Risk prediction method and device for wind power plant in extreme weather, medium and equipment

Abstract

The invention discloses a risk prediction method and device for a wind power plant in extreme weather, a medium and equipment, and the method comprises the steps: obtaining the video, wind speed and wind direction data of each wind generating set, judging whether the rotation of a wind wheel accords with the expectation of the current wind speed and wind direction or not through a matching model, and rapidly recognizing the possible operation abnormality. When it is detected that the rotation of the wind wheel is not matched with the wind speed and the wind direction, the current weather condition is further analyzed, future weather changes are predicted, and potential risk types are estimated in combination with the data. According to the scheme, dynamic monitoring and accurate prediction of the wind power plant are achieved in extreme weather, risks can be effectively avoided, the situation that the power generation efficiency is reduced due to the fact that faults are not detected in time is avoided, and then safe and continuous operation of the wind power plant is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of risk prediction, and in particular to a method, device, medium and equipment for predicting the risks of a wind power plant under extreme weather conditions. Background Art

[0002] In severe weather conditions, the risk of failure in wind power plants increases significantly. Currently, risk management in wind farms still relies mainly on manual operations. Although monitoring devices collect data regularly, the analysis and judgment of these data usually rely on the experience of staff to assess the risk of failure. Once a risk is determined, staff need to personally inspect the site.

[0003] However, due to the influence of subjective factors in manual operation, this management method often fails to detect risks in a timely manner, which in turn leads to a decrease in the power generation efficiency of the wind farm and may even affect the safe operation of the entire wind power plant. Summary of the invention

[0004] Based on this, it is necessary to provide risk prediction methods, devices, media and equipment for wind power plants under extreme weather conditions to solve the problem that existing technologies often find it difficult to detect risks in a timely manner, which in turn leads to a decrease in the power generation efficiency of the wind farm and may even affect the safe operation of the entire wind power plant.

[0005] A risk prediction method for a wind power plant under extreme weather conditions, wherein the wind power plant comprises a plurality of wind turbine generator sets, and the method comprises:

[0006] Obtaining video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period; wherein the video data records the rotation of the wind rotor of the wind turbine generator set;

[0007] The preset matching model is used to determine whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and wind direction data;

[0008] If there is a mismatch between the rotor rotation of the first wind turbine and the wind speed data and wind direction data, the current weather conditions at the location of the first wind turbine are obtained from the video data, the future weather conditions are predicted based on the current weather conditions, and the risk type of the wind power plant is estimated based on the future weather conditions; wherein the first wind turbine is any one of the multiple wind turbines.

[0009] In one embodiment, judging whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and the wind direction data by using a preset matching model includes:

[0010] The rotation of the wind rotor of each wind turbine generator set is divided into discrete wind rotor states by an optical flow algorithm, and the wind speed data of each wind turbine generator set is divided into discrete wind speed states, and the wind direction data of each wind turbine generator set is divided into discrete wind direction states; wherein the wind rotor state includes low speed, medium speed and high speed, the wind speed state includes low wind speed, medium wind speed and high wind speed, and the wind direction state includes multiple wind direction angle intervals;

[0011] Obtaining a preset state rule set; wherein the state rule set includes a plurality of different state rules, each state rule being a combination of a wind rotor state, a wind speed state, and a wind direction state;

[0012] If the combination of the rotor state, wind speed state and wind direction state of the first wind turbine generator set belongs to the state rule set, it is determined that the rotor rotation condition of the first wind turbine generator set matches the wind speed data and wind direction data; if the combination of the rotor state, wind speed state and wind direction state of the first wind turbine generator set does not belong to the state rule set, it is determined that the rotor rotation condition of the first wind turbine generator set does not match the wind speed data and wind direction data.

[0013] In one embodiment, obtaining a preset state rule set includes:

[0014] Acquire multiple groups of sample data; wherein each group of sample data includes a sample wind rotor rotation condition, sample wind speed data, and sample wind direction data of a wind turbine generator set under a risk-free condition;

[0015] By using an optical flow algorithm, the sample wind rotor rotation conditions of each wind turbine generator set are divided into discrete wind rotor states, the sample wind speed data of each wind turbine generator set are divided into discrete wind speed states, and the sample wind direction data of each wind turbine generator set are divided into discrete wind direction states, so as to obtain a plurality of state sets;

[0016] Generate multiple i-th state sets, calculate the frequency proportion of each i-th state set, and retain the state set whose frequency proportion is greater than a preset frequency proportion threshold as a candidate state rule; wherein the i-th state set includes i of the wind rotor state, wind speed state and wind direction state, and the initial value of i is 1;

[0017] Let i=i+1, and return to execute the step of generating multiple i-th state sets and subsequent steps until the number of candidate state rules no longer increases;

[0018] Each candidate state rule is split into a first sub-state set and a second sub-state set. Within each candidate state rule, the joint probability and the correlation coefficient between the first sub-state set and the second sub-state set are calculated, and all candidate state rules whose joint probability is greater than a preset joint probability threshold and whose correlation coefficient is greater than a preset correlation coefficient threshold are retained as the state rule set.

[0019] In one embodiment, the frequency ratio of each i-th state set is calculated as:

[0020]

[0021] In the above formula, FR(x) represents the frequency ratio of state set x, N x represents the total number of state sets x included in the multiple state sets, and T represents the total number of all state sets;

[0022] The formula for calculating the joint probability is:

[0023]

[0024] In the above formula, JP(ab) represents the joint probability between the first sub-state set a and the second sub-state set b;

[0025] The calculation formula of the correlation coefficient is:

[0026]

[0027] In the above formula, AC(ab) represents the correlation coefficient between the first sub-state set a and the second sub-state set b.

[0028] In one embodiment, predicting future weather conditions based on the current weather conditions, and estimating the risk type of the wind power plant according to the future weather conditions, includes:

[0029] The current weather conditions are input into the LSTM prediction model to predict future weather conditions, and a decision tree is used to classify the risk type of the wind power plant according to the future weather conditions.

[0030] In one embodiment, an infrared sensor is disposed around the wind power plant, and the method further comprises:

[0031] Under the premise that there is a risk in the wind power plant, if an instruction indicating being triggered by induction is received from the infrared sensor, an early warning reminder is issued.

[0032] In one embodiment, the method further comprises:

[0033] Collecting historical data; wherein the historical data includes video data, wind speed data and wind direction data of wind turbines under extreme weather conditions;

[0034] Establishing a risk model based on the historical data; wherein the risk model defines the threshold range of normal operating state and abnormal operating state of the wind turbine generator set, and the risk types under different abnormal operating states;

[0035] The video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period are compared as real-time data with the threshold range defined in the risk model. When the real-time data exceeds the threshold range, a warning signal indicating the existence of a risk is generated.

[0036] A risk prediction device for a wind power plant under extreme weather conditions, the risk prediction device for a wind power plant under extreme weather conditions comprising:

[0037] A data acquisition module, used to acquire video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period; wherein the video data records the rotation of the wind rotor of the wind turbine generator set;

[0038] A data matching module is used to determine whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and wind direction data through a preset matching model;

[0039] A risk assessment module is used to obtain the current weather conditions at the location of the first wind turbine from the video data if there is a mismatch between the rotation of the rotor of the first wind turbine and the wind speed data and wind direction data, predict the future weather conditions based on the current weather conditions, and estimate the risk type of the wind power plant based on the future weather conditions; wherein the first wind turbine is any one of the multiple wind turbines.

[0040] A computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to execute the steps of the above-mentioned risk prediction method for wind power plants under extreme weather conditions.

[0041] A terminal device includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the risk prediction method for wind power plants under extreme weather conditions.

[0042] The present invention provides a risk prediction method, device, medium and equipment for wind power plants under extreme weather conditions. By acquiring the video, wind speed and wind direction data of each wind turbine generator set, a matching model is used to determine whether the rotation of the wind rotor meets the expectations of the current wind speed and wind direction, thereby quickly identifying possible operating abnormalities. When it is detected that the rotation of the wind rotor does not match the wind speed and wind direction, the current weather conditions are further analyzed and future weather changes are predicted, and the potential risk types are estimated in combination with this data. This solution realizes dynamic monitoring and accurate prediction of wind farms under extreme weather conditions, can effectively avoid risks, and avoid reduced power generation efficiency due to failure to detect faults in a timely manner, thereby ensuring the safety and continuous operation of wind farms. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] in:

[0045] Figure 1 A flowchart of the risk prediction method for wind power plants under extreme weather conditions;

[0046] Figure 2 It is a schematic diagram of the structure of a risk prediction device for a wind power plant under extreme weather conditions;

[0047] Figure 3 This is a structural block diagram of the terminal equipment. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0049] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. 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 limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0050] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0051] like Figure 1 As shown, Figure 1 The flowchart of a risk prediction method for a wind power plant under extreme weather conditions in one embodiment is shown. The wind power plant includes a plurality of wind turbines in specific geographical locations or within a defined range. The steps provided by the risk prediction method for a wind power plant under extreme weather conditions in this embodiment include:

[0052] S101, obtaining video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period.

[0053] The video data records the rotation of the wind turbine rotor, such as the speed of the wind turbine rotor, the rotation time of the wind turbine rotor, etc. The wind speed data can reflect the wind speed in the area where the wind turbine generator set is located. The wind direction data can reflect the wind direction in the area where the wind turbine generator set is located.

[0054] For example, an independent high-definition camera, wind speed sensor and wind direction sensor are installed on each wind turbine generator set, so that each unit has a separate data acquisition device. The camera records the image data of the wind rotor rotation for 5 minutes each time, while the wind speed sensor collects wind speed data and the sensor collects wind direction data, which are then transmitted together to the monitoring system of the wind farm for subsequent analysis.

[0055] S102: Determine whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and wind direction data through a preset matching model.

[0056] The preset matching model is a comparison model based on the wind rotor rotation, wind speed and wind direction data, which is used to determine whether the wind turbine generator set is operating normally.

[0057] Optionally, by analyzing historical data or designing standards, the expected values ​​and allowable error ranges of the wind rotor speeds at different wind speeds and wind directions are set. The current wind rotor speed is compared with this threshold range to determine whether it meets the standard. For example, assuming that the wind speed is 10 m / s and the wind direction is southwest (225°), the matching model expects the wind rotor speed to be 20±2 rpm. If the currently detected wind rotor speed is 18 to 22 rpm, it meets the threshold, otherwise it is considered abnormal. This method is easy to implement and can monitor wind turbines through simple range judgments, effectively identifying situations where the speed deviates from the normal value, thereby detecting abnormalities in a timely manner.

[0058] Optionally, a machine learning algorithm is used, which determines whether the current wind rotor rotation condition matches the input real-time wind speed and wind direction data. Exemplarily, a reasonable range of wind rotor rotation under different wind speeds and wind directions is established through support vector machine model training. After the real-time data is input, the model determines whether the wind rotor speed deviates from the reasonable range, and triggers an alarm if it deviates.

[0059] If there is a mismatch between the rotor rotation of the first wind turbine generator set and the wind speed data and wind direction data, then S103 is executed. If the rotor rotation of all first wind turbine generator sets matches the wind speed data and wind direction data, then S104 is executed and the process ends. The first wind turbine generator set is any one of the multiple wind turbine generator sets.

[0060] S103, obtaining the current weather condition at the location of the first wind turbine generator set from the video data, predicting the future weather condition based on the current weather condition, and estimating the risk type of the wind power plant according to the future weather condition.

[0061] The current weather conditions refer to the real-time weather conditions at the location of the wind turbine, usually including wind speed, wind direction, precipitation (rain or snow), haze, etc. The future weather conditions are the predictions of the current weather conditions in the future. The risk type refers to the specific risk category that the future weather conditions may cause to the wind turbine, such as rotor overload, frost damage, structural damage, etc. Different risk types have different impacts on wind turbines, and corresponding risk prevention measures are required.

[0062] Optionally, video image processing technology is used to analyze the current weather conditions around the wind turbine in the video in real time. For example, the visibility, precipitation type and intensity in the image can be used to determine the current weather conditions. If the visibility around the wind turbine is significantly reduced as detected by the video, combined with the wind speed data, it indicates that the wind speed has increased. The system can determine that the current weather may be caused by a blizzard, predict the risk of wind rotor icing, and propose countermeasures such as shutdown or preheating.

[0063] Optionally, in a specific embodiment, the current weather conditions are input into the LSTM prediction model to predict future weather conditions, and a decision tree is used to classify the risk type of the wind power plant according to the future weather conditions. Exemplarily, the currently collected weather condition data such as wind speed, temperature and humidity are input into the LSTM model to predict the future weather conditions in the next 30 minutes. The future weather conditions are then input into the decision tree. When the future wind speed predicted by the LSTM exceeds 15 meters per second, the decision tree determines that there may be a risk of "wind rotor overspeeding" and recommends taking deceleration measures for the wind turbine.

[0064] The above-mentioned risk prediction method for wind power plants under extreme weather conditions obtains the video, wind speed and wind direction data of each wind turbine, and uses the matching model to determine whether the rotation of the wind rotor meets the expectations of the current wind speed and wind direction, thereby quickly identifying possible operating abnormalities. When it is detected that the rotation of the wind rotor does not match the wind speed and wind direction, the current weather conditions are further analyzed and future weather changes are predicted, and the potential risk types are estimated based on this data. This solution realizes dynamic monitoring and accurate prediction of wind farms under extreme weather conditions, which can effectively avoid risks and avoid the reduction of power generation efficiency due to failure to detect faults in time, thereby ensuring the safety and continuous operation of wind farms.

[0065] Optionally, S102 determines whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and the wind direction data through a preset matching model, which specifically includes the following steps:

[0066] A1. The rotation of the wind rotor of each wind turbine generator set is divided into discrete wind rotor states through an optical flow algorithm, and the wind speed data of each wind turbine generator set is divided into discrete wind speed states, and the wind direction data of each wind turbine generator set is divided into discrete wind direction states.

[0067] Among them, the optical flow algorithm is an algorithm used to analyze the movement of objects in a video image sequence, and can identify the direction and speed of movement of objects in the image. Applied in the video monitoring of wind turbines, the optical flow algorithm can capture the rotation speed of the wind rotor blades. The wind rotor state includes low speed, medium speed and high speed. For example, the wind rotor speed is defined as low speed when it is less than or equal to 10 revolutions per minute, the wind rotor speed is defined as medium speed when it is greater than 10 revolutions per minute and less than 20 revolutions per minute, and the wind rotor speed is defined as high speed when it is greater than or equal to 20 revolutions per minute.

[0068] Wind speed conditions include low wind speed, medium wind speed and high wind speed. For example, a wind speed below 5 m / s is defined as "low wind speed", 5-15 m / s is defined as "medium wind speed", and above 15 m / s is defined as "high wind speed".

[0069] The wind direction state includes multiple wind direction angle intervals, for example, 0°-30° is defined as the first wind direction state, 30°-60° is defined as the second wind direction state, and so on.

[0070] A2. Obtain a preset state rule set.

[0071] The state rule set includes a plurality of different state rules, each of which is a combination of a wind rotor state, a wind speed state and a wind direction state, and is used to describe the reasonable operating state that the wind rotor should be in under different wind speed and wind direction conditions.

[0072] A3. If the combination of the rotor state, wind speed state and wind direction state of the first wind turbine generator set belongs to the state rule set, it is determined that the rotor rotation condition of the first wind turbine generator set matches the wind speed data and wind direction data; if the combination of the rotor state, wind speed state and wind direction state of the first wind turbine generator set does not belong to the state rule set, it is determined that the rotor rotation condition of the first wind turbine generator set does not match the wind speed data and wind direction data.

[0073] Exemplarily, assume that the status rule set contains the following rules: Rule 1: The wind rotor state is medium wind speed, the wind speed state is medium wind speed, and the wind direction state is 30°-60°. Rule 2: The wind rotor state is high speed, the wind speed state is high wind speed, and the wind direction state is 60°-90°. If the real-time data combination is: the wind rotor state is medium wind speed, the wind speed state is medium wind speed, and the wind direction is 45°, the system will match Rule 1, and therefore determine that the wind rotor is operating normally. If the real-time data combination is: the wind rotor state is low wind speed, the wind speed state is medium wind speed, and the wind direction state is 45°, it is not in the rule set, and the system determines that the wind rotor is operating abnormally and issues an early warning.

[0074] In this way, through state combination matching, abnormal situations where the wind rotor speed, wind speed and wind direction do not match can be quickly identified, which helps to locate potential mechanical failures or operating deviations.

[0075] Optionally, step A2 of obtaining a preset state rule set specifically includes the following steps:

[0076] A21. Obtain multiple sets of sample data.

[0077] Each set of sample data includes sample rotor rotation conditions, sample wind speed data and sample wind direction data of a wind turbine generator set under risk-free conditions. These sample data should cover the rotor rotation conditions, wind speeds and wind directions under various normal conditions so as to represent different operating states under risk-free conditions.

[0078] A22. The sample wind rotor rotation conditions of each wind turbine generator set are divided into discrete wind rotor states through the optical flow algorithm, and the sample wind speed data of each wind turbine generator set is divided into discrete wind speed states, and the sample wind direction data of each wind turbine generator set is divided into discrete wind direction states, so as to obtain multiple state sets.

[0079] It can be understood that the logic of step A22 is basically the same as that of step A1, and the only difference is that sample data is output here, so it will not be described in detail.

[0080] A23. Generate multiple i-th state sets, calculate the frequency share of each i-th state set, and retain the state sets whose frequency share is greater than a preset frequency share threshold as candidate state rules.

[0081] Among them, the i-th state set includes i of the wind rotor state, wind speed state and wind direction state, and the initial value of i is 1. That is to say, the initial state set contains only one state (such as wind rotor state or wind speed state). The frequency ratio represents the frequency ratio of each state set in the risk-free sample data. The frequency ratio is used to judge the representativeness of a certain state combination in the risk-free situation.

[0082] Optionally, calculate the frequency percentage of each i-th state set, expressed as:

[0083]

[0084] In the above formula, FR(x) represents the frequency ratio of state set x, N x represents the total number of state sets x included in multiple state sets, and T represents the total number of all state sets.

[0085] Furthermore, for each i-th state set, if its frequency proportion is greater than a preset frequency proportion threshold, it is retained as a candidate state rule. The setting of the frequency proportion threshold can be adjusted according to the actual situation of the wind farm, and representative data is usually screened out from common state combinations.

[0086] A24. Set i=i+1, and return to execute A23 and subsequent steps until the number of candidate state rules no longer increases.

[0087] In this embodiment, let i=3, generate a ternary state combination (wind rotor state+wind speed state+wind direction state), and no new rules are generated after screening. At this time, because the new combination no longer increases the number of candidate state rules, the iteration ends and the final state rule set is generated.

[0088] A25. Split each candidate state rule into a first sub-state set and a second sub-state set. In each candidate state rule, calculate the joint probability and the correlation coefficient between the first sub-state set and the second sub-state set, and retain all candidate state rules whose joint probability is greater than a preset joint probability threshold and whose correlation coefficient is greater than a preset correlation coefficient threshold as the state rule set.

[0089] For example, assuming that a candidate state rule "wind rotor state = high rotation speed, wind speed state = high wind speed, wind direction state = first wind direction state" can be split into: first sub-state set: "wind rotor state = high rotation speed, wind speed state = high wind speed" second sub-state set: "wind direction state = wind direction state". Of course, it can also be split into other forms, and of course, the same splitting can be performed on other candidate state rules.

[0090] Then calculate the joint probability and correlation coefficient between the first sub-state set and the second sub-state set. The joint probability refers to the probability that the first sub-state set and the second sub-state set appear simultaneously in the risk-free sample data. The high or low joint probability reflects the coexistence relationship of the two sub-state sets in the risk-free state. The correlation coefficient indicates the strength of the correlation between the first sub-state set and the second sub-state set. The correlation coefficient can be used to measure whether the two sub-state sets have a significant correlation.

[0091] Optionally, the joint probability is calculated as:

[0092]

[0093] In the above formula, JP(ab) represents the joint probability between the first sub-state set a and the second sub-state set b;

[0094] The calculation formula of the correlation coefficient is:

[0095]

[0096] In the above formula, AC(ab) represents the correlation coefficient between the first sub-state set a and the second sub-state set b.

[0097] Only when the joint probability and the correlation coefficient are both greater than the corresponding preset thresholds, the candidate state rule will be retained, ensuring that the selected state rule set is highly representative.

[0098] Optionally, infrared sensors are set up around the periphery of the wind power plant. The infrared sensors are installed in the peripheral area of ​​the wind power plant to ensure coverage of key entrances and exits or safe areas near the units to detect possible external threats (such as people approaching equipment, animals or obstacles entering risk areas, etc.). The above method can also perform the following steps: when the sensor detects an abnormal heat source, a trigger signal is generated and a command is sent to the monitoring system to indicate that there is abnormal activity near the equipment. Under the premise that the system has detected other risks, the triggering of the infrared signal will further activate the early warning reminder and notify the operation and maintenance personnel.

[0099] Optionally, the above method may further perform the following steps:

[0100] B1. Collect historical data.

[0101] The historical data include video data, wind speed data and wind direction data of wind turbines in extreme weather conditions, which serve as the basic data set for subsequent model building.

[0102] B2. Establish risk models based on historical data.

[0103] Among them, the risk model defines the threshold range of normal operation and abnormal operation of wind turbines, as well as the risk types under different abnormal operation conditions. Specifically, the data characteristics of wind turbines under normal and abnormal conditions are analyzed based on the collected historical data to form a risk model. The model defines the numerical thresholds of wind turbines in normal operation and different abnormal conditions, and identifies the risk types corresponding to abnormal conditions, such as overspeed, mechanical failure, etc.

[0104] B3. The video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period are compared as real-time data with the threshold range defined in the risk model. When the real-time data exceeds the threshold range, a risk warning signal is generated.

[0105] In this way, the risk model constructed through historical data can more accurately define normal and abnormal conditions and reduce false alarms caused by fluctuations in individual data.

[0106] In one embodiment, Figure 2 As shown, a risk prediction device for a wind power plant under extreme weather conditions is proposed, the device comprising:

[0107] The data acquisition module 201 is used to acquire the video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period; wherein the video data records the rotation of the wind turbine rotor of the wind turbine generator set;

[0108] The data matching module 202 is used to determine whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and the wind direction data through a preset matching model;

[0109] The risk assessment module 203 is used to obtain the current weather conditions at the location of the first wind turbine from the video data if there is a mismatch between the rotor rotation of the first wind turbine and the wind speed data and wind direction data, predict the future weather conditions based on the current weather conditions, and estimate the risk type of the wind power plant based on the future weather conditions; wherein the first wind turbine is any one of the multiple wind turbines.

[0110] Figure 3 FIG. 2 shows an internal structure diagram of a terminal device in an embodiment. Figure 3 As shown, the terminal device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the terminal device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor may implement a risk prediction method for wind power plants under extreme weather conditions. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor may implement a risk prediction method for wind power plants under extreme weather conditions. Those skilled in the art will appreciate that Figure 3 The structure shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the terminal device to which the scheme of the present application is applied. The specific terminal device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0111] A computer-readable storage medium stores a computer program, which implements the following steps when executed by a processor: obtaining video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period; wherein the video data records the rotation of the wind rotor of the wind turbine generator set; judging whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and wind direction data through a preset matching model; if there is a mismatch between the rotation of the wind rotor of the first wind turbine generator set and the wind speed data and wind direction data, obtaining the current weather condition of the location of the first wind turbine generator set from the video data, predicting the future weather condition based on the current weather condition, and estimating the risk type of the wind power plant according to the future weather condition; wherein the first wind turbine generator set is any one of a plurality of wind turbine generator sets.

[0112] A terminal device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: obtaining video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period; wherein the video data records the rotation of the wind rotor of the wind turbine generator set; judging whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and wind direction data through a preset matching model; if there is a mismatch between the rotation of the wind rotor of the first wind turbine generator set and the wind speed data and wind direction data, obtaining the current weather condition of the location of the first wind turbine generator set from the video data, predicting the future weather condition based on the current weather condition, and estimating the risk type of the wind power plant according to the future weather condition; wherein the first wind turbine generator set is any one of a plurality of wind turbine generator sets.

[0113] It should be noted that the above-mentioned risk prediction method, device, equipment and computer-readable storage medium for wind power plants under extreme weather conditions belong to a general inventive concept, and the contents of the embodiments of the risk prediction method, device, equipment and computer-readable storage medium for wind power plants under extreme weather conditions are applicable to each other.

[0114] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0115] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0116] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A risk prediction method for a wind power plant under extreme weather conditions, characterized in that: The wind power plant comprises a plurality of wind turbine generator sets, and the method comprises: Obtaining video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period; wherein the video data records the rotation of the wind rotor of the wind turbine generator set; The preset matching model is used to determine whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and wind direction data; If there is a mismatch between the rotor rotation of the first wind turbine and the wind speed data and wind direction data, the current weather conditions at the location of the first wind turbine are obtained from the video data, the future weather conditions are predicted based on the current weather conditions, and the risk type of the wind power plant is estimated based on the future weather conditions; wherein the first wind turbine is any one of the multiple wind turbines.

2. The method according to claim 1, characterized in that The determining whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and the wind direction data by using a preset matching model includes: The rotation of the wind rotor of each wind turbine generator set is divided into discrete wind rotor states by an optical flow algorithm, and the wind speed data of each wind turbine generator set is divided into discrete wind speed states, and the wind direction data of each wind turbine generator set is divided into discrete wind direction states; wherein the wind rotor state includes low speed, medium speed and high speed, the wind speed state includes low wind speed, medium wind speed and high wind speed, and the wind direction state includes multiple wind direction angle intervals; Obtaining a preset state rule set; wherein the state rule set includes a plurality of different state rules, each state rule being a combination of a wind rotor state, a wind speed state, and a wind direction state; If the combination of the rotor state, wind speed state and wind direction state of the first wind turbine generator set belongs to the state rule set, it is determined that the rotor rotation condition of the first wind turbine generator set matches the wind speed data and wind direction data; if the combination of the rotor state, wind speed state and wind direction state of the first wind turbine generator set does not belong to the state rule set, it is determined that the rotor rotation condition of the first wind turbine generator set does not match the wind speed data and wind direction data.

3. The method according to claim 2, characterized in that The step of obtaining a preset state rule set includes: Acquire multiple groups of sample data; wherein each group of sample data includes a sample wind rotor rotation condition, sample wind speed data, and sample wind direction data of a wind turbine generator set under a risk-free condition; By using an optical flow algorithm, the sample wind rotor rotation conditions of each wind turbine generator set are divided into discrete wind rotor states, the sample wind speed data of each wind turbine generator set are divided into discrete wind speed states, and the sample wind direction data of each wind turbine generator set are divided into discrete wind direction states, so as to obtain a plurality of state sets; Generate multiple i-th state sets, calculate the frequency proportion of each i-th state set, and retain the state set whose frequency proportion is greater than a preset frequency proportion threshold as a candidate state rule; wherein the i-th state set includes i of the wind rotor state, wind speed state and wind direction state, and the initial value of i is 1; Let i=i+1, and return to execute the step of generating multiple i-th state sets and subsequent steps until the number of candidate state rules no longer increases; Each candidate state rule is split into a first sub-state set and a second sub-state set. Within each candidate state rule, the joint probability and the correlation coefficient between the first sub-state set and the second sub-state set are calculated, and all candidate state rules whose joint probability is greater than a preset joint probability threshold and whose correlation coefficient is greater than a preset correlation coefficient threshold are retained as the state rule set.

4. The method according to claim 3, characterized in that The frequency ratio of each i-th state set is calculated as: In the above formula, FR(x) represents the frequency ratio of state set x, N x represents the total number of state sets x included in the multiple state sets, and T represents the total number of all state sets; The formula for calculating the joint probability is: In the above formula, JP(ab) represents the joint probability between the first sub-state set a and the second sub-state set b; The calculation formula of the correlation coefficient is: In the above formula, AC(ab) represents the correlation coefficient between the first sub-state set a and the second sub-state set b.

5. The method according to claim 1, characterized in that The predicting of future weather conditions based on the current weather conditions, and estimating the risk type of the wind power plant according to the future weather conditions, includes: The current weather conditions are input into the LSTM prediction model to predict future weather conditions, and a decision tree is used to classify the risk type of the wind power plant according to the future weather conditions.

6. The method according to claim 1, characterized in that An infrared sensor is arranged at the periphery of the wind power plant, and the method further comprises: Under the premise that there is a risk in the wind power plant, if an instruction indicating being triggered by induction is received from the infrared sensor, an early warning reminder is issued.

7. The method according to claim 1, characterized in that The method further comprises: Collecting historical data; wherein the historical data includes video data, wind speed data and wind direction data of wind turbines under extreme weather conditions; Establishing a risk model based on the historical data; wherein the risk model defines the threshold range of normal operating state and abnormal operating state of the wind turbine generator set, and the risk types under different abnormal operating states; The video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period are compared as real-time data with the threshold range defined in the risk model. When the real-time data exceeds the threshold range, a warning signal indicating the existence of a risk is generated.

8. A risk prediction device for a wind power plant under extreme weather conditions, characterized in that: The risk prediction device for a wind power plant under extreme weather conditions comprises: A data acquisition module, used to acquire video data, wind speed data and wind direction data of each wind turbine generator set within a preset time period; wherein the video data records the rotation of the wind rotor of the wind turbine generator set; A data matching module is used to determine whether the rotation of the wind rotor of each wind turbine generator set matches the wind speed data and wind direction data through a preset matching model; A risk assessment module is used to obtain the current weather conditions at the location of the first wind turbine from the video data if there is a mismatch between the rotation of the rotor of the first wind turbine and the wind speed data and wind direction data, predict the future weather conditions based on the current weather conditions, and estimate the risk type of the wind power plant based on the future weather conditions; wherein the first wind turbine is any one of the multiple wind turbines.

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A terminal device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 7.

Images