Energy efficiency grading and carbon emission evaluation method and device for wind turbine generator

Abstract

The invention relates to an energy efficiency grading and carbon emission evaluation method and device for a wind turbine generator. The method comprises the following steps: collecting fan operation parameters, weather forecast data, power grid operation state data and carbon transaction market data of a wind power plant as an initial data set; preprocessing data in the initial data set by adopting a validity verification and bad data correction method to obtain a target data set; a day-ahead scheduling optimization model considering carbon emission is constructed based on the carbon emission cost, and the carbon emission and the operation cost are reduced; constructing a hierarchical constraint system, and limiting the safety of the power grid in a multi-class constraint mode; and obtaining an optimal low-carbon scheduling scheme based on the real-time operation data of the power grid and the carbon emission constraint condition. According to the invention, by setting the multi-source heterogeneous data fusion acquisition system, the carbon emission cost-considered day-ahead scheduling optimization model, the hierarchical power grid security constraint system and the rolling optimization feedback mechanism, the wind power generation system achieves the effect of considering economical efficiency and low-carbon collaborative optimization.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and apparatus for evaluating the energy efficiency classification and carbon emissions of wind turbine generators. Background Technology

[0002] The energy efficiency rating of wind turbines usually relies on macroscopic performance indicators such as power generation efficiency, capacity factor and annual power generation. The higher the rating, the better the wind energy conversion efficiency and the lower the resource consumption per unit of power generation. In terms of carbon emissions, although wind turbines are almost zero-emission during operation, they still generate certain carbon emissions throughout their entire life cycle, including manufacturing, transportation, installation, maintenance and decommissioning.

[0003] However, currently, most existing technologies for assessing the energy efficiency of wind turbines rely on single, static, posterior statistical indicators such as "unit power generation," resulting in a significant lack of assessment dimensions. This assessment method cannot perceive the real-time impact of external environmental conditions such as wind speed fluctuations, wind direction changes, and air density, nor can it quantify the power generation efficiency losses caused by equipment degradation such as blade surface contamination, gearbox wear, and bearing aging. Furthermore, it fails to consider energy losses caused by wake effects between units within the wind farm. In terms of carbon emission assessment of wind turbines, existing assessment methods typically involve simply multiplying the grid-connected electricity by a fixed, regional-level grid average carbon emission factor. This calculation method ignores the real-time changes in the energy structure within the power system, leading to severely distorted carbon emission calculation results that cannot accurately reflect the true low-carbon contribution of wind turbines. Summary of the Invention

[0004] In view of the above-mentioned problems existing in the prior art, the purpose of the present invention is to provide a method and apparatus for evaluating the energy efficiency classification and carbon emissions of wind turbine units.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: A method for evaluating the energy efficiency classification and carbon emissions of wind turbine generators, comprising: S1: Collect data on the operating status, environmental characteristics, and equipment health of the wind power plant to obtain multi-dimensional raw data and construct the initial dataset; S2, the initial dataset is processed by removing noise, unifying the data format, and extracting key features to obtain the target dataset; S3 generates dynamic weight configuration parameters based on the target dataset, making energy efficiency and carbon emission assessments more aligned with actual operating conditions. Specifically, based on wind turbine model parameters, regional climate conditions, and terrain features, initial dynamic weight parameters are generated using digital elevation models and computational fluid dynamics simulations. The adaptive weighted fusion algorithm formula is as follows:

[0006] in, For environmental impact factors, For equipment wear factor, For wind resource factors, Topographical influencing factors , , , This is a correction factor; S4, based on dynamic weight parameters and real-time operating data, constructs an enhanced digital twin model of the wind turbine and introduces a transfer learning mechanism; S5 constructs a dynamic carbon emission calculation system based on the actual carbon emission intensity of wind turbine units during operation; S6, based on the power generation characteristics and carbon emission intensity of wind turbine units, performs energy efficiency classification and carbon emission assessment.

[0007] A further improvement of this invention is that, in S1, the operation status, environmental characteristics, and equipment health of the wind power plant are collected to obtain multi-dimensional raw data. The initial dataset is constructed by: deploying temperature sensors, vibration sensors, torque sensors, and meteorological monitoring equipment on the blades, gearbox, and generator of the wind turbine to collect real-time operating parameters such as rotational speed, power, temperature, humidity, and wind speed and direction. This data is combined with historical data from the monitoring and control and data acquisition system and LiDAR wind measurement data to construct an initial dataset that includes dimensions of equipment operation, environmental load, and health diagnosis.

[0008] A further improvement of this invention is that, in S2, the initial dataset is processed by removing noise, unifying the data format, and extracting key features to obtain the target dataset, which includes: Step S21: Use data cleaning and noise reduction methods to process outliers in the initial dataset; Specifically, based on the initial dataset collected, noise reduction is performed on sensor data and unstructured image data, and outliers and missing values ​​in sensor data are corrected and imputed; for image data, noise caused by lighting and interference factors is removed to improve data quality. Step S22: Use data alignment and standardization to unify the units and formats of data in the initial dataset; Because different sensors collect data at different frequencies and with different timestamps, time synchronization and data alignment techniques are used to unify various types of data to the same time scale. Linear interpolation is employed for time alignment. Assuming the original time series... Target time series Then the interpolated time series data The calculation formula is as follows:

[0009] in, For the i-th wind turbine at time point The target parameter value after interpolation calculation; For the i-th wind turbine at a known time point The corresponding actual measured values ​​of the target parameters, For the i-th wind turbine at a known time point The corresponding actual measured values ​​of the target parameters; The target time point for calculating the parameter value; and .

[0010] A further improvement of this invention lies in S3, where dynamic weight configuration parameters are generated based on the target dataset to make energy efficiency and carbon emission assessments more closely reflect actual operating conditions. This includes: generating initial dynamic weight parameters based on wind turbine model parameters, regional climate conditions, and terrain features, using a digital elevation model and computational fluid dynamics simulation. The adaptive weighted fusion algorithm formula is as follows:

[0011] in, For environmental impact factors, For equipment wear factor, For wind resource factors, Topographical influencing factors , , , This is a correction factor.

[0012] A further improvement of this invention is that, in S4, an enhanced digital twin model of the wind turbine is constructed based on dynamic weight parameters and real-time operating data, and a transfer learning mechanism is introduced, including: The enhanced digital twin model includes a whole-system model, a component-level model, and a fault physical-level model to analyze the state of the wind turbine. It introduces a transfer learning mechanism to transfer historical fault data to the current model. By constructing a transfer learning framework based on convolutional neural networks, the knowledge of historical fault data is transferred to the current operating conditions, thereby optimizing the prediction accuracy of potential fault modes and changes in power generation efficiency.

[0013] A further improvement of this invention is that, in S5, based on the actual carbon emission intensity of the wind turbine, a dynamic carbon emission calculation system is constructed, including: combining the real-time carbon emission characteristics of the power grid in the enhanced digital twin modeling, monitoring the dynamic changes of the power grid carbon emissions, quantifying the carbon emission intensity of the wind turbine during actual operation, establishing a dynamic carbon emission monitoring model with a time scale from minutes to hours, accurately capturing the carbon emission differences under different time periods and loads, and constructing a dynamic carbon emission calculation system so that the wind turbine can maintain energy efficiency while operating in a low-carbon manner. Construct a dynamic carbon emission intensity matrix that takes into account the impact of wind curtailment and dispatch response; Introducing wind curtailment loss coefficient The wind curtailment loss coefficient is used to quantify the impact of wind curtailment caused by grid dispatch constraints on carbon emission reduction potential. When wind curtailment occurs in the grid, wind turbines fail to fully utilize wind energy resources for power generation, thus affecting their carbon emission reduction effect. The carbon emission intensity matrix... The formula is as follows:

[0014] in, This represents the power generation during the i-th time period; Let be the grid carbon factor for the i-th time period; This refers to the actual wind speed. is the rated starting wind speed; k is the wind condition correction factor.

[0015] An evaluation device for energy efficiency classification and carbon emission assessment of wind turbine generators, comprising: The data acquisition unit collects data on the operating status, environmental characteristics, and equipment health of the wind power plant, obtaining multi-dimensional raw data to construct the initial dataset. The data processing unit processes the initial dataset by removing noise, unifying the data format, and extracting key features to obtain the target dataset. The dynamic weight configuration parameter generation unit generates dynamic weight configuration parameters based on the target dataset, making energy efficiency and carbon emission assessments more closely aligned with actual operating conditions. Specifically, based on wind turbine model parameters, regional climate conditions, and terrain features, initial dynamic weight parameters are generated using digital elevation models and computational fluid dynamics simulations. The adaptive weighted fusion algorithm formula is as follows:

[0016] in, For environmental impact factors, For equipment wear factor, For wind resource factors, Topographical influencing factors , , , This is a correction factor; The model building unit constructs an enhanced digital twin model of the wind turbine based on dynamic weight parameters and real-time operating data, and introduces a transfer learning mechanism. The system construction unit is based on the actual carbon emission intensity of wind turbine units to build a dynamic carbon emission calculation system; The grading and evaluation unit performs energy efficiency grading and carbon emission evaluation based on the power generation characteristics and carbon emission intensity of wind turbine units.

[0017] A further improvement of this invention is that the data acquisition unit collects the operating status, environmental characteristics, and equipment health of the wind power plant, obtains multi-dimensional raw data, and constructs an initial dataset by: deploying temperature sensors, vibration sensors, torque sensors, and meteorological monitoring equipment on the blades, gearbox, and generator of the wind turbine to collect operating parameters such as rotational speed, power, temperature, humidity, and wind speed and direction in real time; and combining historical data from the monitoring and control and data acquisition system with lidar wind measurement data to construct an initial dataset that includes dimensions of equipment operation, environmental load, and health diagnosis.

[0018] A network-side server includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the energy efficiency classification and carbon emission evaluation method for the wind turbine.

[0019] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for evaluating the energy efficiency classification and carbon emissions of the wind turbine generator.

[0020] Compared with the prior art, the present invention has at least the following beneficial technical effects: This invention provides a method and apparatus for evaluating the energy efficiency and carbon emissions of wind turbine generators. It collects wind turbine operating parameters, weather forecast data, power grid operating status data, and carbon trading market data as initial datasets. The initial datasets are preprocessed using validity verification and bad data correction methods to obtain target datasets. A day-ahead scheduling optimization model considering carbon emission costs is constructed to reduce carbon emissions and operating costs. A hierarchical constraint system is built, employing multiple types of constraints to limit power grid security. Based on real-time power grid operating data and carbon emission constraints, the optimal low-carbon scheduling scheme is obtained. By setting up a multi-source heterogeneous data fusion acquisition system, a day-ahead scheduling optimization model considering carbon emission costs, a hierarchical power grid security constraint system, and a rolling optimization feedback mechanism, the method achieves a synergistic optimization effect that balances economic efficiency and low-carbon performance in the wind power generation system. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a method for evaluating the energy efficiency and carbon emissions of wind turbine generators according to the present invention.

[0023] Figure 2 This is a schematic diagram of the network-side server provided by the present invention.

[0024] Figure 3 This is a structural block diagram of an evaluation device for energy efficiency classification and carbon emissions of wind turbine generators according to the present invention. Detailed Implementation

[0025] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0026] In the description of this invention, it should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0027] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0028] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0029] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0030] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0031] Example 1 This invention provides a method for evaluating the energy efficiency and carbon emissions of wind turbine generators. It collects data on the operating status, environmental characteristics, and equipment health of wind farms to obtain multi-dimensional raw data and construct an initial dataset. The initial dataset is then processed by removing noise, standardizing the data format, and extracting key features to obtain a target dataset. Dynamic weight configuration parameters are generated based on the target dataset to make the energy efficiency and carbon emission evaluation more closely reflect actual operating conditions. An enhanced digital twin model of the wind turbine generator is constructed based on the dynamic weight parameters and real-time operating data, and a transfer learning mechanism is introduced. A dynamic carbon emission calculation system is built based on the actual carbon emission intensity of the wind turbine generator. Based on the power generation characteristics and carbon emission intensity of the wind turbine generator, energy efficiency is classified and carbon emission is evaluated. This method achieves the effect of scientifically classifying the energy efficiency level of wind turbine generators and accurately evaluating their carbon emission performance.

[0032] The following is a detailed description of the implementation details of the energy efficiency classification and carbon emission evaluation method for wind turbine generators according to the present invention. The following content is only for ease of understanding and is not necessary for implementing this solution. See Figure 1 S1 collects the operating status, environmental characteristics, and equipment health of the wind power plant to obtain multi-dimensional raw data and construct the initial dataset.

[0033] Specifically, by deploying temperature sensors, vibration sensors, torque sensors, and meteorological monitoring equipment on the blades, gearboxes, and generators of wind turbines, operating parameters such as speed, power, temperature, humidity, wind speed, and wind direction are collected in real time. Combined with historical data from the monitoring and control and data acquisition system and LiDAR wind measurement data, an initial dataset is constructed that includes dimensions such as equipment operation, environmental load, and health diagnosis, providing reliable data support.

[0034] Acoustic monitoring: Acoustic sensors are used to collect data on the contamination status of the blade surface. By analyzing the changes in acoustic characteristics caused by the adhesion of oil and dust, the condition of the blade surface can be understood. Vibration monitoring: Vibration sensors are used to collect vibration spectrum data of transmission components such as gearboxes and spindles. By analyzing the spectrum, the health status of the equipment can be accurately characterized, and potential faults can be detected in a timely manner. Wind field perception: Using lidar to scan wind field flow data in real time, the spatiotemporal distribution characteristics of wind speed, wind direction, turbulence intensity, etc. are obtained, providing environmental data support for the operation optimization of wind turbine units. Edge computing processing: Real-time processing of unit operation data through edge computing nodes, dynamically generating performance degradation indicators such as power generation efficiency decay rate and component aging coefficient, to initially explore the value of data and enrich the content of the initial dataset.

[0035] Visual inspection: The drone's camera acquires image data of damage such as blade cracks and coating peeling, and obtains wind turbine status information from different angles to improve the initial dataset.

[0036] S2, the initial dataset is processed by removing noise, unifying the data format, and extracting key features to obtain the target dataset; Step S21: Use data cleaning and noise reduction methods to process outliers in the initial dataset.

[0037] Specifically, based on the initial dataset collected, noise reduction is performed on sensor data and unstructured image data. Outliers and missing values ​​in the sensor data are corrected and imputed. For image data, noise caused by factors such as lighting and interference is removed to improve data quality.

[0038] Sensor data noise reduction: Outliers are identified using the 3σ principle. The mean and standard deviation of the sensor data in the initial dataset are calculated. The formula for calculating the mean is as follows:

[0039] in, To represent the sample mean; n is the sample size; Let i be the i-th observation in the sensor dataset; The formula for standard deviation is as follows:

[0040] in, n is the standard deviation; n is the sample size. Let i be the i-th observation in the sensor dataset; To represent the sample mean; like Then determine For outliers, use the mean of neighboring points. Replace it.

[0041] Image data denoising: Median filtering algorithm, for each pixel in the image, sorts the pixel values ​​in its neighborhood, takes the median as the new value of the pixel, and removes noise caused by factors such as lighting and interference.

[0042] Step S22: Use data alignment and standardization to unify the dimensions and format of the data in the initial dataset.

[0043] Because different sensors collect data at different frequencies and with different timestamps, time synchronization and data alignment techniques are used to unify various types of data to the same time scale. Linear interpolation is employed for time alignment. Assuming the original time series... Target time series Then the interpolated time series data The calculation formula is as follows:

[0044] in, For the i-th wind turbine at time point The target parameter value after interpolation calculation; For the i-th wind turbine at a known time point The corresponding actual measured values ​​of the target parameters, For the i-th wind turbine at a known time point The corresponding actual measured values ​​of the target parameters; The target time point for calculating the parameter value; and ; Data standardization involves unifying the units and formats of the data to ensure consistency and comparability. The standardization formula is as follows:

[0045] in, Let j be the feature value of the i-th sample. The mean of the j-th feature, Let be the standard deviation of the j-th feature.

[0046] Outliers were removed by data cleaning and denoising, and the units and formats of the data in the initial dataset were unified by data alignment and standardization. Key features that reflect the operating status and health of the wind turbine were extracted from the denoised sensor data. Computer vision technology was used on the image data to extract features such as the shape, location and degree of blade damage, and the target dataset was obtained.

[0047] S3 generates dynamic weight configuration parameters based on the target dataset, making energy efficiency and carbon emission assessments more consistent with actual operating conditions; Specifically, based on wind turbine model parameters, regional climate conditions, and terrain features, initial dynamic weight parameters are generated using digital elevation models and computational fluid dynamics simulations. The adaptive weighted fusion algorithm formula is as follows:

[0048] in, For environmental impact factors, For equipment wear factor, For wind resource factors, Topographical influencing factors , , , This is a correction factor.

[0049] By dynamically integrating key factors such as environment, equipment, wind resources, and terrain, a weighting system that better reflects actual operating conditions is established. The weighting parameter W can accurately reflect the energy efficiency and carbon emission status of wind turbines under different conditions.

[0050] S4, based on dynamic weight parameters and real-time operating data, constructs an enhanced digital twin model of the wind turbine and introduces a transfer learning mechanism; Specifically, the enhanced digital twin model includes a whole-system level model, a component level model, and a fault physical level model to analyze the state of the wind turbine. It introduces a transfer learning mechanism to transfer historical fault data to the current model. By constructing a transfer learning framework based on convolutional neural networks, the knowledge of historical fault data is transferred to the current operating conditions, thereby optimizing the prediction accuracy of potential fault modes and changes in power generation efficiency.

[0051] System-level model: Based on the principles of aerodynamics, structural mechanics and electromechanical energy conversion, the physical equations for the operation of the wind turbine are constructed to simulate the wind turbine capture, transmission chain torque transmission and generator power output process, and integrate real-time environmental data such as wind speed, wind direction and turbulence intensity to dynamically generate power curves and energy consumption distribution; Component-level models: For key components such as blades, gearboxes, generators, and yaw systems, degradation models based on physical characteristics are established, such as gearbox health status assessment models based on vibration signal analysis and blade surface contamination accumulation models based on acoustic wave characteristics, and status parameters are continuously updated through real-time sensor data. Physical-level fault models: Combining Failure Mode and Effects Analysis (FMEA) and historical fault databases, physical models of fault evolution are constructed, such as crack propagation models and bearing wear life models, to simulate the development path of potential faults and their impact on power generation efficiency.

[0052] In the transfer learning process, an adversarial transfer network method is adopted to achieve effective knowledge transfer by minimizing the difference in feature distribution between historical fault data (source domain) and current operating conditions (target domain). The transfer formula is as follows:

[0053] in, The task loss function in the target domain; For adversarial loss function; This is historical fault data. This is the current operating condition data; and These are the parameters for the feature extractor and the classifier, respectively. This is a balancing parameter used to adjust the weights of task loss and adversarial loss.

[0054] By introducing a transfer learning mechanism, the enhanced digital twin model of the wind turbine can output real-time simulation results, which can be used to formulate energy efficiency optimization strategies and fault early warning for the wind turbine, reduce the low operation and maintenance costs of the wind turbine, improve the operating efficiency of the wind turbine, and reduce energy loss and additional carbon emissions caused by failure downtime.

[0055] S5 constructs a dynamic carbon emission calculation system based on the actual carbon emission intensity of wind turbine units during operation.

[0056] Specifically, by combining the real-time carbon emission characteristics of the power grid in the enhanced digital twin modeling, the dynamic changes of the power grid's carbon emissions are monitored, the carbon emission intensity of wind turbines during actual operation is quantified, a dynamic carbon emission monitoring model with a time scale from minutes to hours is established, the carbon emission differences under different time periods and loads are accurately captured, and a dynamic carbon emission calculation system is constructed to enable wind turbines to maintain energy efficiency while operating in a low-carbon manner.

[0057] Step S51: Use a spatiotemporal attention matching algorithm to align the actual emission point feature curve with the carbon emission factor.

[0058] Specifically, an attention matching mechanism is constructed to perform weighted processing of power generation data using matrix operations. Let the power generation data matrix be... The power generation sequence over n time intervals, and the power grid carbon emission factor matrix. The formula for calculating the attention weight matrix A, corresponding to the carbon emission intensity for each time period, is as follows:

[0059] in, and To provide evidence for trainable weights, Scaling factor The function is used to normalize the weights to the probability distribution interval.

[0060] By calculating the attention weight matrix A, periods with high carbon emission intensity are given higher attention weights, resulting in the final weighted power generation data. The formula is as follows:

[0061] in, This is the attention weight vector; This is the original power generation data vector; By assigning corresponding weights to power generation data for each time period based on carbon emission intensity, the impact of power generation on overall carbon intensity during that time period is highlighted, achieving a match between power generation data and carbon emission factors in both time and space dimensions, and quantifying the differences in environmental impact across different time periods.

[0062] Step S52: Construct a dynamic carbon emission intensity matrix that takes into account the impact of wind curtailment and dispatch response.

[0063] Specifically, the wind curtailment loss coefficient is introduced. The wind curtailment loss coefficient is used to quantify the impact of wind curtailment caused by grid dispatch constraints on carbon emission reduction potential. When wind curtailment occurs in the grid, wind turbines fail to fully utilize wind energy resources for power generation, thus affecting their carbon emission reduction effect. The carbon emission intensity matrix... The formula is as follows:

[0064] in, This represents the power generation during the i-th time period; Let be the grid carbon factor for the i-th time period; This refers to the actual wind speed. Rated starting wind speed; k is the wind condition correction factor; The dynamic carbon emission intensity matrix reflects the real carbon emission intensity of wind turbines under complex grid dispatch and variable wind conditions, and quantifies the loss of carbon emission reduction targets due to wind curtailment.

[0065] S6, based on the power generation characteristics and carbon emission intensity of wind turbine units, performs energy efficiency classification and carbon emission assessment.

[0066] Specifically, based on the dynamic power generation characteristics of wind turbine units and the precisely quantified carbon emission intensity data, a multi-objective decision optimization method is adopted to conduct comprehensive energy efficiency classification and carbon efficiency evaluation. The dynamic power generation characteristic data in S3 and the precisely quantified carbon emission intensity data in S4 reflect the carbon emission level of the unit per kilowatt-hour. The wind turbine units are divided into energy efficiency levels such as Level 1 (high efficiency and low carbon), Level 2 (stable compliance), and Level 3 (requires optimization and improvement). The energy efficiency level evaluation results are generated from multiple dimensions such as power generation efficiency, operational stability, carbon emission intensity, and environmental adaptability.

[0067] This process involves collecting data on the operational status, environmental characteristics, and equipment health of wind farms to obtain multi-dimensional raw data and constructing an initial dataset. The initial dataset is then processed by removing noise, standardizing data formats, and extracting key features to obtain a target dataset. Dynamic weight configuration parameters are generated based on the target dataset to make energy efficiency and carbon emission assessments more closely reflect actual operating conditions. An enhanced digital twin model of the wind turbine is constructed based on the dynamic weight parameters and real-time operating data, and a transfer learning mechanism is introduced. A dynamic carbon emission calculation system is built based on the actual carbon emission intensity of the wind turbine. Energy efficiency grading and carbon emission assessment are performed based on the power generation characteristics and carbon emission intensity of the wind turbine. By integrating multi-source IoT sensor data, dynamic perception and comprehensive evaluation of multi-dimensional factors such as equipment health status, environmental conditions, blade contamination, and wake effects are achieved, improving the accuracy and realism of energy efficiency assessment. An enhanced digital twin model is constructed to predict potential faults and future power generation performance, providing a basis for decision-making. This process achieves the goal of scientifically grading the energy efficiency level of wind turbines and accurately evaluating carbon emission performance.

[0068] Example 2 like Figure 3 As shown, the present invention provides an evaluation device for energy efficiency classification and carbon emissions of wind turbine generators, comprising: The data acquisition unit collects data on the operating status, environmental characteristics, and equipment health of the wind power plant, obtaining multi-dimensional raw data to construct the initial dataset. The data processing unit processes the initial dataset by removing noise, unifying the data format, and extracting key features to obtain the target dataset. The dynamic weight configuration parameter generation unit generates dynamic weight configuration parameters based on the target dataset, making energy efficiency and carbon emission assessments more closely aligned with actual operating conditions. Specifically, based on wind turbine model parameters, regional climate conditions, and terrain features, initial dynamic weight parameters are generated using digital elevation models and computational fluid dynamics simulations. The adaptive weighted fusion algorithm formula is as follows:

[0069] in, For environmental impact factors, For equipment wear factor, For wind resource factors, Topographical influencing factors , , , This is a correction factor; The model building unit constructs an enhanced digital twin model of the wind turbine based on dynamic weight parameters and real-time operating data, and introduces a transfer learning mechanism. The system construction unit is based on the actual carbon emission intensity of wind turbine units to build a dynamic carbon emission calculation system; The grading and evaluation unit performs energy efficiency grading and carbon emission evaluation based on the power generation characteristics and carbon emission intensity of wind turbine units.

[0070] In the data acquisition unit of this embodiment, the operating status, environmental characteristics and equipment health of the wind power plant are collected to obtain multi-dimensional raw data. The initial dataset is constructed by deploying temperature sensors, vibration sensors, torque sensors and meteorological monitoring equipment on the blades, gearbox and generator of the wind turbine to collect operating parameters such as speed, power, temperature, humidity and wind speed and direction in real time. The initial dataset is constructed by combining historical data from the monitoring and control and data acquisition system with lidar wind measurement data, which includes dimensions of equipment operation, environmental load and health diagnosis.

[0071] Example 3 like Figure 2 As shown, the present invention provides a network-side server including at least one processor 302; and a memory 301 communicatively connected to at least one processor 302; wherein the memory 301 stores instructions that can be executed by at least one processor 302, and the instructions are executed by at least one processor 302 to enable at least one processor 302 to perform the steps of the above-described data processing method.

[0072] The memory 301 and processor 302 are connected via a bus, which may include any number of interconnecting buses and bridges. The bus connects various circuits of one or more processors 302 and memory 301 together. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by processor 302 is transmitted over a wireless medium via an antenna, which further receives data and transmits it to processor 302.

[0073] Processor 302 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory 301 can be used to store data used by processor 302 during operation.

[0074] Example 4 This invention provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the steps of the energy efficiency classification and carbon emission evaluation method for wind turbine generators in the first embodiment.

[0075] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] This application is described with reference to flowchart illustrations and / or block diagrams of methods, systems, and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0077] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0078] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0079] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the scope of the invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0080] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.

Claims

1. A method for evaluating the energy efficiency classification and carbon emissions of wind turbine generators, characterized in that, include: S1: Collect data on the operating status, environmental characteristics, and equipment health of the wind power plant to obtain multi-dimensional raw data and construct the initial dataset; S2, the initial dataset is processed by removing noise, unifying the data format, and extracting key features to obtain the target dataset; S3 generates dynamic weight configuration parameters based on the target dataset, making energy efficiency and carbon emission assessments more closely aligned with actual operating conditions. Specifically, based on wind turbine model parameters, regional climate conditions, and terrain features, initial dynamic weight parameters are generated using digital elevation models and computational fluid dynamics simulations. The adaptive weighted fusion algorithm formula is as follows: in, For environmental impact factors, For equipment wear factor, For wind resource factors, Topographical influencing factors , , , This is a correction factor; S4, based on dynamic weight parameters and real-time operating data, constructs an enhanced digital twin model of the wind turbine and introduces a transfer learning mechanism; S5 constructs a dynamic carbon emission calculation system based on the actual carbon emission intensity of wind turbine units during operation; S6, based on the power generation characteristics and carbon emission intensity of wind turbine units, performs energy efficiency classification and carbon emission assessment.

2. The method for evaluating the energy efficiency and carbon emissions of wind turbine generators according to claim 1, characterized in that, In S1, the operating status, environmental characteristics, and equipment health of the wind power plant are collected to obtain multi-dimensional raw data. The initial dataset is constructed by deploying temperature sensors, vibration sensors, torque sensors, and meteorological monitoring equipment on the blades, gearboxes, and generators of the wind turbine to collect real-time operating parameters such as speed, power, temperature, humidity, and wind speed and direction. Combined with historical data from the monitoring, control, and data acquisition system and lidar wind measurement data, an initial dataset containing dimensions of equipment operation, environmental load, and health diagnosis is constructed.

3. The method for evaluating the energy efficiency and carbon emissions of wind turbine generators according to claim 2, characterized in that, In S2, the initial dataset is processed by removing noise, standardizing the data format, and extracting key features to obtain the target dataset, which includes: Step S21: Use data cleaning and noise reduction methods to process outliers in the initial dataset; Specifically, based on the initial dataset collected, noise reduction is performed on sensor data and unstructured image data, and outliers and missing values ​​in sensor data are corrected and imputed; for image data, noise caused by lighting and interference factors is removed to improve data quality. Step S22: Use data alignment and standardization to unify the units and formats of data in the initial dataset; Because different sensors collect data at different frequencies and with different timestamps, time synchronization and data alignment techniques are used to unify various types of data to the same time scale. Linear interpolation is employed for time alignment. Assuming the original time series... Target time series Then the interpolated time series data The calculation formula is as follows: in, For the i-th wind turbine at time point The target parameter value after interpolation calculation; For the i-th wind turbine at a known time point The corresponding actual measured values ​​of the target parameters, For the i-th wind turbine at a known time point The corresponding actual measured values ​​of the target parameters; The target time point for calculating the parameter value; and .

4. The method for evaluating the energy efficiency and carbon emissions of wind turbine generators according to claim 1, characterized in that, In S3, dynamic weight configuration parameters are generated based on the target dataset to make energy efficiency and carbon emission assessments more closely reflect actual operating conditions. This includes: generating initial dynamic weight parameters based on wind turbine model parameters, regional climate conditions, and terrain features, using digital elevation models and computational fluid dynamics simulations. The adaptive weighted fusion algorithm formula is as follows: in, For environmental impact factors, For equipment wear factor, For wind resource factors, Topographical influencing factors , , , This is a correction factor.

5. The method for evaluating the energy efficiency and carbon emissions of wind turbine generators according to claim 1, characterized in that, In S4, an enhanced digital twin model of the wind turbine is constructed based on dynamic weight parameters and real-time operating data, and a transfer learning mechanism is introduced, including: The enhanced digital twin model includes a whole-system model, a component-level model, and a fault physical-level model to analyze the state of the wind turbine. It introduces a transfer learning mechanism to transfer historical fault data to the current model. By constructing a transfer learning framework based on convolutional neural networks, the knowledge of historical fault data is transferred to the current operating conditions, thereby optimizing the prediction accuracy of potential fault modes and changes in power generation efficiency.

6. The method for evaluating the energy efficiency and carbon emissions of wind turbine generators according to claim 1, characterized in that, In S5, based on the actual carbon emission intensity of wind turbines, a dynamic carbon emission calculation system is constructed, including: combining the real-time carbon emission characteristics of the power grid in the enhanced digital twin modeling, monitoring the dynamic changes of the power grid's carbon emissions, quantifying the carbon emission intensity of wind turbines during actual operation, establishing a dynamic carbon emission monitoring model with a time scale from minutes to hours, accurately capturing the differences in carbon emissions under different time periods and loads, and constructing a dynamic carbon emission calculation system to enable wind turbines to maintain energy efficiency while operating in a low-carbon manner. Construct a dynamic carbon emission intensity matrix that takes into account the impact of wind curtailment and dispatch response; Introducing wind curtailment loss coefficient The wind curtailment loss coefficient is used to quantify the impact of wind curtailment caused by grid dispatch constraints on carbon emission reduction potential. When wind curtailment occurs in the grid, wind turbines fail to fully utilize wind energy resources for power generation, thus affecting their carbon emission reduction effect. The carbon emission intensity matrix... The formula is as follows: in, This represents the power generation during the i-th time period; Let be the grid carbon factor for the i-th time period; This refers to the actual wind speed. is the rated starting wind speed; k is the wind condition correction factor.

7. A device for evaluating the energy efficiency and carbon emissions of wind turbine generators, characterized in that, include: The data acquisition unit collects data on the operating status, environmental characteristics, and equipment health of the wind power plant, obtaining multi-dimensional raw data to construct the initial dataset. The data processing unit processes the initial dataset by removing noise, unifying the data format, and extracting key features to obtain the target dataset. The dynamic weight configuration parameter generation unit generates dynamic weight configuration parameters based on the target dataset, making energy efficiency and carbon emission assessments more closely aligned with actual operating conditions. Specifically, based on wind turbine model parameters, regional climate conditions, and terrain features, initial dynamic weight parameters are generated using digital elevation models and computational fluid dynamics simulations. The adaptive weighted fusion algorithm formula is as follows: in, For environmental impact factors, For equipment wear factor, For wind resource factors, Topographical influencing factors , , , This is a correction factor; The model building unit constructs an enhanced digital twin model of the wind turbine based on dynamic weight parameters and real-time operating data, and introduces a transfer learning mechanism. The system construction unit is based on the actual carbon emission intensity of wind turbine units to build a dynamic carbon emission calculation system; The grading and evaluation unit performs energy efficiency grading and carbon emission evaluation based on the power generation characteristics and carbon emission intensity of wind turbine units.

8. The device for evaluating the energy efficiency and carbon emissions of wind turbine generators according to claim 7, characterized in that, The data acquisition unit collects the operating status, environmental characteristics, and equipment health of the wind power plant, obtains multi-dimensional raw data, and constructs an initial dataset. This includes: deploying temperature sensors, vibration sensors, torque sensors, and meteorological monitoring equipment on the blades, gearboxes, and generators of the wind turbine to collect real-time operating parameters such as speed, power, temperature, humidity, and wind speed and direction; and combining historical data from the monitoring, control, and data acquisition system with lidar wind measurement data to construct an initial dataset that includes dimensions of equipment operation, environmental load, and health diagnosis.

9. A network-side server, characterized in that, include: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the method for evaluating the energy efficiency classification and carbon emissions of wind turbines as described in any one of claims 1 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for evaluating the energy efficiency classification and carbon emissions of wind turbine generators as described in any one of claims 1 to 6.

Images