Fan blade damage early warning method, device, equipment, medium and program product
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ENVISION DIGITAL INT PTE LTD
- Filing Date
- 2022-10-27
- Publication Date
- 2026-07-21
Smart Images
Figure CN115681019B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of software technology, and in particular to a method, device, equipment, medium, and program product for early warning of wind turbine blade damage. Background Technology
[0002] Wind power generation technology is the technology of converting wind energy into electrical energy. It uses wind power to drive the wind turbine blades to rotate, and the rotation of the wind turbine blades drives the generator to generate electricity.
[0003] In the process of wind power generation, the role of wind turbine blades is very important, as they determine the wind-catching ability of wind power generation equipment and thus affect the power generation efficiency of wind power generation equipment.
[0004] Therefore, timely maintenance of wind turbine blades is of great importance, especially during thunderstorms, when wind turbine blades may be struck by lightning, resulting in lightning damage. Summary of the Invention
[0005] This application provides a method, apparatus, equipment, medium, and program product for early warning of wind turbine blade damage. The technical solution is as follows:
[0006] According to one aspect of this application, a method for early warning of wind turbine blade damage is provided, the method comprising:
[0007] Lightning strike signals are collected using a lightning sensor;
[0008] In response to the lightning sensor collecting the lightning strike signal, the sound acquisition period is switched from the first period to the second period, the duration of the second period being shorter than the duration of the first period;
[0009] The sound sensor is controlled to collect the sound of the wind turbine blades running according to the second cycle, so as to obtain a sound signal of at least one cycle;
[0010] Analyze the sound signal of at least one cycle to determine the casing condition of the wind turbine blades;
[0011] In response to the condition of the casing indicating that the wind turbine blades have been damaged by lightning, a warning signal is issued.
[0012] According to another aspect of this application, a wind turbine blade damage early warning device is provided, the device comprising:
[0013] The first acquisition module is used to acquire lightning strike signals through a lightning sensor;
[0014] A switching module is used to switch the sound acquisition cycle from a first cycle to a second cycle in response to the lightning sensor acquiring the lightning strike signal, wherein the cycle duration of the second cycle is shorter than the cycle duration of the first cycle.
[0015] The second acquisition module is used to control the sound sensor to acquire the sound of the wind turbine blades running according to the second cycle, so as to obtain at least one cycle of sound signal;
[0016] The identification module is used to analyze the sound signal of at least one cycle to determine the casing condition of the wind turbine blades;
[0017] The early warning module is used to issue an early warning signal in response to the condition of the casing indicating that the wind turbine blades have been damaged by lightning.
[0018] According to another aspect of this application, a wind turbine blade inspection device is provided, wherein the wind turbine blade inspection includes:
[0019] A lightning sensor is configured to collect lightning strike signals;
[0020] A sound sensor is configured to collect sound signals during the operation of the wind turbine blades;
[0021] The memory connected to the lightning sensor and the sound sensor respectively is configured to store executable instructions and to store the lightning strike signal and the sound signal;
[0022] Furthermore, a processor connected to the memory is configured to load and execute the executable instructions to implement a wind turbine blade damage early warning method as provided in various aspects of this application.
[0023] According to another aspect of this application, a computer program product (or computer program) is provided, the computer program product (or computer program) including computer instructions stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform the method provided in various optional implementations of the above-described wind turbine blade damage early warning method.
[0024] According to another aspect of this application, a chip is provided, the chip including programmable logic circuitry and / or program instructions, which, when the chip is running, are used to implement a wind turbine blade damage early warning method as provided in various aspects of this application.
[0025] The beneficial effects of the technical solutions provided in this application embodiment may include:
[0026] The wind turbine blade early warning method provided in this application can detect lightning strikes through a lightning sensor during thunderstorms. If a lightning strike signal is collected, there is a possibility that the wind power generation equipment has been struck by lightning. This allows the sound sensor to switch its collection cycle from the first cycle to the second cycle, thereby increasing the frequency of sound collection during wind turbine blade operation and analyzing the condition of the wind turbine blade casing more frequently. When the casing condition indicates that the wind turbine blade has been damaged by lightning, an alarm signal is issued in a timely manner, enabling personnel to take appropriate measures. Attached Figure Description
[0027] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0028] Figure 1 A schematic diagram of an alarm system provided in an exemplary embodiment of this application is shown;
[0029] Figure 2 A flowchart illustrating an exemplary embodiment of the wind turbine blade damage early warning method provided in this application is shown.
[0030] Figure 3 A flowchart illustrating an early warning method for wind turbine blade damage provided in another exemplary embodiment of this application is shown;
[0031] Figure 4 A flowchart illustrating an early warning method for wind turbine blade damage provided in another exemplary embodiment of this application is shown;
[0032] Figure 5 A block diagram of an early warning device for wind turbine blade damage provided in an exemplary embodiment of this application is shown;
[0033] Figure 6 A schematic diagram of the structure of a computer device provided in an exemplary embodiment of this application is shown. Detailed Implementation
[0034] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0035] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0036] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. In the description of this application, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, in the description of this application, unless otherwise stated, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.
[0037] Figure 1 A schematic diagram of an alarm system provided in an exemplary embodiment of this application is shown. The alarm system includes a wind power generation device 120, a wind turbine blade detection device 140, a server 160, and a control console 180.
[0038] The wind power generation equipment 120 includes wind turbine blades 122 and a tower 124. The wind turbine blades 122 are used for wind sweeping, thereby enabling the wind power generation equipment 120 to convert wind energy into electrical energy and store the electrical energy in an energy storage device. The tower 124 is mainly used to support other equipment structures of the wind power generation equipment; for example, the wind turbine blades 122 are connected to the top of the tower 124 via a hub.
[0039] The wind turbine blade inspection device 140 includes a lightning sensor 11, a sound sensor 12, and a controller 13. Exemplarily, the wind turbine blade inspection device 140 is mounted on a tower. Exemplarily, the lightning sensor 11 may be mounted on the top of the tower 124, the sound sensor 12 may be mounted on a tower door, and the controller 13 may be mounted inside the tower. Alternatively, the controller 13 in the wind turbine blade inspection device 140 may be mounted in a separate machine room.
[0040] For example, each wind power generation device 120 is provided with its own controller 13. Alternatively, multiple wind power generation devices 120 may be provided with the same controller 13. For instance, the lightning sensors 11 and sound sensors 12 on multiple wind power generation devices 120 that are close to each other may be controlled by the same controller 13.
[0041] The sound sensor 12 and the lightning sensor 11 are respectively connected to the controller 13, and the connection method can include wired or wireless network connection. Among them, the sound sensor 12 is used to collect the sound signal generated by the air sliding between the blades when the wind turbine blades are swept; the lightning sensor 11 is used to detect lightning strike events; the controller 13 is used for processing lightning strike events and sound signals.
[0042] The wind turbine blade inspection device 140 is connected to the server 160 via a wired or wireless network. For example, the controller 13 is also connected to the server 160 via a wired or wireless network. The controller 13 uploads information about the lightning strike event and various processed data to the server 160, such as the type and extent of damage to the wind turbine blades.
[0043] Server 160 may include at least one of the following: one server 160, multiple servers 160, a cloud computing platform, and a virtualization center.
[0044] Server 160 is also connected to console 180 via a wired or wireless network. For example, console 180 is equipped with input devices, such as at least one of a touchscreen, keyboard, mouse, and physical buttons; console 180 also has a monitor. Console 180 is used for real-time monitoring of the operating status of wind power generation equipment, remote control of wind power generation equipment, and remote control of wind turbine blade inspection equipment. For example, console 180 receives wind turbine blade damage events from server 160, issues alarms for these damage events, and displays information such as the type and extent of damage to the wind turbine blades on the monitor.
[0045] For example, wired networks can be metropolitan area networks, local area networks, fiber optic networks, etc.; wireless networks can be mobile communication networks, wireless Fidelity networks (WiFi), etc.
[0046] For example, the wind turbine blade damage early warning method provided in this application can be implemented in the above system, as follows:
[0047] When the lightning sensor 11 detects a lightning strike, it reports the lightning strike event and lightning current data to the controller 13.
[0048] The controller 13 determines the sound acquisition period based on the lightning current data, thus identifying an acquisition period that matches the lightning current data. For example, the controller 13 determines the acquisition period according to the magnitude of the lightning current: when the lightning current value is less than 10 kA (kiloamperes), the sound acquisition period is determined to be 5 minutes; when the lightning current value is greater than 10 kA but less than 100 kA, the sound acquisition period is determined to be 3 minutes; and when the lightning current value is greater than 100 kA, the sound acquisition period is determined to be 1 minute.
[0049] The controller 13 determines that the acquisition period after the lightning event is the second period, and switches the acquisition period of the sound sensor 12 from the first period to the second period. The duration of the second period is shorter than the duration of the first period.
[0050] The sound sensor 12 collects sound signals according to the second cycle and reports the sound signals of each cycle to the controller 13.
[0051] The controller 13 analyzes the casing condition of the wind turbine blades based on at least one cycle of sound signals. In the event of damage to the wind turbine blades, it analyzes the type and extent of damage, such as lightning strike damage and its extent. The controller then reports the type and extent of damage to the wind turbine blades to the server 160.
[0052] Server 160 sends the damage type and extent of the wind turbine blades to console 180.
[0053] After receiving the damage type and extent of the wind turbine blades, the console 180 issues an alarm to warn of the damage event and displays the damage type and extent of the wind turbine blades on the monitor.
[0054] The damage identification of the wind turbine blades is obtained by the controller 13 through local calculation. In some other embodiments, the controller 13 may also report the sound signal to the server 160, and the server 160 may perform damage identification of the wind turbine blades based on the sound signal.
[0055] Figure 2 This application illustrates a flowchart of an exemplary embodiment of a wind turbine blade damage early warning method, which can be applied to... Figure 1 In the alarm system shown, the method includes:
[0056] Step 210: Collect lightning strike signals using a lightning sensor.
[0057] During thunderstorms, lightning sensors collect lightning strike signals to obtain parameter information about the lightning strike signals. Optionally, the parameter information of the lightning strike signals includes at least one of the following: the current value of the lightning current, the peak value of the lightning current, the total charge of the lightning current, the unit energy of the lightning current, and the steepness of the lightning current.
[0058] The lightning sensor collects lightning strike signals and generates a lightning strike event; the lightning strike event is transmitted to the controller, or the parameter information of the lightning strike event and the lightning strike signal is transmitted to the controller.
[0059] Step 220: In response to the lightning sensor collecting a lightning strike signal, the sound acquisition cycle is switched from the first cycle to the second cycle, and the duration of the second cycle is shorter than the duration of the first cycle.
[0060] In response to a lightning strike event reported by the lightning sensor, the controller switches the sound acquisition cycle from the first cycle to the second cycle.
[0061] Alternatively, in response to a lightning strike event reported by a lightning sensor, the controller switches the sound acquisition period from the first period to the second period based on the parameter information of the lightning strike signal reported by the lightning sensor. For example, the controller has a mapping relationship between signal parameters and periods; in response to the lightning sensor acquiring a lightning strike signal, the controller obtains the parameter information of the lightning strike signal; based on the mapping relationship between signal parameters and periods, it determines the second period corresponding to the parameter information; and switches the sound acquisition period from the first period to the second period.
[0062] For example, the above mapping relationship includes a linear relationship between signal parameters and period. The greater the lightning strike intensity indicated by the signal parameters, the smaller the period in the linear relationship. For instance, when the signal parameter is the current value of the lightning current, the greater the current value of the lightning current, the smaller the period in the linear relationship.
[0063] Optionally, the parameter information of the lightning strike signal includes at least one of the following: the current value of the lightning current, the peak value of the lightning current, the total charge of the lightning current, the unit energy of the lightning current, and the steepness of the lightning current.
[0064] For example, the parameter information of the lightning strike signal includes the current value of the lightning current; the controller, in response to the lightning strike event reported by the lightning sensor, acquires the current value of the lightning current; in response to the current value of the lightning current being greater than a first current threshold and less than a second current threshold, determines the period duration of the second cycle as a first duration; or, in response to the current value of the lightning current being greater than a second current threshold and less than a third current threshold, determines the period duration of the second cycle as a second duration; or, in response to the current value of the lightning current being greater than a third current threshold, determines the period duration of the second cycle as a third duration; wherein, the first current threshold is less than the second current threshold, the second current threshold is less than the third current threshold; and the first duration is greater than the second duration, and the second duration is greater than the third duration.
[0065] For example, the parameter information of the lightning strike signal includes the peak value of the lightning current; the controller, in response to the lightning strike event reported by the lightning sensor, acquires the peak value of the lightning current; in response to the peak value of the lightning current being greater than a first peak threshold and less than a second peak threshold, determines the period duration of the second cycle as a first duration; or, in response to the peak value of the lightning current being greater than a second peak threshold and less than a third peak threshold, determines the period duration of the second cycle as a second duration; or, in response to the peak value of the lightning current being greater than a third peak threshold, determines the period duration of the second cycle as a third duration; wherein, the first peak threshold is less than the second peak threshold, the second peak threshold is less than the third peak threshold; and the first duration is greater than the second duration, and the second duration is greater than the third duration.
[0066] For example, the parameter information of the lightning strike signal includes the total charge of the lightning current; the controller, in response to the lightning strike event reported by the lightning sensor, acquires the total charge of the lightning current; in response to the total charge of the lightning current being greater than a first charge threshold and less than a second charge threshold, determines the period duration of the second cycle as a first duration; or, in response to the total charge of the lightning current being greater than a second charge threshold and less than a third charge threshold, determines the period duration of the second cycle as a second duration; or, in response to the total charge of the lightning current being greater than a third charge threshold, determines the period duration of the second cycle as a third duration; wherein, the first charge threshold is less than the second charge threshold, the second charge threshold is less than the third charge threshold; and the first duration is greater than the second duration, and the second duration is greater than the third duration.
[0067] For example, the parameter information of the lightning strike signal includes the unit energy of the lightning current; the controller, in response to the lightning strike event reported by the lightning sensor, acquires the unit energy of the lightning current; in response to the unit energy of the lightning current being greater than a first energy threshold and less than a second energy threshold, determines the period duration of the second cycle as the first duration; or, in response to the unit energy of the lightning current being greater than the second energy threshold and less than a third energy threshold, determines the period duration of the second cycle as the second duration; or, in response to the unit energy of the lightning current being greater than the third energy threshold, determines the period duration of the second cycle as the third duration; wherein, the first energy threshold is less than the second energy threshold, the second energy threshold is less than the third energy threshold; and the first duration is greater than the second duration, and the second duration is greater than the third duration.
[0068] For example, the parameter information of the lightning strike signal includes the steepness of the lightning current, which refers to the rate of change of the lightning current over time; the controller, in response to the lightning strike event reported by the lightning sensor, acquires the steepness of the lightning current; in response to the lightning current steepness being greater than a first steepness threshold and less than a second steepness threshold, determines the period duration of the second cycle as a first duration; or, in response to the lightning current steepness being greater than a second steepness threshold and less than a third steepness threshold, determines the period duration of the second cycle as a second duration; or, in response to the lightning current steepness being greater than a third steepness threshold, determines the period duration of the second cycle as a third duration; wherein, the first steepness threshold is less than the second steepness threshold, the second steepness threshold is less than the third steepness threshold; and the first duration is greater than the second duration, and the second duration is greater than the third duration.
[0069] It should be noted that the above threshold range can be either left-closed and right-open, or left-open and right-closed; all parameter values are absolute values. Taking a lightning current with a left-closed and right-open threshold range as an example, when the absolute value of the current is less than 10kA, the second cycle after a lightning strike is 5 minutes, meaning the interval between two adjacent sound signal acquisitions is 5 minutes; when the absolute value of the current is greater than or equal to 10kA and less than 100kA, the second cycle after a lightning strike is 3 minutes; when the absolute value of the current is greater than or equal to 100kA, the second cycle after a lightning strike is 1 minute. Alternatively, taking a lightning current with a left-open and right-closed threshold range as an example, when the absolute value of the current is less than or equal to 10kA, the second cycle after a lightning strike is 5 minutes, meaning the interval between two adjacent sound signal acquisitions is 5 minutes; when the absolute value of the current is greater than 10kA and less than or equal to 100kA, the second cycle after a lightning strike is 3 minutes; when the absolute value of the current is greater than 100kA, the second cycle after a lightning strike is 1 minute.
[0070] Step 230: Control the sound sensor to collect the sound of the wind turbine blades running according to the second cycle, and obtain a sound signal of at least one cycle.
[0071] For example, at the next moment after the acquisition period is modified to the second period, the controller controls the sound sensor to collect the sound of the wind turbine blades running according to the second period, so as to detect the health status of the wind turbine blades in a timely manner after a lightning strike event.
[0072] The sound sensor collects the sound of the wind turbine blades running according to the second cycle. After collecting at least one cycle of sound signal, it reports the sound signal of at least one cycle to the controller.
[0073] The aforementioned sound signals include those generated by air sliding between the blades during wind turbine blade sweeping. These sound signals may also include external noise. For example, a processing box is connected to the sound sensor, which transmits the sound signals to the controller. For instance, the sound sensor transmits the collected sound signals to the processing box, which performs noise reduction processing on the sound signals to obtain a denoised sound signal, which is then sent to the controller.
[0074] Step 240: Analyze the sound signal for at least one cycle to determine the condition of the fan blade casing.
[0075] The aforementioned condition of the wind turbine blade casing includes at least one of the following: damage type, damage extent, and damage location. For example, damage type includes lightning strike damage; damage location includes the location of the lightning strike.
[0076] For example, the controller is equipped with a damage identification algorithm that generates a spectrum diagram of at least one cycle of sound signal. The spectrum diagram is input into the damage identification algorithm, which analyzes and identifies the condition of the wind turbine blade casing. For example, the damage identification algorithm may include two modes: a first identification mode and a second identification mode. The first identification mode is for identifying lightning strike damage, used to identify damage to the wind turbine blade when a lightning strike occurs, such as identifying lightning-induced damage such as tip breakage, skin cracking, blade fracture, lightning strike holes on the blade surface, strip skin cracking, wire melting at the tip, and high-temperature expansion. The second identification mode is for identifying other types of damage besides lightning strike damage, used to identify damage to the wind turbine blade when no lightning strike occurs, such as identifying damage such as blade leading-edge corrosion and blade whistling.
[0077] Each time the controller receives at least one cycle of sound signal reported by the sound sensor, it analyzes the sound signal for at least one cycle to determine the condition of the fan blade casing.
[0078] Step 250: In response to the casing condition indicator indicating lightning damage to the wind turbine blades, a warning signal is issued.
[0079] The controller generates a warning signal in response to the casing condition indicating lightning damage to the wind turbine blades. This warning signal is then sent to the control console, which initiates an alarm based on the signal. For example, the controller can first upload the warning signal to a server, which then distributes it to the control console, which in turn initiates an alarm. This warning signal serves to alert personnel that the wind turbine blades have been damaged.
[0080] For example, different levels of damage correspond to different levels of warning signals; in response to the condition of the casing indicating that the wind turbine blades have been damaged by lightning, the degree of damage from the lightning strike is obtained; and a warning signal matching the degree of damage is generated.
[0081] In some embodiments, after generating a warning signal, the controller sends the warning signal and the condition of the wind turbine blade casing to the console. The console then initiates an alarm based on the warning signal and displays the condition of the wind turbine blade casing. For example, the controller uploads the warning signal and the condition of the wind turbine blade casing to a server, which then sends the condition of the wind turbine blade casing to the console. Simultaneously with initiating the alarm, the console displays the condition of the wind turbine blade casing on a monitor, showing information such as whether the wind turbine blade has been damaged by lightning, the extent of the damage, and the location of the damage.
[0082] In other embodiments, the controller may identify other types of damage from the spectrum. These other types of damage refer to damage types other than lightning strike damage, such as at least one of the following: blade protective film cracking, blade leading edge corrosion, blade root fracture, and blade whistling. The controller may also issue a warning signal in response to a casing condition indicating other types of damage to the wind turbine blades. For example, different types of damage correspond to different types of alarm signals; the controller, in response to a casing condition indicating other types of damage to the wind turbine blades, generates a warning signal of a type matching the other types of damage and issues the warning signal.
[0083] In other embodiments, the controller stops the wind turbine in response to a casing condition indication that the turbine blades have been damaged by lightning. That is, upon detection of damage to the turbine blades, the turbine is immediately shut down to prevent further damage.
[0084] In summary, the wind turbine blade early warning method provided in this embodiment can detect lightning strikes through a lightning sensor during thunderstorms. If a lightning strike signal is detected, there is a possibility that the wind power generation equipment has been struck by lightning. This allows the sound sensor's acquisition cycle to be switched from the first cycle to the second cycle, increasing the frequency of sound acquisition during wind turbine blade operation. This enables more frequent analysis of the wind turbine blade casing condition. When the casing condition indicates that the wind turbine blade has been damaged by lightning, an alarm signal is issued in a timely manner, allowing staff to take appropriate action.
[0085] In some embodiments, the controller may employ a preset detection strategy for detecting the health status of wind turbine blades; after a lightning strike event occurs, the controller may adjust the detection strategy. For example, in response to a lightning strike signal collected by a lightning sensor, the controller switches the wind turbine blade detection strategy from a first detection strategy to a second detection strategy. For example, in response to a lightning strike event reported by the lightning sensor, the controller acquires parameter information of the lightning signal; determines the second detection strategy based on the aforementioned parameter information; and switches the detection and measurement of the wind turbine blades from the first detection strategy to the second detection strategy. The first detection strategy is the strategy used to detect the health status of the wind turbine blades before the lightning strike event occurs.
[0086] The above detection strategy includes the acquisition cycle of sound signals during wind turbine blade operation; wherein, the cycle length of the first cycle in the first detection strategy is longer than the cycle length of the second cycle in the second detection strategy.
[0087] The aforementioned detection strategy may further include at least one of the following: the sound signal acquisition duration within each cycle and the sound signal reporting cycle. The reporting cycle refers to the cycle in which the sound sensor reports the sound signal to the controller, and the reporting cycle is an integer multiple of the sound signal acquisition cycle. For example, the first acquisition duration in the first detection strategy is less than or equal to the second acquisition duration in the second detection strategy; the first reporting cycle in the first detection strategy is greater than or equal to the second reporting cycle in the second detection strategy.
[0088] For example, the switching of the above detection strategy can be implemented through steps 220 to 224, and step 230 can be implemented through steps 232 to 234, as follows. Figure 3 As shown, the steps are as follows:
[0089] Step 220: In response to the lightning sensor collecting a lightning strike signal, the sound acquisition cycle is switched from the first cycle to the second cycle.
[0090] The second cycle has a shorter cycle duration than the first cycle.
[0091] Step 222: In response to the lightning sensor collecting a lightning strike signal, the sound collection duration is switched from the first collection duration to the second collection duration.
[0092] After receiving a lightning strike event reported by the lightning sensor, the controller immediately switches the sound acquisition duration from the first acquisition duration to the second acquisition duration. In other words, the default acquisition duration after the lightning strike event is the second acquisition duration.
[0093] Alternatively, in response to a lightning strike event reported by the lightning sensor, the controller determines a second acquisition duration based on the parameter information of the lightning strike signal and switches the sound acquisition duration from the first acquisition duration to the second acquisition duration.
[0094] For example, the controller determines the second acquisition duration corresponding to the parameter information based on the mapping relationship between the signal parameters of the lightning strike signal and the acquisition duration; then, it switches the sound acquisition duration from the first acquisition duration to the second acquisition duration.
[0095] For example, the mapping relationship between the above signal parameters and the acquisition duration includes a one-to-one correspondence between threshold intervals and acquisition durations. For instance, when the signal parameter is the current value of the lightning current, the larger the value of the threshold interval, the longer the acquisition duration corresponding to the threshold interval; or, when the signal parameter is the peak value of the lightning current, the larger the value of the threshold interval, the longer the acquisition duration corresponding to the threshold interval; or, when the signal parameter is the total charge of the lightning current, the larger the value of the threshold interval, the longer the acquisition duration corresponding to the threshold interval.
[0096] For example, the threshold interval division corresponding to the collection duration may be the same as or different from the threshold interval division corresponding to the collection period.
[0097] Step 224: In response to the lightning sensor collecting a lightning strike signal, the reporting period of the sound signal is switched from the first reporting period to the second reporting period.
[0098] After receiving a lightning strike event reported by the lightning sensor, the controller directly switches the reporting cycle of the sound signal from the first reporting cycle to the second reporting cycle. In other words, the default reporting cycle after a lightning strike event is the second reporting cycle.
[0099] Alternatively, in response to a lightning strike event reported by the lightning sensor, the controller determines a second reporting cycle based on the parameter information of the lightning strike signal; and switches the reporting cycle of the sound signal from the first reporting cycle to the second reporting cycle.
[0100] For example, the controller determines the second reporting period corresponding to the parameter information based on the mapping relationship between the signal parameters of the lightning strike signal and the reporting period; then it switches the reporting period of the sound signal from the first reporting period to the second reporting period.
[0101] For example, the mapping relationship between the above signal parameters and the reporting period includes a one-to-one correspondence between threshold intervals and reporting periods. For instance, when the signal parameter is the current value of the lightning current, the larger the value of the threshold interval, the smaller the reporting period corresponding to the threshold interval; or, when the signal parameter is the peak value of the lightning current, the larger the value of the threshold interval, the smaller the reporting period corresponding to the threshold interval; or, when the signal parameter is the total charge of the lightning current, the larger the value of the threshold interval, the smaller the reporting period corresponding to the threshold interval.
[0102] For example, the threshold interval division corresponding to the reporting period may be the same as or different from the threshold interval division corresponding to the collection period, and may be the same as or different from the threshold interval division corresponding to the collection duration.
[0103] Step 232: Control the sound sensor to collect sound signals according to the second cycle to obtain a sound signal with a length of the second collection duration.
[0104] The sound sensor collects sound signals according to a second cycle, and within each cycle, it collects sound signals for a length equal to the second collection duration. For example, if the second cycle is 3 minutes and the second collection duration is 43 seconds, the sound sensor collects sound signals once every 3 minutes, and each time it continuously collects sound signals for 43 seconds.
[0105] Step 234: Report at least one cycle of the sound signal to the controller according to the second reporting cycle.
[0106] The sound sensor reports at least one cycle of sound signal to the controller according to the second reporting cycle. For example, if the second cycle is 3 minutes and the second reporting cycle is 9 minutes, the sound sensor reports once every 3 sound signals collected, and reports three cycles of sound signal to the controller.
[0107] In summary, the wind turbine blade damage early warning method provided in this embodiment improves the detection frequency of wind turbine blade damage by adjusting the sound signal acquisition cycle, acquisition duration, and reporting cycle. This enables timely detection of wind turbine blade damage after a lightning strike, thereby allowing for the development of more reasonable response strategies.
[0108] The controller analyzes the sound signal using a damage recognition algorithm. For example, step 240 in the above embodiment can be implemented using steps 242 to 244. Figure 4 As shown, with Figure 2 Taking the illustrated embodiment as an example, the steps are as follows:
[0109] Step 242: Generate a spectrogram of the sound signal for at least one cycle.
[0110] The controller performs a short-time Fourier transform on the sound signal of at least one cycle to obtain a spectrum of the sound signal. For example, the spectrum may contain information about the sound amplitude; for instance, different colors may be used to represent the frequency of the sound.
[0111] Step 244: Analyze the signal characteristics of the sound signal on the spectrum diagram, and determine the casing condition of the wind turbine blades based on the signal characteristics.
[0112] Optionally, the controller divides the spectrum region of each wind turbine blade on the spectrum diagram; matches each spectrum region with a reference region diagram, which refers to the spectrum region formed by the sound signal generated when a wind turbine blade with lightning damage is running; in response to the matching of the spectrum region with the reference region diagram, it is determined that the casing condition is that the wind turbine blade has been damaged by lightning.
[0113] The controller is equipped with reference area maps, and there are at least two reference area maps. Different reference area maps contain the same type of lightning damage; for example, reference area... Figure 1 With reference area Figure 2 These are two reference images with different representations, both containing the same type of lightning damage. The types of lightning damage contained within the different reference areas differ; for example, the reference area... Figure 3 With reference area Figure 4 These are two reference images with different representations, each containing different types of lightning damage. Each reference area image may include at least one type of lightning damage.
[0114] For example, for each spectrum region, the controller matches the spectrum region with multiple reference region maps, calculates the feature similarity between the spectrum region and each reference region map, determines the target reference region map whose feature similarity is greater than the similarity threshold, and determines the damage type contained in the target reference region map as the damage type contained in the spectrum region to obtain the damage type of the wind turbine blade. For example, if the target reference region map contains lightning damage, it is determined that the wind turbine blade has lightning damage.
[0115] For example, the controller extracts the shell feature vector from the spectral region, calculates the similarity between the shell feature vector and the damage feature vector of the reference region map, and obtains the feature similarity between the spectral region and the reference region map; the damage feature vector is the feature vector characterizing the wind turbine blade damage in the reference region map. The damage feature vector and the shell feature vector are obtained using the same extraction method. The damage feature vector can be pre-extracted, and during the similarity calculation process, the controller can directly retrieve the damage feature vector from memory.
[0116] Optionally, the controller divides the spectrum region of each wind turbine blade on the spectrum diagram to generate a spectrum diagram after region division; the spectrum diagram after region division is input into the damage identification model, and the damage identification model extracts features for each spectrum region to obtain the signal features of each spectrum region; the damage identification model identifies the signal features and outputs the shell condition of the wind turbine blade.
[0117] Optionally, the controller inputs the spectrum into the damage identification model, extracts features from the spectrum through the damage identification model to obtain the signal features of the spectrum, and identifies the signal features through the damage identification model to output the casing condition of the wind turbine blades.
[0118] For example, the damage identification model described above can classify based on signal features to obtain the damage type of the wind turbine blade; or, the damage identification model can match the signal features with the feature vectors of each type of damage to obtain the damage type of the wind turbine blade.
[0119] For example, the loss recognition model described above was trained using machine learning.
[0120] For example, the above-mentioned division of the spectrum region can be achieved by the following steps:
[0121] 21) Use signal analysis algorithms to extract the signal envelope from the time-domain signal graph formed by the sound signal.
[0122] The controller extracts the signal envelope from the time-domain signal graph formed by the sound signal. The signal envelope is a curve that is tangent to each line of the family of curves in the time-domain signal graph at at least one point. The position of the trough in the signal envelope in the time domain is determined as the split point.
[0123] The signal analysis algorithm described above is used to analyze and obtain the signal envelope from the time-domain signal graph of an audio signal. For example, the signal analysis algorithm may include a transformation function, such as the Hilbert transformation function. Optionally, the backend server extracts the signal envelope from the time-domain signal graph using the Hilbert transformation function.
[0124] 22) The location of the trough in the signal envelope in the time domain is determined as the split point.
[0125] 23) Convert the sound signal into a spectrum diagram, and divide the spectrum diagram according to the division points to obtain the spectrum region of each wind turbine blade.
[0126] For example, the sound signal is converted into a spectrum diagram using a short-time Fourier transform or a Laplace transform. The spectrum diagram is then divided along the time axis according to the division points to obtain the spectral region of the wind turbine blade. Specifically, the spectral region between two adjacent division points on the spectrum diagram indicates the spectrum of a wind turbine blade during sweeping.
[0127] In summary, the wind turbine blade damage early warning method provided in this embodiment issues an alarm after accurately determining the wind turbine blade damage based on the spectrum diagram, so as to remind the staff to take appropriate measures in a timely manner.
[0128] In some embodiments, the casing condition of the wind turbine blades can also be used to indicate whether the wind turbine blades are damaged or not; the controller can also issue a warning light signal in response to the casing condition indicating that the wind turbine blades are damaged. The warning signal is used to warn of lightning damage to the wind turbine blades. It should be noted that damage detected after a lightning strike can be considered lightning damage by default.
[0129] The controller can detect whether there is damage to the fan blades using the following steps:
[0130] 31) Divide the spectrum region of each wind turbine blade on the spectrum diagram and generate the spectrum diagram after region division.
[0131] The division of the above-mentioned spectrum region can be referred to steps 21 to 23, and will not be repeated here.
[0132] 32) Calculate the acoustic spectrum difference factor of the wind turbine blades during sweeping based on the spectrum diagram after regional division.
[0133] The aforementioned acoustic spectrum difference factor represents the degree of damage to the wind turbine blades. Optionally, the acoustic spectrum difference factor during wind turbine blade sweeping can be calculated based on the spectrum diagram after regional division.
[0134] Optionally, the spectrum diagram after region division includes at least two spectral regions. The controller calculates the spectral difference factor based on the above at least two spectral regions, as illustrated in the following steps:
[0135] Step 321: Extract signal peaks in at least two spectral regions.
[0136] Step 322: Calculate the time-domain factor and frequency-domain factor of the sound signal based on the signal peak values in at least two spectral regions.
[0137] The wind power generation equipment is equipped with m wind turbine blades; optionally, the controller calculates the time-domain factor of the sound signal by first determining the median of the signal peaks in at least two spectral regions corresponding to each wind turbine blade; secondly, determining the maximum peak value and the minimum peak value from the m medians corresponding to the m wind turbine blades; and finally, determining the ratio of the maximum peak value to the minimum peak value as the time-domain factor.
[0138] For example, a wind turbine blade includes three blades. If the selected curve includes 25 frequency spectrum regions, the controller determines a signal peak in each frequency spectrum region, resulting in a total of 25 signal peaks. Among these, 9 signal peaks correspond to wind turbine blade A, 8 signal peaks correspond to wind turbine blade B, and 8 signal peaks correspond to wind turbine blade C. The controller determines the corresponding medians a, b, and c from the signal peaks of wind turbine blades A, B, and C, respectively. From the medians a, b, and c, the controller determines the maximum and minimum peak values. Finally, the ratio of the maximum peak value to the minimum peak value is determined as the time-domain factor. For example, if the maximum peak value is a and the minimum peak value is c, then the time-domain factor is a / c.
[0139] Optionally, the controller calculates the frequency domain factor of the audio signal by first obtaining the maximum peak value among the signal peak values in each of the m adjacent spectral regions and determining the maximum peak value as a candidate peak value; and secondly, determining the median of at least two candidate peak values as the frequency domain factor.
[0140] Alternatively, the controller calculates the relative entropy between the signal distribution and the theoretical distribution in the spectrum diagram after the region is divided, i.e., the Kullback-Leibler divergence; secondly, the Kullback-Leibler divergence is determined as a frequency domain factor.
[0141] For example, the controller labels 25 spectral regions from left to right as 1 to 25, and obtains the maximum value of the corresponding signal peaks in adjacent spectral regions 1-3, 2-4, 3-5, ..., 23-25, resulting in a total of 23 signal peaks. The median is determined from the above 23 signal peaks, and this median is a frequency domain factor.
[0142] Furthermore, the controller calculates the KL divergence between the signal distribution in the spectrum diagram after the region is divided and the theoretical signal distribution, and confirms the KL divergence as another frequency domain factor.
[0143] It should be noted that the above-mentioned frequency domain factor is used to represent the distribution characteristics of sound signals in the frequency domain. This application provides the above two methods for calculating the distribution characteristics of sound signals in the frequency domain, but the methods for calculating the distribution characteristics of sound signals in the frequency domain in this application are not limited to the two methods provided above.
[0144] Step 323: The weighted average of the time-domain factor and the frequency-domain factor is determined as the acoustic spectrum difference factor.
[0145] For example, the controller calculates a time-domain factor and two frequency-domain factors, then calculates a weighted average of the time-domain factor and the two frequency-domain factors, and determines the weighted average as the spectral difference factor.
[0146] It should also be noted that the controller also filters the audio signal through a filter to obtain a filtered audio signal, and generates a spectrum diagram based on the filtered audio signal, thereby generating a spectrum difference factor.
[0147] 33) If the acoustic spectrum difference factor is greater than the difference threshold, the shell condition is determined to be that the wind turbine blades are damaged.
[0148] In addition, if the acoustic spectrum difference factor is less than or equal to the difference threshold, the casing condition is determined to be that the wind turbine blades are not damaged.
[0149] In summary, the wind turbine blade damage identification method provided in this embodiment can determine whether the wind turbine blade is damaged and the degree of damage by calculating the acoustic spectrum difference factor.
[0150] It should be noted that the aforementioned early warning method for wind turbine blade damage can be applied to wind turbine blade inspection equipment; alternatively, the damage identification step in this method can be applied to wind turbine blade inspection equipment, which then transmits the condition of the wind turbine blade casing to the control console, where the early warning signal is generated and displayed. Furthermore, for a certain period after a lightning strike, the wind turbine blade inspection equipment uses a second cycle, a second data acquisition duration, and a second reporting cycle to monitor the health status of the wind turbine blades. After this period, it reverts to the default detection strategy.
[0151] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.
[0152] Figure 5 This illustration shows a structural block diagram of a wind turbine blade damage early warning device provided in an exemplary embodiment of this application. This wind turbine blade damage early warning device can be implemented as all or part of a wind turbine blade detection device through software, hardware, or a combination of both. The device includes:
[0153] The first acquisition module 410 is used to acquire lightning strike signals through a lightning sensor;
[0154] The switching module 420 is used to switch the sound acquisition cycle from a first cycle to a second cycle in response to the lightning sensor collecting the lightning strike signal, wherein the cycle duration of the second cycle is shorter than the cycle duration of the first cycle.
[0155] The second acquisition module 430 is used to control the sound sensor to acquire the sound of the wind turbine blades running according to the second cycle, so as to obtain at least one cycle of sound signal;
[0156] The identification module 440 is used to analyze the sound signal of at least one cycle to determine the casing condition of the wind turbine blades;
[0157] The early warning module 450 is used to issue an early warning signal in response to the condition of the casing indicating that the wind turbine blades have been damaged by lightning.
[0158] In some embodiments, the switching module 420 is configured to:
[0159] In response to the lightning sensor collecting the lightning strike signal, the parameter information of the lightning strike signal is obtained;
[0160] Based on the mapping relationship between signal parameters and period, the second period corresponding to the parameter information is determined;
[0161] Switch the sound acquisition cycle from the first cycle to the second cycle.
[0162] In some embodiments, the parameter information includes the current value of the lightning current; the switching module 420 is used for:
[0163] In response to the lightning current value being greater than a first current threshold and less than a second current threshold, the duration of the second cycle is determined to be the first duration; or,
[0164] In response to the lightning current value being greater than the second current threshold and less than the third current threshold, the period length of the second cycle is determined to be the second duration; or,
[0165] In response to the lightning current value being greater than the third current threshold, the period duration of the second cycle is determined to be the third duration;
[0166] Wherein, the first current threshold is less than the second current threshold, the second current threshold is less than the third current threshold; and the first duration is greater than the second duration, the second duration is greater than the third duration.
[0167] In some embodiments, the parameter information includes at least one of the following: lightning current value, lightning current peak value, lightning current total charge, lightning current unit energy, and lightning current steepness.
[0168] In some embodiments, the identification module 440 is used for:
[0169] Generate a spectrum diagram of the at least one periodic sound signal;
[0170] Analyze the signal characteristics of the sound signal on the spectrogram;
[0171] The casing condition of the wind turbine blades is determined based on the signal characteristics.
[0172] In some embodiments, the identification module 440 is used for:
[0173] The spectral region of each of the wind turbine blades is divided on the spectrum diagram;
[0174] Each of the aforementioned spectral regions is matched with a reference region map, which refers to the spectral region formed by the sound signal generated when a wind turbine blade with lightning damage is running.
[0175] In response to the matching of the spectral region with the reference region map, the casing condition is determined to be lightning damage to the wind turbine blades.
[0176] In some embodiments, the reference area map includes at least two reference area maps, and the types of lightning damage contained in the different reference area maps may be the same or different.
[0177] In some embodiments, the identification module 440 is used for:
[0178] The spectrum region of each wind turbine blade is divided on the spectrum diagram to generate a spectrum diagram after region division;
[0179] The spectrum map after the region is divided is input into the damage identification model. The damage identification model performs feature extraction for each spectrum region to obtain the signal features of each spectrum region.
[0180] The damage identification model is used to identify the signal features and output the casing condition of the wind turbine blades.
[0181] In some embodiments, the housing condition also indicates the location of lightning damage on the wind turbine blades.
[0182] It should be noted that the wind turbine blade damage early warning device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the wind turbine blade damage early warning method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the wind turbine blade damage early warning device and the wind turbine blade damage early warning method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.
[0183] Figure 6 A schematic diagram of a computer device provided in an exemplary embodiment of this application is shown. This computer device can be a wind turbine blade detection device that performs an early warning method for wind turbine blade damage as provided in this application. Specifically:
[0184] Computer device 700 includes a central processing unit (CPU) 701, a system memory 704 including random access memory (RAM) 702 and read-only memory (ROM) 703, and a system bus 705 connecting the system memory 704 and the CPU 701. Computer device 700 also includes a basic input / output system (I / O system) 706 that facilitates information transfer between various devices within the computer, and a mass storage device 707 for storing the operating system 713, application programs 714, and other program modules 715.
[0185] The basic input / output system 706 includes a display 708 for displaying information and an input device 709 for user input, such as a mouse or keyboard. Both the display 708 and the input device 709 are connected to the central processing unit 701 via an input / output controller 710 connected to the system bus 705. The basic input / output system 706 may also include the input / output controller 710 for receiving and processing input from multiple other devices such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 710 also provides output to a display screen, printer, or other types of output devices.
[0186] Mass storage device 707 is connected to central processing unit 701 via a mass storage controller (not shown) connected to system bus 705. Mass storage device 707 and its associated computer-readable media provide non-volatile storage for computer device 700. That is, mass storage device 707 may include computer-readable media (not shown) such as hard disk or compact disc read-only memory (CD-ROM) drive.
[0187] Computer-readable media can include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented using any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include RAM, ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other solid-state storage technologies, CD-ROM, digital versatile optical disc (DVD), or solid-state drives (SSD), other optical storage, magnetic tape cassettes, magnetic tape, disk storage, or other magnetic storage devices. Random access memory can include resistive random access memory (ReRAM) and dynamic random access memory (DRAM). Of course, those skilled in the art will recognize that computer storage media are not limited to the above-mentioned types. The system memory 704 and the mass storage device 707 mentioned above can be collectively referred to as memory.
[0188] According to various embodiments of this application, the computer device 700 can also be connected to a remote computer on a network, such as the Internet, for operation. That is, the computer device 700 can be connected to a network 712 via a network interface unit 711 connected to the system bus 705, or the network interface unit 711 can be used to connect to other types of networks or remote computer systems (not shown).
[0189] The aforementioned memory also includes one or more programs, which are stored in the memory and configured to be executed by the CPU to implement the wind turbine blade damage early warning method described above.
[0190] This application embodiment also provides a wind turbine blade testing device, the wind turbine blade testing device comprising:
[0191] A lightning sensor is configured to collect lightning strike signals;
[0192] A sound sensor is configured to collect sound signals during the operation of the wind turbine blades;
[0193] The memory connected to the lightning sensor and the sound sensor respectively is configured to store executable instructions and to store the lightning strike signal and the sound signal;
[0194] Furthermore, a processor connected to the memory is configured to load and execute the executable instructions to implement the wind turbine blade damage early warning method as described in the above embodiments.
[0195] This application also provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the wind turbine blade damage early warning method described in the above embodiments.
[0196] Optionally, the computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), solid-state drives (SSDs), or optical discs, etc. The random access memory may include resistive random access memory (ReRAM) and dynamic random access memory (DRAM).
[0197] This application also provides a computer program product (or computer program) including computer instructions stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the wind turbine blade damage early warning method provided in the above embodiments.
[0198] According to another aspect of this application, a chip is provided, the chip including programmable logic circuits and / or program instructions, which, when the chip is running, are used to implement the wind turbine blade damage early warning method as described in the above embodiments.
[0199] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0200] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.
[0201] The above description is merely an exemplary embodiment that can be implemented in this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
Claims
1. A method for early warning of wind turbine blade damage, characterized in that, The method includes: The sound sensor is controlled to collect the sound of the wind turbine blades during operation according to the first cycle, and a sound signal of at least one cycle is obtained; a first spectrum diagram of the sound signal of at least one cycle is generated, and the first spectrum diagram is input into the damage identification algorithm. The shell condition of the wind turbine blade is identified by the second identification mode of the damage identification algorithm; the second identification mode is a mode for identifying other types of damage besides lightning strike damage, and is used to identify blade leading edge corrosion and blade whistling when no lightning strike event has occurred. Lightning strike signals are collected using a lightning sensor; In response to the lightning strike signal collected by the lightning sensor, the detection strategy for the wind turbine blades is switched from a first detection strategy to a second detection strategy. The second detection strategy is determined based on the parameter information of the lightning strike signal. The first detection strategy is the detection strategy used to detect the health status of the wind turbine blades before the lightning strike event occurs. The detection strategy includes the acquisition cycle of the sound signal during wind turbine blade operation. The detection strategy also includes at least one of the sound signal acquisition duration and the sound signal reporting cycle within each cycle. The cycle duration of the second cycle in the second detection strategy is less than the cycle duration of the first cycle in the first detection strategy. The sound sensor is controlled to collect the sound of the wind turbine blades running according to the second cycle, so as to obtain a sound signal of at least one cycle; A second spectrogram of the sound signal of at least one cycle is generated, and the second spectrogram is input into the damage identification algorithm. The condition of the wind turbine blade shell is identified by the first identification mode of the damage identification algorithm. The first identification mode is a mode for identifying lightning strike damage, which is used to identify the blade tip explosion, skin cracking, blade breakage, lightning strike hole on the blade surface, strip skin cracking, wire melting in the blade tip, and high temperature expansion caused by lightning strike when a lightning strike occurs. In response to the condition of the casing indicating that the wind turbine blades have been damaged by lightning, a warning signal is issued.
2. The method according to claim 1, characterized in that, The step of switching the detection strategy of the wind turbine blades from the first detection strategy to the second detection strategy in response to the lightning strike signal collected by the lightning sensor includes: In response to the lightning sensor collecting the lightning strike signal, the parameter information of the lightning strike signal is obtained; Based on the mapping relationship between signal parameters and period, the second period corresponding to the parameter information is determined; Switch the sound acquisition cycle from the first cycle to the second cycle.
3. The method according to claim 2, characterized in that, The parameter information includes the current value of the lightning current; Determining the second period corresponding to the parameter information based on the mapping relationship between signal parameters and period includes: In response to the lightning current value being greater than a first current threshold and less than a second current threshold, the duration of the second cycle is determined to be the first duration; or, In response to the lightning current value being greater than the second current threshold and less than the third current threshold, the period length of the second cycle is determined to be the second duration; or, In response to the lightning current value being greater than the third current threshold, the period duration of the second cycle is determined to be the third duration; Wherein, the first current threshold is less than the second current threshold, the second current threshold is less than the third current threshold; and the first duration is greater than the second duration, the second duration is greater than the third duration.
4. The method according to claim 2, characterized in that, The parameter information includes at least one of the following: lightning current value, lightning current peak value, lightning current total charge, lightning current unit energy, and lightning current steepness.
5. The method according to any one of claims 1 to 3, characterized in that, The method further includes: Analyze the signal characteristics of the sound signal on the second spectrogram; The casing condition of the wind turbine blades is determined based on the signal characteristics.
6. The method according to claim 5, characterized in that, The analysis of the signal characteristics of the sound signal on the second spectrogram includes: The spectral region of each of the wind turbine blades is divided on the second spectrogram; Each of the aforementioned spectral regions is matched with a reference region map, which refers to the spectral region formed by the sound signal generated when a wind turbine blade with lightning damage is running. Determining the casing condition of the wind turbine blades based on the signal characteristics includes: In response to the matching of the spectral region with the reference region map, the casing condition is determined to be lightning damage to the wind turbine blades.
7. The method according to claim 6, characterized in that, The reference area map includes at least two, and the types of lightning damage contained in the different reference area maps may be the same or different.
8. The method according to claim 5, characterized in that, The analysis of the signal characteristics of the sound signal on the second spectrogram includes: The spectral region of each wind turbine blade is divided on the second spectrum diagram to generate the second spectrum diagram after region division; The second spectrum map after the region division is input into the damage identification model. The damage identification model performs feature extraction for each spectrum region to obtain the signal features of each spectrum region. Determining the casing condition of the wind turbine blades based on the signal characteristics includes: The damage identification model is used to identify the signal features and output the casing condition of the wind turbine blades.
9. The method according to any one of claims 1 to 3, characterized in that, The condition of the casing also indicates the location of lightning damage on the wind turbine blades.
10. A wind turbine blade damage early warning device, characterized in that, The device includes: The first acquisition module is used to acquire lightning strike signals through a lightning sensor; A switching module is used to switch the sound acquisition cycle from a first cycle to a second cycle in response to the lightning sensor acquiring the lightning strike signal, wherein the cycle duration of the second cycle is shorter than the cycle duration of the first cycle. The second acquisition module is used to control the sound sensor to acquire the sound of the wind turbine blades running according to the second cycle, so as to obtain at least one cycle of sound signal; The identification module is used to analyze the sound signal of at least one cycle to determine the casing condition of the wind turbine blades; The early warning module is used to issue an early warning signal in response to the indication from the casing condition that the wind turbine blades have been damaged by lightning strikes; The device is used to implement the early warning method for wind turbine blade damage as described in any one of claims 1 to 9.
11. A wind turbine blade testing device, characterized in that, The wind turbine blade testing equipment includes: A lightning sensor is configured to collect lightning strike signals; A sound sensor is configured to collect sound signals during the operation of the wind turbine blades; The memory connected to the lightning sensor and the sound sensor respectively is configured to store executable instructions and to store the lightning strike signal and the sound signal; Furthermore, a processor connected to the memory is configured to load and execute the executable instructions to implement the wind turbine blade damage early warning method as described in any one of claims 1 to 9.
12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program instructions that, when executed by a processor, implement the wind turbine blade damage early warning method as described in any one of claims 1 to 9.
13. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the wind turbine blade damage early warning method as described in any one of claims 1 to 9.