Power generation performance degradation analysis method and device, electronic equipment and storage medium
By performing feature extraction and self-encoder training on the target data of the wind turbine, the labels are generated and the degree of deterioration is predicted, the problems of low prediction accuracy and poor real-time performance in the prior art are solved, and accurate prediction and technical optimization of the degree of deterioration of the wind turbine are achieved.
Patent Information
- Application Number
- CN202311369817.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-20
- Publication Date
- 2025-04-22
AI Technical Summary
The existing wind turbine degradation analysis methods have low prediction accuracy, poor real-time performance, and many manual interventions, making it difficult to effectively capture complex nonlinear relationships and multivariate influencing factors.
By performing feature extraction of target data of wind turbine units, including power, electrical parameters and environmental parameters, labels of feature data are generated using an autoencoder, and the degree of deterioration is predicted based on these tags.
Accurate prediction of the degree of degradation of wind turbines has been achieved, optimization and improvement of wind power generation technology has been improved, and the efficiency and sustainability of wind power generation has been enhanced.
Smart Images
Figure CN119863130A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of wind power generation, and in particular to a method, device, electronic device and storage medium for analyzing power generation performance degradation. Background Art
[0002] Wind power generation is an important form of clean energy, but stability is a challenge. In order to ensure the efficient operation and reliability of wind turbines, power generation performance degradation analysis has become the focus of research and attention.
[0003] Current degradation analysis methods are mainly based on empirical models and statistical methods, and have problems such as low prediction accuracy, poor real-time performance, and frequent manual intervention. Summary of the invention
[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.
[0005] To this end, the first purpose of the present application is to propose a method for analyzing power generation performance degradation to achieve accurate prediction of the degree of degradation of a wind turbine generator set.
[0006] The second objective of the present application is to provide a device for analyzing power generation performance degradation.
[0007] The third objective of the present application is to provide an electronic device.
[0008] A fourth objective of the present application is to provide a computer-readable storage medium.
[0009] A fifth object of the present application is to provide a computer program product.
[0010] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a method for analyzing power generation performance degradation, comprising:
[0011] Extracting features from target data of the wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters, and environmental parameters, and the feature data is used to perform degradation analysis on power generation performance of the wind turbine generator set;
[0012] Training an autoencoder based on the feature data to generate a label for the feature data;
[0013] The degradation degree of the wind turbine generator set is predicted according to the characteristic data and the corresponding labels.
[0014] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a power generation performance degradation analysis device, comprising:
[0015] A determination module, configured to perform feature extraction on target data of the wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters and environmental parameters, and the feature data is used to perform degradation analysis on the power generation performance of the wind turbine generator set;
[0016] A generating module, used for training an autoencoder based on the feature data to generate a label for the feature data;
[0017] The degradation analysis module is used to predict the degradation degree of the wind turbine generator set according to the characteristic data and the corresponding labels.
[0018] To achieve the above-mentioned purpose, the third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;
[0019] The memory stores computer-executable instructions;
[0020] The processor executes the computer-executable instructions stored in the memory to implement a method for analyzing power generation performance degradation proposed in the embodiment of the first aspect of the present application.
[0021] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by the processor, they are used to implement a power generation performance degradation analysis method proposed in the first aspect embodiment of the present application.
[0022] To achieve the above-mentioned purpose, the fifth embodiment of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements a power generation performance degradation analysis method proposed in the first embodiment of the present application.
[0023] The power generation performance degradation analysis method, device, electronic device and storage medium provided in the present application perform feature extraction on target data of a wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters and environmental parameters, and the feature data is used to perform degradation analysis on the power generation performance of the wind turbine generator set; train an autoencoder based on the feature data to generate labels for the feature data; predict the degree of degradation of the wind turbine generator set based on the feature data and the corresponding labels, thereby solving the problem of inaccurate prediction of the degree of degradation of the generator set, promoting the optimization and improvement of wind power generation technology, and improving the efficiency and sustainability of wind power generation.
[0024] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0026] Figure 1 A schematic diagram of a flow chart of a method for analyzing power generation performance degradation provided in an embodiment of the present application;
[0027] Figure 2 A schematic flow chart of another power generation performance degradation analysis method provided in an embodiment of the present application;
[0028] Figure 3 A schematic diagram of the structure of a power generation performance degradation analysis device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0029] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.
[0030] The following describes the power generation performance degradation analysis method and device according to the embodiments of the present application with reference to the accompanying drawings.
[0031] Figure 1 A schematic flow chart of a method for analyzing power generation performance degradation provided in an embodiment of the present application.
[0032] At present, there are some wind turbine degradation analysis methods based on SCADA data. These methods mainly use feature engineering, statistical models, machine learning and other technologies to analyze and predict the degree of degradation. Among them, some studies use statistical methods such as regression analysis and time series analysis to predict the degree of degradation by processing and modeling wind turbine data. In addition, some studies use machine learning algorithms such as support vector machines and neural networks to build degradation prediction models.
[0033] Existing methods have improved the accuracy and real-time performance of degradation analysis to a certain extent, but there are still some problems. Traditional methods mainly rely on manual feature selection and human intervention, which are subjective and limited in data processing and analysis. In addition, existing methods have limited processing capabilities for complex nonlinear relationships and multivariate influencing factors, making it difficult to capture potential degradation patterns and trends.
[0034] In view of the above problems, the present application provides a method for analyzing power generation performance degradation to achieve accurate prediction of the degree of degradation of a wind turbine generator set, such as Figure 1 As shown, the power generation performance degradation analysis method includes the following steps:
[0035] Step 101 , extracting features from target data of a wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters and environmental parameters, and the feature data is used to perform degradation analysis on power generation performance of the wind turbine generator set.
[0036] Optionally, the electrical parameter is a physical quantity in the circuit of the wind turbine generator set, which can be expressed by a numerical value, such as voltage, current, active power, etc.
[0037] Optionally, the environmental parameter is a parameter value characterizing the climate and environmental conditions of the environment in which the wind turbine generator set is located, such as temperature, humidity, wind speed, atmospheric pressure, etc.
[0038] Optionally, the characteristic data is obtained by extracting characteristics of the target data, and extracting characteristics related to the power generation performance degradation analysis.
[0039] Step 102: train an autoencoder based on the feature data to generate labels for the feature data.
[0040] Optionally, the autoencoder is a learning model that decodes and reconstructs the input raw data, and the autoencoder is used to reconstruct the feature data to determine the label corresponding to each feature data.
[0041] The number of labels can be determined according to actual conditions. For example, there can be two labels, a high degradation degree and a low degradation degree.
[0042] Step 103: predicting the degree of degradation of the wind turbine generator set according to the characteristic data and the corresponding labels.
[0043] Optionally, after determining the label of the feature data, a classification model may be trained based on the feature data and the label. The trained classification model can predict the corresponding label based on the input feature data, that is, can determine the corresponding degree of degradation.
[0044] The classification model may be a support vector machine (SVM) model.
[0045] In this embodiment, feature extraction is performed on target data of the wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters and environmental parameters, and the feature data is used to perform degradation analysis on the power generation performance of the wind turbine generator set; an autoencoder is trained based on the feature data to generate labels for the feature data; and the degree of degradation of the wind turbine generator set is predicted based on the feature data and the corresponding labels, which solves the problem of inaccurate prediction of the degree of degradation of the wind turbine generator set, can promote the optimization and improvement of wind power generation technology, and improve the efficiency and sustainability of wind power generation.
[0046] This embodiment provides another method for analyzing power generation performance degradation. Figure 2 A schematic flow chart of another method for analyzing power generation performance degradation provided in an embodiment of the present application.
[0047] like Figure 2 As shown, the power generation performance degradation analysis method may include the following steps:
[0048] Step 201 , extracting features from target data of a wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters and environmental parameters, and the feature data is used to perform degradation analysis on power generation performance of the wind turbine generator set.
[0049] In the embodiment of the present application, the target data comes from a supervisory control and data acquisition system (SCADA system for short). In the power system, the SCADA system can monitor and control the on-site operating equipment to achieve various functions such as data acquisition, equipment control, measurement, parameter adjustment, and various signal alarms. The target data in the embodiment of the present application is easily obtained in modern wind turbines.
[0050] In the embodiment of the present application, the target data includes power, generator speed, electrical parameters and environmental parameters.
[0051] Among them, electrical parameters are physical quantities in the circuit of the wind turbine generator set, which can be expressed by numerical values, such as voltage, current, active power, etc.
[0052] The environmental parameters are parameter values that characterize the climate and environmental conditions of the environment in which the wind turbine generator set is located, such as temperature, humidity, wind speed, atmospheric pressure, etc.
[0053] Optionally, the target data is first preprocessed, and the preprocessing at least includes removing outliers and filling missing values.
[0054] The target data is cleaned and completed through preprocessing to ensure the validity of the target data.
[0055] In the embodiment of the present application, the characteristic data includes power curve slope, wind speed change rate, generator speed, electrical parameters, and environmental parameters.
[0056] The power in the target data is curve-fitted to determine the slope of the power curve; the wind speed change rate is determined based on the wind speed; the power curve slope, wind speed change rate, electrical parameters and environmental parameters are combined to determine characteristic data.
[0057] As a possible implementation method, the relationship between wind speed and power is fitted by linear regression to obtain a fitting curve, and the slope of the fitting curve is calculated, which is the slope of the power curve.
[0058] As a possible implementation method, the change of wind speed within a certain period of time is calculated as the wind speed change rate. For example, within a certain period of time, the wind speed at each moment is collected, and the ratio of the wind speed difference at adjacent moments to the wind speed at the previous moment in the adjacent moments is calculated, which is the wind speed change rate.
[0059] As a possible implementation method, the number of revolutions of the generator per unit time is calculated, that is, the generator speed.
[0060] The target data include electrical parameters and environmental parameters.
[0061] The power curve slope, wind speed change rate, electrical parameters and environmental parameters are combined to determine characteristic data. The characteristic data is described by a vector, for example, a 6-dimensional vector composed of the power curve slope, wind speed change rate, temperature, humidity, voltage and current is used as the characteristic data.
[0062] Step 202: input the feature data into the autoencoder to obtain decoded data; and generate a label for the feature data based on an error between the feature data and the decoded data.
[0063] It should be noted that the autoencoder is a learning model that decodes and reconstructs the input raw data. The autoencoder is used to reconstruct the feature data and determine the label corresponding to each feature data.
[0064] In the embodiment of the present application, the label of the feature data is divided into a first label and a second label according to the magnitude relationship between the error and a preset threshold.
[0065] As a possible implementation, in response to the error being greater than a preset threshold, the label of the corresponding feature data is a first label; in response to the error being less than or equal to the preset threshold, the label of the corresponding feature data is a second label.
[0066] Among them, the first label is a higher degree of degradation, and the second label is a lower degree of degradation.
[0067] The autoencoder structure includes an input layer, an encoding layer, a decoding layer and an output layer. The preprocessed target data is input into the autoencoder, and the autoencoder model is trained by minimizing the reconstruction error. The reconstruction error can be a mean square error, and a trained autoencoder is obtained.
[0068] Generate labels for feature data using the trained autoencoder.
[0069] Furthermore, the generated labels are displayed through a graphical interface, and domain experts review and correct some misjudged labels based on their actual experience and understanding of the data, and correct them to correct labels.
[0070] The embodiment of the present application introduces a domain expert feedback and correction mechanism, which improves the credibility of the labels, thereby improving the quality and reliability of the degradation degree prediction model subsequently trained using the labels.
[0071] Step 203: predicting the degree of degradation of the wind turbine generator set according to the characteristic data and the corresponding labels.
[0072] Optionally, a degradation degree prediction model is obtained based on the characteristic data and the corresponding labels; the characteristic data obtained in real time is input into the degradation degree prediction model, and the predicted degradation degree of the wind turbine generator set is output.
[0073] Among them, the degradation degree prediction model can be obtained through the following steps:
[0074] The characteristic data is input into the target model, and the predicted value of the degree of degradation is output; based on the difference between the predicted value of the degree of degradation and the corresponding label, the target model is trained; in response to the convergence of the target model, a prediction model of the degree of degradation is obtained.
[0075] Among them, the target model can be a support vector machine (SVM) model. The input layer of the SVM model receives the preprocessed feature data, and the output layer gives a predicted value of the degree of degradation. The predicted value is a value between 0 and 1. The larger the predicted value, the greater the possibility of a high degree of degradation.
[0076] In an embodiment of the present application, a hinge loss function is used to quantify the difference between the predicted value of the degree of degradation and the corresponding label, and the SVM model is trained until the loss function converges to obtain a trained degree of degradation prediction model.
[0077] Furthermore, the kernel function of the SVM model is used to capture the relationship between the feature data. In the embodiment of the present application, the kernel function K of the SVM model is designed as:
[0078]
[0079] Where d is the dimension of the feature data (described by a vector); x and y are two feature data respectively; f i () is a nonlinear mapping function of the i-th feature, and appropriate mapping can be selected according to the wind power characteristics, such as Fourier transform, wavelet transform, etc.; w i is the weight of the i-th feature, which can be determined by feature selection or based on domain knowledge; γ is a regularization parameter that controls the shape of the kernel function; exp() is based on the natural constant e.
[0080] The above kernel function actually calculates the exponential decay of the weighted distance of the feature vector after nonlinear mapping, where the weight w iThe weight can be adjusted according to the importance of each feature. For example, for key features such as wind speed and power, the weight can be relatively high.
[0081] It should be noted that the above kernel function is based on the structure and characteristics of wind power SCADA data to build a basic model that can capture these characteristics. In practical applications, it may be necessary to adjust and optimize according to the characteristics of the data and the problem requirements.
[0082] Furthermore, the characteristic data acquired in real time is input into a degradation degree prediction model, and the predicted degradation degree of the wind turbine generator set is output.
[0083] In the embodiment of the present application, the degradation degree prediction model can accurately predict the degradation degree of the wind turbine generator set, extract features from the target data acquired in real time, obtain corresponding feature data, and input it into the degradation degree prediction model to output the predicted degradation degree.
[0084] Here, the degree of degradation is a value between 0 and 1.
[0085] Furthermore, a threshold is set based on the statistical analysis results of historical data and the experience of domain experts. For example, the mean of the degradation degree plus a certain multiple of the standard deviation can be selected as the threshold. The predicted degradation degree is compared with the set threshold, and if it exceeds the threshold, it is judged to be degraded. In response to the wind turbine being judged to be degraded, an early warning message is issued to prompt the operation and maintenance personnel to conduct inspection and maintenance, which can help the operation and maintenance personnel monitor the power generation performance of the wind turbine in real time, discover and deal with degradation problems in a timely manner, reduce operation and maintenance costs, and improve the overall operation efficiency of the wind farm.
[0086] In this embodiment, feature extraction is performed on target data of the wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters and environmental parameters, and the feature data is used to perform degradation analysis on the power generation performance of the wind turbine generator set; the feature data is input into an autoencoder to obtain decoded data; based on an error between the feature data and the decoded data, a label of the feature data is generated; the autoencoder is trained based on the feature data to generate a label of the feature data; based on the feature data and the corresponding label, the degree of degradation of the wind turbine generator set is predicted, which solves the problem of inaccurate prediction of the degree of degradation of the wind turbine generator set, can promote the optimization and improvement of wind power generation technology, and improve the efficiency and sustainability of wind power generation.
[0087] In order to implement the above-mentioned embodiment, the present application also proposes a power generation performance degradation analysis device.
[0088] Figure 3 A schematic diagram of the structure of a power generation performance degradation analysis device provided in an embodiment of the present application.
[0089] like Figure 3 As shown, the power generation performance degradation analysis device 300 includes: a determination module 301 , a generation module 302 and a degradation analysis module 303 .
[0090] A determination module 301 is used to extract features from target data of the wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters and environmental parameters, and the feature data is used to perform degradation analysis on the power generation performance of the wind turbine generator set;
[0091] A generating module 302, for training an autoencoder based on the feature data to generate a label for the feature data;
[0092] The degradation analysis module 303 is used to predict the degradation degree of the wind turbine generator set according to the characteristic data and the corresponding labels.
[0093] Further, in a possible implementation manner of the embodiment of the present application, the environmental parameter includes wind speed, and the determination module 301 is further configured to:
[0094] Performing a curve fit on the power in the target data to determine the slope of the power curve;
[0095] determining a rate of change of wind speed based on the wind speed;
[0096] The power curve slope, wind speed change rate, electrical parameters and environmental parameters are combined to determine the characteristic data.
[0097] The target data is preprocessed, which at least includes removing outliers and filling missing values.
[0098] Furthermore, in a possible implementation of the embodiment of the present application, the generating module 302 is further configured to:
[0099] Input the feature data into the autoencoder to obtain decoded data;
[0100] Based on the error between the feature data and the decoded data, a label for the feature data is generated.
[0101] According to the magnitude relationship between the error and a preset threshold, the label of the feature data is divided into a first label and a second label.
[0102] Furthermore, in a possible implementation of the embodiment of the present application, the degradation analysis module 303 is further configured to:
[0103] Obtain a degradation degree prediction model based on the feature data and the corresponding labels;
[0104] The characteristic data acquired in real time is input into the degradation degree prediction model, and the predicted degradation degree of the wind turbine generator set is output.
[0105] Input the characteristic data into the target model and output the predicted value of the degree of degradation;
[0106] Based on the difference between the predicted value of the degradation degree and the corresponding label, the target model is trained;
[0107] In response to the target model converging, a degradation degree prediction model is obtained.
[0108] It should be noted that the above explanation of the embodiment of the power generation performance degradation analysis method is also applicable to the power generation performance degradation analysis device of this embodiment, and will not be repeated here.
[0109] In an embodiment of the present application, feature extraction is performed on target data of the wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters and environmental parameters, and the feature data is used to perform degradation analysis on the power generation performance of the wind turbine generator set; an autoencoder is trained based on the feature data to generate labels for the feature data; and the degree of degradation of the wind turbine generator set is predicted based on the feature data and the corresponding labels, thereby solving the problem of inaccurate prediction of the degree of degradation of the wind turbine generator set, promoting the optimization and improvement of wind power generation technology, and improving the efficiency and sustainability of wind power generation.
[0110] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.
[0111] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.
[0112] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.
[0113] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.
[0114] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.
[0115] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.
[0116] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.
[0117] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0118] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.
[0119] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.
[0120] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0121] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0122] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
[0123] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.
Claims
1. A method for analyzing power generation performance degradation, characterized in that: The following steps are involved: Extracting features from target data of the wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters, and environmental parameters, and the feature data is used to perform degradation analysis on power generation performance of the wind turbine generator set; Training an autoencoder based on the feature data to generate a label for the feature data; The degradation degree of the wind turbine generator set is predicted according to the characteristic data and the corresponding labels.
2. The power generation performance degradation analysis method according to claim 1, characterized in that: The environmental parameter includes wind speed, and the feature extraction of target data of the wind turbine generator set to determine feature data includes: Performing curve fitting on the power in the target data to determine the slope of the power curve; determining a rate of change of wind speed based on the wind speed; The power curve slope, the wind speed change rate, the electrical parameters and the environmental parameters are combined to determine the characteristic data.
3. The power generation performance degradation analysis method according to claim 2, characterized in that: Before extracting the features of the target data of the wind turbine generator set, the method further includes: The target data is preprocessed, and the preprocessing at least includes removing outliers and filling missing values.
4. The power generation performance degradation analysis method according to claim 1, characterized in that: The step of training an autoencoder based on the feature data to generate a label for the feature data includes: Inputting the feature data into an autoencoder to obtain decoded data; A label of the feature data is generated based on an error between the feature data and the decoded data.
5. The power generation performance degradation analysis method according to claim 4, characterized in that: The step of generating a label of the feature data based on an error between the feature data and the decoded data comprises: According to the magnitude relationship between the error and a preset threshold, the label of the feature data is divided into a first label and a second label.
6. The power generation performance degradation analysis method according to any one of claims 1 to 5, characterized in that: The predicting the degree of degradation of the wind turbine generator set according to the characteristic data and the corresponding label includes: Obtaining a degradation degree prediction model according to the feature data and the corresponding labels; The characteristic data acquired in real time is input into the degradation degree prediction model, and the predicted degradation degree of the wind turbine generator set is output.
7. The power generation performance degradation analysis method according to claim 6, characterized in that: The step of obtaining a degradation degree prediction model according to the feature data and the corresponding labels includes: Inputting the characteristic data into a target model and outputting a predicted value of the degree of degradation; Training the target model based on the difference between the predicted value of the degradation degree and the corresponding label; In response to the target model converging, the degradation degree prediction model is acquired.
8. A power generation performance degradation analysis device, characterized in that: include: A determination module, configured to perform feature extraction on target data of the wind turbine generator set to determine feature data, wherein the target data includes at least one of power, electrical parameters and environmental parameters, and the feature data is used to perform degradation analysis on the power generation performance of the wind turbine generator set; A generating module, used for training an autoencoder based on the feature data to generate a label for the feature data; The degradation analysis module is used to predict the degradation degree of the wind turbine generator set according to the characteristic data and the corresponding labels.
9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.