Dynamic verification and correction method for new energy data analysis model

Abstract

The invention provides a dynamic verification and correction method for a new energy data analysis model, and the method comprises the steps: carrying out the standardization processing based on the obtained real-time operation data of a fan, and obtaining standard data; utilizing a machine learning algorithm to dynamically correct a traditional fan power curve based on the standard data; performing fan efficiency evaluation based on the modified fan power curve; identifying potential faults through a fan fault diagnosis and early warning mechanism based on the acquired fan state data, and making a control strategy and early warning information for processing the potential faults; and optimizing the control strategy based on the fan state data and the historical data by using a reinforcement learning algorithm, and adjusting control parameters of the fan. According to the method, intelligent management of the wind power plant is realized, the power generation efficiency of the fan is remarkably improved, and the fault occurrence rate is effectively reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of new energy, and in particular to a dynamic verification and correction method of a new energy data analysis model. Background Art

[0002] With the global emphasis on renewable energy, wind power generation has been widely used as a green and environmentally friendly energy form. Wind power generation systems usually consist of wind turbines and control systems. The core task of wind turbines is to convert wind energy into electrical energy. The operating status, power generation efficiency and fault conditions of wind turbines are closely related to multiple factors such as wind speed, temperature, humidity, and current. In order to achieve efficient and stable wind power generation, real-time monitoring and efficiency evaluation of wind turbine operation are essential. Accurate power curve correction, fault diagnosis and early warning, and dynamic optimization of control strategies are key technologies to ensure that wind turbines can operate under different working conditions.

[0003] At present, the management and optimization of wind power generation systems mainly rely on power curves based on static models, which are usually set under fixed environmental conditions. However, this method cannot effectively cope with the impact of real-time changes in wind speed, temperature, etc. Traditional wind turbine power curves are usually preset based on historical data and do not take into account the performance fluctuations and operating conditions of actual wind turbines. In addition, wind turbine fault diagnosis mainly relies on manual inspections and experience judgments, and fails to make full use of real-time data for intelligent early warning and fault identification. Although the wind turbine fault diagnosis and early warning systems in the existing technology can monitor the status of wind turbines to a certain extent, most systems cannot locate the cause of the fault in a timely and accurate manner, and lack the real-time optimization function of the wind turbine control strategy. Summary of the invention

[0004] In order to solve the problem that the prior art cannot correct the wind turbine power curve according to the real-time operating conditions during the wind turbine efficiency evaluation process, and then perform fault analysis and control strategy optimization, resulting in low power generation efficiency and poor operation reliability of the wind farm, the present invention provides a dynamic verification and correction method for a new energy data analysis model.

[0005] To achieve the above object, the present invention provides the following technical solutions: The present invention proposes a dynamic verification and correction method for a new energy data analysis model, comprising the following steps: Standardized processing is performed based on the acquired real-time operation data of the fan to obtain standard data; Using a machine learning algorithm, dynamically correcting a conventional wind turbine power curve based on the standard data; Evaluate wind turbine efficiency based on the modified wind turbine power curve; Based on the acquired fan status data, potential faults are identified through a fan fault diagnosis and early warning mechanism, and a control strategy and early warning information for handling the potential faults are formulated; The control strategy is optimized based on the fan status data and historical data using a reinforcement learning algorithm to adjust the control parameters of the fan.

[0006] Preferably, the real-time operation data of the wind farm includes wind speed, temperature, voltage, current and power output.

[0007] Preferably, the standardized processing of the real-time operation data includes: Performing denoising processing on the real-time operation data to obtain real-time operation denoised data; Performing interpolation processing on the real-time denoised data to obtain real-time interpolated data; Perform missing value repair processing on the real-time interpolation data, the standard data.

[0008] Preferably, the dynamically correcting the traditional wind turbine power curve based on the standard data using a machine learning algorithm includes: Taking the standard data as input, a power curve correction model is constructed using a machine learning algorithm; The traditional wind turbine power curve is input into the power curve correction model for dynamic correction.

[0009] Preferably, the power curve correction model is:

[0010] in, Indicates wind speed and time The corrected fan power output is It is a power correction function generated based on a machine learning algorithm.

[0011] Preferably, the identifying potential faults through a fan fault diagnosis and early warning mechanism based on the acquired fan status data includes: Get status data of the fan; The state data is predicted through a fan fault diagnosis and early warning mechanism to obtain a fault risk value; identifying the potential fault based on the fault risk value; Wherein, the state data includes temperature, rotation speed, and current; The process of predicting the state data through the fan fault diagnosis and early warning mechanism to obtain the fault risk value is as follows:

[0012] in, Indicates at time The failure risk value under is the weight coefficient of status data in risk assessment, is the state data at time The value at time.

[0013] Preferably, the process of optimizing the control strategy based on the wind turbine status data and historical data by using a reinforcement learning algorithm is:

[0014] in, Indicates in status Next action The Q value, is the learning rate, It’s an instant reward. is the discount factor, The next state The maximum Q value under .

[0015] The present invention also proposes a dynamic verification and correction system for a new energy data analysis model, which is used to implement the above-mentioned dynamic verification and correction method for a new energy data analysis model, including: The data acquisition module is configured as follows: Used to obtain real-time operation data and status data of the fan; The standard processing module is configured as follows: Used to standardize the real-time operation data of the fan to obtain standard data; The correction module is configured as follows: For dynamically correcting the power curve of a conventional wind turbine based on the standard data using a machine learning algorithm; The performance evaluation module is configured as follows: Used for wind turbine efficiency evaluation based on modified wind turbine power curve; The data processing module is configured as follows: Used to identify potential faults through a fan fault diagnosis and early warning mechanism based on the acquired fan status data, and formulate a control strategy and early warning information for handling the potential faults; The optimization module is configured as follows: The control strategy is optimized based on the fan status data and historical data using a reinforcement learning algorithm to adjust the control parameters of the fan.

[0016] The present invention also proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable in the processor, wherein the processor implements the steps of the above-mentioned method for dynamic verification and correction of a new energy data analysis model when executing the computer program.

[0017] The present invention also proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the above-mentioned method for dynamic verification and correction of a new energy data analysis model.

[0018] Compared with the prior art, the present invention has the following beneficial technical effects: The present invention proposes a dynamic verification and correction method for a new energy data analysis model. This method can eliminate dimensional differences and outlier interference between different data sources by acquiring real-time operating data of the wind turbine and performing standardized processing, thereby facilitating the effective use of machine learning algorithms, improving the efficiency of data analysis, and ensuring the reliability and accuracy of the analysis results.

[0019] Furthermore, this method uses a machine learning algorithm to dynamically correct the traditional wind turbine power curve, and corrects the wind turbine power curve in real time, so that the corrected power curve can reflect the changes in the wind turbine operating state in real time, thereby more accurately evaluating the wind turbine performance, making the wind turbine performance evaluation closer to reality, and helping to promptly discover and solve the problem of performance degradation.

[0020] Furthermore, this method can quickly identify potential faults by combining real-time monitoring of fan status data with fan fault diagnosis and early warning mechanisms, and formulate corresponding control strategies and early warning information, which helps to reduce the risk of failures. It can also take preventive measures before failures occur, reduce fan downtime and maintenance costs, and extend the service life of the fan.

[0021] Furthermore, the reinforcement learning algorithm of this method can automatically adjust the control parameters according to the status data and historical data of the wind turbine through continuous trial and error and learning to achieve the best control effect, so that the wind turbine can maintain the best operating state when facing different operating environments and conditions, further improving the efficiency and stability of the wind turbine, and dynamically adapting to the actual working conditions of the wind turbine, accurately evaluating the power generation capacity of the wind turbine, and optimizing the control strategy to maximize the power generation efficiency. At the same time, the system can perform intelligent diagnosis and early warning of wind turbine faults based on real-time data, identify potential faults in advance, and provide decision support. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of a dynamic verification and correction method for a new energy data analysis model proposed by the present invention; Figure 2A connection block diagram of a dynamic verification and correction system for a new energy data analysis model proposed by the present invention; DETAILED DESCRIPTION In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0023] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0024] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or a communication; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0026] With the global emphasis on renewable energy, wind power generation has been widely used as a green and environmentally friendly energy form. Wind power generation systems usually consist of wind turbines and control systems. The core task of wind turbines is to convert wind energy into electrical energy. The operating status, power generation efficiency and fault conditions of wind turbines are closely related to multiple factors such as wind speed, temperature, humidity, and current. In order to achieve efficient and stable wind power generation, real-time monitoring and efficiency evaluation of wind turbine operation are essential. Accurate power curve correction, fault diagnosis and early warning, and dynamic optimization of control strategies are key technologies to ensure that wind turbines can operate under different working conditions.

[0027] At present, the management and optimization of wind power generation systems mainly rely on power curves based on static models, which are usually set under fixed environmental conditions. However, this method cannot effectively cope with the impact of real-time changes in wind speed, temperature, etc. The traditional wind turbine power curve is usually preset based on historical data, and does not take into account the performance fluctuations and operating conditions of the actual wind turbine. In addition, wind turbine fault diagnosis mainly relies on manual inspections and experience judgments, and fails to make full use of real-time data for intelligent early warning and fault identification. Although the wind turbine fault diagnosis and early warning system in the prior art can monitor the status of the wind turbine to a certain extent, most systems cannot locate the cause of the fault in a timely and accurate manner, and lack the real-time optimization function of the wind turbine control strategy. Therefore, the prior art has certain limitations in wind turbine efficiency evaluation, fault early warning and control strategy optimization, and is difficult to adapt to complex and changing environmental conditions. In order to solve these problems, a new method is urgently needed that can correct the wind turbine power curve according to the real-time operating conditions, and on this basis, perform fault analysis and control strategy optimization, so as to improve the power generation efficiency and operation reliability of the wind farm.

[0028] In order to solve the above-mentioned technical defects, the inventors of the present invention provide a dynamic verification and correction method for a new energy data analysis model, which aims to correct the wind turbine power curve based on real-time data, and dynamically adjust the operating parameters and control strategies of the wind turbine through intelligent analysis and optimization, thereby improving the power generation efficiency of the wind farm.

[0029] In the first aspect, the present invention proposes a dynamic verification and correction method for a new energy data analysis model, such as Figure 1 As shown, the following steps are included: S101. Performing standardization processing on the acquired real-time operation data of the wind turbine to obtain standard data; specifically, obtaining the real-time operation data of the wind turbine, such as wind speed, temperature, voltage, current and power output, through the SCADA system, sensors and historical databases, these data are stored in a relational database and a time series database respectively, calling the data such as wind speed, temperature, voltage, current and power output from the relational database and the time series database, performing denoising processing on these data to obtain real-time denoised operation data, performing interpolation processing on the real-time denoised operation data to obtain real-time interpolated operation data, performing missing value repair processing on the real-time interpolated operation data to obtain standard data, the standard data includes wind speed standard data, temperature standard data, voltage standard data, current standard data and power output standard data; performing denoising processing, interpolation processing and missing value repair processing to ensure the integrity and accuracy of the data, and provide accurate data support for subsequent power curve correction and wind turbine fault diagnosis.

[0030] S102, using a machine learning algorithm to dynamically correct a traditional wind turbine power curve based on the standard data; Specifically, taking standard data as input, that is, taking wind speed standard data, temperature standard data, voltage standard data, current standard data and power output standard data as data input respectively, a power curve correction model is constructed using machine learning algorithms (such as support vector machine, random forest, etc.); the traditional wind turbine power curve is input into the power curve correction model for dynamic correction. The corrected power curve can more accurately reflect the actual power generation capacity of the wind turbine under different working conditions. The dynamically corrected power curve provides an accurate basis for the wind turbine efficiency evaluation, thereby providing real-time support for the wind turbine efficiency evaluation. Compared with the traditional fixed wind turbine power curve, the dynamically corrected power curve can fully reflect the actual performance of the wind turbine under different environmental conditions.

[0031] Among them, the power curve correction model is:

[0032] in, Indicates wind speed and time The corrected fan power output is It is a power correction function generated based on a machine learning algorithm.

[0033] S103, performing fan efficiency evaluation based on the modified fan power curve; S104, identifying potential faults through a fan fault diagnosis and early warning mechanism based on the acquired fan status data, and formulating a control strategy and early warning information for handling the potential faults; Specifically, the operating status of the fan is monitored in real time, and the status data of the fan, that is, the temperature, speed and current, are obtained in real time. The temperature, speed and current are predicted through the fan fault diagnosis and early warning mechanism to obtain the fault risk value. The fault mode of the fan is predicted by the fault risk value, and the possible fault type and probability of occurrence are predicted. When the probability of occurrence exceeds the set critical value, the potential fault is determined, and warning information is generated based on the potential fault. The warning information is transmitted to the operation and maintenance management platform for warning, and historical fault control decision data is obtained. Combined with the status data of the existing fan, a control decision is made, and decision support is provided through the operation and maintenance management platform to help on-site maintenance personnel handle the fault in advance.

[0034] The process of predicting the status data through the fan fault diagnosis and early warning mechanism to obtain the fault risk value is as follows:

[0035] in, Indicates at time The failure risk value under is the weight coefficient of status data in risk assessment, is the state data at time The value at time.

[0036] S105 , using a reinforcement learning algorithm, optimizing the control strategy based on the wind turbine status data and historical data, and adjusting the control parameters of the wind turbine.

[0037] Specifically, the current environmental state data, such as temperature, is obtained, and the temperature, the speed and current of the current operating state of the fan are simulated and calculated through a reinforcement learning algorithm, the initial action in the control strategy is selected, the speed and current in the operating parameters of the fan are adjusted, and the response of the fan and the temperature change in the environment, that is, the speed and current of the fan in the next state, and the temperature of the environment where the fan is located are analyzed in combination with historical data. The speed and current of the fan in the next state, as well as the temperature of the environment where the fan is located, are used to evaluate the effect, a reward function is preset, and a reward value of the simulated calculation is calculated through the reward function. The Q value corresponding to the state-action in the control strategy is updated by using the reinforcement learning algorithm, and the action in the control strategy is adjusted through the updated Q value. The above operation is repeated to continuously optimize the fan control strategy through multiple iterations. When the preset number of iterations is reached, the stable Q value is converged, or a specific performance indicator is reached, the optimization of the control strategy is completed.

[0038] The process of optimizing the control strategy based on the wind turbine status data and historical data using a reinforcement learning algorithm is as follows:

[0039] in, Indicates in status Next action The Q value, is the learning rate, It’s an instant reward. is the discount factor, The next state The maximum Q value under .

[0040] The present invention realizes intelligent management of wind farms, significantly improves the power generation efficiency of wind turbines, and effectively reduces the failure rate. Through real-time monitoring and dynamic adjustment, wind farms can adapt to complex environmental changes and achieve optimal operation and maintenance efficiency.

[0041] On the other hand, the present invention also proposes a dynamic verification and correction system for a new energy data analysis model, such as Figure 2 As shown, the method for implementing the above method includes a data acquisition module, a standardization processing module, a correction module, a performance evaluation module, a data processing module and an optimization module; Wherein, the data acquisition module is configured as follows: Used to obtain real-time operation data and status data of the fan; It is further configured to obtain real-time operating data of the fan, such as wind speed, temperature, voltage, current and power output, through the SCADA system, sensors and historical databases; and to monitor the operating status of the fan in real time and obtain the status data of the fan in real time, i.e., temperature, speed and current.

[0042] The standard processing module is configured as follows: Used to standardize the real-time operation data of the fan to obtain standard data; It is further configured to perform denoising, interpolation and missing value repair processing on data such as wind speed, temperature, voltage, current and power output in turn, and obtain corresponding wind speed standard data, temperature standard data, voltage standard data, current standard data and power output standard data.

[0043] The correction module is configured as follows: For dynamically correcting the power curve of a conventional wind turbine based on the standard data using a machine learning algorithm; It is further configured to take standard data as input, that is, wind speed standard data, temperature standard data, voltage standard data, current standard data and power output standard data as data input respectively, and use machine learning algorithms (such as support vector machines, random forests, etc.) to build a power curve correction model, and input the traditional wind turbine power curve into the power curve correction model for dynamic correction.

[0044] The performance evaluation module is configured as follows: Used for wind turbine efficiency evaluation based on modified wind turbine power curve; The data processing module is configured as follows: Used to identify potential faults through a fan fault diagnosis and early warning mechanism based on the acquired fan status data, and formulate a control strategy and early warning information for handling the potential faults; It is further configured to predict the temperature, speed and current through the fan fault diagnosis and early warning mechanism to obtain the fault risk value, predict the fault mode of the fan through the fault risk value, and predict the possible fault type and probability of occurrence. When the probability of occurrence exceeds the set critical value, the potential fault is determined, and warning information is generated based on the potential fault. The warning information is transmitted to the operation and maintenance management platform for warning, and historical fault control decision data is obtained. Combined with the status data of the existing fan, a control decision is made.

[0045] The optimization module is configured as follows: The control strategy is optimized based on the fan status data and historical data using a reinforcement learning algorithm to adjust the control parameters of the fan.

[0046] It is further configured to simulate and calculate the temperature, speed and current of the fan's current operating state through a reinforcement learning algorithm, select the initial action in the control strategy, adjust the speed and current in the fan's operating parameters, and analyze the fan's response and the change in temperature in the environment in combination with historical data, that is, the speed and current of the fan in the next state, and the temperature of the environment where the fan is located. The speed and current of the fan in the next state, as well as the temperature of the environment where the fan is located, evaluate the effect, preset a reward function, calculate the reward value of the simulated calculation through the reward function, and then update the Q value corresponding to the state-action in the control strategy by using the reinforcement learning algorithm. The action in the control strategy is adjusted through the updated Q value. The above operation is repeated through multiple iterations to continuously optimize the fan control strategy. When the preset number of iterations is reached, the stable Q value is converged, or a specific performance indicator is reached, the optimization of the control strategy is completed.

[0047] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable in the processor, wherein when the processor executes the computer program, the steps of a method for dynamic verification and correction of a new energy data analysis model as described above are implemented.

[0048] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the dynamic verification and correction method of a new energy data analysis model as described above are implemented.

[0049] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

[0050] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented 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.

[0051] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0052] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0053] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0054] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0055] In addition, it should be understood that although this specification is described in accordance with the implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation modes that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of ​​the present invention, and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A dynamic verification and correction method for a new energy data analysis model, characterized in that: The following steps are involved: Standardized processing is performed based on the acquired real-time operation data of the fan to obtain standard data; Using a machine learning algorithm, dynamically correcting a conventional wind turbine power curve based on the standard data; Evaluate wind turbine efficiency based on the modified wind turbine power curve; Based on the acquired fan status data, potential faults are identified through a fan fault diagnosis and early warning mechanism, and a control strategy and early warning information for handling the potential faults are formulated; The control strategy is optimized based on the status data and historical data of the fan by using a reinforcement learning algorithm, and the control parameters of the fan are adjusted.

2. The method for dynamic verification and correction of a new energy data analysis model according to claim 1, characterized in that: The real-time operation data of the wind farm includes wind speed, temperature, voltage, current and power output.

3. The dynamic verification and correction method of a new energy data analysis model according to claim 1 is characterized in that: The standardized processing of the real-time operation data includes: Performing denoising processing on the real-time operation data to obtain real-time operation denoised data; Performing interpolation processing on the real-time denoised data to obtain real-time interpolated data; Perform missing value repair processing on the real-time interpolation data, the standard data.

4. The dynamic verification and correction method of a new energy data analysis model according to claim 1 is characterized in that: The dynamically correcting the traditional wind turbine power curve based on the standard data by using a machine learning algorithm includes: Taking the standard data as input, a power curve correction model is constructed using a machine learning algorithm; The traditional wind turbine power curve is input into the power curve correction model for dynamic correction.

5. The method for dynamic verification and correction of a new energy data analysis model according to claim 4, characterized in that: The power curve correction model is: in, Indicates wind speed and time The corrected fan power output is It is a power correction function generated based on a machine learning algorithm.

6. The method for dynamic verification and correction of a new energy data analysis model according to claim 1, characterized in that: The method of identifying potential faults through a fan fault diagnosis and early warning mechanism based on the acquired fan status data includes: Get status data of the fan; The state data is predicted through a fan fault diagnosis and early warning mechanism to obtain a fault risk value; identifying the potential fault based on the fault risk value; Wherein, the state data includes temperature, rotation speed, and current; The process of predicting the state data through the fan fault diagnosis and early warning mechanism to obtain the fault risk value is as follows: in, Indicates at time The failure risk value under is the weight coefficient of status data in risk assessment, is the state data at time The value at time.

7. The method for dynamic verification and correction of a new energy data analysis model according to claim 1, characterized in that: The process of optimizing the control strategy based on the wind turbine status data and historical data by using the reinforcement learning algorithm is as follows: in, Indicates in status Next action The Q value, is the learning rate, It’s an instant reward. is the discount factor, The next state The maximum Q value under .

8. A dynamic verification and correction system for a new energy data analysis model, based on the implementation of a dynamic verification and correction method for a new energy data analysis model according to any one of claims 1 to 7, characterized in that: include: The data acquisition module is configured as follows: Used to obtain real-time operation data and status data of the fan; The standard processing module is configured as follows: Used to standardize the real-time operation data of the fan to obtain standard data; The correction module is configured as follows: For dynamically correcting the power curve of a conventional wind turbine based on the standard data using a machine learning algorithm; The performance evaluation module is configured as follows: Used for wind turbine efficiency evaluation based on modified wind turbine power curve; The data processing module is configured as follows: Used to identify potential faults through a fan fault diagnosis and early warning mechanism based on the acquired fan status data, and formulate a control strategy and early warning information for handling the potential faults; The optimization module is configured as follows: The control strategy is optimized based on the fan status data and historical data using a reinforcement learning algorithm to adjust the control parameters of the fan.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable in the processor, wherein the processor implements the steps of a method for dynamic verification and correction of a new energy data analysis model as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the dynamic verification and correction method of a new energy data analysis model described in any one of claims 1 to 7 is implemented.

Images