Wind turbine monitoring method and device, wind turbine and storage medium

Abstract

The invention discloses a wind turbine monitoring method and device, a wind turbine and a storage medium, and the method comprises the steps: obtaining real-time data monitored by each voiceprint sensor and each vibration sensor in a current wind turbine, and transmitting the real-time data to a server; according to a preset voiceprint judgment algorithm, judging whether an abnormal voiceprint signal appears in the plurality of voiceprint signals received by each voiceprint sensor; according to a preset vibration judgment algorithm, judging whether an abnormal vibration signal occurs in the plurality of vibration signals received by each vibration sensor; and according to the occurrence conditions of the abnormal voiceprint signal and the abnormal vibration signal, judging whether the current wind turbine has a fault or not. A voiceprint sensor on the wind turbine obtains a voiceprint signal of the blade, a vibration sensor on the wind turbine obtains a vibration signal of the blade, whether the voiceprint signal and the vibration signal are abnormal or not is judged, and whether the current wind turbine breaks down or not and the position where the fault occurs are judged according to the abnormal conditions of the voiceprint signal and the vibration signal.

Description

Technical Field

[0001] The present application relates to the field of wind power technology, and in particular to a wind turbine monitoring method, device, wind turbine and storage medium. Background Art

[0002] As a renewable energy source, wind energy can be converted into electricity through wind turbines, which can reduce the dependence on fossil fuels. The blades are the main energy capture device of wind turbines, and their status directly affects the safety and stability of the entire system. Since the working environment of the blades belongs to the outdoor natural environment, they are affected by the environment during operation, especially lightning, rain, snow, gusts, etc., which may cause damage to the blades and even the wind turbine.

[0003] In the related art, the detection mechanism only detects the signal emitted by the blade at a single specific position, but this detection method requires pre-setting the threshold of the characteristic signal. However, due to the influence of weather and installation environment, the external noise environment of each blade is complex and diverse, resulting in different signal characteristics when the blade fails at different positions. This detection mechanism can only detect some more obvious blade failures with significant characteristics. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a wind turbine monitoring method, device, wind turbine and storage medium, which can monitor the wind turbine and accurately determine the fault of the wind turbine.

[0005] According to the wind turbine of the first aspect embodiment of the present application, the wind turbine includes blades and a tower, and at least one vibration sensor is provided on the surface of the blades; and a plurality of soundprint sensors are provided on the surface of the tower, and each of the soundprint sensors faces a different position of the blades.

[0006] According to some embodiments of the present application, the voiceprint sensors are distributed in a straight line in the vertical direction.

[0007] A wind turbine monitoring method according to a second aspect of the present application is applied to the above-mentioned wind turbine, including:

[0008] Obtain the real-time data monitored by each soundprint sensor and each vibration sensor in the current wind turbine and transmit it to the server;

[0009] According to a preset voiceprint judgment algorithm, judging whether an abnormal voiceprint signal appears in a plurality of voiceprint signals received by each voiceprint sensor;

[0010] According to a preset vibration judgment algorithm, it is judged whether an abnormal vibration signal appears in a plurality of vibration signals received by each vibration sensor;

[0011] Whether a current wind turbine fails is determined based on the occurrence of the abnormal soundprint signal and the abnormal vibration signal.

[0012] The wind turbine monitoring method according to the embodiment of the present application has at least the following beneficial effects: the soundprint sensor on the wind turbine obtains the soundprint signal of the blade, and the vibration sensor on the wind turbine obtains the vibration signal of the blade, and determines whether the soundprint signal and the vibration signal are abnormal, and determines whether the current wind turbine is faulty and the location of the fault based on the abnormal conditions of the soundprint signal and the vibration signal.

[0013] According to some embodiments of the present application, judging whether a current wind turbine fails according to the occurrence of the abnormal soundprint signal and the abnormal vibration signal includes:

[0014] When the abnormal sound print signal and the abnormal vibration signal appear at the same time, it is determined that the blade of the current wind turbine is faulty;

[0015] The position corresponding to the soundprint sensor with the strongest abnormal soundprint signal is the vibration position where the blade generates the abnormal soundprint.

[0016] According to some embodiments of the present application, judging whether a current wind turbine fails according to the occurrence of the abnormal soundprint signal and the abnormal vibration signal includes:

[0017] When the abnormal voiceprint signal appears and the abnormal vibration signal does not appear, or when the abnormal vibration signal appears and the abnormal voiceprint signal does not appear, the vibration signal, the voiceprint signal and the comparison signal are compared;

[0018] The comparison signal is the average value of the real-time data monitored by the soundprint sensors and vibration sensors of all wind turbines except the current wind turbine;

[0019] Whether the current wind turbine is faulty is determined based on the difference between the sound print signal and vibration signal of the current wind turbine and the comparison signal.

[0020] According to some embodiments of the present application, judging whether the current wind turbine has a fault according to the difference between the soundprint signal and the vibration signal of the current wind turbine and the comparison signal includes:

[0021] If the difference between the soundprint signal and vibration signal of the current wind turbine and the comparison signal is not greater than the difference threshold, it is determined that the current wind turbine has no abnormality;

[0022] If the difference between the soundprint signal and vibration signal of the current wind turbine and the comparison signal is greater than the difference threshold, it is preliminarily determined that the current wind turbine is abnormal, and further confirmation is performed manually to determine whether the wind turbine is abnormal.

[0023] According to some embodiments of the present application, comparing the vibration signal, the voiceprint signal and the comparison signal includes:

[0024] Obtain real-time data monitored by the soundprint sensors and vibration sensors of all wind turbines except the current wind turbine;

[0025] Conduct discrete rate analysis on the real-time data corresponding to each wind turbine;

[0026] The real-time data corresponding to the fans whose discrete rate is greater than the standard threshold are eliminated, and the average value of the remaining real-time data is calculated as the comparison signal.

[0027] According to some embodiments of the present application, the further manual confirmation of whether the wind turbine is abnormal includes:

[0028] When only the vibration signal is abnormal and the soundprint signal is not abnormal, check whether the installation method corresponding to the blade with abnormal vibration signal meets the standard;

[0029] If only the voiceprint signal is abnormal and the vibration signal is not abnormal, check whether there is abnormal noise interference in the current environment.

[0030] According to the wind turbine monitoring device of the third aspect embodiment of the present application, the wind turbine monitoring device includes a data collection module and a data processing module, which are used to collect sound print signals and vibration signals emitted by the wind turbine; used to process the sound print signals and vibration signals emitted by the wind turbine, and used to determine whether the current wind turbine is faulty.

[0031] According to the computer-readable storage medium of the fourth aspect of the present application, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned wind turbine monitoring method.

[0032] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings are used to provide further understanding of the technical solution disclosed in the present application and constitute a part of the specification. Together with the embodiments disclosed in the present application, they are used to explain the technical solution disclosed in the present application and do not constitute a limitation on the technical solution disclosed in the present application.

[0034] Figure 1 It is a schematic diagram of the structure of a wind turbine according to an embodiment of the present application;

[0035] Figure 2 is a flow chart of an embodiment of the wind turbine monitoring method of the present application;

[0036] Figure 3is a flow chart of another embodiment of the wind turbine monitoring method of the present application;

[0037] Figure 4 is a flow chart of another embodiment of the wind turbine monitoring method of the present application;

[0038] Figure 5 is a flow chart of another embodiment of the wind turbine monitoring method of the present application;

[0039] Figure 6 is a flow chart of another embodiment of the wind turbine monitoring method of the present application;

[0040] Figure 7 This is the architecture flow chart of the wind turbine of this application.

[0041] Reference numerals:

[0042] Blade 101; Tower 102;

[0043] Voiceprint sensor 201; Vibration sensor 202. DETAILED DESCRIPTION

[0044] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0045] In the description of the present application, it should be understood that descriptions involving orientation, such as up, down, front, back, left, right, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0046] In the description of this application, "several" means more than one, "more" means more than two, "greater than", "less than", "exceed", etc. are understood to exclude the number itself, and "above", "below", "within", etc. are understood to include the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0047] In the description of this application, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in this application based on the specific content of the technical solution.

[0048] In the description of the present application, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0049] like Figure 1 As shown, the embodiment of the present application provides a wind turbine, which includes a tower 102 and blades 101. A plurality of blades 101 are fixedly connected to a rotating shaft and are rotatably connected to the top of the tower 102 through the rotating shaft. It can be understood that the blades 101 are used to receive wind from the external environment.

[0050] Furthermore, at least one vibration sensor 202 is provided on the surface of each blade 101, and the vibration sensor 202 rotates with the blade 101. Then, there is a corresponding relationship between the vibration sensor 202 and the blade 101, and the vibration sensor 202 is used to collect the vibration signal of the corresponding blade 101. It can be understood that when the vibration sensor 202 collects an abnormal vibration signal, it means that the blade 101 corresponding to the vibration sensor 202 may be faulty.

[0051] At the same time, a plurality of soundprint sensors 201 are arranged on the surface of the tower 102. Since the position of the tower 102 is fixed when the wind turbine is working, each soundprint sensor 201 also has a fixed position. It is understandable that each blade 101 will pass through the position of the tower 102 during the rotation process.

[0052] Wherein, each soundprint sensor 201 is within the rotation range of the blade 101, and each soundprint sensor 201 can receive the soundprint signals emitted by all blades 101. When the soundprint sensor 201 receives an abnormal soundprint signal, it means that the blade 101 of the current wind turbine may be faulty.

[0053] Specifically, each soundprint sensor 201 is distributed in a straight line in the vertical direction, and each soundprint sensor 201 faces different positions of the blade 101, and is used to detect the soundprint signal at different positions of each blade 101. When a soundprint sensor 201 detects an abnormal soundprint signal, the blade 101 of the current wind turbine may have a fault at the position corresponding to the soundprint sensor 201. Therefore, the soundprint sensor 201 combined with the vibration sensor 202 can detect the faulty blade 101 and the specific fault position of the blade 101.

[0054] Based on the above wind turbine, various embodiments of the wind turbine monitoring method of the present application are proposed below.

[0055] like Figure 2 As shown, Figure 2 This is a flow chart of a wind turbine monitoring method provided by an embodiment of the present application. The wind turbine monitoring method can be applied to the above-mentioned wind turbine. The wind turbine monitoring method includes but is not limited to step S100, step S101, step S102 and step S103.

[0056] Step S100, real-time data monitored by each soundprint sensor 201 and each vibration sensor 202 in the current wind turbine is obtained and transmitted to the service end.

[0057] In some examples, the soundprint sensor 201 is used to monitor the real-time soundprint signal emitted by the blade 101, and the vibration sensor 202 is used to monitor the real-time vibration signal emitted by the blade 101, and the real-time data is the real-time soundprint signal and the real-time vibration signal.

[0058] Furthermore, the server is used to collect and process real-time data. When there are many wind turbines, the real-time data of several wind turbines are transmitted to the server, and the server determines whether the wind turbine is faulty by processing the real-time data.

[0059] Step S101 , judging whether an abnormal voiceprint signal appears in a plurality of voiceprint signals received by each voiceprint sensor 201 according to a preset voiceprint judging algorithm.

[0060] In some examples, the server determines the voiceprint signal. Specifically, the server can extract features from the voiceprint signal and determine whether an abnormal voiceprint signal appears based on the extracted features. It is understandable that the server can also determine whether an abnormal voiceprint signal appears through time domain analysis, frequency domain analysis, and wavelet analysis.

[0061] Step S102 , judging whether an abnormal vibration signal appears in the plurality of voiceprint signals received by each voiceprint sensor 201 according to a preset vibration judgment algorithm.

[0062] In some examples, the server determines the vibration signal. Specifically, the server can extract features from the vibration signal and determine whether an abnormal vibration signal occurs based on the extracted features. It is understandable that the server can also determine whether an abnormal vibration signal occurs through time domain analysis, frequency domain analysis, and wavelet analysis.

[0063] It is understandable that the soundprint signal is also generated by the vibration process of the blade 101 , so the soundprint signal and the vibration signal are essentially derived from the vibration of the blade 101 .

[0064] Step S103: judging whether the current wind turbine fails according to the occurrence of the abnormal soundprint signal and the abnormal vibration signal.

[0065] In some examples, since the current wind turbine will send out voiceprint signals and vibration signals at the same time, and both the voiceprint signals and the vibration signals are abnormal and normal, the server has the following three judgment situations: neither the voiceprint signal nor the vibration signal is abnormal; both the voiceprint signal and the vibration signal are abnormal; the voiceprint signal is abnormal, and the vibration signal is not abnormal; the voiceprint signal is not abnormal, and the vibration signal is abnormal.

[0066] It is understandable that when there is no abnormality in the voiceprint signal and the vibration signal, the server determines that the current wind turbine is not faulty.

[0067] In addition, refer to Figure 3 In some examples, step S103 may include but is not limited to the following steps:

[0068] Step S200: When the abnormal sound print signal and the abnormal vibration signal appear at the same time, it is determined that the blade 101 of the current wind turbine is faulty.

[0069] In some examples, when both the voiceprint signal and the vibration signal are abnormal, there are problems with the vibration and operating sound of the wind turbine, and the server determines that the current wind turbine is faulty.

[0070] Furthermore, the soundprint sensor 201 that detects the abnormal soundprint signal is acquired. Since the soundprint sensor 201 corresponds to the position of each blade 101 of the current wind turbine, the fault position of the blade 101 is obtained.

[0071] At the same time, the vibration sensor 202 that detects the abnormal vibration signal is obtained. Since the vibration sensor 202 corresponds to the blade 101 of the current wind turbine, the specific blade 101 that has a fault is obtained.

[0072] In addition, after the faulty blade 101 and the faulty position are identified, the service end may also send the information of the blade 101 and the position information of the wind turbine to the corresponding maintenance department, and issue a remote shutdown command and other operations.

[0073] Step S201 : The position corresponding to the voiceprint sensor 201 with the strongest abnormal voiceprint signal is the vibration position of the blade 101 generating the abnormal voiceprint.

[0074] In some examples, when a blade 101 of the current wind turbine fails, the soundprint signals received by each soundprint sensor 201 may all be abnormal, making it difficult to determine the fault location of the blade 101 .

[0075] In this case, the server compares the abnormal soundprint signals horizontally. The position corresponding to the soundprint sensor 201 with the strongest abnormal soundprint signal is the vibration position of the blade 101 generating the abnormal soundprint, so as to assist in determining the type of fault of the blade 101.

[0076] Furthermore, the types of faults that are prone to occur at different positions of the blade 101 and the types of acoustic print signals and vibration signals that may be generated can be prefabricated in the database in advance. In this way, the fault position can be quickly located, the fault type can be determined, and a maintenance plan can be formulated.

[0077] In addition, refer to Figure 4 In some examples, step S103 may include but is not limited to the following steps:

[0078] Step S300, when the abnormal voiceprint signal appears and the abnormal vibration signal does not appear, or when the abnormal vibration signal appears and the abnormal voiceprint signal does not appear, the vibration signal, the voiceprint signal and the comparison signal are compared.

[0079] In some examples, when an abnormal sound print signal appears but no abnormal vibration signal appears, there is a problem with the operating sound of the wind turbine blade 101, but there is no problem with the vibration of the wind turbine blade 101. At this time, the service end preliminarily determines that the wind turbine blade 101 is suspected to be faulty.

[0080] In addition, when an abnormal vibration signal appears but no abnormal sound print signal appears, there is no problem with the operating sound of the wind turbine blade 101, but there is a problem with the vibration of the wind turbine blade 101. At this time, the service end also preliminarily determines that the wind turbine blade 101 is suspected to be faulty.

[0081] In the above two suspected fault situations, the server needs to make further judgments. Specifically, the server calculates the comparison signal, compares the vibration signal and the soundprint signal of the current wind turbine blade 101 with the comparison signal, and thus completes the judgment process.

[0082] Step S301: The comparison signal is an average value of the real-time data monitored by the soundprint sensors 201 and the vibration sensors 202 of all wind turbines except the current wind turbine.

[0083] In some examples, the comparison signal is a signal emitted when the wind turbine is operating normally. Since the current wind turbine is suspected to be faulty and most wind turbines are in normal operation, the comparison signal needs to be extracted from other wind turbines.

[0084] Step S302: judging whether the current wind turbine has a fault according to the difference between the soundprint signal and the vibration signal of the current wind turbine and the comparison signal.

[0085] Since the comparison signal is a signal emitted when the wind turbine is operating normally, the sound print signal and vibration signal of the current wind turbine can be compared with the comparison signal to determine whether the current wind turbine has a fault.

[0086] In addition, refer to Figure 4 In some examples, step S302 may include but is not limited to the following steps:

[0087] Step S303: if the difference between the soundprint signal and the vibration signal of the current wind turbine and the comparison signal is not greater than the difference threshold, it is determined that the current wind turbine has no abnormality.

[0088] In some examples, a difference threshold is preset according to actual conditions. When the difference between the signal emitted by the current wind turbine and the comparison signal is not greater than the difference threshold, the server determines that the wind turbine currently suspected of failure has no abnormality.

[0089] Step S304: if the difference between the soundprint signal and the vibration signal of the current wind turbine and the comparison signal is greater than the difference threshold, it is preliminarily determined that the current wind turbine is abnormal, and further confirmation is performed manually to determine whether the wind turbine is abnormal.

[0090] In some examples, when the difference between the signal emitted by the current wind turbine and the comparison signal is greater than a difference threshold, the server determines that the current wind turbine has an abnormality.

[0091] Among them, the vibration signal and soundprint signal collected at the current wind turbine may be caused by the surrounding environment of the current wind turbine. Therefore, even if the difference between the signal emitted by the current wind turbine and the comparison signal is greater than the relevant threshold, it cannot be determined that the current wind turbine has an abnormality, and further manual confirmation is still required.

[0092] In addition, refer to Figure 5 In some examples, step S300 may include but is not limited to the following steps:

[0093] Step S400, acquiring real-time data monitored by the soundprint sensors 201 and the vibration sensors 202 of all wind turbines except the current wind turbine.

[0094] Step S401, performing discrete rate analysis on the real-time data corresponding to each wind turbine.

[0095] Step S402: remove the real-time data corresponding to the fans whose discrete rate is greater than the standard threshold, and calculate the average value of the remaining real-time data as a comparison signal.

[0096] In some examples, the comparison signal is extracted from other wind turbines except the current wind turbine, and the other wind turbines except the current wind turbine may also fail.

[0097] Therefore, in the process of calculating the comparison signal, the server first extracts the soundprint signals and vibration signals of all wind turbines except the current wind turbine, and then performs a discrete rate analysis on the wind turbines except the current wind turbine. A standard threshold is preset, and wind turbines with a discrete rate greater than the standard threshold are removed from other wind turbines.

[0098] Furthermore, the remaining wind turbines are regarded as wind turbines operating normally, and average values ​​of the soundprint signals and vibration signals of the remaining wind turbines are calculated to obtain comparison signals.

[0099] In addition, refer to Figure 6 In some examples, the manual confirmation of whether the wind turbine is abnormal in step S304 may include but is not limited to the following steps:

[0100] Step S500, when only the vibration signal is abnormal and the voiceprint signal is not abnormal, check whether the installation method corresponding to the blade 101 with the abnormal vibration signal meets the standard.

[0101] In some examples, when manual judgment is performed, the sound print signal or vibration signal emitted by the current wind turbine is abnormal. When both the sound print signal and the vibration signal are abnormal, the server has determined that the current wind turbine is faulty and is not within the scope of manual judgment.

[0102] If only the vibration signal is abnormal and the soundprint signal is not abnormal, it may be caused by improper installation of the corresponding blade 101. Therefore, it is necessary to check whether the installation method corresponding to the blade 101 with abnormal vibration signal meets the standard.

[0103] Step S501: When only the voiceprint signal is abnormal and the vibration signal is not abnormal, check whether there is abnormal noise interference in the current environment.

[0104] In some examples, if only the soundprint signal is abnormal and the vibration signal is not abnormal, it may be that the corresponding wind turbine is in a noisy environment. It is understandable that external noise will also affect the soundprint signal obtained by the soundprint sensor 201, causing the soundprint signal received by the soundprint sensor 201 to be a combination of external noise and blade 101 vibration noise, causing the server to misjudge.

[0105] Therefore, in this case, manual judgment is required. If the manual judgment indicates that the current wind turbine is not in a noisy environment, the server determines that the current wind turbine is faulty; if the manual judgment indicates that the current wind turbine is in a noisy environment, the server further monitors the current wind turbine after eliminating the noise.

[0106] In addition, if Figure 7As shown, another embodiment of the present invention further provides a wind turbine monitoring device, which includes a data collection module and a data processing module. The data collection module is used to collect the sound print signal and vibration signal emitted by the wind turbine, and the data processing module is used to process the sound print signal and vibration signal emitted by the wind turbine, and is used to determine whether the current wind turbine is faulty.

[0107] The data collection module includes each voiceprint sensor 201 and each vibration sensor 202 disposed on the wind turbine, and the data collection module transmits the monitored real-time data to the data node, which is then transmitted to the server by the data node. Furthermore, the server includes a processor.

[0108] Specifically, the layout environment of wind turbines in the same area is basically similar and close in location. A data node can be set in each area or multiple areas. The data node is usually composed of routing, relay, computer, etc. Each data node is connected to the soundprint sensor 201 and vibration sensor 202 on all wind turbines in the area to receive and transmit the monitored soundprint data and vibration data. It is understandable that the data node can also collect other operating data of the wind turbines in its area, such as pitch angle, output power, real-time speed, power and other information, and transmit these data to the server.

[0109] In addition, the wind turbine monitoring device also includes a memory and a computer program stored in the memory and executable on the processor. In the server, the processor and the memory may be connected via a bus or other means.

[0110] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0111] The non-transient software program and instructions required to implement the wind turbine monitoring method of the above embodiment are stored in the memory. When executed by the processor, the wind turbine monitoring method of the above embodiment is executed, for example, the above described Figure 2 Steps S100 to S103 of the method, Figure 3 Steps S200 to S201 of the method, Figure 4 Steps S300 to S304 of the method, Figure 5 Steps S400 to S402 of the method, Figure 6 Method steps S500 to S501 in.

[0112] During the actual implementation process, the soundprint sensor 201 on the wind turbine obtains the soundprint signal of the blade 101, and the vibration sensor 202 on the wind turbine obtains the vibration signal of the blade 101. The soundprint signal and the vibration signal are transmitted to the server, and the server determines whether the current wind turbine is faulty based on the specific conditions of the soundprint signal and the vibration signal.

[0113] The embodiment of the present application discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the wind turbine monitoring method disclosed in the embodiment of the present application.

[0114] In addition, another embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. The computer-executable instructions are executed by a processor or a controller, for example, by a processor in the above-mentioned device embodiment, so that the above-mentioned processor can execute the wind turbine monitoring method in the above-mentioned embodiment, for example, execute the above-mentioned Figure 2 Steps S100 to S103 of the method, Figure 3 Steps S200 to S201 of the method, Figure 4 Steps S300 to S304 of the method, Figure 5 Steps S400 to S402 of the method, Figure 6 Method steps S500 to S501 in.

[0115] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0116] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present invention. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present invention.

[0117] The above describes the implementation modes of the present application in detail in conjunction with the accompanying drawings, but the present application is not limited to the above implementation modes, and various changes can be made within the knowledge scope of ordinary technicians in the technical field without departing from the purpose of the present application.

Claims

1. A wind turbine, characterized in that: include: A blade, wherein at least one vibration sensor is provided on a surface of the blade; A tower, wherein a plurality of soundprint sensors are arranged on the surface of the tower, and each of the soundprint sensors faces a different position of the blade.

2. The wind turbine according to claim 1, characterized in that: The voiceprint sensors are distributed in a straight line in the vertical direction.

3. A wind turbine monitoring method, applied to the wind turbine according to any one of claims 1 to 2, characterized in that: include: Obtain the real-time data monitored by each soundprint sensor and each vibration sensor in the current wind turbine and transmit it to the server; According to a preset voiceprint judgment algorithm, judging whether an abnormal voiceprint signal appears in a plurality of voiceprint signals received by each voiceprint sensor; According to a preset vibration judgment algorithm, it is judged whether an abnormal vibration signal appears in a plurality of vibration signals received by each vibration sensor; Whether a current wind turbine fails is determined based on the occurrence of the abnormal soundprint signal and the abnormal vibration signal.

4. The wind turbine monitoring method according to claim 3, characterized in that: Judging whether the current wind turbine fails according to the occurrence of the abnormal soundprint signal and the abnormal vibration signal includes: When the abnormal sound print signal and the abnormal vibration signal appear at the same time, it is determined that the blade of the current wind turbine is faulty; The position corresponding to the soundprint sensor with the strongest abnormal soundprint signal is the vibration position where the blade generates the abnormal soundprint.

5. The wind turbine monitoring method according to claim 3, characterized in that: Judging whether the current wind turbine fails according to the occurrence of the abnormal soundprint signal and the abnormal vibration signal includes: When the abnormal voiceprint signal appears and the abnormal vibration signal does not appear, or when the abnormal vibration signal appears and the abnormal voiceprint signal does not appear, the vibration signal, the voiceprint signal and the comparison signal are compared; The comparison signal is the average value of the real-time data monitored by the soundprint sensors and vibration sensors of all wind turbines except the current wind turbine; Whether the current wind turbine is faulty is determined based on the difference between the soundprint signal and vibration signal of the current wind turbine and the comparison signal.

6. The wind turbine monitoring method according to claim 5, characterized in that: After judging whether the current wind turbine has a fault according to the difference between the soundprint signal and the vibration signal of the current wind turbine and the comparison signal, the method includes: If the difference between the soundprint signal and vibration signal of the current wind turbine and the comparison signal is not greater than the difference threshold, it is determined that the current wind turbine has no abnormality; If the difference between the soundprint signal and vibration signal of the current wind turbine and the comparison signal is greater than the difference threshold, it is preliminarily determined that the current wind turbine is abnormal, and further confirmation is performed manually to determine whether the wind turbine is abnormal.

7. The wind turbine monitoring method according to claim 5, characterized in that: The comparing the vibration signal, the voiceprint signal and the comparison signal includes: Obtain real-time data monitored by the soundprint sensors and vibration sensors of all wind turbines except the current wind turbine; Conduct discrete rate analysis on the real-time data corresponding to each wind turbine; The real-time data corresponding to the fans whose discrete rate is greater than the standard threshold are eliminated, and the average value of the remaining real-time data is calculated as the comparison signal.

8. The wind turbine monitoring method according to claim 6, characterized in that: The manual confirmation of whether the wind turbine is abnormal includes: When only the vibration signal is abnormal and the soundprint signal is not abnormal, check whether the installation method corresponding to the blade with abnormal vibration signal meets the standard; If only the voiceprint signal is abnormal and the vibration signal is not abnormal, check whether there is abnormal noise interference in the current environment.

9. A wind turbine monitoring device, characterized in that: include: A data collection module, used to collect sound print signals and vibration signals emitted by the wind turbine; The data processing module is used to process the sound print signal and vibration signal emitted by the wind turbine and to determine whether the current wind turbine is faulty.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the wind turbine monitoring method according to any one of claims 3 to 8.

Images