F:

[0070] F = Concat(f) s (D s ),f i (D i ))

[0071] Where: f s (·) represents the sensor data feature extraction function; f i (·) is the image data feature extraction function; Concat(·) represents the feature vector concatenation operation.

[0072] The digital twin module enables intelligent monitoring, optimized operation, and predictive maintenance of wind turbines, while the digital twin of the substation achieves a one-to-one simulation of the real substation.

[0073] The management decision module displays the status of the site camera equipment, alarm images, alarm data analysis, equipment operating status, fault warning information, and digital twin simulation results through visual charts.

[0074] It also includes a hardware integration module, which uses hardware integration technology to enable different types of computing nodes to work together, achieve data sharing and communication through high-speed networks and shared storage systems, and use load balancing and task scheduling technologies to achieve efficient utilization and management of computing resources.

[0075] This system integrates diverse modules to achieve comprehensive and accurate monitoring of wind farm transmission equipment. The data acquisition module ensures data comprehensiveness and real-time performance; the data processing module utilizes advanced algorithms to extract data features, providing strong support for fault early warning; the fault early warning module combines multiple models and algorithms to improve the accuracy and timeliness of fault early warnings; the intelligent inspection module enables intelligent on-site equipment inspection, reducing labor costs and improving inspection efficiency; the data fusion module and digital twin module provide robust data and technical support for intelligent equipment monitoring and decision-making; and the management decision-making module facilitates user decision-making and management through visual displays. Overall, this system improves the operational efficiency and reliability of wind farm transmission equipment, reduces operating and maintenance costs, and demonstrates significant economic and social benefits.

[0076] Example 2

[0077] according to Figure 1 , 2As shown in Figure 3, this embodiment proposes a wind farm transmission equipment monitoring system deployed in a wind farm. The data acquisition module collects real-time operating data from wind turbines and substations using high-precision sensors, while intelligent sensing cameras periodically capture on-site images. The data processing module uses big data analytics algorithms to clean and integrate the massive amounts of collected data, removing noise and unifying the format of different data types. A Long Short-Term Memory (LSTM) machine learning algorithm is used to train historical fault data from wind turbines to establish a fault prediction model. The fault early warning module, combined with the diagnostic model, retrieves diagnostic information according to turbine unit and time range. When the vibration data of a wind turbine exceeds a set threshold, it uses expert system knowledge to determine if a bearing fault is possible and issues an early warning. The intelligent inspection module processes the images captured by the cameras and uses the YOLO algorithm to identify bolt loosening defects in the substation equipment, generating alarm information. The data fusion module integrates multi-source data from wind turbines, substations, and energy management systems to construct digital twins of the wind turbines and substations, simulating the equipment's operating status in real time. The management decision-making module displays the equipment's operating status and fault warning information through visual charts, allowing staff to perform timely maintenance and repairs based on this information.

[0078] Verification data: After implementing this system, the accuracy of wind turbine fault early warning increased by 30%, the maintenance cost of booster station equipment decreased by 25%, and the overall operating efficiency of wind farms increased by 20%.

[0079] Example 3

[0080] according to Figure 1 , 2 As shown in Figure 3, this embodiment proposes a monitoring system for transmission equipment in a wind farm, deployed in another wind farm, with a focus on the application of an intelligent inspection module. Intelligent sensing cameras use edge computing and human recognition to monitor personnel entering the equipment area, while simultaneously capturing images of the transmission and transformation equipment on a regular rotating basis. The image processing unit uses the Faster R-CNN algorithm to process the images, annotating external defects such as insulator damage and broken conductor strands. When a defect is detected, an alarm message is generated based on the camera's location and time, and the alarm image and short video are captured. Statistical analysis shows that the intelligent inspection module can identify more than 95% of equipment external defects, improving efficiency by 40% and reducing the missed detection rate by 20% compared to traditional manual inspection.

[0081] This wind farm transmission equipment monitoring system integrates multiple modules to achieve comprehensive monitoring of wind farm transmission equipment. These modules include digital twin technology, high-precision sensor technology, big data analysis technology, machine learning technology, and AI intelligent inspection technology. It constructs an integrated and interoperable system of interdisciplinary knowledge models, enhancing the system's technological advancement and comprehensive monitoring capabilities, and enabling a complete grasp of the overall operating status of the wind farm transmission equipment. Furthermore, this invention features diverse fault early warning mechanisms, combining diagnostic models, expert systems, time series analysis algorithms, and year-on-year and month-on-month comparison algorithms to improve the accuracy and timeliness of fault early warnings, enabling early detection and prevention of faults. Simultaneously, the intelligent inspection module of this invention employs edge computing and multiple image acquisition methods, combined with advanced algorithm models for image processing and defect identification, achieving intelligent on-site inspection of transmission equipment and improving inspection efficiency and reliability. In addition, the data fusion module of this invention achieves efficient fusion of multi-source data and integration of interdisciplinary knowledge models, providing a stable and reliable data foundation for the digital twin module and management decision-making module, supporting intelligent monitoring and decision-making for wind farm transmission equipment.

[0082] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A monitoring system for wind farm transmission equipment, comprising a data acquisition module, a data processing module, a fault early warning module, an intelligent inspection module, a data fusion module, a digital twin module, and a management decision-making module, characterized in that: The data acquisition module uses high-precision sensors to collect real-time operating status data of wind farm transmission equipment and intelligent sensing cameras to collect on-site image data; the data processing module is used to process and analyze the collected data using big data analysis algorithms and machine learning algorithms. The fault warning module provides fault warnings based on the processed data. The intelligent inspection module is used to process on-site image data and identify defects, generating alarm information; the data fusion module is used to collect multi-source data and establish the integration and interoperability of cross-disciplinary knowledge models; the digital twin module is used to construct digital twins of wind turbines and substations; the management decision module is used to provide decision support for users. In the data processing module, big data analysis algorithms are used to extract the patterns and characteristics of equipment operation. These algorithms include a time series analysis algorithm (TSA) and a year-on-year / month-on-month analysis algorithm (YOA). The formula for the time series analysis algorithm (TSA) is as follows: X t =T t +S t +R t ； Where: X t The device status parameters collected at time t; T t The trend component represents the long-term trend of equipment status over time; S t The seasonal component represents a periodic pattern of change; R t For random error components, representing unpredictable random fluctuations; In the year-on-year and month-on-month analysis algorithm (YOA), the formula for calculating the year-on-year growth rate is as follows: ； The formula for calculating the month-on-month growth rate is: ； Where: YGR t MGR is the year-on-year growth rate at time t. t X represents the month-on-month growth rate at time t; t This refers to the device status data collected in the current cycle; X t-n This provides equipment status data for the same period last year at n-period intervals; X t-1 This is the device status data from the previous cycle; The machine learning algorithm is used to train a fault prediction model on historical fault data of the equipment. The machine learning algorithm includes a Support Vector Machine (SVM) model, a Random Forest (RF) model, and a Long Short-Term Memory (LSTM) network model. The decision function of the Support Vector Machine (SVM) model is: ； Where f(x) is the equipment fault prediction result, 1 represents fault and 0 represents normal; W is the weight vector of the feature space; is the nonlinear feature mapping function for the input data x; b is the bias term of the classification hyperplane; The random forest (RF) model consists of K decision trees. Composition, and the final prediction result is: ； In the formula: is the predicted value for the equipment fault type; C is the fault type category; I(·) is the indicator function, which takes the value 1 when the condition is true and 0 otherwise; Tk(x) is the prediction result of the k-th decision tree for the input data x; The cell state update equation of the Long Short-Term Memory (LSTM) network model is as follows: ； Among them, f t The output of the forget gate controls the cell state C. t-1 The degree of forgetting; i t The input gate outputs control new information. Write level; C t The current state of the cell; o t Output gate output, controls the hidden state h t The output of W; f W i W C W o b is the weight matrix for each gate; f ,b i ,b C ,b o These are the bias vectors for each gate; sigmoid is the activation function, and tanh is the hyperbolic tangent activation function; Represents element-wise multiplication; The intelligent inspection module's algorithm model includes a target detection algorithm and image classification functionality, used to process and annotate on-site image data to identify actual defects. The target detection algorithm's bounding box coordinates are represented as follows: ； In the formula: (b x ,b y (b) represents the coordinates of the detection box center. w ,b h ) represents the width and height of the detection frame; (c x ,c y (p) represents the coordinates of the top-left corner of the current grid; w ,p h ) represents the width and height of the prior bounding box; (t) x ,t y ,t w ,t h ) represents the offset and scaling factor predicted by the network; The sigmoid function is used to map coordinate offsets to the grid area; The data fusion module collects multi-source data including substation data, generator unit data, energy management system data, wind power prediction system data, fire alarm system data, and video surveillance data. It also employs a cross-modal data fusion algorithm to integrate numerical sensor data (D...). s With image-based inspection data D i Merge into a unified feature vector F: F=Concat(f s (D s ),f i (D i )); Where: f s (·) represents the sensor data feature extraction function; f i (·) is the image data feature extraction function; Concat(·) represents the feature vector concatenation operation.

2. The wind farm transmission equipment monitoring system according to claim 1, characterized in that: The data acquisition module includes high-precision sensors such as a temperature sensor, a vibration sensor, a voltage sensor, and a current sensor, which are used to acquire the temperature, vibration, voltage, and current parameters of the device, respectively.

3. The wind farm transmission equipment monitoring system according to claim 1, characterized in that: The fault early warning module includes a diagnostic model and an expert system. The diagnostic model is used to retrieve diagnostic information according to region, unit, and time range. The expert system provides fault early warning and maintenance suggestions based on expert knowledge and experience.

4. The wind farm transmission equipment monitoring system according to claim 1, characterized in that: The digital twin module enables intelligent monitoring, optimized operation, and predictive maintenance of wind turbines, while the digital twin of the substation achieves a one-to-one simulation of the real substation.

5. The wind farm transmission equipment monitoring system according to claim 1, characterized in that: The management decision module displays the status of the site camera equipment, alarm images, alarm data analysis, equipment operating status, fault warning information, and digital twin simulation results through visual charts.

6. A wind farm transmission equipment monitoring system according to any one of claims 1-5, characterized in that: It also includes a hardware integration module, which uses hardware integration technology to enable different types of computing nodes to work together, achieve data sharing and communication through high-speed networks and shared storage systems, and use load balancing and task scheduling technologies to achieve efficient utilization and management of computing resources.

Images