Wind power data anomaly monitoring method and related device

Abstract

The invention belongs to the field of wind power, and discloses a wind power data anomaly monitoring method and a related device, and the method comprises the steps: obtaining to-be-monitored wind power data and historical wind power data; inputting the to-be-monitored wind power data and the historical wind power data into a preset wind power data anomaly monitoring model to obtain residual data of the to-be-monitored wind power data; obtaining an abnormal monitoring result of the to-be-monitored wind power data according to the residual data of the to-be-monitored wind power data and a preset residual threshold; wherein the wind power data anomaly monitoring model is obtained by pre-training a seasonal autoregressive moving average model. The characteristic that wind power data can be influenced by changes of factors such as seasonality is fully considered, a seasonal autoregressive moving average model is adopted for self-adaptive modeling, and the seasonality and tendency of the wind power data are automatically captured, so that a wind power data anomaly monitoring model can adapt to different data characteristics and change dynamics, and the monitoring accuracy is improved. The wind power data with time sequence, nonlinearity and complexity can be effectively processed, and the accuracy of wind power data anomaly monitoring is improved.

Description

Technical Field

[0001] The invention belongs to the field of wind power, and relates to a wind power data abnormality monitoring method and related devices. Background Art

[0002] With the rapid development of renewable energy technology, wind power, as a clean and renewable energy form, has been widely used around the world. In order to ensure the stable operation of wind power equipment, the data acquisition and monitoring system (SCADA system) plays a vital role in the field of wind power industrial control. The system can collect and store various parameters of the wind turbine in real time, including wind speed, wind direction, temperature, generator speed and output power, etc., which provides an important basis for the operation monitoring and fault diagnosis of wind power equipment.

[0003] However, in the existing SCADA system, there are still some challenges in data monitoring and exception handling capabilities. Traditional anomaly detection methods mainly rely on threshold detection, that is, setting a fixed value range as the threshold for normal operation. Once the collected data exceeds this range, it is judged as abnormal.

[0004] However, this method has the following shortcomings: Unable to adapt to dynamic changes: Wind power data is affected by many factors, such as weather conditions, equipment aging, etc., and its dynamic change characteristics are complex. Traditional threshold detection methods cannot fully consider these dynamic changes, which may lead to false alarms or missed alarms in some cases. Difficult threshold setting: In wind power systems, the threshold setting of different parameters needs to be based on a large amount of historical data and professional knowledge. When the complexity of the system increases and the amount of collected data is too large, the setting and updating of thresholds becomes very difficult, time-consuming and prone to errors. Low processing efficiency: Traditional threshold detection methods need to judge each collected data point one by one. When the amount of data is large, this method has low processing efficiency and cannot meet real-time requirements. In order to solve the above problems and improve the ability to monitor abnormal wind power data, it is necessary to introduce new methods. Summary of the invention

[0005] The purpose of the present invention is to overcome the above-mentioned shortcomings of the prior art and provide a method for monitoring abnormality of wind power data and related devices.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for monitoring abnormal wind power data, comprising:

[0008] Obtain wind power data to be monitored and historical wind power data;

[0009] Input the wind power data to be monitored and the historical wind power data into a preset wind power data anomaly monitoring model to obtain residual data of the wind power data to be monitored;

[0010] Obtaining abnormal monitoring results of the wind power data to be monitored according to the residual data of the wind power data to be monitored and a preset residual threshold;

[0011] Among them, the wind power data anomaly monitoring model is obtained by pre-training the seasonal autoregressive moving average model.

[0012] Optionally, before inputting the wind power data to be monitored and the historical wind power data into a preset wind power data abnormality monitoring model, the method further includes:

[0013] The wind power data to be monitored and the historical wind power data are preprocessed; wherein the data preprocessing includes one or more of the following: data cleaning, missing value filling, denoising and normalization.

[0014] Optionally, the data cleaning includes: obtaining cleaning rules for wind power data based on time characteristics, type characteristics and range characteristics of wind power data, and cleaning wind power data that does not comply with the cleaning rules according to the cleaning rules for wind power data; the missing value filling adopts the average value filling method or the median filling method; the denoising adopts the digital filtering method.

[0015] Optionally, the seasonal autoregressive moving average model is specifically:

[0016] SARIMA(p, d, q)(P, D, Q) s

[0017] Among them, p represents the order of non-seasonal autoregression, q represents the order of non-seasonal moving average; P represents the order of seasonal autoregression, Q represents the order of seasonal moving average; d represents the order of non-seasonal difference, D represents the order of seasonal difference; s represents the seasonal cycle;

[0018] Among them, p, d, q, P, D and Q are all 1, and s is December.

[0019] Optionally, also include:

[0020] The preset residual threshold is corrected according to the abnormal monitoring result of the wind power data to be monitored.

[0021] Optionally, the step of correcting a preset residual threshold value according to an abnormal monitoring result of the wind power data to be monitored includes:

[0022] When the accuracy of the abnormal monitoring results of the wind power data to be monitored is lower than the preset accuracy threshold, the proportion of positive sample abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored is obtained, and when the proportion of positive sample abnormal wind power data is lower than the preset proportion threshold, the preset residual threshold is lowered; when the proportion of positive sample abnormal wind power data is not lower than the preset proportion threshold, the preset residual threshold is increased;

[0023] When the accuracy of the abnormal monitoring result of the wind power data to be monitored is not lower than the preset accuracy threshold, the preset residual threshold is kept unchanged;

[0024] Among them, the proportion of positive sample abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored is the proportion of positive sample abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored in all abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored; the positive sample abnormal wind power data is the wind power data that is abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored and is actually abnormal wind power data.

[0025] Optionally, also include:

[0026] Storing abnormal monitoring results of wind power data to be monitored, and visually displaying the abnormal monitoring results of wind power data to be monitored in a preset display mode;

[0027] Among them, the preset display methods include one or more of the following: line chart, bar chart and scatter chart.

[0028] A second aspect of the present invention provides a wind power data abnormality monitoring system, comprising:

[0029] A data acquisition module is used to acquire wind power data to be monitored and historical wind power data;

[0030] A model processing module is used to input the wind power data to be monitored and the historical wind power data into a preset wind power data abnormality monitoring model to obtain residual data of the wind power data to be monitored;

[0031] A monitoring module, used for obtaining abnormal monitoring results of the wind power data to be monitored according to the residual data of the wind power data to be monitored and a preset residual threshold;

[0032] Among them, the wind power data anomaly monitoring model is obtained by pre-training the seasonal autoregressive moving average model.

[0033] According to a third aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned wind power data abnormality monitoring method when executing the computer program.

[0034] According to a fourth aspect of the present invention, 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 above-mentioned wind power data abnormality monitoring method are implemented.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The wind power data anomaly monitoring method of the present invention obtains residual data of the wind power data to be monitored by inputting the wind power data to be monitored and the historical wind power data into a preset wind power data anomaly monitoring model, and then obtains the abnormal monitoring result of the wind power data to be monitored according to the residual data of the wind power data to be monitored and the preset residual threshold, so as to realize the accurate identification of abnormal wind power data of the wind power data. Among them, the wind power data anomaly monitoring model is obtained by pre-training the seasonal autoregressive moving average model, and the characteristics that the wind power data will be affected by the seasonal and other factors are fully considered. The seasonal autoregressive moving average model is used for adaptive modeling, and the seasonality and trend of the wind power data are automatically captured, so that the wind power data anomaly monitoring model can adapt to different data characteristics and dynamic changes, and can effectively process wind power data with time series, nonlinearity and complexity, and improve the accuracy of wind power data anomaly monitoring. At the same time, the residual threshold is used to realize monitoring, which greatly reduces the difficulty of threshold setting and effectively improves the processing efficiency compared with the current threshold detection method in which each wind power data independently establishes a threshold and independently judges, and can fully guarantee the safe operation of wind power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of a method for monitoring abnormal wind power data according to an embodiment of the present invention.

[0038] Figure 2 The structure block diagram of the wind power data abnormality monitoring system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0040] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0041] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0042] See also Figure 1 In one embodiment of the present invention, a method for monitoring wind power data anomalies is provided, specifically a method for monitoring wind power data anomalies based on a seasonal autoregressive moving average model, which fully considers the dynamic changes of wind power data, predicts and monitors the operating status of wind power equipment, and ensures safe operation.

[0043] Specifically, the wind power data abnormality monitoring method of the present invention comprises the following steps:

[0044] S1: Obtain wind power data to be monitored and historical wind power data.

[0045] S2: Input the wind power data to be monitored and the historical wind power data into a preset wind power data anomaly monitoring model to obtain residual data of the wind power data to be monitored.

[0046] S3: Obtaining abnormal monitoring results of the wind power data to be monitored according to the residual data of the wind power data to be monitored and a preset residual threshold.

[0047] Among them, the wind power data anomaly monitoring model (SARIMA model) is obtained by pre-training the seasonal autoregressive moving average model.

[0048] The wind power data anomaly monitoring method of the present invention obtains residual data of the wind power data to be monitored by inputting the wind power data to be monitored and the historical wind power data into a preset wind power data anomaly monitoring model, and then obtains the abnormal monitoring result of the wind power data to be monitored according to the residual data of the wind power data to be monitored and the preset residual threshold, so as to realize the accurate identification of abnormal wind power data of the wind power data. Among them, the wind power data anomaly monitoring model is obtained by pre-training the seasonal autoregressive moving average model, and the characteristics that the wind power data will be affected by the seasonal and other factors are fully considered. The seasonal autoregressive moving average model is used for adaptive modeling, and the seasonality and trend of the wind power data are automatically captured, so that the wind power data anomaly monitoring model can adapt to different data characteristics and dynamic changes, and can effectively process wind power data with time series, nonlinearity and complexity, and improve the accuracy of wind power data anomaly monitoring. At the same time, the residual threshold is used to realize monitoring, which greatly reduces the difficulty of threshold setting and effectively improves the processing efficiency compared with the current threshold detection method in which each wind power data independently establishes a threshold and independently judges, and can fully guarantee the safe operation of wind power equipment.

[0049] Specifically, during the actual monitoring process, the wind power data anomaly monitoring model obtained by pre-training with the seasonal autoregressive moving average model first predicts the wind power data at the same time as the wind power data to be monitored based on the input historical wind power data, and obtains the predicted value of the wind power data at the same time as the wind power data to be monitored. Then, the predicted value of the wind power data at the same time as the wind power data to be monitored is compared with the wind power data to be monitored, and the residual data of the wind power data to be monitored is obtained, which serves as the basis for anomaly monitoring of the wind power data to be monitored.

[0050] In a possible implementation, before inputting the wind power data to be monitored and the historical wind power data into a preset wind power data anomaly monitoring model, it also includes: performing data preprocessing on the wind power data to be monitored and the historical wind power data; wherein the data preprocessing includes one or more of the following: data cleaning, missing value filling, denoising and normalization.

[0051] As an important part of wind power industrial control, the data acquisition and monitoring system (SCADA system) collects and stores a lot of wind power data related to the operating status of wind turbines. Therefore, wind power data can be obtained through the SCADA system, but the directly obtained wind power data cannot be used directly. Some preprocessing work is required, such as data cleaning, missing value filling, denoising and normalization.

[0052] Optionally, the data cleaning includes obtaining cleaning rules for wind power data based on time characteristics, type characteristics and range characteristics of the wind power data, and cleaning wind power data that does not comply with the cleaning rules according to the cleaning rules for the wind power data, so as to delete or replace invalid, erroneous or incomplete wind power data. For example, wind power data that exceeds a normal range can be deleted or replaced to reduce interference.

[0053] Optionally, the missing value filling adopts the mean value filling method or the median filling method, and the data integrity and consistency are ensured by filling the missing values.

[0054] Optionally, if there is noise interference in the wind power data due to sensor failure, signal interference or other factors, digital filtering or other methods can be used to filter and remove noise.

[0055] In a possible implementation, the seasonal autoregressive moving average model is specifically:

[0056] SARIMA(p, d, q)(P, D, Q) s

[0057] Among them, p represents the order of non-seasonal autoregression, q represents the order of non-seasonal moving average; P represents the order of seasonal autoregression, Q represents the order of seasonal moving average; d represents the order of non-seasonal difference, D represents the order of seasonal difference; s represents the seasonal cycle; p, d and q are non-seasonal parameters, s, P, D and Q are seasonal parameters, among which p, d, q, P, D and Q are all 1, and s is December.

[0058] Specifically, choose the simple SARIMA (1, 1, 1) (1, 1, 1) 12 The model is used as a prediction model, and historical wind power data that has been preprocessed is selected as training data for model training. The influence of interference factors and abnormal data is eliminated through data preprocessing to improve the model training effect. The normality, independence and non-autocorrelation of the model residuals are tested, and cross-validation is combined to find the optimal configuration of the SARIMA model and solidify it to obtain a wind power data anomaly monitoring model.

[0059] When the wind power data anomaly monitoring model is built, the wind power data is monitored online. When the real-time wind power data of the SCADA system is obtained as the wind power data to be monitored, the data preprocessing of the wind power data to be monitored is first performed. Next, the wind power data to be monitored and the historical wind power data of the wind power data to be monitored for a period of time before the wind power data to be monitored are input into the wind power data anomaly monitoring model. The residual data of the wind power data to be monitored is obtained through the wind power data anomaly monitoring model. Then, combined with the preset residual threshold, the wind power data to be monitored whose residual data is greater than the residual threshold is taken as abnormal wind power data, and the abnormal monitoring result of the wind power data to be monitored is obtained.

[0060] In a possible implementation manner, the wind power data anomaly monitoring method further includes: correcting a preset residual threshold value according to an abnormal monitoring result of the wind power data to be monitored.

[0061] Specifically, the preset residual threshold is corrected according to the abnormal monitoring result of the wind power data to be monitored, and dynamic threshold setting is realized. The residual threshold can be dynamically adjusted to improve the accuracy and flexibility of abnormality detection.

[0062] Optionally, the correction of the preset residual threshold according to the abnormal monitoring results of the wind power data to be monitored includes: when the accuracy of the abnormal monitoring results of the wind power data to be monitored is lower than the preset accuracy threshold, obtaining the proportion of positive sample abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored, and when the proportion of positive sample abnormal wind power data is lower than the preset proportion threshold, lowering the preset residual threshold; when the proportion of positive sample abnormal wind power data is not lower than the preset proportion threshold, increasing the preset residual threshold; when the accuracy of the abnormal monitoring results of the wind power data to be monitored is not lower than the preset accuracy threshold, keeping the preset residual threshold unchanged; wherein, the proportion of positive sample abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored is the proportion of positive sample abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored to all abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored; the positive sample abnormal wind power data is wind power data that is abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored and is actually abnormal wind power data.

[0063] Specifically, first, an initial residual threshold is set according to the characteristics of actual wind power data and analysis results, which can be set according to the statistical values ​​and experience of historical wind power data. Then, it is continuously adjusted according to the fluctuation of wind power data and the accuracy of anomaly detection. At the same time, during the adjustment of the residual threshold, a feedback mechanism is established to use the adjusted residual threshold for real-time wind power data anomaly monitoring, thereby improving the monitoring accuracy and real-time performance.

[0064] In a possible implementation, the wind power data anomaly monitoring method further includes: storing the anomaly monitoring results of the wind power data to be monitored, and visually displaying the anomaly monitoring results of the wind power data to be monitored in a preset display method; wherein the preset display method includes one or more of the following: a line graph, a bar graph, and a scatter graph.

[0065] Specifically, a data storage and visualization mechanism is established to store the detected abnormal wind power data in a relational database, retain the historical records of abnormal wind power data, and facilitate subsequent data analysis and tracking. In addition, the abnormal wind power data is visualized to operators in the form of line charts, bar charts, and scatter charts, so that operators can intuitively view abnormal situations and make corresponding decisions.

[0066] The following are device embodiments of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0067] See also Figure 2 In another embodiment of the present invention, a wind power data anomaly monitoring system is provided, which can be used to implement the above-mentioned wind power data anomaly monitoring method. Specifically, the wind power data anomaly monitoring system includes a data acquisition module, a model processing module and a monitoring module.

[0068] Among them, the data acquisition module is used to obtain the wind power data to be monitored and the historical wind power data; the model processing module is used to input the wind power data to be monitored and the historical wind power data into the preset wind power data anomaly monitoring model to obtain the residual data of the wind power data to be monitored; the monitoring module is used to obtain the abnormal monitoring results of the wind power data to be monitored based on the residual data of the wind power data to be monitored and the preset residual threshold; among them, the wind power data anomaly monitoring model is obtained by pre-training through the seasonal autoregressive moving average model.

[0069] All relevant contents of each step involved in the embodiment of the wind power data anomaly monitoring method described above can be referred to the functional description of the functional modules corresponding to the wind power data anomaly monitoring system in the embodiment of the present invention, and will not be repeated here.

[0070] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0071] In another embodiment of the present invention, a computer device is provided, the computer device comprising a processor and a memory, the memory being used to store a computer program, the computer program comprising program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in a computer storage medium to implement a corresponding method flow or a corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the wind power data abnormality monitoring method.

[0072] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the wind power data abnormality monitoring method in the above embodiment.

[0073] Those skilled in the art will appreciate 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. Moreover, 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.

[0074] 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.

[0075] 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.

[0076] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for monitoring abnormal wind power data, characterized in that: include: Obtain wind power data to be monitored and historical wind power data; Input the wind power data to be monitored and the historical wind power data into a preset wind power data anomaly monitoring model to obtain residual data of the wind power data to be monitored; Obtaining abnormal monitoring results of the wind power data to be monitored according to the residual data of the wind power data to be monitored and a preset residual threshold; Among them, the wind power data anomaly monitoring model is obtained by pre-training the seasonal autoregressive moving average model.

2. The wind power data abnormality monitoring method according to claim 1, characterized in that: Before inputting the wind power data to be monitored and the historical wind power data into the preset wind power data abnormality monitoring model, the method further includes: The wind power data to be monitored and the historical wind power data are preprocessed; wherein the data preprocessing includes one or more of the following: data cleaning, missing value filling, denoising and normalization.

3. The wind power data abnormality monitoring method according to claim 2, characterized in that: The data cleaning includes: obtaining cleaning rules for wind power data according to the time characteristics, type characteristics and range characteristics of wind power data, and cleaning wind power data that does not meet the cleaning rules according to the cleaning rules for wind power data; the missing value filling adopts the average value filling method or the median filling method; the denoising adopts the digital filtering method.

4. The wind power data abnormality monitoring method according to claim 1, characterized in that: The seasonal autoregressive moving average model is specifically: SARIMA(p,d,q)(P,D,Q) s Among them, p represents the order of non-seasonal autoregression, q represents the order of non-seasonal moving average; P represents the order of seasonal autoregression, Q represents the order of seasonal moving average; d represents the order of non-seasonal difference, D represents the order of seasonal difference; s represents the seasonal cycle; Among them, p, d, q, P, D and Q are all 1, and s is December.

5. The wind power data abnormality monitoring method according to claim 1, characterized in that: Also includes: The preset residual threshold is corrected according to the abnormal monitoring result of the wind power data to be monitored.

6. The wind power data abnormality monitoring method according to claim 5, characterized in that: The method of correcting the preset residual threshold according to the abnormal monitoring result of the wind power data to be monitored includes: When the accuracy of the abnormal monitoring results of the wind power data to be monitored is lower than the preset accuracy threshold, the proportion of positive sample abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored is obtained, and when the proportion of positive sample abnormal wind power data is lower than the preset proportion threshold, the preset residual threshold is lowered; when the proportion of positive sample abnormal wind power data is not lower than the preset proportion threshold, the preset residual threshold is increased; When the accuracy of the abnormal monitoring result of the wind power data to be monitored is not lower than the preset accuracy threshold, the preset residual threshold is kept unchanged; Among them, the proportion of positive sample abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored is the proportion of positive sample abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored in all abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored; the positive sample abnormal wind power data is the wind power data that is abnormal wind power data in the abnormal monitoring results of the wind power data to be monitored and is actually abnormal wind power data.

7. The wind power data abnormality monitoring method according to claim 1, characterized in that: Also includes: Storing abnormal monitoring results of wind power data to be monitored, and visually displaying the abnormal monitoring results of wind power data to be monitored in a preset display mode; Among them, the preset display methods include one or more of the following: line chart, bar chart and scatter chart.

8. A wind power data abnormality monitoring system, characterized in that: include: A data acquisition module is used to acquire wind power data to be monitored and historical wind power data; A model processing module is used to input the wind power data to be monitored and the historical wind power data into a preset wind power data abnormality monitoring model to obtain residual data of the wind power data to be monitored; A monitoring module, used for obtaining abnormal monitoring results of the wind power data to be monitored according to the residual data of the wind power data to be monitored and a preset residual threshold; Among them, the wind power data anomaly monitoring model is obtained by pre-training the seasonal autoregressive moving average model.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the wind power data abnormality monitoring method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the wind power data abnormality monitoring method according to any one of claims 1 to 7 are implemented.

Images