CN113417809B - Visual lightning stroke monitoring method and system - Google Patents
Visual lightning stroke monitoring method and system Download PDFInfo
- Publication number
- CN113417809B CN113417809B CN202110569479.0A CN202110569479A CN113417809B CN 113417809 B CN113417809 B CN 113417809B CN 202110569479 A CN202110569479 A CN 202110569479A CN 113417809 B CN113417809 B CN 113417809B
- Authority
- CN
- China
- Prior art keywords
- lightning stroke
- data
- visual
- visual information
- lightning
- 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
- 208000025274 Lightning injury Diseases 0.000 title claims abstract description 183
- 230000000007 visual effect Effects 0.000 title claims abstract description 140
- 238000012544 monitoring process Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000012423 maintenance Methods 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims description 15
- 238000013523 data management Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000007726 management method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 238000003709 image segmentation Methods 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000004075 alteration Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000002803 fossil fuel Substances 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- 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
- F03D7/00—Controlling wind motors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2270/00—Control
- F05B2270/10—Purpose of the control system
- F05B2270/107—Purpose of the control system to cope with emergencies
-
- 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
Abstract
The invention discloses a visual lightning stroke monitoring method and a visual lightning stroke monitoring system, wherein the method comprises the following steps: step S1: acquiring lightning stroke data, analyzing and processing the acquired lightning stroke data to acquire the lightning stroke times, judging whether a lightning stroke alarm signal is formed according to the lightning stroke times, executing the step S2 if the lightning stroke alarm signal is formed, otherwise, circularly executing the step S1; step S2: acquiring visual information data comprising image data of a hit object, analyzing and processing the visual information data, comparing the image data in the acquired visual information data with the image data of the hit object in a normal state through an image aberration contrast algorithm, judging whether the hit object is damaged or not, and generating an operation and maintenance work order information report comprising the visual information data of the hit object if the damage exists; otherwise, step S1 is performed. The monitoring method improves the accuracy of fault positioning information; and finally forming an operation and maintenance work order information report comprising the visual information data of the hit object, so that on-site personnel can find the lightning stroke problem in time and perform maintenance in time.
Description
Technical Field
The invention belongs to the technical field of fault diagnosis, and particularly relates to a visual lightning stroke monitoring method and a visual lightning stroke monitoring system which can be used for monitoring the damage fault state of a blade of a wind generating set after lightning stroke.
Background
The development progress of human society is not separated from the efficient utilization of energy. Today, the energy utilization of human beings mainly uses the combustion of fossil fuel to convert chemical energy into electric energy, but a series of environmental problems are brought about at the same time. It is highly desirable to replace non-renewable fossil fuels with clean renewable energy sources, leading to a change in energy structure. Wind driven generator technology is mature day by day, and the wind driven generator technology is greatly developed in all countries of the world due to factors such as large-scale and easy engineering realization.
Wind farms are generally built in relatively open places such as mountains, plains, hills and the like. As the capacity of wind power generation sets (wind power generation sets) is increasing, the height of the tower is increasing in order to obtain enough wind energy, so that the probability of suffering from lightning is much higher than that of the opposite region. After the blade is damaged by lightning strike, the blade can be manually inspected only through post shutdown. But is usually very long after the blades are struck by lightning, especially in offshore wind turbines. By adopting the hysteresis checking mode, after the wind turbine generator is struck by lightning, the blades are damaged and run in a fault mode, and the fault is possibly further expanded. Thereby increasing the maintenance cost and even causing serious accidents such as blade breakage, unit tower falling and the like due to the operation of the blade with faults.
At present, two methods for monitoring lightning strokes of a wind turbine generator are mainly adopted, one method is to monitor the damage fault state of the blade in a manual inspection mode after the lightning strokes occur, the operation is labor-intensive and labor-consuming, the effect is not ideal, and hidden danger is buried for safe and stable operation of the wind turbine generator. The other is to install a large number of sensors to monitor and analyze the lightning stroke state of the wind turbine, and the method improves the monitoring precision of the single wind turbine of the whole wind power plant, but improves the cost of the wind turbine, and is not beneficial to the economy of the wind power plant. Meanwhile, only the wind turbine is known to be struck by lightning, but the damage fault state of the wind turbine blade struck by lightning and the damage fault position information of the wind turbine blade are not known.
Disclosure of Invention
In order to solve the defects and shortcomings of the prior art, the invention aims at providing a visual lightning stroke monitoring method which at least can timely discover damage faults of a hit object after lightning stroke and improve the monitoring precision of the state of the hit object.
In order to achieve the purpose of the invention, the visual lightning stroke monitoring method provided herein comprises the following steps:
step S1: acquiring lightning stroke data, analyzing and processing the acquired lightning stroke data to acquire the lightning stroke times, judging whether a lightning stroke alarm signal is formed according to the lightning stroke times, executing the step S2 if the lightning stroke alarm signal is formed, otherwise, circularly executing the step S1;
step S2: acquiring visual information data comprising image data of a hit object, analyzing and processing the visual information data, comparing the image data in the acquired visual information data with the image data of the hit object in a normal state through an image aberration contrast algorithm, judging whether the hit object is damaged or not, and generating an operation and maintenance work order information report comprising the visual information data of the hit object if the damage exists; otherwise, step S1 is performed.
In some embodiments, the monitoring method provided by the invention further comprises a storage step for storing lightning stroke data and visual information data, wherein the storage step stores each lightning stroke data and the visual information data corresponding to each lightning stroke data; the storage and management of lightning stroke data and visual information data in the whole life cycle of the whole monitored object are realized, and data support is provided for the subsequent state analysis report of the monitored object after lightning stroke.
Another aspect of the invention herein provides a visual lightning strike monitoring system comprising:
the first acquisition terminal is used for acquiring lightning stroke data;
the second acquisition terminal is used for acquiring visual information data;
the main control device is respectively connected with the first acquisition terminal and the second acquisition terminal in a signal manner, receives the lightning stroke data acquired by the first acquisition terminal, processes and analyzes the lightning stroke data to judge whether a lightning stroke alarm signal is formed, triggers the second acquisition terminal to acquire visual information data comprising the image data of the object to be shot according to the lightning stroke alarm signal, processes and analyzes the visual information data to generate an operation and maintenance work order information report comprising the visual information data of the object to be shot.
In some embodiments, the monitoring system further comprises a storage device for storing lightning strike data and visual information data for data provision.
The third aspect of the invention also provides a visual lightning strike monitoring method for a large wind generating set, comprising the following steps:
step S1: acquiring lightning stroke data, analyzing and processing the acquired lightning stroke data to acquire the lightning stroke times, judging whether a lightning stroke alarm signal is formed according to the lightning stroke times, executing the step S2 if the lightning stroke alarm signal is formed, otherwise, circularly executing the step S1;
step S2: acquiring visual information data comprising the image data of the impacted blade, analyzing and processing the visual information data, comparing the image data in the acquired visual information data with the image data of the impacted blade in a normal state through an image aberration contrast algorithm, judging whether the impacted blade is damaged, generating an operation and maintenance work order information report comprising the visual information data of the impacted blade if the damage exists, and executing a step S3; otherwise, executing the step S1;
step S3: and sending out a control instruction to control the wind turbine generator to act, so that the wind turbine generator can be safely stopped.
The invention in a fourth aspect thereof provides a visual lightning strike monitoring system for a large wind turbine generator set, comprising:
the first acquisition terminal is used for acquiring lightning stroke data;
the second acquisition terminal is used for acquiring visual information data;
the main control device is respectively connected with the first acquisition terminal and the second acquisition terminal in a signal manner, receives the lightning stroke data acquired by the first acquisition terminal, processes and analyzes the lightning stroke data to judge whether a lightning stroke alarm signal is formed, triggers the second acquisition terminal to acquire visual information data comprising the image data of the impacted blade according to the lightning stroke alarm signal, processes and analyzes the visual information data to generate an operation and maintenance work order information report comprising the visual information data of the impacted blade;
the main control device is connected with the wind turbine generator control system, provides instructions for the wind turbine generator control system when the hit blade is damaged, and controls the wind turbine generator to act after receiving the instructions, so that the wind turbine generator is safely stopped.
By adopting the technical scheme provided by the invention, the beneficial effects can be achieved at least as follows: according to the monitoring method provided by the invention, the lightning stroke data are acquired, and the visual information data comprising the image data of the hit object are acquired according to the triggering of the lightning stroke data, so that the positions of lightning stroke and damage in positioning can be accurately known, and the accuracy of fault positioning information is improved; and finally forming an operation and maintenance work order information report comprising the visual information data of the hit object, so that on-site personnel can find the lightning stroke problem in time and perform maintenance in time.
Drawings
The above and other features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.
FIG. 1 is a flow chart of a visual lightning strike monitoring method according to an embodiment of the disclosure;
FIG. 2 is a schematic diagram of a visual lightning strike monitoring method for a large wind turbine generator set according to an embodiment of the disclosure;
FIG. 3 is a flowchart of a visual lightning strike monitoring method for a large wind turbine generator system according to an embodiment of the disclosure.
Detailed Description
Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. In the drawings, the size of some of the elements may be exaggerated or otherwise distorted for clarity. The same reference numerals in the drawings denote the same or similar structures, and thus detailed descriptions thereof will be omitted.
An exemplary structure of the visual lightning stroke monitoring system in this embodiment includes a first acquisition terminal, a second acquisition terminal, and a main control device; the main control device comprises a lightning stroke data processing module, a lightning stroke alarming module, a control module, a visual data processing module and a damage alarming module.
The first acquisition terminal is used as a lightning stroke monitoring data acquisition device for sensing lightning strokes, and monitoring the condition of the monitored object suffering from the lightning strokes in real time to form lightning stroke data; the second acquisition terminal is used as a visual acquisition device for acquiring visual information data comprising the image data of the object to be shot; the lightning stroke data processing module is used for processing the lightning stroke data formed by the first acquisition terminal and acquiring the occurrence times of lightning strokes; the lightning stroke alarming module judges whether a lightning stroke alarming signal is formed according to the number of lightning strokes acquired by the lightning stroke data processing module, if the lightning stroke alarming signal is formed, the control module triggers the second acquisition module to acquire visual information data containing image data of the hit object when the lightning stroke data processing module outputs the lightning stroke alarming signal, the visual information data are transmitted to the visual data processing module, the visual recognition algorithm is utilized to analyze and process the acquired visual information data, the state of the hit object after the lightning stroke is judged, a lightning stroke damage report comprising information data such as a hit object picture, a damage area recognized by the visual data processing module and a damage type which can be positioned is generated and is input into the damage alarming module, the damage alarming module compares the image data in the acquired visual information data with the image data in a normal state of the hit object, if the hit object exists, the damage alarming signal is generated (namely, the information for judging that the damage exists is pushed) to the control module, the control module generates an operation order information report comprising the visual information data of the hit object as an alarming report, and the alarming report is used by workers, so that the workers can timely monitor and maintain the lightning stroke object in real time.
The exemplary structure of the visual lightning stroke monitoring system provided herein further comprises a storage device comprising a lightning stroke data storage and management module for realizing the storage and management of lightning stroke whole process data in the whole life cycle of the object to be monitored, and providing data support for the lightning stroke analysis report of the object to be monitored; and/or a visual data storage and management module for storing and managing lightning stroke visual information data in the whole life cycle of the whole object to be monitored is realized, and data support is provided for a later state analysis report of the object to be monitored after being struck by lightning.
With reference to FIG. 1, the method of monitoring the visual lightning strike monitoring system comprises the steps of:
step S1: acquiring lightning stroke data, cleaning and analyzing the acquired lightning stroke data to acquire the lightning stroke times, judging whether a lightning stroke alarm signal is formed according to the lightning stroke times, executing the step S2 if the lightning stroke alarm signal is formed, otherwise, circularly executing the step S1; the number of lightning strokes can be set at will according to the situation, for example, the number of lightning strokes is once, namely, the alarm is given as long as the lightning strokes are suffered;
step S2: acquiring visual information data comprising image data of a hit object, analyzing and processing the visual information data, comparing the image data in the acquired visual information data with the image data of the hit object in a normal state through an image aberration contrast algorithm, judging whether the hit object is damaged or not, and generating an operation and maintenance work order information report comprising the visual information data of the hit object if the damage exists; otherwise, step S1 is performed.
In which the acquired visual information data may be processed in any manner in step S2, and an exemplary processing procedure is provided herein in this embodiment, which is, of course, merely exemplary and not limiting.
The exemplary process specifically includes:
step S21: image preprocessing, namely performing edge monitoring, filtering operation, image scaling and image segmentation on an image in the acquired visual information data;
step S22: feature extraction, namely extracting hog features from the image preprocessed in the step S21;
step S23: and classifying the image quality, and classifying the acquired image by adopting a machine learning method or fitting an SVM model.
In the above step, the classification model is trained by using a large number of normal blade picture features and lost blade picture features in advance, and the collected images are classified by using the trained model after the image features are extracted, so that the collected images are confirmed to be normal or damaged.
In order to better provide data support, a storage step for storing lightning strike data and visual information data is also included, which stores each lightning strike data and visual information data corresponding thereto.
The monitoring system and method provided herein may be applied to any lightning strike visual monitoring, and in this embodiment, the monitoring principle is described in detail by taking the monitoring of a large wind turbine blade as an example, which is of course only exemplary, and those skilled in the art will understand that the monitoring system and method are not limited to be applied to the lightning strike visual monitoring of a large wind turbine blade.
2, 3, a schematic diagram and a flowchart of a visual lightning stroke monitoring method for a large wind turbine generator system according to an embodiment of the disclosure are shown, and a first acquisition terminal is installed at a position where a turbine blade can sense lightning stroke so as to ensure that lightning stroke data can be acquired; the second acquisition terminal is arranged at a position capable of acquiring the visual information data of the blade so as to ensure that the visual information data of the blade can be acquired; the first acquisition terminal and the second acquisition terminal are respectively used as a lightning stroke monitoring data acquisition device and a vision acquisition device to acquire lightning stroke data and vision information data, and after installation is completed, the specific monitoring process is as follows:
when the blade state of the wind turbine is normal, the wind turbine normally operates; when the wind turbine is in a thunderstorm weather working condition state, ensuring that the lightning stroke monitoring data acquisition device is in a normal working condition to acquire lightning stroke data of the wind turbine blade, analyzing and processing the acquired lightning stroke data to acquire lightning stroke times, and judging whether the wind turbine suffers lightning stroke according to the lightning stroke times acquired through analysis, if not, indicating that the wind turbine is in a safe running condition, and continuously acquiring the lightning stroke data by the lightning stroke monitoring data acquisition device; if the wind turbine generator is in an unsafe running state, the lightning stroke alarming module forms a lightning stroke alarming signal input control module, the control module triggers the second acquisition module to acquire visual information data containing the image data of the hit object when the lightning stroke alarming module outputs the visual information data, the visual information data are transmitted to the visual data processing module, the visual information data are induced, analyzed and processed through a visual identification algorithm, the state (damaged or undamaged) of the blade after the lightning stroke is judged, and a blade lightning stroke damage report is automatically generated; the method comprises the steps that a blade lightning damage report is input into a damage alarm module, the damage alarm module compares image data in acquired visual information data with image data of a wind turbine blade in a normal state according to the blade lightning damage report through an image difference comparison algorithm, whether the wind turbine blade is damaged or not is judged, if the wind turbine blade is damaged, a blade damage alarm signal is generated to a control module, and the control module generates an operation and maintenance work order information report comprising the visual information data of the struck wind turbine blade as an alarm report, so that maintenance personnel can effectively maintain and maintain the blade in time, and the state of the wind turbine blade is restored to be normal. If the wind turbine generator system blade is not damaged, the wind turbine generator system is in a safe running state, namely the wind turbine generator system blade is in a normal state, and the lightning stroke monitoring data acquisition device continues to acquire lightning stroke data.
In order to ensure the safety of the wind turbine, the visual data processing module in the main control device is also connected with the wind turbine control system, provides instructions for the wind turbine control system when the struck blade is damaged, and controls the wind turbine to act after the wind turbine receives the instructions, so that the wind turbine is safely stopped.
The lightning stroke data and visual information data acquired by the first acquisition terminal and the second acquisition terminal are respectively stored after being generalized, analyzed and processed, and relevant data support is provided for the later blade after lightning stroke.
The monitoring system and the method provided by the invention are applied to monitoring of the wind turbine generator blade, and are characterized in that: and a lightning stroke monitoring data acquisition device and a vision acquisition device are arranged at the proper positions of the wind turbine generator. And acquiring lightning stroke information of the wind turbine generator through the lightning stroke monitoring data acquisition device. The lightning stroke alarm device sends out alarm information, and the main control module controls the vision acquisition device to start running. And acquiring blade information after the unit is struck by lightning through a visual acquisition device. And (3) processing the appearance information of the blade in real time through an advanced visual recognition algorithm, judging the damage fault state of the blade and the lightning stroke point of the blade after the wind turbine generator is struck by lightning, and automatically generating a blade lightning stroke report. Whether the wind turbine generator system blade is damaged or not is judged by analyzing the lightning strike report of the blade, and meanwhile, the blade damage alarm device judges whether alarm information is sent or not. The visual lightning stroke monitoring of the wind turbine generator is realized, the lightning stroke-appearing blade and the damage position of the lightning stroke blade can be accurately positioned, and the accuracy of fault positioning information is improved. The blade state information can be timely sent to the main control device. The master control device timely generates an operation and maintenance work order information report so as to enable on-site personnel to timely find lightning stroke problems of the wind turbine generator, maintain and maintain the blades and ensure that the wind turbine generator runs in a safe and stable state. The damage faults of the blades of the wind turbine generator after lightning strike can be found in time, the monitoring precision of the damage state of the blades of the wind turbine generator is improved, the safety accidents of the wind turbine generator are avoided, and the safe and stable operation of the wind turbine generator is ensured; meanwhile, the monitoring method and the monitoring system are easy to realize and economical.
The technical scheme has the advantages of low cost, wide environmental adaptability, capability of being comprehensively popularized and the like, and can help field personnel to quickly and accurately locate the damage fault position information of the monitored object. Timely maintain the maintenance to the monitored object, effectually reduced the potential safety hazard of monitored object.
The foregoing has outlined rather broadly the more detailed description of the invention in order that the detailed description of the invention may be better understood, and in order that the present description may be better understood. It is pointed out that it is still possible for the person skilled in the art to modify the aforementioned cases or to make equivalent substitutions in part of the technology. Accordingly, any improvements and modifications that do not depart from the scope of the present invention are intended to be within the scope of the present invention.
Claims (8)
1. A method of visual lightning strike monitoring, the method comprising the steps of:
step S1: acquiring lightning stroke data, analyzing and processing the acquired lightning stroke data to acquire the lightning stroke times, judging whether a lightning stroke alarm signal is formed according to the lightning stroke times, executing the step S2 if the lightning stroke alarm signal is formed, otherwise, circularly executing the step S1;
step S2: the second acquisition module acquires visual information data comprising image data of the object to be struck, analyzes and processes the visual information data through a visual recognition algorithm, judges the state of the blade after the object to be struck is struck, automatically generates a blade lightning stroke damage report comprising the image of the object to be struck, the damage area recognized by the visual data processing module and possibly positioned damage type information data, inputs the blade lightning stroke damage report into the damage alarm module, compares the image data in the acquired visual information data with the image data in the normal state of the object to be struck through an image difference contrast algorithm, judges whether the object to be struck is damaged, and generates an operation and maintenance work order information report comprising the visual information data of the object to be struck if the object to be struck exists;
otherwise, step S1 is performed.
2. The visual lightning strike monitoring method of claim 1, wherein: the step S2 processes the acquired visual information data through the following steps: step S21: image preprocessing, namely performing edge monitoring, filtering operation, image scaling and image segmentation on an image in the acquired visual information data;
step S22: feature extraction, namely extracting hog features from the image preprocessed in the step S21;
step S23: and classifying the image quality, and classifying the acquired image by adopting a machine learning method or fitting an SVM model.
3. The visual lightning strike monitoring method according to claim 1 or 2, wherein: the method further comprises a storage step for storing lightning stroke data and visual information data, wherein the storage step stores each lightning stroke data and the visual information data corresponding to each lightning stroke data.
4. A visual lightning strike monitoring system, wherein the visual lightning strike monitoring method of claim 1 is employed;
the system comprises: the first acquisition terminal is used for acquiring lightning stroke data;
the second acquisition terminal is used for acquiring visual information data;
the main control device is respectively connected with the first acquisition terminal and the second acquisition terminal in a signal manner, receives the lightning stroke data acquired by the first acquisition terminal, processes and analyzes the lightning stroke data to judge whether a lightning stroke alarm signal is formed, triggers the second acquisition terminal to acquire visual information data comprising the image data of the object to be shot according to the lightning stroke alarm signal, processes and analyzes the visual information data to generate an operation and maintenance work order information report comprising the visual information data of the object to be shot;
the device also comprises a storage device for storing lightning stroke data and visual information data, and is used for data provision;
the storage device comprises a lightning stroke data storage and management module for realizing storage and management of lightning stroke whole process data in the whole life cycle of the object to be monitored;
and/or a visual data storage and management module for storing and managing the lightning stroke visual information data in the whole life cycle of the whole object to be monitored.
5. The visual lightning stroke monitoring system according to claim 4, wherein the main control device comprises a lightning stroke data processing module, a lightning stroke alarming module, a control module, a visual data processing module and a damage alarming module, wherein the lightning stroke data processing module is used for processing lightning stroke data formed by the first acquisition terminal and acquiring the occurrence times of lightning strokes;
the lightning stroke alarming module judges whether a lightning stroke alarming signal is formed according to the lightning stroke times acquired by the lightning stroke data processing module, if the lightning stroke alarming signal is formed, the lightning stroke alarming signal is input into the control module, the control module triggers the second acquisition module to acquire visual information data containing the image data of the object to be struck when the lightning stroke alarming module outputs the visual information data, the visual information data are transmitted to the visual data processing module, the visual information data are analyzed and processed by utilizing a visual recognition algorithm, the state of the object to be struck after the lightning stroke is judged, and a lightning stroke damage report of the object to be struck is generated;
and inputting the damage alarm module, wherein the damage alarm module compares the image data in the acquired visual information data with the image data of the object under the normal state by an image difference comparison algorithm, judges whether the object is damaged, generates a damage alarm signal to the control module if the object is damaged, and generates an operation and maintenance work order information report comprising the visual information data of the object under the condition that the object under the condition is damaged, as an alarm report.
6. A visual lightning stroke monitoring method for a large wind generating set is characterized by comprising the following steps:
step S1: acquiring lightning stroke data, analyzing and processing the acquired lightning stroke data to acquire the lightning stroke times, judging whether a lightning stroke alarm signal is formed according to the lightning stroke times, executing the step S2 if the lightning stroke alarm signal is formed, otherwise, circularly executing the step S1;
step S2: the lightning strike alarm signal is input into the control module, the second acquisition module acquires visual information data comprising the image data of the hit blade, analysis and processing are carried out through a visual recognition algorithm, the state of the blade after the lightning strike is judged, a blade lightning strike damage report comprising the image of the hit object, the damage area recognized by the visual data processing module and possibly positioned damage type information data is automatically generated, the blade lightning strike damage report is input into the damage alarm module, the image data in the acquired visual information data is compared with the image data in the normal state of the hit blade through an image difference comparison algorithm, whether the hit blade is damaged or not is judged, if yes, an operation and maintenance work order information report comprising the visual information data of the hit blade is generated, and the step S3 is executed;
otherwise, executing the step S1;
step S3: and sending out a control instruction to control the wind turbine generator to act, so that the wind turbine generator can be safely stopped.
7. A visual lightning stroke monitoring system for a large wind generating set, which is characterized by applying the visual lightning stroke monitoring method for the large wind generating set according to claim 6;
the system comprises: the first acquisition terminal is used for acquiring lightning stroke data;
the second acquisition terminal is used for acquiring visual information data;
the main control device is respectively connected with the first acquisition terminal and the second acquisition terminal in a signal manner, receives the lightning stroke data acquired by the first acquisition terminal, processes and analyzes the lightning stroke data to judge whether a lightning stroke alarm signal is formed, triggers the second acquisition terminal to acquire visual information data comprising the image data of the impacted blade according to the lightning stroke alarm signal, processes and analyzes the visual information data to generate an operation and maintenance work order information report comprising the visual information data of the impacted blade;
the main control device is connected with the wind turbine generator control system, provides a command for the wind turbine generator control system when the hit blade is damaged, and controls the wind turbine generator to act after receiving the command so as to ensure that the wind turbine generator is safely stopped;
the device also comprises a storage device for storing lightning stroke data and visual information data, and is used for data provision;
the storage device comprises a lightning stroke data storage and management module for realizing storage and management of lightning stroke whole process data in the whole life cycle of the object to be monitored;
and/or a visual data storage and management module for storing and managing the lightning stroke visual information data in the whole life cycle of the whole object to be monitored.
8. The visual lightning strike monitoring system of a large wind turbine generator set of claim 7, wherein: the main control device comprises a lightning stroke data processing module, a lightning stroke alarming module, a control module, a visual data processing module and a damage alarming module, wherein the lightning stroke data processing module is used for processing lightning stroke data formed by the first acquisition terminal and acquiring the occurrence times of lightning strokes;
the lightning stroke alarming module judges whether a lightning stroke alarming signal is formed according to the lightning stroke times acquired by the lightning stroke data processing module, if the lightning stroke alarming signal is formed, the lightning stroke alarming signal is input into the control module, the control module triggers the second acquisition module to acquire visual information data containing the image data of the struck blade when the lightning stroke alarming module outputs the visual information data, the visual information data are transmitted to the visual data processing module, the visual information data are analyzed and processed by utilizing a visual recognition algorithm, the state of the struck blade after the struck blade is struck by lightning is judged, and a lightning stroke damage report of the struck blade is generated;
and inputting the damage alarm module, wherein the damage alarm module compares the image data in the acquired visual information data with the image data in the normal state of the blade through an image difference comparison algorithm, judges whether the damaged blade exists, generates a damage alarm signal to the control module if the damaged blade exists, and the control module generates an operation and maintenance work order information report comprising the visual information data of the damaged object as an alarm report.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110569479.0A CN113417809B (en) | 2021-05-25 | 2021-05-25 | Visual lightning stroke monitoring method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110569479.0A CN113417809B (en) | 2021-05-25 | 2021-05-25 | Visual lightning stroke monitoring method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113417809A CN113417809A (en) | 2021-09-21 |
CN113417809B true CN113417809B (en) | 2023-07-18 |
Family
ID=77712887
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110569479.0A Active CN113417809B (en) | 2021-05-25 | 2021-05-25 | Visual lightning stroke monitoring method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113417809B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014024303A1 (en) * | 2012-08-10 | 2014-02-13 | 三菱重工業株式会社 | State observation system and state observation method for wind power generation device |
CN104198827A (en) * | 2014-08-07 | 2014-12-10 | 新疆金风科技股份有限公司 | Thunder and lightning monitoring device of wind power generator set |
JP2016136009A (en) * | 2015-01-23 | 2016-07-28 | 独立行政法人国立高等専門学校機構 | Anti-lightning device for wind turbine |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5427757B2 (en) * | 2010-11-30 | 2014-02-26 | 三菱重工業株式会社 | Lightning strike detection device for hollow structure, wind turbine rotor and wind power generator equipped with the same |
JP5535886B2 (en) * | 2010-11-30 | 2014-07-02 | 三菱重工業株式会社 | Lightning strike detection device, wind turbine rotor and wind power generator equipped with the same |
US8239150B2 (en) * | 2011-05-16 | 2012-08-07 | General Electric Company | System, device, and method for detecting electrical discharges on a structure |
JP5670435B2 (en) * | 2011-12-09 | 2015-02-18 | 三菱重工業株式会社 | Wind turbine |
CN107191338B (en) * | 2017-07-24 | 2023-06-13 | 广州特种承压设备检测研究院 | Lightning stroke fault monitoring system and lightning protection system of wind turbine generator |
JP7208034B2 (en) * | 2019-01-28 | 2023-01-18 | 株式会社日立製作所 | Blade inspection system for wind power generators, wind power generation systems, remote integrated monitoring systems for wind farms |
CN112583115A (en) * | 2020-09-27 | 2021-03-30 | 中节能(阳江)风力发电有限公司 | System for collecting lightning parameters of wind power plant cluster |
-
2021
- 2021-05-25 CN CN202110569479.0A patent/CN113417809B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014024303A1 (en) * | 2012-08-10 | 2014-02-13 | 三菱重工業株式会社 | State observation system and state observation method for wind power generation device |
CN104198827A (en) * | 2014-08-07 | 2014-12-10 | 新疆金风科技股份有限公司 | Thunder and lightning monitoring device of wind power generator set |
JP2016136009A (en) * | 2015-01-23 | 2016-07-28 | 独立行政法人国立高等専門学校機構 | Anti-lightning device for wind turbine |
Non-Patent Citations (1)
Title |
---|
某风电场兆瓦级风电机组叶片雷击故障分析;赵少伟;王洪波;王宝归;;风能(第02期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN113417809A (en) | 2021-09-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114241730B (en) | Substation equipment monitoring and early warning system based on data acquisition | |
CN103306893A (en) | Failure early warning and alarming method for wind-driven generator | |
WO2021073280A1 (en) | Infrared imaging technology-based intelligent fault diagnosis system for photovoltaic panels | |
JP2018037078A (en) | Power generation monitoring system with failure detection function | |
CN108593304A (en) | Nuclear power Emergency diesel multi-state alert status monitors and diagnostic analysis system and method | |
CN113738595A (en) | Method and system for monitoring state of blade of wind generating set | |
CN111555776B (en) | Fusion sensing and joint diagnosis method, system and device for power transmission line | |
CN113253181A (en) | Intelligent information data acquisition and analysis system based on big data | |
CN108506171A (en) | A kind of large-scale half direct-drive unit cooling system for gear box fault early warning method | |
CN112085233A (en) | Power digital information model based on station domain BIM data fusion multi-source information | |
CN106950926B (en) | System and method for controlling and monitoring a power generation facility | |
CN113417809B (en) | Visual lightning stroke monitoring method and system | |
Liu et al. | Wind turbine fault detection with multimodule feature extraction network and adaptive strategy | |
Dhanraj et al. | Statistical data mining through credal decision tree classifiers for fault prediction on wind turbine blades using vibration signals | |
CN110608133B (en) | Offshore wind power generation control system and method | |
CN110865329B (en) | Electric energy metering method and system based on big data self-diagnosis | |
CN117081249A (en) | Automatic monitoring management platform for power supply line and line fault identification method | |
CN109209785A (en) | A kind of Wind turbines intellectual status repair method based on Matlab | |
Wei et al. | Wind turbine pitch system condition monitoring based on performance curves in multiple states | |
CN112283050A (en) | Machine vision-based online monitoring method for wind turbine blade | |
CN105201755B (en) | A kind of identification device of wind-power blade superficial failure | |
CN109521314A (en) | A kind of steam-electric power plant remote fault diagnosis method | |
CN111539642B (en) | Object-oriented power plant data acquisition and processing system and method thereof | |
CN202916207U (en) | Blade damage on-line examination system for wind generating set | |
CN108223270B (en) | The method for early warning and device of the wind vane bearing clamping stagnation of wind power 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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 618099 No.99, Zhujiang East Road, Jingyang District, Deyang City, Sichuan Province Applicant after: Dongfang Electric Wind Power Co.,Ltd. Address before: 618099 No.99, Zhujiang East Road, Jingyang District, Deyang City, Sichuan Province Applicant before: DONGFANG ELECTRIC WIND POWER Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |