CN114704438B - Wind turbine generator set fault monitoring method and device - Google Patents
Wind turbine generator set fault monitoring method and device Download PDFInfo
- Publication number
- CN114704438B CN114704438B CN202210619792.5A CN202210619792A CN114704438B CN 114704438 B CN114704438 B CN 114704438B CN 202210619792 A CN202210619792 A CN 202210619792A CN 114704438 B CN114704438 B CN 114704438B
- Authority
- CN
- China
- Prior art keywords
- picture
- wind turbine
- fault
- turbine generator
- fault identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Wind Motors (AREA)
Abstract
The application relates to artificial intelligence and motor technology, and provides a wind turbine generator system fault monitoring method and device. The core component and the core working parameters of the wind turbine generator are monitored in real time in a long-distance mode in time, fault judgment is conducted on the basis of the core component and the core working parameters of the wind turbine generator in time, the fault condition of the wind turbine generator can be detected quickly, and the fault maintenance efficiency of the wind turbine generator is improved.
Description
Technical Field
The application relates to the technical field of motors, in particular to a method and a device for monitoring faults of a wind turbine generator.
Background
The wind generating set (namely a wind generating set) comprises a wind wheel and a generator; the wind wheel comprises blades, a hub, a reinforcing member and the like; it has the functions of wind driven blade rotation to generate electricity, generator head rotation, etc. The wind power generation power supply comprises a wind generating set, a tower frame for supporting the generating set, a storage battery charging controller, an inverter, an unloader, a grid-connected controller, a storage battery pack and the like.
The wind turbine generator is generally high in manufacturing cost, and once a fault occurs, if the fault is not maintained in time, high cost loss can be caused. At present, a common maintenance mode of a wind turbine generator adopts a mode of scheduled maintenance and after-repair maintenance. Scheduled maintenance refers to routine maintenance of the wind turbine after a specified period of operation (e.g., 2500 hours and 5000 hours). The post maintenance means that the wind turbine generator is maintained after obvious failure occurs. Therefore, whether the wind turbine generator is maintained in a planned way or in a follow-up way, the wind turbine generator is not maintained in time, and the fault maintenance efficiency of the wind turbine generator is low.
Disclosure of Invention
The embodiment of the application provides a wind turbine generator system fault monitoring method and device, which can timely and remotely monitor core components and core working parameters of the wind turbine generator system in real time and timely perform fault judgment based on the core components and the core working parameters of the wind turbine generator system, can timely and quickly detect the fault condition of the wind turbine generator system and inform maintenance personnel of maintenance, and improves the fault maintenance efficiency of the wind turbine generator system.
In a first aspect, an embodiment of the present application provides a wind turbine generator fault monitoring method, which includes:
responding to a fault detection instruction of the wind turbine generator, and acquiring a current first monitoring picture corresponding to a brake disc in the wind turbine generator;
acquiring a hydraulic oil level parameter of the wind turbine generator;
acquiring a current second monitoring picture corresponding to an yaw speed reducer in the wind turbine;
acquiring first picture characteristics of the current first monitoring picture, and determining a brake disc fault identification result based on the similarity between the first picture characteristics and each picture characteristic in a first picture characteristic library;
determining a hydraulic oil level fault identification result based on the hydraulic oil level parameter and a preset hydraulic oil level threshold value;
acquiring second picture characteristics of the current second monitoring picture, and determining a yaw system fault identification result based on the similarity between the second picture characteristics and each yaw speed reducer in a second picture characteristic library;
and determining a fault identification result of the wind turbine generator based on the brake disc fault identification result, the hydraulic oil level fault identification result and the yaw system fault identification result.
In a second aspect, an embodiment of the present application provides a wind turbine generator system fault monitoring device, which includes:
the first acquisition unit is used for responding to a fault detection instruction of the wind turbine generator and acquiring a current first monitoring picture corresponding to a brake disc in the wind turbine generator;
the second acquisition unit is used for acquiring the hydraulic oil level parameter of the wind turbine;
the third acquisition unit is used for acquiring a current second monitoring picture corresponding to the yaw reducer in the wind turbine;
the first identification unit is used for acquiring first picture characteristics of the current first monitoring picture and determining a brake disc fault identification result based on the similarity between the first picture characteristics and each picture characteristic in a first picture characteristic library;
the second identification unit is used for determining a hydraulic oil level fault identification result based on the hydraulic oil level parameter and a preset hydraulic oil level threshold value;
the third identification unit is used for the first identification unit and is used for acquiring a second picture characteristic of the current second monitoring picture and determining a yaw system fault identification result based on the similarity between the second picture characteristic and each yaw speed reducer in a second picture characteristic library;
and the fan fault identification unit is used for determining a wind turbine generator fault identification result based on the brake disc fault identification result, the hydraulic oil level fault identification result and the yaw system fault identification result.
In a third aspect, an embodiment of the present application further provides a computer device, which includes a memory, a processor, and a computer program that is stored on the memory and is executable on the processor, where the processor implements the wind turbine generator failure monitoring method according to the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, causes the processor to execute the wind turbine generator fault monitoring method according to the first aspect.
The embodiment of the application provides a method and a device for monitoring faults of a wind turbine generator, firstly, a brake disc fault identification result is determined based on a current first monitoring picture and a first picture feature library of a brake disc in the wind turbine generator, a hydraulic oil level fault identification result is determined based on a hydraulic oil level parameter and a preset hydraulic oil level threshold value of the wind turbine generator, a yaw system fault identification result is determined based on a current second monitoring picture and a second picture feature library corresponding to a yaw speed reducer in the wind turbine generator, and finally, a wind turbine generator fault identification result is determined based on the brake disc fault identification result, the hydraulic oil level fault identification result and the yaw system fault identification result. The wind turbine generator system fault detection method and the system have the advantages that the core components and the core working parameters of the wind turbine generator system are monitored in real time in a long-distance mode in time, fault judgment is conducted on the basis of the core components and the core working parameters of the wind turbine generator system in time, the fault condition of the wind turbine generator system can be detected rapidly in time, maintenance personnel are informed of maintenance, and the fault maintenance efficiency of the wind turbine generator system is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a wind turbine generator fault monitoring method provided in an embodiment of the present application;
fig. 2 is a schematic block diagram of a wind turbine generator fault monitoring apparatus provided in an embodiment of the present application;
fig. 3 is a schematic block diagram of a computer device provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1, fig. 1 is a schematic flow chart of a wind turbine generator fault monitoring method according to an embodiment of the present application, where the wind turbine generator fault monitoring method is applied to a server and is executed by application software installed in the server.
As shown in FIG. 1, the method includes steps S101 to S107.
S101, responding to a fault detection instruction of the wind turbine generator, and acquiring a current first monitoring picture corresponding to a brake disc in the wind turbine generator.
In this embodiment, a server in communication connection with a wind turbine generator is used as an execution main body to describe the technical solution. The wind turbine generator system is provided with a plurality of monitoring cameras, one monitoring camera is aligned with a brake disc in the wind turbine generator system to perform real-time video monitoring on the brake disc, and the other monitoring camera is aligned with a yaw speed reducer in the wind turbine generator system to perform real-time video monitoring on the yaw speed reducer. And whether the hydraulic oil level is low due to the fact that the gear box in the wind turbine generator is leaked or not is also one of reasons for causing the faults of the wind turbine generator, so that the brake disc, the hydraulic oil level and the yaw speed reducer in the wind turbine generator are monitored in real time and judged through fault detection, and whether the current fault of the wind turbine generator is generated or not and needs to be maintained can be timely checked.
The wind turbine generator fault detection instruction is generated in at least two ways, namely, the wind turbine generator fault detection instruction is generated in the server at regular time (for example, the interval time can be set according to the actual monitoring requirement every 1 hour), and when a wind turbine generator operation and maintenance worker selects one wind turbine generator from an equipment list consisting of a plurality of wind turbine generators and immediately triggers the server to send the wind turbine generator fault detection instruction to the selected wind turbine generator.
When the wind turbine receives a fault detection instruction of the wind turbine, a monitoring camera aligned with a brake disc is driven to acquire a current first monitoring picture corresponding to the brake disc in the wind turbine, and then the current first monitoring picture can be used as a picture basis for judging whether the brake disc has a fault.
In one embodiment, step S101 includes:
responding to a wind turbine generator fault detection instruction, and acquiring a first monitoring video corresponding to the wind turbine generator fault detection instruction;
and splitting the first monitoring video and randomly acquiring a frame of picture to be used as a current first monitoring picture corresponding to a brake disc in the wind turbine generator.
In this embodiment, when the current first monitoring picture corresponding to the brake disc is obtained, specifically, after the first monitoring camera aligned with the brake disc in the wind turbine generator receives the fault detection instruction of the wind turbine generator, a first monitoring video with a specified duration (for example, 10 s) is acquired, then, after the video frame splitting is performed on the first monitoring video, multiple frames of monitoring pictures are obtained, and one of the multiple frames of monitoring pictures can be arbitrarily selected to be used as the current first monitoring picture corresponding to the brake disc in the wind turbine generator. Therefore, the current first monitoring picture is extracted based on the first monitoring video, the monitoring picture of the brake disc can be rapidly acquired, and then the current first monitoring picture is used as a picture basis for judging whether the brake disc has faults or not.
S102, obtaining hydraulic oil level parameters of the wind turbine generator.
In this embodiment, the hydraulic oil level parameter of the gearbox in the wind turbine may be understood as a hydraulic value and a level value of the gearbox, and for example, the level value of the gearbox may be specifically selected as the hydraulic oil level parameter of the wind turbine.
When the hydraulic oil level parameter of a general wind turbine is within a normal range, it indicates that the gear box of the wind turbine has no fault, and the fault of the gear box cannot become a factor causing the fault of the wind turbine. If the hydraulic oil level parameter of the wind turbine generator is not within the normal range, for example, if the wind turbine generator successively reports a low hydraulic oil level fault within a period of time, it may be that the lubricating oil level in the gearbox of the wind turbine generator is too high and the oil quality changes, and at this time, the fault of the gearbox may possibly become a factor causing the fault of the wind turbine generator. Therefore, the hydraulic oil level parameter of the wind turbine generator can be used as a parameter basis for judging whether the gear box has faults or not.
In an embodiment, step S102 further includes:
and generating a current hydraulic oil level acquisition instruction and sending the instruction to the wind power generation set.
In this embodiment, after the wind turbine generator fault detection instruction is generated in the server, a current hydraulic oil level acquisition instruction corresponding to the wind turbine generator may also be correspondingly generated and sent to the wind turbine generator. Therefore, after the wind turbine generator receives the wind turbine generator fault detection instruction, the wind turbine generator receives the current hydraulic oil level acquisition instruction after short time delay so as to acquire the hydraulic oil level of the gear box in the wind turbine generator. The hydraulic sensor can be arranged on the gear box in the wind turbine generator system to acquire the hydraulic pressure of the gear box, and the liquid level sensor is arranged to acquire the liquid level of the gear box.
S103, acquiring a current second monitoring picture corresponding to the yaw reducer in the wind turbine generator.
In this embodiment, after the wind turbine receives the wind turbine fault detection instruction, the wind turbine also drives the monitoring camera aligned to the yaw reducer to acquire a current second monitoring picture corresponding to the yaw reducer in the wind turbine, and then the current second monitoring picture can be used as a picture basis for judging whether the yaw reducer has a fault.
In one embodiment, step S103 includes:
acquiring a second monitoring video corresponding to the wind turbine generator fault detection instruction;
and splitting the second monitoring video and randomly acquiring two frames of pictures to be used as the current second monitoring picture corresponding to the yaw speed reducer in the wind turbine generator.
In this embodiment, similarly, when the current second monitoring picture corresponding to the yaw reducer is obtained, a second monitoring video with a specified duration (for example, 10 s) may be collected specifically based on that a second monitoring camera aligned with the yaw reducer in the wind turbine receives the wind turbine fault detection instruction, then a multi-frame monitoring picture is obtained after the video frame splitting is performed on the second monitoring video, and one of the multi-frame monitoring pictures may be arbitrarily selected to be used as the current second monitoring picture corresponding to the yaw reducer in the wind turbine. Therefore, the current second monitoring picture is extracted based on the second monitoring video, the monitoring picture of the yaw speed reducer can be rapidly acquired, and then the current second monitoring picture is used as a picture basis for judging whether the yaw speed reducer has faults or not.
S104, obtaining a first picture characteristic of the current first monitoring picture, and determining a brake disc fault identification result based on the similarity between the first picture characteristic and each picture characteristic in a first picture characteristic library.
In this embodiment, a convolutional neural network pre-stored in the server may be obtained, and then image feature extraction is performed based on a convolutional layer, a pooling layer, and a full-link layer of the convolutional neural network (specifically, convolution, pooling, and full-link processing are sequentially performed on the current first monitoring picture), so that the first picture feature of the current first monitoring picture may be obtained.
And a large number of picture feature vectors corresponding to brake disc pictures in different states (such as a normal state, a fault damage state and the like) are stored in the server, and the picture feature vectors corresponding to the brake disc pictures can form a first picture feature library. After the first picture feature of the current first monitoring picture is known, a brake disc fault identification result can be determined based on the similarity between the first picture feature and each picture feature in a first picture feature library, and specifically, fault identification information corresponding to the picture feature with the largest cosine similarity to the first picture feature is selected as the brake disc fault identification result. Therefore, whether a brake disc in the air outlet motor set has a fault or not can be remotely identified based on image identification.
In one embodiment, step S104 includes:
the cosine similarity between the first picture feature and each picture feature in the first picture feature library is obtained, and the picture feature with the largest cosine similarity with the first picture feature is obtained as a first target picture feature;
and acquiring a first original picture corresponding to the first target picture characteristic and fault identification information corresponding to the first original picture, and taking the fault identification information corresponding to the first original picture as a brake disc fault identification result.
In this embodiment, a large number of brake disc pictures in different states and picture feature vectors corresponding to the brake disc pictures are stored in the server, and each picture feature vector corresponds to only one piece of first fault identification information, for example, the value of the first fault identification information is 1 or 0, where the value of the first fault identification information is 1 indicates that the brake disc is in fault, and the value of the first fault identification information is 0 indicates that the brake disc is normal. Thus, after the first picture feature of the current first monitoring picture is obtained, the cosine similarity between the first picture feature and each picture feature in the first picture feature library can be calculated, and the picture feature having the largest cosine similarity with the first picture feature is obtained as the first target picture feature. At this time, the first original picture corresponding to the first target picture characteristic may be used as a picture most similar to the current first monitoring picture, and the fault identification information of the first original picture may be used as a brake disc fault identification result. Therefore, the judgment of whether the brake disc has the fault can be quickly realized based on the image comparison mode.
Generally, after the brake disc is determined to have a fault, the corresponding maintenance strategy is to replace the originally used 15# hydraulic oil in the brake disc with 32# hydraulic oil and replace a brake damping tube, so that the time from the braking action to the unit braking is prolonged, meanwhile, the stacked springs in the caliper type spring brake body are replaced, the braking force is reduced, and through the improvement, the newly replaced brake disc is realized.
And S105, determining a hydraulic oil level fault identification result based on the hydraulic oil level parameter and a preset hydraulic oil level threshold value.
In the present embodiment, it is generally determined whether the hydraulic oil level parameter is lower than a preset hydraulic oil level threshold value to obtain a hydraulic oil level fault identification result. Similarly, the hydraulic oil level fault recognition result can also be represented by 1 or 0, the hydraulic oil level fault recognition result is that 1 indicates that the hydraulic oil level parameter is lower than the hydraulic oil level threshold value and has a fault, and the hydraulic oil level fault recognition result is that 0 indicates that the hydraulic oil level parameter is higher than the hydraulic oil level threshold value and has no fault. Therefore, the judgment of whether the gearbox has faults or not can be quickly realized based on the parameter value comparison mode.
Generally, after the fault of the gearbox is determined, the corresponding maintenance strategy is to perform anti-seepage treatment on the hydraulic pipeline inside the gearbox. After the anti-seepage treatment is carried out on the hydraulic pipeline inside the gear box, the wind turbine generator set can be recovered to a normal state.
S106, obtaining a second picture characteristic of the current second monitoring picture, and determining a yaw system fault identification result based on the similarity between the second picture characteristic and each yaw speed reducer in a second picture characteristic library.
In this embodiment, a convolutional neural network pre-stored in the server may also be obtained first, and then image feature extraction is performed based on a convolutional layer, a pooling layer, and a full-link layer of the convolutional neural network (specifically, convolution, pooling, and full-link processing are sequentially performed on the current second monitoring picture), so that a second picture feature of the current second monitoring picture may be obtained.
And a large number of picture feature vectors corresponding to the yaw reducer pictures in different states (such as a normal state, a fault damage state and the like) are also stored in the server, and the picture feature vectors corresponding to the yaw reducer pictures can form a second picture feature library. After the second picture feature of the current second monitoring picture is known, a yaw reducer fault identification result can be determined based on the similarity between the second picture feature and each picture feature in a second picture feature library, and specifically, fault identification information corresponding to the picture feature with the maximum cosine similarity to the second picture feature is selected as the yaw reducer fault identification result. Therefore, whether a yaw speed reducer in the wind turbine generator set has a fault or not can be remotely identified based on image identification.
In one embodiment, step S106 includes:
the cosine similarity between the second picture characteristic and each picture characteristic in the second picture characteristic library is obtained, and the picture characteristic with the largest cosine similarity with the second picture characteristic is obtained as a second target picture characteristic;
and acquiring a second original picture corresponding to the second target picture characteristic and fault identification information corresponding to the second original picture, and taking the fault identification information corresponding to the second original picture as a yaw system fault identification result.
In this embodiment, a large number of yaw reducer pictures in different states and picture feature vectors corresponding to the yaw reducer pictures are stored in the server, and each picture feature vector corresponds to only one piece of second fault identification information, for example, the value of the second fault identification information is 1 or 0, where the value of the second fault identification information is 1 indicates that the yaw reducer is in fault, and the value of the second fault identification information is 0 indicates that the yaw reducer is normal. Thus, after the second picture feature of the current second monitoring picture is obtained, the cosine similarity between the second picture feature and each picture feature in the second picture feature library can be calculated, and the picture feature having the largest cosine similarity with the second picture feature is obtained as the second target picture feature. At this time, the second original picture corresponding to the second target picture characteristic may be used as a picture most similar to the current second monitoring picture, and the fault identification information of the second original picture may be used as a yaw reducer fault identification result. Therefore, the judgment of whether the yaw speed reducer has the fault can be quickly realized based on the image comparison mode.
The yaw speed reducer mainly has the functions of driving the engine room to rotate, tracking the change of the wind direction and playing a part of the role of braking the engine room after the yaw process is finished. The working characteristics are that the intermittent working start and stop are more frequent, the transmission torque is larger, and the transmission ratio is high. And the yaw speed reducer adopts a multi-stage planetary speed reducing mechanism mostly, and the fault of the yaw speed reducer is represented as fatigue crack or fracture damage of the multi-stage planetary speed reducing mechanism. Generally, after the yaw speed reducer is determined to have faults, the corresponding maintenance strategy is to reasonably adjust the contact surface clearance, strengthen the lubrication of the contact surface and avoid the long-term heavy load or overload operation of the yaw speed reducer.
And S107, determining a wind turbine generator fault identification result based on the brake disc fault identification result, the hydraulic oil level fault identification result and the yaw system fault identification result.
In this embodiment, after the brake disc fault identification result, the hydraulic oil level fault identification result, and the yaw system fault identification result are determined, the three identification results may be comprehensively considered to finally determine the wind turbine generator fault identification result. Due to the fact that multi-dimensional fault factors are considered, the fault identification result of the wind turbine generator is more accurate.
In one embodiment, step S107 includes:
acquiring a current input vector consisting of a brake disc fault identification result, a hydraulic oil level fault identification result and a yaw system fault identification result;
and acquiring a pre-trained classification model, and inputting the current input vector into the classification model to obtain a wind turbine generator fault identification result.
In this embodiment, since the brake disc fault identification result, the hydraulic oil level fault identification result, and the yaw system fault identification result are all identification values of 0 or 1, the brake disc fault identification result, the hydraulic oil level fault identification result, and the yaw system fault identification result may be sequentially connected in series to form the current input vector. And then inputting the current input vector into a classification model (such as a convolutional neural network) obtained by a server through a large amount of sample data training, and then obtaining a wind turbine generator fault identification result output by the classification model. And taking the fault recognition result of the wind turbine generator as a judgment basis for judging whether the wind turbine generator has faults or not. And the corresponding wind turbine generator maintenance strategy can be retrieved in the database of the server correspondingly based on the wind turbine generator fault identification result, and the server pushes the wind turbine generator maintenance strategy to a receiving terminal used by a corresponding maintenance worker so as to prompt the maintenance worker to timely maintain the wind turbine generator by referring to the wind turbine generator maintenance strategy.
The method realizes real-time monitoring of the core components and the core working parameters of the wind turbine generator in time and remote monitoring of the core components and the core working parameters of the wind turbine generator in time, and fault judgment based on the core components and the core working parameters of the wind turbine generator in time, can detect the fault condition of the wind turbine generator in time and quickly and inform maintenance personnel to maintain the wind turbine generator, and improves the fault maintenance efficiency of the wind turbine generator.
The embodiment of the application also provides a wind turbine generator fault monitoring device, and the wind turbine generator fault monitoring device is used for executing any embodiment of the wind turbine generator fault monitoring method. Specifically, please refer to fig. 2, fig. 2 is a schematic block diagram of a wind turbine generator fault monitoring apparatus 100 according to an embodiment of the present disclosure.
As shown in fig. 2, the wind turbine generator fault monitoring apparatus 100 includes a first obtaining unit 101, a second obtaining unit 102, a third obtaining unit 103, a first identifying unit 104, a second identifying unit 105, a third identifying unit 106, and a fan fault identifying unit 107.
The first obtaining unit 101 is configured to obtain, in response to a wind turbine generator fault detection instruction, a current first monitoring picture corresponding to a brake disc in the wind turbine generator.
In this embodiment, a server in communication connection with a wind turbine generator is used as an execution main body to describe the technical solution. The wind turbine generator system is provided with a plurality of monitoring cameras, one monitoring camera is aligned with a brake disc in the wind turbine generator system to perform real-time video monitoring on the brake disc, and the other monitoring camera is aligned with a yaw speed reducer in the wind turbine generator system to perform real-time video monitoring on the yaw speed reducer. And whether the hydraulic oil level is low due to the fact that the gear box in the wind turbine generator is leaked or not is also one of reasons for causing the faults of the wind turbine generator, so that the brake disc, the hydraulic oil level and the yaw speed reducer in the wind turbine generator are monitored in real time and judged through fault detection, and whether the current fault of the wind turbine generator is generated or not and needs to be maintained can be timely checked.
The wind turbine generator fault detection instruction is generated in at least two ways, namely, the wind turbine generator fault detection instruction is generated in the server at regular time (for example, the interval time can be set according to the actual monitoring requirement every 1 hour), and when a wind turbine generator operation and maintenance worker selects one wind turbine generator from an equipment list consisting of a plurality of wind turbine generators and immediately triggers the server to send the wind turbine generator fault detection instruction to the selected wind turbine generator.
After the wind turbine generator receives a fault detection instruction of the wind turbine generator, a monitoring camera aligned to a brake disc is driven to acquire a current first monitoring picture corresponding to the brake disc in the wind turbine generator, and then the current first monitoring picture can be used as a picture basis for judging whether the brake disc has a fault or not.
In an embodiment, the first obtaining unit 101 is specifically configured to:
responding to a wind turbine generator fault detection instruction, and acquiring a first monitoring video corresponding to the wind turbine generator fault detection instruction;
and splitting the first monitoring video and randomly acquiring a frame of picture as a current first monitoring picture corresponding to a brake disc in the wind turbine generator.
In this embodiment, when the current first monitoring picture corresponding to the brake disc is obtained, specifically, after the first monitoring camera aligned with the brake disc in the wind turbine generator receives the fault detection instruction of the wind turbine generator, a first monitoring video with a specified duration (for example, 10 s) is acquired, then, after the video frame splitting is performed on the first monitoring video, multiple frames of monitoring pictures are obtained, and one of the multiple frames of monitoring pictures can be arbitrarily selected to be used as the current first monitoring picture corresponding to the brake disc in the wind turbine generator. Therefore, the current first monitoring picture is extracted based on the first monitoring video, the monitoring picture of the brake disc can be rapidly acquired, and then the current first monitoring picture is used as a picture basis for judging whether the brake disc has faults or not.
And the second obtaining unit 102 is configured to obtain a hydraulic oil level parameter of the wind turbine.
In this embodiment, the hydraulic oil level parameter of the gearbox in the wind turbine may be understood as a hydraulic value and a level value of the gearbox, and for example, the level value of the gearbox may be specifically selected as the hydraulic oil level parameter of the wind turbine.
When the hydraulic oil level parameter of a general wind turbine generator is within a normal range, the condition that the gear box of the wind turbine generator has no fault is shown, and the fault of the gear box cannot become a factor causing the fault of the wind turbine generator. If the hydraulic oil level parameter of the wind turbine generator is not within the normal range, for example, if the wind turbine generator successively reports a low hydraulic oil level fault within a period of time, it may be that the lubricating oil level in the gearbox of the wind turbine generator is too high and the oil quality changes, and at this time, the fault of the gearbox may possibly become a factor causing the fault of the wind turbine generator. Therefore, the hydraulic oil level parameter of the wind turbine generator can be used as a parameter basis for judging whether the gear box has faults or not.
In an embodiment, the wind turbine generator fault monitoring apparatus 100 further includes:
and the current hydraulic oil level acquisition instruction generating unit is used for generating a current hydraulic oil level acquisition instruction and sending the current hydraulic oil level acquisition instruction to the wind power generation unit.
In this embodiment, after the wind turbine generator fault detection instruction is generated in the server, a current hydraulic oil level acquisition instruction corresponding to the wind turbine generator may also be correspondingly generated and sent to the wind turbine generator. Therefore, after the wind turbine generator receives the wind turbine generator fault detection instruction, the wind turbine generator receives the current hydraulic oil level acquisition instruction after short time delay so as to acquire the hydraulic oil level of the gear box in the wind turbine generator. The gearbox in the wind turbine generator set can be provided with a hydraulic sensor to acquire hydraulic pressure of the gearbox, and a liquid level sensor is arranged to acquire liquid level of the gearbox.
And the third obtaining unit 103 is configured to obtain a current second monitoring picture corresponding to the yaw reducer in the wind turbine.
In this embodiment, after the wind turbine receives the wind turbine fault detection instruction, the wind turbine also drives the monitoring camera aligned to the yaw reducer to acquire a current second monitoring picture corresponding to the yaw reducer in the wind turbine, and then the current second monitoring picture can be used as a picture basis for judging whether the yaw reducer has a fault.
In an embodiment, the third obtaining unit 103 is specifically configured to:
acquiring a second monitoring video corresponding to the wind turbine generator fault detection instruction;
and splitting the second monitoring video and randomly acquiring two frames of pictures to be used as the current second monitoring picture corresponding to the yaw speed reducer in the wind turbine generator.
In this embodiment, similarly, when the current second monitoring picture corresponding to the yaw reducer is obtained, a second monitoring video with a specified duration (for example, 10 s) may be collected specifically based on that a second monitoring camera aligned with the yaw reducer in the wind turbine receives the wind turbine fault detection instruction, then a multi-frame monitoring picture is obtained after the video frame splitting is performed on the second monitoring video, and one of the multi-frame monitoring pictures may be arbitrarily selected to be used as the current second monitoring picture corresponding to the yaw reducer in the wind turbine. Therefore, the current second monitoring picture is extracted based on the second monitoring video, the monitoring picture of the yaw speed reducer can be rapidly acquired, and then the current second monitoring picture is used as a picture basis for judging whether the yaw speed reducer has faults or not.
And the first identification unit 104 is configured to acquire a first picture feature of the current first monitoring picture, and determine a brake disc fault identification result based on the similarity between the first picture feature and each picture feature in the first picture feature library.
In this embodiment, a convolutional neural network pre-stored in the server may be obtained, and then image feature extraction is performed based on a convolutional layer, a pooling layer, and a full-link layer of the convolutional neural network (specifically, convolution, pooling, and full-link processing are sequentially performed on the current first monitoring picture), so that the first picture feature of the current first monitoring picture may be obtained.
And a large number of picture feature vectors corresponding to brake disc pictures in different states (such as a normal state, a fault damage state and the like) are also stored in the server, and the picture feature vectors corresponding to the brake disc pictures can form a first picture feature library. After the first picture feature of the current first monitoring picture is known, a brake disc fault identification result can be determined based on the similarity between the first picture feature and each picture feature in a first picture feature library, and specifically, fault identification information corresponding to the picture feature with the largest cosine similarity to the first picture feature is selected as the brake disc fault identification result. Therefore, whether a brake disc in the air outlet motor set has a fault or not can be remotely identified based on image identification.
In an embodiment, the first identifying unit 104 is specifically configured to:
the cosine similarity between the first picture feature and each picture feature in the first picture feature library is obtained, and the picture feature with the largest cosine similarity with the first picture feature is obtained as a first target picture feature;
and acquiring a first original picture corresponding to the first target picture characteristic and fault identification information corresponding to the first original picture, and taking the fault identification information corresponding to the first original picture as a brake disc fault identification result.
In this embodiment, a large number of brake disc pictures in different states and picture feature vectors corresponding to the brake disc pictures are stored in the server, and each picture feature vector corresponds to only one piece of first fault identification information, for example, the value of the first fault identification information is 1 or 0, where the value of the first fault identification information is 1 indicates that the brake disc is in fault, and the value of the first fault identification information is 0 indicates that the brake disc is normal. After the first picture feature of the current first monitoring picture is obtained, the cosine similarity between the first picture feature and each picture feature in the first picture feature library can be calculated, and the picture feature having the largest cosine similarity with the first picture feature is obtained as the first target picture feature. At this time, the first original picture corresponding to the first target picture characteristic may be used as a picture most similar to the current first monitoring picture, and the fault identification information of the first original picture may be used as a brake disc fault identification result. Therefore, the judgment of whether the brake disc has the fault can be quickly realized based on the image comparison mode.
Generally, after the brake disc is determined to have a fault, the corresponding maintenance strategy is to replace the originally used 15# hydraulic oil in the brake disc with 32# hydraulic oil and replace a brake damping tube, so that the time from the braking action to the unit braking is prolonged, meanwhile, the stacked springs in the caliper type spring brake body are replaced, the braking force is reduced, and through the improvement, the newly replaced brake disc is realized.
And a second identification unit 105, configured to determine a hydraulic oil level fault identification result based on the hydraulic oil level parameter and a preset hydraulic oil level threshold.
In the present embodiment, it is generally determined whether the hydraulic oil level parameter is lower than a preset hydraulic oil level threshold value to obtain a hydraulic oil level fault identification result. Similarly, the hydraulic oil level fault recognition result can also be represented by 1 or 0, the hydraulic oil level fault recognition result is that 1 indicates that the hydraulic oil level parameter is lower than the hydraulic oil level threshold value and has a fault, and the hydraulic oil level fault recognition result is that 0 indicates that the hydraulic oil level parameter is higher than the hydraulic oil level threshold value and has no fault. Therefore, the judgment of whether the gearbox has faults or not can be quickly realized based on the parameter value comparison mode.
Generally, after determining that the gearbox has a fault, the corresponding maintenance strategy is to perform anti-seepage treatment on the hydraulic pipeline inside the gearbox. After the anti-seepage treatment is carried out on the hydraulic pipeline inside the gear box, the wind turbine generator set can be recovered to a normal state.
And the third identifying unit 106 is configured to obtain a second picture feature of the current second monitoring picture, and determine a yaw system fault identification result based on the similarity between the second picture feature and each yaw reducer in the second picture feature library.
In this embodiment, a convolutional neural network pre-stored in the server may also be obtained first, and then image feature extraction is performed based on a convolutional layer, a pooling layer, and a full-link layer of the convolutional neural network (specifically, convolution, pooling, and full-link processing are sequentially performed on the current second monitoring picture), so that a second picture feature of the current second monitoring picture may be obtained.
And a large number of picture feature vectors corresponding to the yaw reducer pictures in different states (such as a normal state, a fault damage state and the like) are also stored in the server, and the picture feature vectors corresponding to the yaw reducer pictures can form a second picture feature library. After the second picture feature of the current second monitoring picture is known, a yaw reducer fault identification result can be determined based on the similarity between the second picture feature and each picture feature in a second picture feature library, and specifically, fault identification information corresponding to the picture feature with the largest cosine similarity with the second picture feature is selected as the yaw reducer fault identification result. Therefore, whether a yaw speed reducer in the wind turbine generator set has a fault or not can be remotely identified based on image identification.
In an embodiment, the third identifying unit 106 is specifically configured to:
the cosine similarity between the second picture characteristic and each picture characteristic in the second picture characteristic library is obtained, and the picture characteristic with the largest cosine similarity with the second picture characteristic is obtained as a second target picture characteristic;
and acquiring a second original picture corresponding to the second target picture characteristic and fault identification information corresponding to the second original picture, and taking the fault identification information corresponding to the second original picture as a yaw system fault identification result.
In this embodiment, a large number of yaw reducer pictures in different states and picture feature vectors corresponding to the yaw reducer pictures are stored in the server, and each picture feature vector corresponds to only one piece of second fault identification information, for example, the value of the second fault identification information is 1 or 0, where the value of the second fault identification information is 1 indicates that the yaw reducer is in fault, and the value of the second fault identification information is 0 indicates that the yaw reducer is normal. Thus, after the second picture feature of the current second monitoring picture is obtained, the cosine similarity between the second picture feature and each picture feature in the second picture feature library can be calculated, and the picture feature having the largest cosine similarity with the second picture feature is obtained as the second target picture feature. At this time, the second original picture corresponding to the second target picture characteristic may be used as a picture most similar to the current second monitoring picture, and the fault identification information of the second original picture may be used as a yaw reducer fault identification result. Therefore, the judgment of whether the yaw speed reducer has the fault can be quickly realized based on the image comparison mode.
The yaw speed reducer mainly has the functions of driving the engine room to rotate, tracking the change of the wind direction and playing a part of the role of braking the engine room after the yaw process is finished. The working characteristics are that the intermittent working start and stop are more frequent, the transmission torque is larger, and the transmission ratio is high. And the yaw speed reducer adopts a multi-stage planetary speed reducing mechanism mostly, and the fault of the yaw speed reducer is represented as fatigue crack or fracture damage of the multi-stage planetary speed reducing mechanism. Generally, after the yaw speed reducer is determined to have a fault, the corresponding maintenance strategy is to reasonably adjust the gap of the contact surface, strengthen the lubrication of the contact surface and avoid the long-term heavy load or overload operation of the yaw speed reducer.
And the fan fault identification unit 107 is used for determining a wind turbine generator fault identification result based on the brake disc fault identification result, the hydraulic oil level fault identification result and the yaw system fault identification result.
In this embodiment, after the brake disc fault identification result, the hydraulic oil level fault identification result and the yaw system fault identification result are determined, the three identification results may be comprehensively considered to finally determine the wind turbine generator fault identification result. Due to the fact that multi-dimensional fault factors are considered, the fault identification result of the wind turbine generator is more accurate.
In an embodiment, the fan failure identification unit 107 is specifically configured to:
acquiring a current input vector consisting of a brake disc fault identification result, a hydraulic oil level fault identification result and a yaw system fault identification result;
and acquiring a pre-trained classification model, and inputting the current input vector into the classification model to obtain a wind turbine generator fault identification result.
In this embodiment, since the brake disc fault identification result, the hydraulic oil level fault identification result, and the yaw system fault identification result are all identification values of 0 or 1, the brake disc fault identification result, the hydraulic oil level fault identification result, and the yaw system fault identification result may be sequentially connected in series to form the current input vector. And then inputting the current input vector into a classification model (such as a convolutional neural network) obtained by a server through a large amount of sample data training, and then obtaining a wind turbine generator fault identification result output by the classification model. And taking the fault recognition result of the wind turbine generator as a judgment basis for judging whether the wind turbine generator has faults or not. And the corresponding wind turbine generator maintenance strategy can be retrieved in the database of the server correspondingly based on the wind turbine generator fault identification result, and the server pushes the wind turbine generator maintenance strategy to a receiving terminal used by a corresponding maintenance worker so as to prompt the maintenance worker to timely maintain the wind turbine generator by referring to the wind turbine generator maintenance strategy.
The device has realized in time long-range core part and the core working parameter to wind turbine generator system and in time carries out fault diagnosis based on wind turbine generator system's core part and core working parameter, can in time short-term test go out the trouble condition of wind turbine generator system and inform maintenance personal to maintain, improves wind turbine generator system's trouble maintenance efficiency.
The wind turbine generator fault monitoring apparatus described above may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 3.
Referring to fig. 3, fig. 3 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server or a server cluster. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.
Referring to fig. 3, the computer apparatus 500 includes a processor 502, a memory, which may include a storage medium 503 and an internal memory 504, and a network interface 505 connected by a device bus 501.
The storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032, when executed, may cause the processor 502 to perform a wind turbine fault monitoring method.
The processor 502 is used to provide computing and control capabilities that support the operation of the overall computer device 500.
The internal memory 504 provides an environment for running the computer program 5032 in the storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 may be enabled to execute the wind turbine generator failure monitoring method.
The network interface 505 is used for network communication, such as providing transmission of data information. Those skilled in the art will appreciate that the configuration shown in fig. 3 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation of the computer device 500 to which the present application may be applied, and that a particular computer device 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The processor 502 is configured to run the computer program 5032 stored in the memory, so as to implement the wind turbine generator fault monitoring method disclosed in the embodiment of the present application.
Those skilled in the art will appreciate that the embodiment of a computer device illustrated in fig. 3 does not constitute a limitation on the specific construction of the computer device, and in other embodiments a computer device may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor, and in such embodiments, the structures and functions of the memory and the processor are consistent with those of the embodiment shown in fig. 3, and are not described herein again.
It should be understood that in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium may be a nonvolatile computer-readable storage medium or a volatile computer-readable storage medium. The computer readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the wind turbine generator fault monitoring method disclosed in the embodiments of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, devices and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus, device and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only a logical division, and there may be other divisions when the actual implementation is performed, or units having the same function may be grouped into one unit, for example, a plurality of units or components may be combined or may be integrated into another device, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electrical, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the elements may be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a backend server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. A wind turbine generator system fault monitoring method is characterized by comprising the following steps:
responding to a fault detection instruction of the wind turbine generator, and acquiring a current first monitoring picture corresponding to a brake disc in the wind turbine generator;
acquiring a hydraulic oil level parameter of the wind turbine generator;
acquiring a current second monitoring picture corresponding to an yaw speed reducer in the wind turbine generator;
acquiring first picture characteristics of the current first monitoring picture, and determining a brake disc fault identification result based on the similarity between the first picture characteristics and each picture characteristic in a first picture characteristic library;
determining a hydraulic oil level fault identification result based on the hydraulic oil level parameter and a preset hydraulic oil level threshold value;
acquiring second picture characteristics of the current second monitoring picture, and determining a yaw system fault identification result based on the similarity between the second picture characteristics and each yaw speed reducer in a second picture characteristic library;
determining a fault identification result of the wind turbine generator based on the brake disc fault identification result, the hydraulic oil level fault identification result and the yaw system fault identification result;
the determining of the fault identification result of the wind turbine generator based on the brake disc fault identification result, the hydraulic oil level fault identification result and the yaw system fault identification result comprises the following steps:
acquiring a current input vector consisting of a brake disc fault identification result, a hydraulic oil level fault identification result and a yaw system fault identification result;
acquiring a pre-trained classification model, and inputting the current input vector into the classification model to obtain a fault recognition result of the wind turbine generator;
the determining of the brake disc fault identification result based on the similarity between the first picture feature and each picture feature in the first picture feature library comprises the following steps:
the cosine similarity between the first picture feature and each picture feature in the first picture feature library is obtained, and the picture feature with the largest cosine similarity with the first picture feature is obtained as a first target picture feature;
acquiring a first original picture corresponding to the first target picture characteristic and fault identification information corresponding to the first original picture, and taking the fault identification information corresponding to the first original picture as a brake disc fault identification result;
determining a yaw system fault identification result based on the similarity between the second picture characteristic and each yaw speed reducer in the second picture characteristic library, wherein the determining comprises the following steps:
the cosine similarity between the second picture characteristic and each picture characteristic in the second picture characteristic library is obtained, and the picture characteristic with the largest cosine similarity with the second picture characteristic is obtained as a second target picture characteristic;
acquiring a second original picture corresponding to the second target picture characteristic and fault identification information corresponding to the second original picture, and taking the fault identification information corresponding to the second original picture as a yaw system fault identification result;
the obtaining of the pre-trained classification model and the inputting of the current input vector into the classification model to obtain the wind turbine generator fault recognition result further include:
retrieving a corresponding wind turbine maintenance strategy in a database of a server on the basis of the wind turbine fault identification result, pushing the wind turbine maintenance strategy to a receiving terminal used by a corresponding maintenance worker by the server so as to prompt the maintenance worker to timely maintain the wind turbine by referring to the wind turbine maintenance strategy;
the maintenance strategy of the brake disc fault is to replace 15# hydraulic oil in the brake disc with 32# hydraulic oil, replace a brake damping tube and replace a stacked spring in a caliper type spring brake body;
the maintenance strategy of the hydraulic oil level fault is to perform anti-seepage treatment on the hydraulic pipeline inside the gearbox;
the maintenance strategy of the yaw system fault is to enlarge the contact surface clearance and enhance the lubrication of the contact surface.
2. The method according to claim 1, wherein the obtaining a current first monitoring picture corresponding to a brake disc in the wind turbine in response to the wind turbine fault detection instruction comprises:
responding to a wind turbine generator fault detection instruction, and acquiring a first monitoring video corresponding to the wind turbine generator fault detection instruction;
and splitting the first monitoring video and randomly acquiring a frame of picture to be used as a current first monitoring picture corresponding to a brake disc in the wind turbine generator.
3. The method according to claim 1, wherein before obtaining the hydraulic oil level parameter of the wind turbine generator, the method further comprises:
and generating a current hydraulic oil level acquisition instruction and sending the instruction to the wind power generation set.
4. The method of claim 1, wherein the obtaining a current second monitoring picture corresponding to an yaw reducer in the wind turbine comprises:
acquiring a second monitoring video corresponding to the wind turbine generator fault detection instruction;
and splitting the second monitoring video and randomly acquiring two frames of pictures to be used as the current second monitoring picture corresponding to the yaw speed reducer in the wind turbine generator.
5. A wind turbine generator system fault monitoring device, comprising:
the first acquisition unit is used for responding to a fault detection instruction of the wind turbine generator and acquiring a current first monitoring picture corresponding to a brake disc in the wind turbine generator;
the second acquisition unit is used for acquiring the hydraulic oil level parameter of the wind turbine;
the third acquisition unit is used for acquiring a current second monitoring picture corresponding to the yaw reducer in the wind turbine;
the first identification unit is used for acquiring first picture characteristics of the current first monitoring picture and determining a brake disc fault identification result based on the similarity between the first picture characteristics and each picture characteristic in a first picture characteristic library;
the second identification unit is used for determining a hydraulic oil level fault identification result based on the hydraulic oil level parameter and a preset hydraulic oil level threshold value;
the third identification unit is used for the first identification unit and is used for acquiring the second picture characteristics of the current second monitoring picture and determining the fault identification result of the yaw system based on the similarity between the second picture characteristics and each yaw speed reducer in the second picture characteristic library;
the fan fault identification unit is used for determining a wind turbine generator fault identification result based on the brake disc fault identification result, the hydraulic oil level fault identification result and the yaw system fault identification result;
the fan fault identification unit is specifically used for:
acquiring a current input vector consisting of a brake disc fault identification result, a hydraulic oil level fault identification result and a yaw system fault identification result;
acquiring a pre-trained classification model, and inputting the current input vector into the classification model to obtain a fault recognition result of the wind turbine generator;
the first identification unit is specifically configured to:
the cosine similarity between the first picture feature and each picture feature in the first picture feature library is obtained, and the picture feature with the largest cosine similarity with the first picture feature is obtained as a first target picture feature;
acquiring a first original picture corresponding to the first target picture characteristic and fault identification information corresponding to the first original picture, and taking the fault identification information corresponding to the first original picture as a brake disc fault identification result;
the third identification unit is specifically configured to:
the cosine similarity between the second picture characteristic and each picture characteristic in the second picture characteristic library is obtained, and the picture characteristic with the largest cosine similarity with the second picture characteristic is obtained as a second target picture characteristic;
acquiring a second original picture corresponding to the second target picture characteristic and fault identification information corresponding to the second original picture, and taking the fault identification information corresponding to the second original picture as a yaw system fault identification result;
the wind turbine generator system fault monitoring device is also used for:
retrieving a corresponding wind turbine maintenance strategy in a database of a server on the basis of the wind turbine fault identification result, pushing the wind turbine maintenance strategy to a receiving terminal used by a corresponding maintenance worker by the server so as to prompt the maintenance worker to timely maintain the wind turbine by referring to the wind turbine maintenance strategy;
the maintenance strategy of the brake disc fault is to replace 15# hydraulic oil in the brake disc with 32# hydraulic oil, replace a brake damping tube and replace a stacked spring in a caliper type spring brake body;
the maintenance strategy of the hydraulic oil level fault is to perform anti-seepage treatment on a hydraulic pipeline in the gearbox;
the maintenance strategy of the yaw system fault is to enlarge the contact surface clearance and enhance the lubrication of the contact surface.
6. Computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the wind turbine generator system fault monitoring method according to any of claims 1 to 4 when executing the computer program.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to carry out the wind turbine generator set fault monitoring method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210619792.5A CN114704438B (en) | 2022-06-02 | 2022-06-02 | Wind turbine generator set fault monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210619792.5A CN114704438B (en) | 2022-06-02 | 2022-06-02 | Wind turbine generator set fault monitoring method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114704438A CN114704438A (en) | 2022-07-05 |
| CN114704438B true CN114704438B (en) | 2022-09-20 |
Family
ID=82178103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210619792.5A Active CN114704438B (en) | 2022-06-02 | 2022-06-02 | Wind turbine generator set fault monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114704438B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600581A (en) * | 2016-12-02 | 2017-04-26 | 北京航空航天大学 | Train operation fault automatic detection system and method based on binocular stereoscopic vision |
| EP3306330A1 (en) * | 2016-10-05 | 2018-04-11 | Rolls-Royce plc | Brushless synchronous generator stator winding fault |
| CN108331718A (en) * | 2018-04-10 | 2018-07-27 | 国电联合动力技术有限公司 | Wind turbines yaw system monitors mechanism and fault diagnosis system and method on-line |
| CN109213102A (en) * | 2018-09-11 | 2019-01-15 | 深圳众城卓越科技有限公司 | More order monitoring methods, device, computer equipment and storage medium |
| CN110778453A (en) * | 2019-11-29 | 2020-02-11 | 中国船舶重工集团海装风电股份有限公司 | Yaw fault-tolerant control method and equipment for wind generating set and storage medium |
| CN110909669A (en) * | 2019-11-19 | 2020-03-24 | 湖南国奥电力设备有限公司 | Underground cable fault determination method and device based on image detection |
| CN111339872A (en) * | 2020-02-18 | 2020-06-26 | 国网信通亿力科技有限责任公司 | Power grid fault classification method based on classification model |
| WO2021037447A1 (en) * | 2019-08-28 | 2021-03-04 | Siemens Gamesa Renewable Energy A/S | Method and system for monitoring blades of a wind turbine |
| WO2021121499A1 (en) * | 2019-12-16 | 2021-06-24 | Vestas Wind Systems A/S | Yaw supervision |
| KR102309559B1 (en) * | 2020-06-17 | 2021-10-07 | 광주과학기술원 | The method for detecting fault of motor |
Family Cites Families (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003201951A (en) * | 2002-01-07 | 2003-07-18 | Fuji Heavy Ind Ltd | Excessive rotation avoiding mechanism of horizontal axis wind mill |
| JP4866274B2 (en) * | 2007-03-16 | 2012-02-01 | 豊興工業株式会社 | Hydraulic device |
| JP2011127551A (en) * | 2009-12-18 | 2011-06-30 | Mitsubishi Heavy Ind Ltd | Wind-powered generator apparatus |
| JP2013181412A (en) * | 2012-02-29 | 2013-09-12 | Mitsubishi Heavy Ind Ltd | Fault detecting method and fault detecting system of wind power generation device |
| CN103953509B (en) * | 2014-05-14 | 2016-08-17 | 中科恒源科技股份有限公司 | A kind of fan monitor method and fan monitor system |
| CN105510038B (en) * | 2015-12-31 | 2018-07-27 | 北京金风科创风电设备有限公司 | Wind turbine generator fault monitoring method and device |
| DK3409940T3 (en) * | 2017-05-30 | 2022-09-19 | Gen Electric | PROCEDURE FOR REDUCING LOADS DURING STANDBY OR PARKED CONDITION FOR A WIND TURBINE VIA YAW OFFSET |
| US10662923B2 (en) * | 2017-09-29 | 2020-05-26 | General Electric Company | Contingency autonomous yaw control for a wind turbine |
| CN108335019A (en) * | 2018-01-12 | 2018-07-27 | 天津瑞源电气有限公司 | The fault diagnosis recognition methods of fan yaw system |
| CN110094296B (en) * | 2018-01-29 | 2020-06-09 | 江苏金风科技有限公司 | Yaw control method and device of wind generating set under typhoon |
| CN108488037B (en) * | 2018-03-01 | 2019-07-19 | 北京金风科创风电设备有限公司 | Anti-runaway control method and device and wind generating set |
| CN108757341B (en) * | 2018-05-02 | 2019-11-05 | 明阳智慧能源集团股份公司 | A kind of high intelligent fault diagnosis method of large-scale half direct-drive unit yawing velocity |
| CN109142883A (en) * | 2018-10-17 | 2019-01-04 | 深圳众城卓越科技有限公司 | A kind of super capacitor volume test device and method of wind power pitch-controlled system |
| CN109854446B (en) * | 2018-12-11 | 2021-03-30 | 山东瑞其能电气有限公司 | Control system for ensuring safety of wind turbine generator |
| US20210239099A1 (en) * | 2020-01-30 | 2021-08-05 | Honeywell International Inc. | Systems and methods for model based wind turbine diagnostics |
| CN111594396A (en) * | 2020-06-09 | 2020-08-28 | 中国华能集团清洁能源技术研究院有限公司 | Wind turbine generator system state monitoring system |
| CN111664061B (en) * | 2020-06-15 | 2021-12-17 | 三一重能有限公司 | Fault diagnosis method and device for yaw system in wind generating set |
| CN114202727A (en) * | 2021-12-10 | 2022-03-18 | 大唐东北电力试验研究院有限公司 | Fan fault recognition system based on visual tracking |
-
2022
- 2022-06-02 CN CN202210619792.5A patent/CN114704438B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3306330A1 (en) * | 2016-10-05 | 2018-04-11 | Rolls-Royce plc | Brushless synchronous generator stator winding fault |
| CN106600581A (en) * | 2016-12-02 | 2017-04-26 | 北京航空航天大学 | Train operation fault automatic detection system and method based on binocular stereoscopic vision |
| CN108331718A (en) * | 2018-04-10 | 2018-07-27 | 国电联合动力技术有限公司 | Wind turbines yaw system monitors mechanism and fault diagnosis system and method on-line |
| CN109213102A (en) * | 2018-09-11 | 2019-01-15 | 深圳众城卓越科技有限公司 | More order monitoring methods, device, computer equipment and storage medium |
| WO2021037447A1 (en) * | 2019-08-28 | 2021-03-04 | Siemens Gamesa Renewable Energy A/S | Method and system for monitoring blades of a wind turbine |
| CN110909669A (en) * | 2019-11-19 | 2020-03-24 | 湖南国奥电力设备有限公司 | Underground cable fault determination method and device based on image detection |
| CN110778453A (en) * | 2019-11-29 | 2020-02-11 | 中国船舶重工集团海装风电股份有限公司 | Yaw fault-tolerant control method and equipment for wind generating set and storage medium |
| WO2021121499A1 (en) * | 2019-12-16 | 2021-06-24 | Vestas Wind Systems A/S | Yaw supervision |
| CN111339872A (en) * | 2020-02-18 | 2020-06-26 | 国网信通亿力科技有限责任公司 | Power grid fault classification method based on classification model |
| KR102309559B1 (en) * | 2020-06-17 | 2021-10-07 | 광주과학기술원 | The method for detecting fault of motor |
Non-Patent Citations (2)
| Title |
|---|
| 基于粒子群优化KFCM的风电齿轮箱故障诊断;李状等;《振动.测试与诊断》;20170615(第03期);全文 * |
| 大型风电机组电机驱动型主动偏航***故障诊断技术概述;邓子豪等;《太阳能》;20200428(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114704438A (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110991666B (en) | Fault detection method, training device, training equipment and training equipment for model, and storage medium | |
| CN111597682B (en) | Method for predicting remaining life of bearing of gearbox of wind turbine | |
| CN105787584B (en) | Wind turbine group fault early warning method based on cloud platform | |
| CN105809255A (en) | IoT-based heat-engine plantrotary machine health management method and system | |
| CN110689141B (en) | Fault diagnosis method and equipment for wind generating set | |
| CN110388315B (en) | Oil transfer pump fault identification method, device and system based on multi-source information fusion | |
| CN116502072B (en) | Robust fault diagnosis method for key components of wind generating set under complex variable working conditions | |
| CN110969315A (en) | Monitoring method of water injection pump and related equipment | |
| CN115909203A (en) | Construction safety panoramic monitoring system and method | |
| CN116771610A (en) | Method for adjusting fault evaluation value of variable pitch system of wind turbine | |
| CN114704438B (en) | Wind turbine generator set fault monitoring method and device | |
| WO2022147684A1 (en) | Method and apparatus for identifying abnormalities in mechanical apparatus or mechanical component | |
| EP2728177A1 (en) | Windmill repair timing determination support device and repair timing determination support method | |
| Bayir et al. | Serial wound starter motor faults diagnosis using artificial neural network | |
| CN116071053A (en) | Reciprocating compressor state early warning system based on digital twinning | |
| CN116221037A (en) | Wind turbine generator monitoring method and device | |
| CN109209781B (en) | The Fault Locating Method and device of wind power generating set | |
| CN112160868B (en) | Monitoring method, system, equipment and medium of variable pitch system | |
| CN115659778A (en) | On-line construction method and on-line updating equipment of wind turbine generator bearing fault diagnosis model | |
| EP3303835B1 (en) | Method for windmill farm monitoring | |
| Zhang | Comparison of data-driven and model-based methodologies of wind turbine fault detection with SCADA data | |
| CN114881321A (en) | Mechanical component failure prediction method, device, electronic device and storage medium | |
| CN113705840A (en) | Equipment predictive maintenance method and device, computer equipment and storage medium | |
| CN113570473A (en) | Equipment fault monitoring method and device, computer equipment and storage medium | |
| CN115828439A (en) | Method and device for identifying abnormal loss of wind generating set |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |