Power curve bifurcation anomaly detection method, system, storage medium and computing device

Abstract

This invention relates to a method, system, storage medium, and computing device for detecting power curve bifurcation anomalies. The method includes: acquiring normal operating data of a wind turbine during its non-full-load phase; dividing the normal operating data into intervals based on wind speed and power, obtaining multiple sub-intervals for wind speed and power respectively; determining the multi-peak distribution of data within each sub-interval to obtain corresponding multi-peak distribution results; and weighting the multi-peak distribution results of the multiple sub-intervals for wind speed and power to obtain a first curve bifurcation index and a second curve bifurcation index respectively; and obtaining the power curve bifurcation result based on the first curve bifurcation index and the second curve bifurcation index. This invention can identify performance anomalies in wind turbine equipment during power generation, analyze the critical boundary states of wind turbine abnormalities or deficiencies, and provide support for improving the power generation performance of wind turbines.

Description

Technical Field

[0001] This invention relates to the field of new energy analysis technology, specifically to a method, system, storage medium, and computing device for detecting power curve bifurcation anomalies. Background Technology

[0002] As wind turbines become increasingly larger, the importance of detecting anomalies in their power curves is growing. The normality of the power curve greatly affects the turbine's power generation performance and operating efficiency, as well as its safety. If the power curve remains abnormal for an extended period, the turbine will lose a significant amount of potential electricity.

[0003] A power curve bifurcation is a manifestation of an abnormal power curve. In areas below rated wind speed and not operating at full capacity, changes in the unit's control strategy can cause a power curve bifurcation.

[0004] Existing methods can effectively identify and filter out obvious outliers in power curves to some extent. However, because the confidence interval of wind turbine power curves is adaptive, the calculated confidence interval range is often larger than the actual effective range. Therefore, it cannot effectively detect morphological anomalies in the power curve within the confidence interval, especially common power curve morphological anomalies such as power curve bifurcation. Summary of the Invention

[0005] To address the aforementioned problems, the present invention aims to provide a power curve bifurcation anomaly detection method, system, storage medium, and computing device that can identify performance anomalies in wind turbine equipment during power generation, analyze the switching of equipment control strategies, analyze the critical boundary states of wind turbine abnormalities or deficiencies, and provide support for improving the power generation performance of wind turbines.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for detecting power curve bifurcation anomalies, comprising: acquiring normal operating data of the unit during non-full-load operation; dividing the normal operating data into intervals according to wind speed and power, respectively obtaining multiple operating data sub-intervals for wind speed and multiple operating data sub-intervals for power; performing multimodality judgment on the data within each operating data sub-interval to obtain the corresponding multimodal distribution results, and performing weighted average of the multimodal distribution results of the multiple operating data sub-intervals for wind speed and power to obtain a first curve bifurcation index and a second curve bifurcation index; and obtaining the power curve bifurcation result based on the first curve bifurcation index and the second curve bifurcation index.

[0007] Furthermore, obtain normal operating data of the unit during non-full-capacity periods, including:

[0008] Range selection is performed for operating condition variables such as unit speed, blade pitch angle, wind speed, and power;

[0009] Data is removed based on the selected range to obtain normal operating data for the non-full-capacity section of the unit.

[0010] Furthermore, the range of operating variables such as unit speed, pitch angle, wind speed, and power is selected, including:

[0011] Plot the unit's operating data to create speed histograms and pitch angle histograms, and measure the unit's operating condition variables based on the speed histograms and pitch angle histograms;

[0012] The upper and lower limits of each operating condition variable are adaptively determined based on the data distribution of the unit's operating condition variables;

[0013] Based on the range of each operating condition variable, data under special operating conditions of the unit are removed, and normal operating data of the unit during non-full-load periods are selected.

[0014] Furthermore, the normal operation data is divided into intervals according to wind speed and power, resulting in multiple sub-intervals for wind speed and power, respectively.

[0015] The normal operation data is divided into intervals according to wind speed, resulting in multiple sub-intervals of normal operation data for wind speed.

[0016] The normal operation data is divided into intervals according to power, resulting in multiple sub-intervals of normal operation data with different power levels.

[0017] Furthermore, the wind speed is divided into intervals using a preset wind speed as the interval division step size;

[0018] The power of the unit's normal operation data is divided into power ranges using a preset power as the interval division step size.

[0019] Furthermore, the data within each sub-interval of the operational data are analyzed for multimodality to obtain the corresponding multimodal distribution results, including:

[0020] Cluster the data in each sub-interval of the running data;

[0021] The clustered data is divided into N equal intervals according to size, and the proportion of data points in each interval to the total data is calculated.

[0022] If the proportion of data points in the middle interval to all data is less than the set threshold, it is considered that the current normal operating data interval has a multi-peak distribution.

[0023] Furthermore, based on the bifurcation indices of the first and second curves, the power curve bifurcation results are obtained, including:

[0024] The weighted average of the bifurcation indices of the first and second curves is used to obtain the composite bifurcation index.

[0025] The bifurcation index of the composite curve is compared with a set threshold. If it is greater than the threshold, the power curve bifurcates; otherwise, the power curve does not bifurcate.

[0026] A power curve bifurcation anomaly detection system includes: a data acquisition module for acquiring normal operating data of the unit during non-full-load periods; a data processing module for dividing the normal operating data into intervals according to wind speed and power, respectively, to obtain multiple operating data sub-intervals for wind speed and multiple operating data sub-intervals for power; a multi-peak judgment module for judging the multi-peakity of the data in each operating data sub-interval to obtain the corresponding multi-peak distribution results, and for weighted averaging the multi-peak distribution results of the multiple operating data sub-intervals for wind speed and power, respectively, to obtain a first curve bifurcation index and a second curve bifurcation index; and a bifurcation judgment module for obtaining the power curve bifurcation result based on the first curve bifurcation index and the second curve bifurcation index.

[0027] A computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform any of the methods described above.

[0028] A computing device includes: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods described above.

[0029] The present invention has the following advantages due to the adoption of the above technical solutions:

[0030] This invention acquires normal operating data of the wind turbine during its non-full-load phase; divides this data into multiple intervals; performs multi-peak determination on each interval to obtain a multi-peak determination result; and determines whether the power curve exhibits bifurcation based on the multi-peak determination result. This anomaly detection of the wind turbine's power curve enables the identification of performance anomalies during power generation, providing support for optimizing wind turbine control strategies, evaluating turbine condition, and improving power generation performance. Attached Figure Description

[0031] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a flowchart of the power curve bifurcation anomaly detection method in an embodiment of the present invention;

[0034] Figure 2 This is a schematic diagram of the wind turbine speed distribution in an embodiment of the present invention;

[0035] Figure 3 This is a schematic diagram of the blade pitch angle distribution of the wind turbine in an embodiment of the present invention;

[0036] Figure 4 This is a schematic diagram of power curve screening in an embodiment of the present invention;

[0037] Figure 5 This is a schematic diagram of a typical power curve bifurcation case in an embodiment of the present invention;

[0038] Figure 6 This is a schematic diagram of a data sub-interval of the normal power curve and the data distribution within the interval in an embodiment of the present invention;

[0039] Figure 7 This is a schematic diagram of a data sub-interval of the bifurcation power curve and the data distribution within the interval in an embodiment of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0041] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0042] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" and "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0043] Existing methods can effectively identify and filter out obvious outliers in power curves to some extent. However, because the confidence interval of wind turbine power curves is adaptive, the calculated confidence interval range is often larger than the actual effective range. Therefore, it cannot effectively detect morphological anomalies in the power curve within the confidence interval, especially common power curve morphological anomalies such as power curve bifurcation.

[0044] To address the difficulty in accurately identifying power curve anomalies in existing technologies, this invention provides a method, system, storage medium, and computing device for detecting power curve bifurcation anomalies in wind turbines. It filters normal operating data from the turbine's non-full-load phase and performs fine-grained dual-interval division of the wind speed-power scatter plot. Within each interval, it assesses the multi-peak nature of the data to ultimately determine whether a power curve bifurcates. This invention makes the detection results more accurate and effectively avoids false positives. This invention enables the identification of performance anomalies in wind turbine equipment during power generation, providing support for optimizing wind turbine control strategies, evaluating turbine condition, and improving turbine power generation performance.

[0045] Example 1

[0046] In one embodiment of the present invention, a power curve bifurcation anomaly detection method is provided, focusing on the power curve anomaly detection of wind power equipment. This method identifies performance anomalies during the power generation process, providing support for optimizing unit control strategies, evaluating unit condition, and improving unit power generation performance. In this embodiment, as... Figure 1 As shown, the method includes the following steps:

[0047] S100, acquire normal operating data of the unit during non-full-capacity operation;

[0048] S200 divides the normal operation data into intervals according to wind speed and power, respectively, to obtain multiple sub-intervals of wind speed and power.

[0049] S300, performs multimodality judgment on the data in each sub-interval of the operating data to obtain the corresponding multimodal distribution results, and performs weighted average of the multimodal distribution results of multiple sub-intervals of the operating data for wind speed and power to obtain the first curve bifurcation index R1 and the second curve bifurcation index R2 respectively.

[0050] S400 obtains the power curve bifurcation result based on the first curve bifurcation index R1 and the second curve bifurcation index R2, completes the power curve anomaly detection of wind power equipment, and realizes the identification of performance anomalies of unit equipment during power generation.

[0051] In use, the wind turbine power curve bifurcation anomaly detection method of the present invention solves the technical problem of power curve anomaly detection of wind power equipment. It is used to identify performance anomalies of wind turbine equipment during power generation, analyze the switching of wind turbine equipment control strategies, analyze the critical boundary states of wind turbine abnormality or excellence, and provide support for improving the power generation performance of wind turbine.

[0052] In a preferred embodiment, step S100, acquiring the normal operating data of the unit during its non-full-capacity operation phase, includes the following steps:

[0053] S101. Select the range of operating variables such as unit speed, pitch angle, wind speed and power.

[0054] In this embodiment, the unit's operating data is plotted as a speed histogram and a pitch angle histogram; the unit's speed distribution... Figure 1 Generally, there will be two peaks, P1 and P2, such as Figure 2 As shown; while the pitch angle distribution Figure 1 Generally, there will be a very large peak near 0, accompanied by a small tail, such as Figure 3 As shown.

[0055] Based on the distribution of the above variables, and using manual or automatic methods, the operating condition measurement variables of the unit (including but not limited to speed, pitch angle, wind speed, power, etc.) are range-selected. The range selection includes, but is not limited to, setting the selection range based on mechanism rules, manually selecting the range, or adaptively determining the upper and lower limits V1 and V2 of each variable based on data distribution.

[0056] S102. Based on the selected range, the data is removed to obtain the normal operation data of the unit during the non-full-load period.

[0057] In this embodiment, valid data is filtered using the aforementioned variables and upper and lower limits. Data from abnormal power generation states such as faults and power limitations, as well as data from special operating conditions such as startup and full-load operation, are removed to obtain normal operating data for the unit's non-full-load phase. Figure 4 As shown.

[0058] like Figure 5 The image shown is a schematic diagram of a typical bifurcation power curve obtained after data removal.

[0059] In a preferred embodiment, step S200 involves dividing the normal operation data into intervals based on wind speed and power, respectively, to obtain multiple sub-intervals of wind speed and power operation data, including the following steps:

[0060] S201. Divide the normal operation data into intervals according to wind speed to obtain multiple normal operation data sub-intervals for wind speed;

[0061] Specifically, the wind speed is used as the interval division step size to divide the normal operation data of the unit during the non-full-load period.

[0062] In this embodiment, preferably, the preset wind speed is 0.1 m / s.

[0063] S202. Divide the normal operation data into intervals according to power to obtain multiple sub-intervals of normal operation data with different power levels.

[0064] Specifically, the power of the unit's non-full-load normal operation data is divided into intervals using a preset power as the interval division step size;

[0065] In this embodiment, preferably, the preset power is 10KW.

[0066] In use, this invention can set the division step size according to different wind speeds and power. A smaller division step size can make the multi-peak determination result more accurate. However, a smaller division step size will increase the number of normal operation data intervals, which will greatly increase the amount of calculation. As a preferred embodiment, this invention sets the wind speed to 0.1 m / s as the interval division step size to divide the normal operation data of the unit in the non-full-load section, and sets the power to 10 kW as the interval division step size to divide the normal operation data of the unit in the non-full-load section.

[0067] In a preferred embodiment, step S300 involves determining the multimodality of the data within each running data sub-interval to obtain the corresponding multimodal distribution result, including the following steps:

[0068] S301. Cluster the data in each running data sub-interval;

[0069] In this embodiment, it is preferred to divide the clusters into 3 clusters, but adaptive clustering is also possible, including but not limited to using more complex manual rules, unsupervised learning and other methods to determine the number of clusters num.

[0070] S302. Divide the clustered data into N equal intervals according to size, and calculate the proportion of data points in each interval to the total data.

[0071] S303. If the proportion of data points in the middle interval to all data is less than a set threshold, then the current normal operating data interval is considered to have a multi-peak distribution. For example... Figure 6 As shown, this illustrates an example of a non-multimodal distribution; for example... Figure 7 The image shows an example of a multimodal distribution.

[0072] In this embodiment, preferably, the threshold is set to 10%. This threshold can be set by the user or obtained through historical data statistics or training methods such as machine learning.

[0073] In use, this invention divides data into dual intervals based on wind speed and power, which is a finer-grained dual data division compared to other existing methods, further reducing the probability of misjudgment and omission. It also performs independent distribution tests on each interval, thereby improving the accuracy of the results.

[0074] In a preferred embodiment, in step S400, as Figure 5 , Figure 6 and Figure 7 As shown, the power curve bifurcation result is obtained based on the bifurcation index R1 of the first curve and the bifurcation index R2 of the second curve, including the following steps:

[0075] S401. Set weights and take a weighted average of the first curve bifurcation index R1 and the second curve bifurcation index R2 to obtain the comprehensive curve bifurcation index. In this embodiment, the weights can be the result of normalizing the average value of the data in the interval (i.e., high wind speed, high weight; low wind speed, low weight, etc.), or the result of normalizing the number of valid data points in the interval, or they can be defined by the user based on other rules.

[0076] S402. Compare the bifurcation index of the composite curve with the set threshold. If it is greater than the threshold, the power curve bifurcates; otherwise, the power curve does not bifurcate.

[0077] In this embodiment, the threshold can preferably be set to 0.5, or it can be defined by the user.

[0078] Example 2

[0079] This embodiment provides a power curve bifurcation anomaly detection system, the system comprising:

[0080] The data acquisition module is used to acquire normal operating data of the unit during non-full-capacity periods;

[0081] The data processing module is used to divide the normal operation data into intervals according to wind speed and power, respectively, to obtain multiple sub-intervals of wind speed and power.

[0082] The multi-peak judgment module is used to judge the multi-peakity of the data in each sub-interval of the operating data to obtain the corresponding multi-peak distribution results, and to perform weighted average of the multi-peak distribution results of multiple sub-intervals of the operating data for wind speed and power to obtain the first curve bifurcation index and the second curve bifurcation index respectively.

[0083] The bifurcation judgment module obtains the power curve bifurcation result based on the bifurcation index of the first curve and the bifurcation index of the second curve.

[0084] In the above embodiments, obtaining normal operating data of the unit during non-full-capacity operation includes:

[0085] Range selection is performed for operating condition variables such as unit speed, blade pitch angle, wind speed, and power;

[0086] Data is removed based on the selected range to obtain normal operating data for the non-full-capacity section of the unit.

[0087] This includes selecting a range for operating variables such as unit speed, pitch angle, wind speed, and power, including:

[0088] Plot the unit's operating data to create speed histograms and pitch angle histograms, and measure the unit's operating condition variables based on the speed histograms and pitch angle histograms;

[0089] The upper and lower limits of each operating condition variable are adaptively determined based on the data distribution of the unit's operating condition variables;

[0090] Based on the range of each operating condition variable, data under special operating conditions of the unit are removed, and normal operating data of the unit during non-full-load periods are selected.

[0091] In the above embodiments, the normal operation data is divided into intervals according to wind speed and power, respectively, to obtain multiple sub-intervals of operating data for wind speed and multiple sub-intervals of operating data for power, including:

[0092] The normal operation data is divided into intervals according to wind speed, resulting in multiple sub-intervals of normal operation data for wind speed.

[0093] The normal operation data is divided into intervals according to power, resulting in multiple sub-intervals of normal operation data with different power levels.

[0094] In this embodiment, the normal operating data of the unit is divided into wind speeds using a preset wind speed as the interval division step size; and the normal operating data of the unit is divided into power using a preset power as the interval division step size.

[0095] In the above embodiments, the multimodality judgment of data within each running data sub-interval is performed to obtain the corresponding multimodal distribution result, including:

[0096] Cluster the data in each sub-interval of the running data;

[0097] The clustered data is divided into N equal intervals according to size, and the proportion of data points in each interval to the total data is calculated.

[0098] If the proportion of data points in the middle interval to all data is less than the set threshold, it is considered that the current normal operating data interval has a multi-peak distribution.

[0099] In the above embodiments, the power curve bifurcation result is obtained based on the first curve bifurcation index and the second curve bifurcation index, including:

[0100] The weighted average of the bifurcation indices of the first and second curves is used to obtain the composite bifurcation index.

[0101] The bifurcation index of the composite curve is compared with a set threshold. If it is greater than the threshold, the power curve bifurcates; otherwise, the power curve does not bifurcate.

[0102] The system provided in this embodiment is used to execute the above-described method embodiments. For specific processes and details, please refer to the above embodiments, which will not be repeated here.

[0103] This invention acquires normal operating data of the wind turbine during its non-full-load phase; divides this data into multiple intervals; performs multi-peak determination on each interval to obtain a multi-peak determination result; and determines whether the power curve exhibits bifurcation based on the multi-peak determination result. This anomaly detection of the wind turbine's power curve enables the identification of performance anomalies during power generation, providing support for optimizing wind turbine control strategies, evaluating turbine condition, and improving power generation performance.

[0104] Example 3

[0105] In one embodiment of the present invention, a computing device is provided, which can be a terminal and may include: a processor, a communication interface, memory, a display screen, and an input device. The processor, communication interface, and memory communicate with each other via a communication bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs, which, when executed by the processor, implement the methods described in the above embodiments. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals. Wireless communication can be achieved through Wi-Fi, a management network, NFC (Near Field Communication), or other technologies. The display screen can be a liquid crystal display or an e-ink display. The input device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad mounted on the casing of the computing device, or an external keyboard, touchpad, or mouse. The processor can call logical instructions stored in the memory.

[0106] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0107] In one embodiment of the present invention, a computer program product is provided, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, and when the program instructions are executed by a computer, the computer is able to perform the methods provided in the above-described method embodiments.

[0108] Example 4

[0109] In one embodiment of the present invention, a non-transitory computer-readable storage medium is provided, which stores server instructions that cause a computer to perform the methods provided in the above embodiments.

[0110] The computer-readable storage medium provided in the above embodiments has a similar implementation principle and technical effect to the above method embodiments, and will not be described again here.

[0111] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0112] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A power curve bifurcation anomaly detection method, characterized in that, include: Acquire normal operating data of the unit during non-full-capacity periods; The normal operation data is divided into intervals according to wind speed and power, resulting in multiple sub-intervals of wind speed and power. Multimodality judgment is performed on the data in each sub-interval of the operating data to obtain the corresponding multimodal distribution results. The multimodal distribution results of multiple sub-intervals of the operating data for wind speed and power are weighted and averaged to obtain the first curve bifurcation index and the second curve bifurcation index respectively. Based on the bifurcation indices of the first and second curves, the power curve bifurcation results are obtained, including: The weighted average of the bifurcation indices of the first and second curves is used to obtain the composite bifurcation index. The bifurcation index of the composite curve is compared with a set threshold. If it is greater than the threshold, the power curve bifurcates; otherwise, the power curve does not bifurcate. Multimodality assessment is performed on the data within each sub-interval of the operational data to obtain the corresponding multimodal distribution results, including: Cluster the data in each sub-interval of the running data; The clustered data is divided into N equal intervals according to size, and the proportion of data points in each interval to the total data is calculated. If the proportion of data points in the middle interval to all data is less than the set threshold, it is considered that the current normal operating data interval has a multi-peak distribution.

2. The power curve bifurcation anomaly detection method of claim 1, wherein, Obtain normal operating data of the unit during non-full-capacity operation, including: Select a range for the unit's speed, pitch angle, wind speed, and power operating condition variables; Data is removed based on the selected range to obtain the normal operating data of the unit during the non-full-capacity operation period.

3. The power curve bifurcation anomaly detection method of claim 2, wherein, The range of variables for the unit's operating conditions, including speed, pitch angle, wind speed, and power, is selected, including: Plot the unit's operating data to create speed histograms and pitch angle histograms, and measure the unit's operating condition variables based on the speed histograms and pitch angle histograms; The upper and lower limits of each operating condition variable are adaptively determined based on the data distribution of the unit's operating condition variables; Based on the range of each operating condition variable, data under special operating conditions of the unit are removed, and normal operating data of the unit during non-full-load periods are selected.

4. A power curve bifurcation anomaly detection system, used to implement the power curve bifurcation anomaly detection method as described in any one of claims 1 to 3, characterized in that, include: The data acquisition module is used to acquire normal operating data of the unit during non-full-capacity periods; The data processing module is used to divide the normal operation data into intervals according to wind speed and power, respectively, to obtain multiple sub-intervals of wind speed and power. The multi-peak judgment module is used to judge the multi-peakity of the data in each sub-interval of the operating data to obtain the corresponding multi-peak distribution results, and to perform weighted average of the multi-peak distribution results of multiple sub-intervals of the operating data for wind speed and power to obtain the first curve bifurcation index and the second curve bifurcation index respectively. The bifurcation judgment module obtains the power curve bifurcation result based on the bifurcation index of the first curve and the bifurcation index of the second curve.

5. A computer-readable storage medium for storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods described in claims 1 to 3.

6. A computing device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods described in claims 1 to 3.

Images