CN115965579A - Method and system for identifying and positioning three-dimensional defects in transformer substation inspection - Google Patents
Method and system for identifying and positioning three-dimensional defects in transformer substation inspection Download PDFInfo
- Publication number
- CN115965579A CN115965579A CN202211419444.XA CN202211419444A CN115965579A CN 115965579 A CN115965579 A CN 115965579A CN 202211419444 A CN202211419444 A CN 202211419444A CN 115965579 A CN115965579 A CN 115965579A
- Authority
- CN
- China
- Prior art keywords
- data
- inspection
- substation
- equipment
- transformer substation
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a three-dimensional defect identification and positioning method and system for substation inspection, and belongs to the technical field of defect identification and positioning of substation equipment. The method comprises the following steps: collecting multisource inspection data and point cloud data of a transformer substation, and recording the spatial position and the attitude of inspection collection equipment; finely positioning the inspection equipment in a pre-built real-scene three-dimensional model of the transformer substation based on the point cloud data; generating patrol data with extensible time sequence; generating component-level data; determining change data of the substation parameters in the component-level data, performing defect diagnosis of the substation component equipment based on the change data to identify defect types of the substation equipment components, and locating defect spaces of the substation equipment components. The invention can realize the rapid diagnosis and positioning of external thermal defects and insulation defects typical of substation equipment.
Description
Technical Field
The invention relates to the technical field of transformer equipment defect identification and positioning, in particular to a transformer station inspection three-dimensional defect identification and positioning method and system.
Background
With the continuous development of Chinese economy, the demand of various industries on electric power is continuously increased, and electric energy becomes one of the fastest-developing industries in the energy industry; along with intelligent, intensive, the unmanned continuous promotion of requirement of transformer substation, more and more changeable power station adopts long-range intelligence system of patrolling and examining, and long-range system of patrolling and examining includes: high definition camera, infrared, ultraviolet, robot, unmanned aerial vehicle and voiceprint equipment etc. can realize to the outside observable of transformer substation equipment, audible, measurable, "combine artificial intelligence image recognition and neural network algorithm, can realize categorizing, target detection and the example segmentation to the result. However, due to the complex scene of the transformer substation, the accuracy of the defect diagnosis of the transformer equipment is improved, and the following problems are mainly existed:
1) Artificial intelligence recognition algorithms of different acquisition means are mutually independent
At present, visible light, infrared and ultraviolet images adopt a computer vision algorithm based on an artificial intelligent neural network to carry out target detection and example segmentation; voiceprint, acoustic imaging and classification algorithms mainly based on artificial intelligence deep neural networks are adopted; the results output by artificial intelligence algorithms corresponding to different acquisition means have no direct relation, and comprehensive study and judgment can not be formed for the state evaluation of the power transformation equipment.
2) The results of different acquisition means lack a uniform data level fusion carrier
Currently, data such as visible light, infrared, ultraviolet, voiceprint and acoustic imaging are stored and analyzed in separate unstructured files, such as RGB image files, infrared thermographic image files, ultraviolet image files, voiceprint audio files and acoustic imaging image files. The results of the different acquisition approaches lack a uniform data-level fusion carrier, e.g., defects in visible light, overheating defects, and corona discharges cannot be represented in a uniform result. Therefore, the more and more data bring difficulties to data fusion analysis and heavier data burden to operation and maintenance personnel for data maintenance and diagnosis.
3) Artificial intelligence recognition algorithm of different acquisition means lacks prior knowledge of equipment service attribute
At present, artificial intelligence recognition algorithms of different acquisition means are all algorithm models based on sample marking and learning, but the accuracy of the artificial intelligence recognition algorithms in transformer substation defect recognition cannot reach a higher level, and on one hand, the artificial intelligence recognition algorithms have a relatively large relation with the number of samples and the quality of the samples. On the other hand, strong relation exists between the substation equipment and the defects, and the artificial intelligent recognition algorithm only learns through the sample itself, and is short of important priori knowledge of the service attributes of the equipment.
4) Different acquisition approaches all lack timing dimensionality while preserving spatial attributes
At present, spatial information of a picture at the acquisition time is reserved in data such as visible light, infrared, ultraviolet and sound imaging, but due to the fact that a large number of defects are difficult to judge at a single time, judgment needs to be carried out in combination with a historical change rule. When comparing different time dimension, the traditional way is to mark the name or field of the unstructured data with a timestamp, and then compare the unstructured data at different time. For example, the positions of the equipment components corresponding to the temperature values of the same coordinate point of the infrared images acquired at different moments are not completely the same and cannot be directly compared, and the equipment space positions corresponding to the highest temperature and the lowest temperature at different moments are also different, so that an effective means for time sequence dimension comparison is lacked.
Disclosure of Invention
Aiming at the problems, the invention provides a method for identifying and positioning three-dimensional defects in substation inspection, which comprises the following steps:
calibrating a relative physical position of patrol acquisition equipment carried by the mobile patrol equipment of the transformer substation to convert internal and external parameters of the patrol acquisition equipment, acquiring multisource patrol data and point cloud data of the transformer substation based on the patrol acquisition equipment after the internal and external parameters of the patrol acquisition equipment are converted, and recording the spatial position and the attitude of the patrol acquisition equipment;
the inspection equipment is roughly positioned in a preset live-action three-dimensional model of the transformer substation according to the spatial position and the attitude, and after rough positioning, the inspection equipment is finely positioned in the preset live-action three-dimensional model of the transformer substation based on point cloud data;
registering and mapping the multi-source patrol data on the live-action three-dimensional model according to the spatial position, the posture and the internal and external parameters of the patrol acquisition equipment corresponding to the precise positioning, and storing the multi-source patrol data subjected to registering and mapping in a time sequence extensible structured data format to generate time sequence extensible patrol data;
performing data division on the patrol data with the extensible time sequence based on a pre-established component-level live-action three-dimensional model to generate component-level data;
determining change data of the substation parameters in the component-level data, performing defect diagnosis of the substation component equipment based on the change data to identify defect types of the substation equipment components, and locating defect spaces of the substation equipment components.
Optionally, the detection and collection device includes at least one of the following: the device comprises a laser radar, a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor and an ultrahigh frequency sensor.
Optionally, the visible light camera, the infrared camera, the ultraviolet camera, the acoustic imaging sensor and the ultrahigh frequency sensor are used for acquiring multi-source inspection data of the transformer substation.
Optionally, the laser radar is used for scanning and acquiring point cloud data of the transformer substation.
Optionally, laser point cloud data of the transformer substation are collected through a multi-station laser radar, and the laser point cloud data are spliced to build a real-scene three-dimensional model of the transformer substation.
Optionally, the pre-built live-action three-dimensional model of the transformer substation is subjected to space and business semantic segmentation through the ledger information of the transformer substation so as to build the component-level live-action three-dimensional model of the transformer substation.
Optionally, the change data includes at least one of: the three-dimensional appearance change data, the temperature change data, the corona discharge change data, the vibration change data and the internal discharge change data of the transformer substation.
Optionally, the method further comprises: and verifying the identification accuracy of the multi-source inspection data according to a preset initial confidence value, adjusting the confidence value of the multi-source inspection data according to the accuracy, and sending a state abnormality alarm to the corresponding inspection acquisition equipment for the multi-source inspection data with the constantly reduced confidence value.
Optionally, initial values of the defect diagnosis confidence coefficients of different multi-source inspection data are set according to the equipment types of the substation component equipment.
On the other hand, the invention also provides a transformer substation inspection three-dimensional defect identification and positioning system, which comprises:
the system comprises a data acquisition unit, a data processing unit and a data processing unit, wherein the data acquisition unit is used for calibrating relative physical positions of patrol acquisition equipment carried by the mobile patrol equipment of the transformer substation so as to convert internal and external parameters of the patrol acquisition equipment, acquiring multi-source patrol data and point cloud data of the transformer substation based on the patrol acquisition equipment after the internal and external parameters of the patrol acquisition equipment are converted, and recording the spatial position and the attitude of the patrol acquisition equipment;
the positioning unit is used for roughly positioning the inspection equipment in a preset live-action three-dimensional model of the transformer substation according to the spatial position and the attitude, and finely positioning the inspection equipment in the preset live-action three-dimensional model of the transformer substation based on point cloud data after rough positioning;
the data processing unit is used for carrying out registration mapping on the multi-source inspection data on the live-action three-dimensional model according to the spatial position, the posture and the internal and external parameters of the inspection acquisition equipment corresponding to the precise positioning, and storing the multi-source inspection data subjected to registration mapping in a time sequence extensible structured data format to generate time sequence extensible inspection data;
the data conversion unit is used for carrying out data division on the patrol data with the extensible time sequence based on a pre-built component-level live-action three-dimensional model so as to generate component-level data;
and the diagnosis unit is used for determining the change data of the substation parameters in the component-level data, diagnosing the defects of the substation component equipment based on the change data so as to identify the defect types of the substation equipment components and locate the defect spaces of the substation equipment components.
Optionally, the inspection acquisition device includes at least one of the following: the system comprises a laser radar, a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor and an ultrahigh frequency sensor.
Optionally, the visible light camera, the infrared camera, the ultraviolet camera, the acoustic imaging sensor and the ultrahigh frequency sensor are used for acquiring multi-source inspection data of the transformer substation.
Optionally, the laser radar is used for scanning and acquiring point cloud data of the transformer substation.
Optionally, laser point cloud data of the transformer substation are collected through a multi-station laser radar, and the laser point cloud data are spliced to build a real-scene three-dimensional model of the transformer substation.
Optionally, the space and business semantics of the pre-built live-action three-dimensional model of the transformer substation are segmented through the ledger information of the transformer substation, so as to build a component-level live-action three-dimensional model of the transformer substation.
Optionally, the change data includes at least one of the following: three-dimensional appearance change data, temperature change data, corona discharge change data, vibration change data and internal discharge change data of the transformer substation.
Optionally, the diagnostic unit is further configured to: and verifying the identification accuracy of the multi-source inspection data according to a preset initial confidence value, adjusting the confidence value of the multi-source inspection data according to the accuracy, and sending a state abnormality alarm to the corresponding inspection acquisition equipment for the multi-source inspection data with the constantly reduced confidence value.
Optionally, initial values of the defect diagnosis confidence coefficients of different multi-source inspection data are set according to the equipment types of the substation component equipment.
In yet another aspect, the present invention also provides a computing device comprising: one or more processors;
a processor for executing one or more programs;
when executed by the one or more processors, implement the methods as described above.
In yet another aspect, the invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, performs the method as described above.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a method for identifying and positioning three-dimensional defects of a transformer substation, which comprises the following steps: calibrating a relative physical position of patrol acquisition equipment carried by the mobile patrol equipment of the transformer substation to convert internal and external parameters of the patrol acquisition equipment, acquiring multisource patrol data and point cloud data of the transformer substation based on the patrol acquisition equipment after the internal and external parameters of the patrol acquisition equipment are converted, and recording the spatial position and the attitude of the patrol acquisition equipment; the inspection equipment is roughly positioned in a preset live-action three-dimensional model of the transformer substation according to the spatial position and the attitude, and after rough positioning, the inspection equipment is finely positioned in the preset live-action three-dimensional model of the transformer substation based on point cloud data; registering and mapping the multi-source inspection data on the live-action three-dimensional model according to the spatial position, the posture and the internal and external parameters of the inspection acquisition equipment corresponding to the precise positioning, and storing the multi-source inspection data subjected to registering and mapping in a time sequence extensible structured data format to generate time sequence extensible inspection data; performing data division on the patrol data with the extensible time sequence based on a pre-built component-level real-scene three-dimensional model to generate component-level data; determining change data of the substation parameters in the component-level data, performing defect diagnosis on substation component equipment based on the change data to identify defect types of the substation equipment components, and locating defect spaces of the substation equipment components. The invention can realize the rapid diagnosis and positioning of external thermal defects and insulation defects typical of substation equipment.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic flow chart of an embodiment of the method of the present invention;
FIG. 3 (a) is a schematic view of a multi-station laser point cloud scanning method for realizing a whole station live-action three-dimensional model;
fig. 3 (b) is a schematic diagram of a complete substation area real-scene three-dimensional model constructed by multi-station laser point cloud splicing according to the embodiment of the method;
FIG. 4 is a schematic diagram of a defect identification and location system in accordance with an embodiment of the method of the present invention;
FIG. 5 is a schematic diagram of space and service semantic segmentation of a substation live-action three-dimensional model through substation equipment ledger information according to an embodiment of the method of the present invention;
fig. 6 is a schematic diagram of a substation mobile inspection device according to an embodiment of the method of the present invention;
FIG. 7 is a schematic diagram of internal and external parameter conversion of a polling acquisition module according to an embodiment of the method of the present invention;
FIG. 8 is a schematic diagram of the method embodiment of the present invention for realizing fine positioning by comparing and registering point cloud data with a real-world three-dimensional model of a transformer substation;
FIG. 9 is a schematic illustration of defect type identification and defect spatial localization of a device component of an embodiment of the method of the present invention;
FIG. 10 is a schematic diagram of defect identification accuracy adjusting confidence levels of different data source diagnoses according to an embodiment of the method of the present invention;
FIG. 11 is a schematic diagram of an inspection equipment state anomaly alarm performed on a data source with a continuously decreasing diagnostic confidence level according to an embodiment of the method of the present invention;
FIG. 12 is a block diagram of the system of the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the embodiments described herein, which are provided for complete and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, the same units/elements are denoted by the same reference numerals.
Unless otherwise defined, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Further, it will be understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
Example 1:
the invention provides a method for identifying and positioning three-dimensional defects in substation routing inspection, which comprises the following steps of:
step 1, calibrating a relative physical position of patrol and inspection acquisition equipment carried by mobile patrol and inspection equipment of a transformer substation so as to convert internal and external parameters of the patrol and inspection acquisition equipment, acquiring multi-source patrol and inspection data and point cloud data of the transformer substation based on the patrol and inspection acquisition equipment after the internal and external parameters of the patrol and inspection acquisition equipment are converted, and recording the spatial position and the attitude of the patrol and inspection acquisition equipment;
step 2, performing rough positioning on the inspection equipment in a preset live-action three-dimensional model of the transformer substation according to the spatial position and the attitude, and performing fine positioning on the inspection equipment in the preset live-action three-dimensional model of the transformer substation based on point cloud data after the rough positioning;
step 3, registering and mapping the multi-source patrol data on the live-action three-dimensional model according to the spatial position, the posture and the internal and external parameters of the patrol acquisition equipment corresponding to the precise positioning, and storing the multi-source patrol data subjected to registering and mapping in a time sequence extensible structured data format to generate time sequence extensible patrol data;
step 4, performing data division on the patrol data with the extensible time sequence based on a pre-built component-level real-scene three-dimensional model to generate component-level data;
and 5, determining the change data of the transformer substation parameters in the component level data, and diagnosing the defects of the transformer substation component equipment based on the change data so as to identify the defect types of the transformer substation equipment components and position the defect spaces of the transformer substation equipment components.
Wherein, examine collection equipment, include at least one of following: the device comprises a laser radar, a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor and an ultrahigh frequency sensor.
The system comprises a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor and a ultrahigh frequency sensor, wherein the visible light camera, the infrared camera, the ultraviolet camera, the acoustic imaging sensor and the ultrahigh frequency sensor are used for acquiring multi-source inspection data of a transformer substation.
The laser radar is used for scanning and acquiring point cloud data of the transformer substation.
The method comprises the steps of collecting laser point cloud data of a transformer substation through a multi-station laser radar, and splicing the laser point cloud data to build a real-scene three-dimensional model of the transformer substation.
The method comprises the steps of carrying out space and business semantic segmentation on a pre-built live-action three-dimensional model of the transformer substation through the ledger information of the transformer substation so as to build a component-level live-action three-dimensional model of the transformer substation.
Wherein, the change data comprises at least one of the following data: three-dimensional appearance change data, temperature change data, corona discharge change data, vibration change data and internal discharge change data of the transformer substation.
Wherein, the method further comprises: and verifying the identification accuracy of the multi-source inspection data according to a preset initial confidence value, adjusting the confidence value of the multi-source inspection data according to the accuracy, and sending a state abnormality alarm to the corresponding inspection acquisition equipment for the multi-source inspection data with the constantly reduced confidence value.
And setting initial values of the defect diagnosis confidence coefficients of different multi-source inspection data according to the equipment types of the substation component equipment.
The invention will be further described below with reference to a specific implementation of a substation:
as shown in fig. 2, the implementation steps include:
101, building a complete substation live-action three-dimensional model through multi-station laser point cloud splicing according to laser point cloud data acquired by a multi-station laser radar.
Specifically, a schematic diagram of constructing a complete substation live-action three-dimensional model by multi-station laser point cloud splicing is shown in fig. 3 (a).
Specifically, the number of stations scanned by the laser radar is set according to the scale of the transformer substation, the area, the equipment density and the equipment shielding condition.
Specifically, the space coordinates of the laser radars are recorded at each laser radar scanning station, rough registration of laser point clouds is carried out through the space coordinates, fine registration is achieved through the feature points of the laser point clouds, and a complete substation live-action three-dimensional model is constructed.
Specifically, as shown in fig. 3 (b), at least a different angle lidar scan is included at each area and device to ensure a complete three-dimensional model of the area and device.
Specifically, the erection height of the laser radar is generally 1.5 m-2 m, and the height observed by a general inspection worker is considered to be about 1.7 m; and the scanning distance is within the range of 20m, the precision reduction of the laser radar outside 20m is considered, and the point cloud data within the range of 20m is intercepted and used as the effective point cloud data of the station.
And 102, performing space and service semantic segmentation on the substation live-action three-dimensional model through substation equipment ledger information, and constructing a component-level substation live-action three-dimensional model.
Specifically, as shown in fig. 4, a schematic diagram of a three-dimensional defect identification and location system for substation inspection is shown. The method comprises the following steps: and combining the inspection equipment with the station side analysis host.
Wherein, jointly patrol and examine equipment and include: the combined inspection integrated sensing device, the motion module and the positioning module; the combined inspection integrated sensing device is used for collecting visible light images, infrared thermal imaging images, ultraviolet corona discharge images, acoustic imaging images, ultrahigh frequency partial discharge array space positioning images and laser point clouds; the motion module is used for changing the posture of the combined inspection integrated sensing device in the horizontal and vertical directions; the positioning module is used for determining the position of the combined inspection equipment; the combined inspection equipment can be used for carrying a robot or an unmanned aerial vehicle.
Wherein, jointly patrol and examine integrated perception device and include: the system comprises a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor, an ultrahigh frequency sensor, a laser radar and time synchronization module, a front-end signal processing module and a front-end communication module; the visible light camera is used for collecting electromagnetic wave images with the wavelength of 400 nm-780 nm and reflecting the surface color, texture and edge information of the equipment; the infrared camera is used for collecting electromagnetic wave images with the wavelength of 780 nm-14 um in the temperature range of-20 ℃ to +200 ℃ and reflecting the surface temperature distribution of the equipment; the ultraviolet camera is used for collecting electromagnetic wave images with the wavelength of 10 nm-400 nm and reflecting the corona discharge amount distribution of the equipment; the acoustic imaging sensor is used for acquiring acoustic waves with the frequency of 20 Hz-20 kHz and reflecting the sound field distribution of the running sound of the equipment; the ultrahigh frequency sensor is used for collecting the spatial distribution of electromagnetic waves with the wavelength of 0.1-1 m and reflecting the local discharge field intensity distribution of the equipment; the laser radar is used for transmitting and receiving electromagnetic waves with the wavelengths of 850nm, 905nm,1550nm and the like, and reflecting the appearance space shape of the equipment; the time synchronization module is used for sending us-level synchronization instructions to realize synchronous data acquisition of different modules; the front-end signal processing module is used for compressing and coding the video stream with high frame rate and high definition to realize the compression and coding of the high frame rate data collected by the multi-channel module; the front-end communication module is used for transmitting the compressed and coded data stream to the station-end analysis host, and can be configured with a wired transmission protocol or a wireless transmission protocol according to requirements.
Wherein, station end analysis host computer includes: the system comprises a station end communication module and an analysis and calculation module; the station end communication module is used for receiving the data stream compressed and coded by the front end communication module; the analysis and calculation module is used for realizing 1) space and service semantic segmentation of the substation equipment ledger information on the substation live-action three-dimensional model, and constructing a component-level substation live-action three-dimensional model; 2) The conversion of internal and external parameters of different polling acquisition equipment is realized; 3) The rough positioning of the patrol inspection acquisition equipment on the live-action three-dimensional model is realized through the spatial position and the posture of the patrol inspection acquisition equipment, and the fine positioning is realized through the comparison and registration of the point cloud data and the live-action three-dimensional model of the transformer substation; 4) According to the spatial position and the posture of fine positioning and internal and external parameters of the inspection acquisition device, registration mapping of two-dimensional inspection data on the live-action three-dimensional model is realized, and the inspection data is stored and analyzed in a structured data format with an extensible time sequence; 5) Performing data division on patrol data with an extensible time sequence according to a component-level substation live-action three-dimensional model, and realizing defect type identification and defect space positioning on equipment components through three-dimensional appearance change, temperature change, corona discharge change, vibration change and internal discharge change of the component-level data; 6) Setting initial confidence values of defect diagnosis of different data sources according to defect types, calculating the defect identification accuracy of different data sources under different defects through manual defect type verification, and adjusting the confidence coefficients of the diagnosis of different data sources according to the defect identification accuracy; 7) And (5) performing inspection equipment state abnormity warning on the data source with the continuously reduced diagnosis confidence coefficient.
Specifically, as shown in fig. 5, the space and service semantic segmentation refers to that a component-level substation realistic three-dimensional model is constructed by dividing point sets according to a region Z, equipment E and a component U and assigning service attributes to the point sets through a point set P { P1, P2, P3,. And pn } of the substation realistic three-dimensional model.
TABLE 1
Specifically, there is no common point between different component point sets, all component point sets under the same device construct a complete device point set, and all device point sets under the same region construct a complete region point set.
Specifically, the part-level substation live-action three-dimensional model refers to a complete external laser point cloud point set P for describing a substation equipment part ZnEmUk The point set includes different spatial points { pa, pa +1, pa + 2.,. Pb }, and spatial points pk = { xk, yk, zk } are described by three-dimensional spatial coordinates.
103, carrying a laser radar, a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor, an ultrahigh frequency sensor and other patrol inspection acquisition modules on the transformer substation mobile patrol inspection equipment, and realizing conversion of internal and external parameters of different patrol inspection acquisition equipment by calibrating relative physical positions of the laser radar, the visible light camera, the infrared camera, the ultraviolet camera, the acoustic imaging sensor and the ultrahigh frequency sensor.
Specifically, as shown in fig. 6, the mobile substation inspection equipment provided by the invention can be used for carrying inspection acquisition modules such as a laser radar, a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor, a ultrahigh frequency sensor and the like. The cloud platform can carry different polling acquisition modules, different polling acquisition module combinations can be realized, and combined polling of different sensing parameters can be realized.
Specifically, the laser radar module is fixed on the two-degree-of-freedom holder and used for acquiring the external space state of the equipment, and the positioning of the position posture of the substation mobile inspection equipment can be realized by comparing the external space state with the live-action three-dimensional model.
Specifically, collection module is patrolled and examined for general commonly used transformer substation to visible light camera, infrared camera, demountable installation on laser radar to can tear open according to special requirement of patrolling and look over and trade other collection module of patrolling and examining, for example sound imaging sensor, ultraviolet camera or superfrequency sensor.
Specifically, the internal and external reference conversion is shown in fig. 7, the coordinate system of the patrol inspection acquisition module is Oc-XcYcZc, the coordinate system of the laser radar is OL-XLYLZL, the coordinate system of the two-dimensional image is Oi-uv, and the unified coordinate system is Ow-XwYwZw. The internal reference conversion is to obtain coordinates of an Oc-XcYcZc coordinate system by transforming an Oi-uv two-dimensional image coordinate system through (fx, fy); 4) And the external reference conversion is to convert the Oc-XcYcZc coordinate system and the OL-XXYLZL coordinate system into a unified coordinate system of Ow-XwYwZw, wherein the Oc-XcYcZc obtains an Ow-XwYwZw coordinate system coordinate through Pc conversion, and the OL-XLYLZL obtains an Ow-XwYwZw coordinate system coordinate through (RL-w, TL-w) conversion.
And 104, recording the spatial position and the posture of the patrol inspection acquisition equipment and the point cloud data scanned by the laser radar while acquiring the multi-source patrol inspection data.
Specifically, the time synchronization module shown in fig. 4 is used to realize the synchronous data acquisition of different polling acquisition modules.
Specifically, the spatial position of the patrol inspection acquisition equipment is positioned by the positioning module shown in fig. 4, including but not limited to Beidou positioning system, GPS, RTK and other positioning modes, spatial position information is transmitted to the front-end communication module through the time synchronization module synchronization timestamp and the front-end signal processing module, and the spatial position information is transmitted back to the station-end communication module after being coded and is used for the rough positioning of the patrol inspection acquisition equipment in the real three-dimensional model in the station-end analysis and calculation module.
Specifically, the posture of the inspection acquisition equipment transmits the angle of a pan/tilt code wheel to a front-end communication module through a time synchronization module synchronization timestamp through a motion module shown in fig. 4, and the angle is transmitted to a station-end communication module through a front-end signal processing module, is coded and then transmitted back to the station-end communication module and is used for coarse positioning of the inspection acquisition equipment on the live-action three-dimensional model in a station-end analysis and calculation module.
And 105, realizing coarse positioning of the patrol inspection acquisition equipment on the live-action three-dimensional model through the spatial position and the posture of the patrol inspection acquisition equipment, and realizing fine positioning through comparison and registration of the point cloud data and the live-action three-dimensional model of the transformer substation.
Specifically, the positioning module can provide meter-level positioning accuracy, the live-action three-dimensional model has absolute space coordinates, the coarse positioning of the patrol inspection acquisition equipment on the live-action three-dimensional model is realized through the meter-level space positioning of the positioning module, and meanwhile, the local live-action three-dimensional model under the coarse positioning is obtained.
Specifically, fine positioning is shown in fig. 8, 1) extracting feature points from the local live-action three-dimensional model; 2) Extracting characteristic points from point cloud data acquired by a laser radar; 3) The characteristic points of the point cloud collected by the laser radar are matched with the characteristic points of the local real-scene three-dimensional model under rough positioning, and the matching precision can reach millimeter level; 4) Acquiring point cloud by a laser radar, and reversely deducing the coordinate position of the laser radar; 5) And mapping the coordinate position to the live-action three-dimensional model to realize the fine positioning of the patrol inspection acquisition equipment in the live-action three-dimensional model.
And 106, realizing registration mapping of the two-dimensional inspection data on the live-action three-dimensional model according to the precisely positioned spatial position, the precisely positioned attitude and internal and external parameters of the inspection acquisition device, and storing and analyzing the inspection data through a structured data format with an extensible time sequence.
Specifically, the registration mapping of the two-dimensional inspection data on the live-action three-dimensional model is realized through the internal and external parameter conversion mode in step 103 and the coarse positioning and fine positioning mode in step 105.
Specifically, the time-series extensible structured data format is shown in FIG. 9, in which the X, Y, Z spatial coordinates of the point cloud are unchanged, and all other attributes are changed with time, for example, the color attribute RGB value (R) of the point cloud p1 is collected at time t0 p1-t0 ,G p1-t0 ,B p1-t0 ) (ii) a Collecting point cloud P1 sound field intensity value P at t1 moment p1-t1 (ii) a Collecting point cloud P2 sound field intensity value P at time t2 p2-t2 Acquiring the attribute temperature T value T of the point cloud p3 at the moment T3 p3-t3 。
TABLE 2
And 107, carrying out data division on the inspection data with the extensible sequence according to a part-level substation live-action three-dimensional model, and realizing defect type identification and defect space positioning on equipment parts through three-dimensional appearance change, temperature change, corona discharge change, vibration change and internal discharge change of the part-level data.
Specifically, the temperature change, the corona discharge change, the vibration change and the internal discharge change can realize the positioning of the abnormal region through the time domain change of the temperature attribute T, the corona discharge attribute C, the vibration change attribute P and the internal partial discharge attribute D of the point cloud.
Specifically, as shown in fig. 9, the horizontal axis is time, the vertical axis is attribute values of different point clouds, the general point cloud attribute value is between pmax and pmin, and when the attribute of a certain point cloud or a certain area point cloud exceeds the range of pmax and pmin and the overrun ratio exceeds 30%, active early warning can be performed on defects corresponding to the attribute.
Specifically, the three-dimensional appearance change is compared with the coordinate of the live-action three-dimensional model through the acquired point cloud coordinate, the trend of the space position coordinate difference value for 3 times continuously is larger than 10mm, and appearance deformation warning can be performed.
Specifically, the identification of different types of defects can be realized by combining the attribute values of the component-level point cloud with the diagnosis rules of the guide rules.
Specifically, the initial confidence value is set according to the statistical condition of the defect type, and then after the defect location and defect identification in step 107, the confidence is corrected by manually verifying whether the defect type is correct or not. Taking the lightning arrester affected with damp defect as an example, the initial confidence value of infrared is 60%, the initial confidence value of ultraviolet is 60%, the initial confidence value of ultrahigh frequency is 20%, the initial confidence value of acoustic imaging is 50%, and the initial confidence value of laser point cloud is 20%. Because infrared is correct to arrester defect identification that wets, and ultraviolet judges the mistake, and the superfrequency judges the mistake, and the acoustic imaging can't be judged, and the laser point cloud can't be judged, therefore the confidence after the renewal is: the initial confidence value of infrared is 90%, the initial confidence value of ultraviolet is 55%, the initial confidence value of ultrahigh frequency is 15%, the initial confidence value of acoustic imaging is 50%, and the initial confidence value of laser point cloud is 20%.
In particular, the confidence may be used as a weight for the diagnosis result at the time of fusion diagnosis. The fusion diagnosis result = infrared confidence degree + ultraviolet confidence degree + ultra-high frequency confidence degree + acoustic imaging diagnosis result + laser point cloud confidence degree.
And step 109, performing inspection equipment state abnormity warning on the data source with the continuously reduced diagnosis confidence coefficient.
Specifically, as shown in fig. 11, under the condition of long-term monitoring and diagnosis of the inspection acquisition equipment, the confidence coefficients of different inspection data diagnoses are regressed stably from the initial confidence coefficient values, and this interval is a confidence coefficient regression region; but with the further increase of the polling times of the polling device, the confidence coefficient can not change greatly, the interval is a confidence coefficient stable area, and the polling acquisition equipment has the highest fusion diagnosis accuracy in the confidence coefficient stable area; when the confidence coefficient of diagnosis of certain inspection data continuously decreases, the condition that hidden danger exists in the front-end hardware collection of the inspection equipment is shown, and the interval is a confidence coefficient decreasing area, so that active warning can be performed on the abnormal state of the inspection equipment, and operation and maintenance personnel are reminded to check the front-end hardware of the inspection equipment.
Example 2:
the invention further provides a transformer substation inspection three-dimensional defect identification and positioning system 200, as shown in fig. 12, including:
the data acquisition unit 201 is used for calibrating relative physical positions of patrol inspection acquisition equipment carried by the mobile patrol inspection equipment of the transformer substation so as to convert internal and external parameters of the patrol inspection acquisition equipment, acquiring multi-source patrol inspection data and point cloud data of the transformer substation based on the patrol inspection acquisition equipment after the internal and external parameters of the patrol inspection acquisition equipment are converted, and recording the spatial positions and postures of the patrol inspection acquisition equipment;
the positioning unit 202 is used for roughly positioning the inspection equipment in a preset live-action three-dimensional model of the transformer substation according to the spatial position and the attitude, and finely positioning the inspection equipment in the preset live-action three-dimensional model of the transformer substation based on point cloud data after rough positioning;
the data processing unit 203 is used for carrying out registration mapping on the multi-source inspection data on the live-action three-dimensional model according to the spatial position, the posture and the internal and external parameters of the inspection acquisition equipment corresponding to the precise positioning, and storing the multi-source inspection data subjected to registration mapping in a time sequence extensible structured data format to generate time sequence extensible inspection data;
the data conversion unit 204 is used for carrying out data division on the patrol data with the extensible time sequence based on a pre-established component-level real-scene three-dimensional model so as to generate component-level data;
the diagnosis unit 205 determines variation data of the substation parameters in the component-level data, performs defect diagnosis of the substation component equipment based on the variation data to identify defect types of the substation equipment components, and locates defect spaces of the substation equipment components.
Wherein, patrol and examine collection equipment, include at least one of following: the device comprises a laser radar, a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor and an ultrahigh frequency sensor.
The system comprises a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor and an ultrahigh frequency sensor, wherein the visible light camera, the infrared camera, the ultraviolet camera, the acoustic imaging sensor and the ultrahigh frequency sensor are used for acquiring multisource inspection data of the transformer substation.
The laser radar is used for scanning and acquiring point cloud data of the transformer substation.
The method comprises the steps of collecting laser point cloud data of a transformer substation through a multi-station laser radar, and splicing the laser point cloud data to build a real-scene three-dimensional model of the transformer substation.
The method comprises the steps of carrying out space and business semantic segmentation on a pre-built live-action three-dimensional model of the transformer substation through the ledger information of the transformer substation so as to build a component-level live-action three-dimensional model of the transformer substation.
Wherein the change data comprises at least one of the following data: three-dimensional appearance change data, temperature change data, corona discharge change data, vibration change data and internal discharge change data of the transformer substation.
Wherein the diagnostic unit is further configured to: and verifying the identification accuracy of the multi-source inspection data according to a preset initial confidence value, adjusting the confidence value of the multi-source inspection data according to the accuracy, and sending a state abnormality alarm to the corresponding inspection acquisition equipment for the multi-source inspection data with continuously reduced confidence value.
According to the equipment types of the substation component equipment, initial values of the defect diagnosis confidence coefficients of different multi-source inspection data are set.
The present invention solves the following problems:
1) The artificial intelligence recognition algorithms of different acquisition means are mutually independent;
2) Results of different acquisition means lack a unified data-level fusion carrier;
3) The artificial intelligent identification algorithms of different acquisition means lack prior knowledge of the service attribute of the equipment;
4) Different acquisition approaches lack timing dimensionality while preserving spatial attributes.
The invention can realize the functions of quickly diagnosing and positioning typical external thermal defects and insulation defects of the transformer substation equipment and realize the intellectualization and automation of transformer substation routing inspection.
Example 3:
based on the same inventive concept, the present invention also provides a computer apparatus comprising a processor and a memory, the memory being configured to store a computer program comprising program instructions, the processor being configured to execute the program instructions stored by the computer storage medium. The Processor may be a Central Processing Unit (CPU), or may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable gate array (FPGA) or other Programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc., which is a computing core and a control core of the terminal, and is specifically adapted to load and execute one or more instructions in a computer storage medium to implement a corresponding method flow or a corresponding function, so as to implement the steps of the method in the above embodiments.
Example 4:
based on the same inventive concept, the present invention further provides a storage medium, in particular, a computer-readable storage medium (Memory), which is a Memory device in a computer device and is used for storing programs and data. It is understood that the computer readable storage medium herein can include both built-in storage medium in the computer device and, of course, extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also, the memory space stores one or more instructions, which may be one or more computer programs (including program code), adapted to be loaded and executed by the processor. It should be noted that the computer-readable storage medium may be a high-speed RAM memory, or may be a non-volatile memory (non-volatile memory), such as at least one disk memory. One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the steps of the method in the above-described embodiments.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the invention can be realized by adopting various computer languages, such as object-oriented programming language Java and transliteration scripting language JavaScript.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (20)
1. A transformer substation inspection three-dimensional defect identification and positioning method is characterized by comprising the following steps:
calibrating a relative physical position of patrol and inspection acquisition equipment carried by the mobile patrol and inspection equipment of the transformer substation so as to convert internal and external parameters of the patrol and inspection acquisition equipment, acquiring multi-source patrol and inspection data and point cloud data of the transformer substation based on the patrol and inspection acquisition equipment after the internal and external parameters of the patrol and inspection acquisition equipment are converted, and recording the spatial position and the posture of the patrol and inspection acquisition equipment;
the inspection equipment is roughly positioned in a preset live-action three-dimensional model of the transformer substation according to the spatial position and the attitude, and after rough positioning, the inspection equipment is finely positioned in the preset live-action three-dimensional model of the transformer substation based on point cloud data;
registering and mapping the multi-source inspection data on the live-action three-dimensional model according to the spatial position, the posture and the internal and external parameters of the inspection acquisition equipment corresponding to the precise positioning, and storing the multi-source inspection data subjected to registering and mapping in a time sequence extensible structured data format to generate time sequence extensible inspection data;
performing data division on the patrol data with the extensible time sequence based on a pre-established component-level live-action three-dimensional model to generate component-level data;
determining change data of the substation parameters in the component-level data, performing defect diagnosis on substation component equipment based on the change data to identify defect types of the substation equipment components, and locating defect spaces of the substation equipment components.
2. The method of claim 1, wherein the inspection acquisition device includes at least one of: the device comprises a laser radar, a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor and an ultrahigh frequency sensor.
3. The method of claim 2, wherein the visible light camera, the infrared camera, the ultraviolet camera, the acoustic imaging sensor and the ultrahigh frequency sensor are used for collecting multi-source inspection data of the substation.
4. The method of claim 2, wherein the lidar is configured to scan point cloud data of the substation.
5. The method of claim 1, wherein the laser point cloud data of the transformer substation are collected through a multi-station laser radar, and are spliced to build a real-scene three-dimensional model of the transformer substation.
6. The method of claim 1, wherein the pre-built live-action three-dimensional model of the transformer substation is subjected to space and business semantic segmentation through the ledger information of the transformer substation so as to build a component-level live-action three-dimensional model of the transformer substation.
7. The method of claim 1, wherein the change data comprises at least one of: three-dimensional appearance change data, temperature change data, corona discharge change data, vibration change data and internal discharge change data of the transformer substation.
8. The method of claim 1, further comprising: and verifying the identification accuracy of the multi-source inspection data according to a preset initial confidence value, adjusting the confidence value of the multi-source inspection data according to the accuracy, and sending a state abnormality alarm to the corresponding inspection acquisition equipment for the multi-source inspection data with continuously reduced confidence value.
9. The method of claim 8, wherein initial values of the confidence levels of the defect diagnosis of different multi-source inspection data are set according to the equipment types of the substation component equipment.
10. The utility model provides a transformer substation patrols and examines three-dimensional defect discernment and location's system which characterized in that, the system includes:
the system comprises a data acquisition unit, a data processing unit and a data processing unit, wherein the data acquisition unit is used for calibrating relative physical positions of routing inspection acquisition equipment carried by the mobile routing inspection equipment of the transformer substation so as to convert internal and external parameters of the routing inspection acquisition equipment, acquiring multi-source routing inspection data and point cloud data of the transformer substation based on the routing inspection acquisition equipment after the internal and external parameters of the routing inspection acquisition equipment are converted, and recording the spatial position and the attitude of the routing inspection acquisition equipment;
the positioning unit is used for roughly positioning the inspection equipment in a preset live-action three-dimensional model of the transformer substation according to the spatial position and the attitude, and finely positioning the inspection equipment in the preset live-action three-dimensional model of the transformer substation based on point cloud data after rough positioning;
the data processing unit is used for carrying out registration mapping on the multi-source inspection data on the live-action three-dimensional model according to the spatial position, the posture and the internal and external parameters of the inspection acquisition equipment corresponding to the precise positioning, and storing the multi-source inspection data subjected to registration mapping in a time sequence extensible structured data format to generate time sequence extensible inspection data;
the data conversion unit is used for carrying out data division on the patrol data with the extensible time sequence based on a pre-built component-level real-scene three-dimensional model so as to generate component-level data;
and the diagnosis unit is used for determining the change data of the substation parameters in the component-level data, diagnosing the defects of the substation component equipment based on the change data so as to identify the defect types of the substation equipment components and locate the defect spaces of the substation equipment components.
11. The system of claim 10, wherein the inspection collection device includes at least one of: the system comprises a laser radar, a visible light camera, an infrared camera, an ultraviolet camera, an acoustic imaging sensor and an ultrahigh frequency sensor.
12. The system of claim 11, wherein the visible light camera, the infrared camera, the ultraviolet camera, the acoustic imaging sensor, and the uhf sensor are used to collect multi-source inspection data for the substation.
13. The system of claim 11, wherein the lidar is configured to scan point cloud data of a substation.
14. The system of claim 10, wherein the laser point cloud data of the transformer substation is collected through a multi-station laser radar and spliced to build a real-scene three-dimensional model of the transformer substation.
15. The system of claim 10, wherein the pre-built realistic three-dimensional model of the substation is subjected to space and business semantic segmentation through the ledger information of the substation to build a component-level realistic three-dimensional model of the substation.
16. The system of claim 10, wherein the change data comprises at least one of: the three-dimensional appearance change data, the temperature change data, the corona discharge change data, the vibration change data and the internal discharge change data of the transformer substation.
17. The system of claim 10, wherein the diagnostic unit is further configured to: and verifying the identification accuracy of the multi-source inspection data according to a preset initial confidence value, adjusting the confidence value of the multi-source inspection data according to the accuracy, and sending a state abnormality alarm to the corresponding inspection acquisition equipment for the multi-source inspection data with the constantly reduced confidence value.
18. The system of claim 17, wherein initial values of the confidence levels for the defect diagnosis of different multi-source inspection data are set according to equipment types of substation component equipment.
19. A computer device, comprising:
one or more processors;
a processor for executing one or more programs;
the one or more programs, when executed by the one or more processors, implement the method of any of claims 1-9.
20. A computer-readable storage medium, having stored thereon a computer program which, when executed, performs the method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211419444.XA CN115965579B (en) | 2022-11-14 | 2022-11-14 | Substation inspection three-dimensional defect identification and positioning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211419444.XA CN115965579B (en) | 2022-11-14 | 2022-11-14 | Substation inspection three-dimensional defect identification and positioning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115965579A true CN115965579A (en) | 2023-04-14 |
| CN115965579B CN115965579B (en) | 2023-09-22 |
Family
ID=87353800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211419444.XA Active CN115965579B (en) | 2022-11-14 | 2022-11-14 | Substation inspection three-dimensional defect identification and positioning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115965579B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2009228317B2 (en) * | 2008-03-28 | 2014-01-23 | Lockheed Martin Corporation | System, program product, and related methods for registering three-dimensional models to point data representing the pose of a part |
| CN111091609A (en) * | 2019-12-11 | 2020-05-01 | 云南电网有限责任公司保山供电局 | Transformer substation field operation management and control system and method based on three-dimensional dynamic modeling |
| CN112767391A (en) * | 2021-02-25 | 2021-05-07 | 国网福建省电力有限公司 | Power grid line part defect positioning method fusing three-dimensional point cloud and two-dimensional image |
| US20220051395A1 (en) * | 2020-08-11 | 2022-02-17 | Baker Hughes Oilfield Operations Llc | Automated defect detection |
| CN114627021A (en) * | 2022-03-18 | 2022-06-14 | 南通拓维思智能科技有限公司 | Point cloud and deep learning based defect detection method and system |
-
2022
- 2022-11-14 CN CN202211419444.XA patent/CN115965579B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2009228317B2 (en) * | 2008-03-28 | 2014-01-23 | Lockheed Martin Corporation | System, program product, and related methods for registering three-dimensional models to point data representing the pose of a part |
| CN111091609A (en) * | 2019-12-11 | 2020-05-01 | 云南电网有限责任公司保山供电局 | Transformer substation field operation management and control system and method based on three-dimensional dynamic modeling |
| US20220051395A1 (en) * | 2020-08-11 | 2022-02-17 | Baker Hughes Oilfield Operations Llc | Automated defect detection |
| CN112767391A (en) * | 2021-02-25 | 2021-05-07 | 国网福建省电力有限公司 | Power grid line part defect positioning method fusing three-dimensional point cloud and two-dimensional image |
| CN114627021A (en) * | 2022-03-18 | 2022-06-14 | 南通拓维思智能科技有限公司 | Point cloud and deep learning based defect detection method and system |
Non-Patent Citations (2)
| Title |
|---|
| IGOR JOVANČEVIĆ ET AL.: "3D Point Cloud Analysis for Detection and Characterization of Defects on Airplane Exterior Surface", 《HAL》 * |
| 赵文慈等: "基于点云处理的产品表面质量缺陷识别研究综述", 《冶金自动化》, vol. 46, no. 5 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115965579B (en) | 2023-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109977813B (en) | Inspection robot target positioning method based on deep learning framework | |
| CN109752722A (en) | Multi-modal acoustics imaging tool | |
| CN112465401A (en) | Electric power operation safety control system based on multi-dimensional information fusion and control method thereof | |
| CN111753712A (en) | Method, system and equipment for monitoring safety of power production personnel | |
| WO2018197585A1 (en) | Identifying targets within images | |
| CN109752721A (en) | Portable acoustics imaging tool with scanning and analysis ability | |
| CN112396019A (en) | Vegetation distribution identification method and system based on unmanned aerial vehicle and readable storage medium | |
| CN113205116A (en) | Automatic extraction and flight path planning method for unmanned aerial vehicle inspection shooting target point of power transmission line | |
| CN113284144B (en) | Tunnel detection method and device based on unmanned aerial vehicle | |
| CN115170792B (en) | Infrared image processing method, device and equipment and storage medium | |
| CN116148801B (en) | Millimeter wave radar-based target detection method and system | |
| CN112557512A (en) | Acoustic imaging method, device and equipment and inspection robot based on acoustic imaging equipment | |
| TWI779957B (en) | Image analysis model establishment method and image analysis apparatus | |
| CN113935379A (en) | Human body activity segmentation method and system based on millimeter wave radar signals | |
| CN113706496A (en) | Aircraft structure crack detection method based on deep learning model | |
| He et al. | Visual recognition and location algorithm based on optimized YOLOv3 detector and RGB depth camera | |
| CN115965579A (en) | Method and system for identifying and positioning three-dimensional defects in transformer substation inspection | |
| CN113674205A (en) | Method and system for measuring human body based on monocular depth camera | |
| CN113932712A (en) | Melon and fruit vegetable size measuring method based on depth camera and key points | |
| CN113298163A (en) | Target identification monitoring method based on LiDAR point cloud data | |
| CN112580578A (en) | Binocular living camera face ranging method and system | |
| CN112288019A (en) | Chef cap detection method based on key point positioning | |
| Sun | Robot Obstacle Recognition and Target Tracking Based on Binocular Vision | |
| CN117113283B (en) | State identification method and system of isolating switch | |
| CN116821409B (en) | Production safety management method and system based on image data processing |
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 |