CN116168351B - Inspection method and device for power equipment - Google Patents
Inspection method and device for power equipment Download PDFInfo
- Publication number
- CN116168351B CN116168351B CN202310460521.4A CN202310460521A CN116168351B CN 116168351 B CN116168351 B CN 116168351B CN 202310460521 A CN202310460521 A CN 202310460521A CN 116168351 B CN116168351 B CN 116168351B
- Authority
- CN
- China
- Prior art keywords
- data
- point cloud
- equipment
- representing
- cloud data
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 108
- 230000002159 abnormal effect Effects 0.000 claims abstract description 97
- 230000011218 segmentation Effects 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 21
- 230000007547 defect Effects 0.000 claims description 15
- 238000003708 edge detection Methods 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000013508 migration Methods 0.000 claims description 6
- 230000005012 migration Effects 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of equipment quality inspection, and discloses a power equipment inspection method and device, wherein the method comprises the following steps: collecting equipment images of the power equipment, extracting equipment characteristic points from the equipment images, converting the equipment characteristic points into three-dimensional point cloud data, and constructing a three-dimensional point cloud model of the three-dimensional point cloud data; performing point cloud data segmentation on the three-dimensional point cloud data to obtain segmented point cloud data, calculating a point cloud difference value between the segmented point cloud data and preset standard point cloud data, and removing an error difference value in the difference value to obtain a screened difference value; dividing interference information in the equipment image to obtain a divided equipment image, and detecting local quality of the power equipment; and carrying out standardization processing on the historical operation data to obtain standardized data, identifying candidate abnormal data in the standardized data, and extracting an abnormal data set of the candidate abnormal data from the standardized data. The invention can improve the quality detection detail of the power equipment.
Description
Technical Field
The invention relates to the field of equipment quality inspection, in particular to a power equipment inspection method and device.
Background
At present, the quality detection of the power equipment is realized mainly by collecting an image of the power equipment and carrying out defect detection on information in the image, and the process has the following defects: 1. when a label on the surface of the electric power equipment is attached to a corresponding position by a machine or a worker, the attached position cannot be completely the same as a standard position, at the moment, defect detection is successful when an image of the label position is subjected to defect detection, but the actual situation is that no defect exists at the moment, the conventional image defect detection technology generally uses a deep learning model to carry out global detection on the content in the image, the process has the problems of neglecting the depth defect detection and local detail defect detection of the equipment, wherein the equipment depth defect is the defect of the depth position of holes, ravines and the like in the electric power equipment, the detection of abnormal operation data of the electric power equipment at present ignores the detection of associated data and attached data of each abnormal data, for example, abnormal data point K is detected, and 3 similar data of A, B, C exist, namely the associated data and the related data, and A, B, C are classified as the abnormal data, so that the quality detection of the electric power equipment is lost due to the neglect of the associated data of the attached depth information, the local information and the abnormal data of the electric power equipment.
Disclosure of Invention
In order to solve the problems, the invention provides a power equipment inspection method and a device, which can improve the quality detection detail of power equipment by focusing on the associated data of depth information, local information and abnormal data of the power equipment.
In a first aspect, the present invention provides a method for inspecting electrical equipment, including:
acquiring equipment information of electric equipment, acquiring equipment images of the electric equipment, extracting equipment characteristic points from the equipment images, converting the equipment characteristic points into three-dimensional point cloud data, and constructing a three-dimensional point cloud model of the three-dimensional point cloud data;
performing point cloud data segmentation on the three-dimensional point cloud data in the three-dimensional point cloud model to obtain segmented point cloud data, calculating point cloud difference values between the segmented point cloud data and preset standard point cloud data, removing error difference values in the difference values to obtain screened difference values, and determining a global quality detection result of the power equipment based on the screened difference values;
dividing the interference information in the equipment image to obtain a divided equipment image, and carrying out local quality detection on the power equipment based on the divided equipment image to obtain a local quality detection result of the power equipment;
Acquiring historical operation data of the power equipment, carrying out standardization processing on the historical operation data to obtain standardized data, identifying candidate abnormal data in the standardized data, and extracting an abnormal data set of each candidate abnormal data in the candidate abnormal data from the standardized data based on a time scale of the candidate abnormal data, wherein the identifying the candidate abnormal data in the standardized data comprises the following steps:
sequencing the standardized data according to a time sequence to obtain a historical data sequence; calculating the surrounding values of the historical operating data in the historical data sequence by using the following formula:
wherein ,representing the surrounding values +.>Represents +.>Distance between the data point and the data point at the centre instant in the p-time period,/v>，/>Representation ofMean value of middle distance,/">The absolute difference between the distance at time p and the distance at time p-1,
when the absolute difference value between the surrounding numerical value and the current numerical value in the historical data sequence is larger than a preset difference value, the current numerical value in the historical data sequence is used as the candidate abnormal data;
and taking the global quality detection result, the local quality detection result and the abnormal data set as quality inspection results of the power equipment.
In a possible implementation manner of the first aspect, the converting the device feature point into three-dimensional point cloud data includes:
performing feature point matching on the equipment feature points to obtain matching feature point pairs;
calculating a position migration matrix between two feature points matched with each other in the matched feature point pair by using the following formula:
wherein ,representing the position transition matrix, i.e. the rotation change matrix from the image in which feature point a is located to the image in which feature point b is located,/o>A vector of coordinates representing a feature point of two feature points each of which matches the matching feature point pair,/->Representing the coordinates of feature point a in its corresponding image, < >>Vector of coordinates representing feature point b matching feature point a +.>Representing coordinates of the feature point b in its corresponding image;
according to the position migration matrix, calculating the three-dimensional coordinates of the equipment characteristic points in a preset three-dimensional space by using the following formula:
wherein ,representing the three-dimensional coordinates->Representing the position transition matrix, i.e. the rotation change matrix from the image in which feature point a is located to the image in which feature point b is located,/o>Vector of coordinates representing feature point b matching feature point a +. >Representing the coordinates of feature point b in its corresponding image,/->Representing the presentation to beMapping the coordinate vector to a mapping relation matrix in a preset three-dimensional space;
and screening the characteristic points at the three-dimensional coordinates, and taking the characteristic points obtained by screening as the three-dimensional point cloud data.
In one possible implementation manner of the first aspect, the performing, in the three-dimensional point cloud model, point cloud data segmentation on the three-dimensional point cloud data to obtain segmented point cloud data includes:
and gridding the three-dimensional point cloud data in the three-dimensional point cloud model to obtain a grid surface of the three-dimensional point cloud data, and taking the point cloud data in the grid surface as the segmentation point cloud data.
In a possible implementation manner of the first aspect, the calculating a point cloud difference value between the partitioned point cloud data and preset standard point cloud data includes:
calculating the point cloud distance between the partitioned point cloud data and the preset standard point cloud data by using the following formula:
wherein ,representing the point cloud distance,/->Representing the ith point cloud in the partitioned point cloud data,/and->Representing the j-th point cloud in the preset standard point cloud data, and n represents the number of point clouds in the preset standard point cloud data;
Selecting a shortest distance from the point cloud distances, and taking the shortest distance as a first point cloud difference value;
obtaining a grid surface corresponding to the grid surface where the segmentation point cloud data is located in the preset standard point cloud data, obtaining a target grid surface, and calculating the point-surface distance between the segmentation point cloud data and the target grid surface by using the following formula:
wherein ,representing the dot-plane distance,/->Representing the ith point cloud in the partitioned point cloud data,/and->Representing the t-th mesh node in the target mesh plane s, a +.>Representing mesh surface s midnetThe number of lattice nodes;
and taking the point-to-surface distance as a second point cloud difference value.
In one possible implementation manner of the first aspect, the removing the error difference value in the difference value to obtain a filtered difference value includes:
acquiring target point clouds corresponding to the difference values from preset standard point cloud data, and identifying target positions of the target point clouds in the preset standard point cloud data;
judging whether the target part is a preset part or not;
and when the target part is the preset part, taking the difference value corresponding to the target part as an error difference value, and removing the error difference value to obtain the screened difference value.
In a possible implementation manner of the first aspect, the determining, based on the screened difference value, a global quality detection result of the power device includes:
when the screened difference value is larger than a preset difference threshold value, acquiring point cloud data corresponding to the screened difference value from the segmented point cloud data, and taking the position of the acquired point cloud data in the power equipment as a first global quality detection result;
and when the screened difference value is not greater than the preset difference threshold value, obtaining a second global quality detection result.
In a possible implementation manner of the first aspect, the segmenting the interference information in the device image to obtain a segmented device image includes:
calculating an edge detection value in the device image using the following formula:
wherein ,representing the edge detection value,/->Represents the gradient value in the horizontal direction +.>Represents the vertical gradient value +_>Representing the device image,/->、/>、/>、/>、/>、/>、/>Representing pixel values of the device image within a convolution kernel when the device image is convolved with a Sobel operator;
taking the pixel position when the edge detection value is larger than a preset edge threshold value as an edge position in the equipment image;
Measuring the length and width of the edge part;
identifying an interference area in the device image based on the length and width of the edge portion;
and dividing the interference area in the equipment image to obtain the divided equipment image.
In one possible implementation manner of the first aspect, the performing, based on the segmented device image, local quality detection on the electrical device to obtain a local quality detection result of the electrical device includes:
acquiring a local detection template of the power equipment, and acquiring an area with the same size as the local detection template in the segmented equipment image to obtain a local area to be detected;
calculating the region similarity between the local region to be detected and the local detection template by using the following formula:
wherein ,representing the similarity of the regions>* N represents the size of the local detection template, < >>Representing the upper left corner coordinates of the local detection template,,, of>Expressed as +.>The local detection template with coordinates in the upper left corner,and->Representing the left of the local area to be detectedUpper angular coordinates;
determining a target local area from the local areas to be detected based on the area similarity;
And performing defect detection on the target local area to obtain the local quality detection result.
In a possible implementation manner of the first aspect, the identifying candidate abnormal data in the normalized data includes:
sequencing the standardized data according to a time sequence to obtain a historical data sequence;
calculating the surrounding values of the historical operating data in the historical data sequence by using the following formula:
wherein ,representing the surrounding values +.>Represents +.>Distance between the data point and the data point at the centre instant in the p-time period,/v>，/>Representation ofMean value of middle distance,/">Representing the time pAbsolute difference of distance from p-1 time;
and when the absolute difference value between the surrounding numerical value and the current numerical value in the historical data sequence is larger than a preset difference value, taking the current numerical value in the historical data sequence as the candidate abnormal data.
In a possible implementation manner of the first aspect, the extracting, from the normalized data, an abnormal data set of each candidate abnormal data in the candidate abnormal data based on the time scale of the candidate abnormal data includes:
performing cluster analysis on the standardized data to obtain data clusters;
Inquiring a data cluster corresponding to the time scale of the candidate abnormal data from the data cluster based on the time scale of the candidate abnormal data and the time scale of the data cluster to obtain a target data cluster;
and clustering the target data as the abnormal data set.
In a second aspect, the present invention provides an electrical equipment inspection device, the device comprising:
the three-dimensional construction module is used for acquiring equipment information of the power equipment, acquiring equipment images of the power equipment, extracting equipment characteristic points from the equipment images, converting the equipment characteristic points into three-dimensional point cloud data, and constructing a three-dimensional point cloud model of the three-dimensional point cloud data;
the global quality inspection module is used for carrying out point cloud data segmentation on the three-dimensional point cloud data in the three-dimensional point cloud model to obtain segmented point cloud data, calculating point cloud difference values between the segmented point cloud data and preset standard point cloud data, removing error difference values in the difference values to obtain screened difference values, and determining a global quality detection result of the power equipment based on the screened difference values;
the local quality inspection module is used for dividing the interference information in the equipment image to obtain a divided equipment image, and carrying out local quality inspection on the power equipment based on the divided equipment image to obtain a local quality inspection result of the power equipment;
The abnormal selection module is used for acquiring historical operation data of the power equipment, carrying out standardization processing on the historical operation data to obtain standardized data, identifying candidate abnormal data in the standardized data, and extracting an abnormal data set of each candidate abnormal data in the candidate abnormal data from the standardized data based on the time scale of the candidate abnormal data, wherein the identification of the candidate abnormal data in the standardized data comprises the following steps:
sequencing the standardized data according to a time sequence to obtain a historical data sequence; calculating the surrounding values of the historical operating data in the historical data sequence by using the following formula:
wherein ,representing the surrounding values +.>Represents +.>Distance between the data point and the data point at the centre instant in the p-time period,/v>，/>Representation ofMean value of middle distance,/">The absolute difference between the distance at time p and the distance at time p-1,
when the absolute difference value between the surrounding numerical value and the current numerical value in the historical data sequence is larger than a preset difference value, the current numerical value in the historical data sequence is used as the candidate abnormal data;
And the result determining module is used for taking the global quality detection result, the local quality detection result and the abnormal data set as the quality inspection result of the power equipment.
Compared with the prior art, the technical principle and beneficial effect of this scheme lie in:
according to the embodiment of the invention, firstly, the device characteristic points are converted into three-dimensional point cloud data for extracting depth data points of the power device, the quality detection of depth positions such as holes, ravines and the like of the power device is guaranteed, further, the preset standard point cloud data are point cloud data established when the power device leaves a factory and are used for comparing the point cloud data of the used power device with standard point cloud data when the power device leaves the factory in the subsequent quality detection, further, the embodiment of the invention can be used for guaranteeing that the used power device is associated with each piece of abnormal data by removing error difference values in the difference values and removing detail data of the candidate abnormal data according to the abnormal data through removing error difference values in the difference values, reducing the false detection condition of global quality detection and improving the quality detection degree of the power device. Therefore, according to the power equipment inspection method, the power equipment inspection device, the electronic equipment and the storage medium, the depth information, the local information and the associated data of the abnormal data of the power equipment can be focused, so that the quality detection detail degree of the power equipment can be improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 is a schematic flow chart of an inspection method for power equipment according to an embodiment of the invention;
fig. 2 is a flowchart illustrating one step of the inspection method of the power equipment provided in fig. 1 according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating another step of the inspection method of the power device according to the embodiment of the present invention;
fig. 4 is a schematic block diagram of an inspection device for electrical equipment according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an internal structure of an electronic device for implementing a power device inspection method according to an embodiment of the present invention.
Detailed Description
It should be understood that the detailed description is presented by way of example only and is not intended to limit the invention.
The embodiment of the invention provides a power equipment inspection method, and an execution subject of the power equipment inspection method comprises, but is not limited to, at least one of a server, a terminal and the like which can be configured to execute the electronic equipment of the method provided by the embodiment of the invention. In other words, the power device inspection method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Fig. 1 is a schematic flow chart of an inspection method for power equipment according to an embodiment of the invention. The power equipment inspection method depicted in fig. 1 comprises the following steps:
S1, acquiring equipment information of electric equipment, acquiring equipment images of the electric equipment, extracting equipment characteristic points from the equipment images, converting the equipment characteristic points into three-dimensional point cloud data, and constructing a three-dimensional point cloud model of the three-dimensional point cloud data.
In the embodiment of the invention, the power equipment refers to a part of a power system and comprises key equipment such as a power transformer, a high-voltage circuit breaker, a power transmission line and the like; the device information refers to information describing the identity of the power device, and includes information such as the name, model number, size, factory appearance and the like of the power device.
Alternatively, the extracting the device feature points from the device image may be implemented by a feature point extraction algorithm. Wherein the feature point extraction algorithm is, for example, a Scale-invariant feature transform algorithm (Scale-invariantfeature transform, SIFT).
Further, the embodiment of the invention ensures the subsequent quality detection of depth positions such as holes, ravines and the like of the power equipment by converting the equipment characteristic points into three-dimensional point cloud data for extracting the depth data points of the power equipment.
In an embodiment of the present invention, the converting the device feature point into three-dimensional point cloud data includes: performing feature point matching on the equipment feature points to obtain matching feature point pairs; calculating a position migration matrix between two feature points matched with each other in the matched feature point pair by using the following formula:
wherein ,representing the position transition matrix, i.e. the rotation change matrix from the image in which feature point a is located to the image in which feature point b is located,/o>A vector of coordinates representing a feature point of two feature points each of which matches the matching feature point pair,/->Representing the coordinates of feature point a in its corresponding image, < >>Vector of coordinates representing feature point b matching feature point a +.>Representing coordinates of the feature point b in its corresponding image;
according to the position migration matrix, calculating the three-dimensional coordinates of the equipment characteristic points in a preset three-dimensional space by using the following formula:
wherein ,representing the three-dimensional coordinates->Representing the position transition matrix, i.e. the rotation change matrix from the image in which feature point a is located to the image in which feature point b is located,/o>Vector of coordinates representing feature point b matching feature point a +.>Representing the coordinates of feature point b in its corresponding image,/->Representing the presentation to beMapping the coordinate vector to a mapping relation matrix in a preset three-dimensional space;
and screening the characteristic points at the three-dimensional coordinates, and taking the characteristic points obtained by screening as the three-dimensional point cloud data.
The three-dimensional space is a space for generating the three-dimensional point cloud data.
Optionally, the process of performing feature point matching on the device feature points to obtain a matching feature point pair refers to a process of matching similar feature points under different camera angles, and feature point matching can be achieved by calculating feature similarity between two images under different shooting angles; the feature point screening process for the feature points at the three-dimensional coordinates may be implemented by a multi-view stereo vision (MVS) algorithm, which is a generic term for a group of techniques using stereo matching as a main clue and using two or more images.
Optionally, the process of constructing the three-dimensional point cloud model of the three-dimensional point cloud data may be implemented by performing point connection and rendering on the three-dimensional point cloud data.
S2, performing point cloud data segmentation on the three-dimensional point cloud data in the three-dimensional point cloud model to obtain segmented point cloud data, calculating point cloud difference values between the segmented point cloud data and preset standard point cloud data, removing error difference values in the difference values to obtain screened difference values, and determining a global quality detection result of the power equipment based on the screened difference values.
In an embodiment of the present invention, the performing point cloud data segmentation on the three-dimensional point cloud data in the three-dimensional point cloud model to obtain segmented point cloud data includes: and gridding the three-dimensional point cloud data in the three-dimensional point cloud model to obtain a grid surface of the three-dimensional point cloud data, and taking the point cloud data in the grid surface as the segmentation point cloud data.
Wherein the grid surface refers to an irregular triangular grid surface.
Further, the preset standard point cloud data in the embodiment of the invention refers to point cloud data established when the power equipment leaves the factory, and the point cloud data is used for comparing the point cloud data of the used power equipment with the standard point cloud data when the power equipment leaves the factory when the quality of the power equipment is checked later.
In an embodiment of the present invention, the calculating a point cloud difference value between the partitioned point cloud data and preset standard point cloud data includes: calculating the point cloud distance between the partitioned point cloud data and the preset standard point cloud data by using the following formula:
wherein ,representing the point cloud distance,/->Representing the ith point cloud in the partitioned point cloud data,/and->Representing the j-th point cloud in the preset standard point cloud data, and n represents the number of point clouds in the preset standard point cloud data;
Selecting a shortest distance from the point cloud distances, and taking the shortest distance as a first point cloud difference value;
obtaining a grid surface corresponding to the grid surface where the segmentation point cloud data is located in the preset standard point cloud data, obtaining a target grid surface, and calculating the point-surface distance between the segmentation point cloud data and the target grid surface by using the following formula:
wherein ,representing the dot-plane distance,/->Representing the ith point cloud in the partitioned point cloud data,/and->Representing the t-th mesh node in the target mesh plane s, a +.>Representing the number of mesh nodes in the target mesh surface s;
and taking the point-to-surface distance as a second point cloud difference value.
Further, the embodiment of the invention is used for removing the difference value which accords with the font label part in the difference value by removing the error difference value in the difference value, so that the false detection condition of global quality detection is reduced, and the quality detection detail degree of the power equipment is improved.
In an embodiment of the present invention, referring to fig. 2, the removing the error difference value from the difference values to obtain the filtered difference value includes:
s201, acquiring target point clouds corresponding to the difference values from preset standard point cloud data, and identifying target positions of the target point clouds in the preset standard point cloud data;
S202, judging whether the target part is a preset part or not; and when the target part is the preset part, taking the difference value corresponding to the target part as an error difference value, and removing the error difference value to obtain the screened difference value.
The preset position is a position containing a font label, the label attached position of the preset position cannot be guaranteed to be the same as the standard position, printing distortion can occur on the label of the preset position, the point cloud difference value at the position is large, and false detection can occur.
In an embodiment of the present invention, referring to fig. 3, the determining, based on the filtered difference value, a global quality detection result of the power device includes:
s301, when the screened difference value is larger than a preset difference threshold value, acquiring point cloud data corresponding to the screened difference value from the segmented point cloud data, and taking the position of the acquired point cloud data in the power equipment as a first global quality detection result;
s302, when the screened difference value is not larger than the preset difference threshold value, a second global quality detection result is obtained.
Wherein the preset variance threshold represents a threshold in the case where no quality problem is detected; the first global quality detection result is a detection result indicating a position constitution where a quality problem occurs.
S3, dividing the interference information in the equipment image to obtain a divided equipment image, and carrying out local quality detection on the power equipment based on the divided equipment image to obtain a local quality detection result of the power equipment.
Further, the embodiment of the invention is used for removing the interference information containing the font label in the equipment image by dividing the interference information in the equipment image.
In an embodiment of the present invention, the segmenting the interference information in the device image to obtain a segmented device image includes: calculating an edge detection value in the device image using the following formula:
wherein ,representing the edge detection value,/->Represents the gradient value in the horizontal direction +.>Represents the vertical gradient value +_>Representing the device image,/->、/>、/>、/>、/>、/>、/>Representing pixel values of the device image within a convolution kernel when the device image is convolved with a Sobel operator;
taking the pixel position when the edge detection value is larger than a preset edge threshold value as an edge position in the equipment image; measuring the length and width of the edge part; identifying an interference area in the device image based on the length and width of the edge portion; and dividing the interference area in the equipment image to obtain the divided equipment image.
In an embodiment of the present invention, the performing local quality detection on the electrical equipment based on the segmented equipment image to obtain a local quality detection result of the electrical equipment includes: acquiring a local detection template of the power equipment, and acquiring an area with the same size as the local detection template in the segmented equipment image to obtain a local area to be detected; calculating the region similarity between the local region to be detected and the local detection template by using the following formula:
wherein ,representing the similarity of the regions>* N represents the size of the local detection template, < >>Representing the upper left corner coordinates of said local detection template,/->Expressed as +.>Said local detection template with coordinates in upper left corner,>and->Representing the local area to be detectedUpper left corner coordinates;
determining a target local area from the local areas to be detected based on the area similarity; and performing defect detection on the target local area to obtain the local quality detection result.
Alternatively, the process of performing defect detection on the target local area may be implemented by a YOLOX defect detection algorithm.
S4, acquiring historical operation data of the power equipment, carrying out standardization processing on the historical operation data to obtain standardized data, identifying candidate abnormal data in the standardized data, and extracting an abnormal data set of each candidate abnormal data in the candidate abnormal data from the standardized data based on the time scale of the candidate abnormal data.
In an embodiment of the present invention, the identifying candidate abnormal data in the normalized data includes: sequencing the standardized data according to a time sequence to obtain a historical data sequence; calculating the surrounding values of the historical operating data in the historical data sequence by using the following formula:
wherein ,representing the surrounding values +.>Represents +.>Distance between the data point and the data point at the centre instant in the p-time period,/v>，/>Representation ofMean value of middle distance,/">An absolute difference between the distance at time p and the distance at time p-1;
and when the absolute difference value between the surrounding numerical value and the current numerical value in the historical data sequence is larger than a preset difference value, taking the current numerical value in the historical data sequence as the candidate abnormal data.
Wherein the current value in the historical data sequence refers to the formulaIs->。
Further, the embodiment of the invention extracts the abnormal data set of each candidate abnormal data in the candidate abnormal data from the standardized data based on the time scale of the candidate abnormal data, so as to ensure the detection of the associated data and the auxiliary data of each abnormal data of the power equipment.
In an embodiment of the present invention, the extracting, from the normalized data, the abnormal data set of each of the candidate abnormal data based on the time scale of the candidate abnormal data includes: performing cluster analysis on the standardized data to obtain data clusters; inquiring a data cluster corresponding to the time scale of the candidate abnormal data from the data cluster based on the time scale of the candidate abnormal data and the time scale of the data cluster to obtain a target data cluster; and clustering the target data as the abnormal data set.
And S5, taking the global quality detection result, the local quality detection result and the abnormal data set as quality inspection results of the power equipment.
It can be seen that, in the embodiment of the present invention, the depth data points of the electrical equipment are firstly converted into three-dimensional point cloud data to be used for extracting depth data points of the electrical equipment, so as to ensure the quality detection of depth positions such as holes, ravines, etc. of the electrical equipment, further, the preset standard point cloud data are point cloud data established when the electrical equipment leaves the factory, and are used for comparing the point cloud data of the used electrical equipment with standard point cloud data when the electrical equipment leaves the factory, further, the embodiment of the present invention, by removing error difference values in the difference values, is used for removing difference values conforming to font label positions in the difference values, so as to reduce the false detection condition of global quality detection, and improve the quality detection detail of the electrical equipment. Therefore, the inspection method for the power equipment provided by the embodiment of the invention can improve the quality detection detail degree of the power equipment by focusing on the depth information, the local information and the associated data of the abnormal data of the power equipment.
Fig. 4 is a functional block diagram of the inspection device for electric power equipment according to the present invention.
The power equipment inspection device 400 of the present invention may be installed in an electronic device. Depending on the implemented functions, the power device inspection apparatus may include a three-dimensional construction module 401, a global quality inspection module 402, a local quality inspection module 403, and an anomaly selection module 404. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the embodiment of the present invention, the functions of each module/unit are as follows:
the three-dimensional construction module 401 is configured to acquire device information of a power device, acquire a device image of the power device, extract a device feature point from the device image, convert the device feature point into three-dimensional point cloud data, and construct a three-dimensional point cloud model of the three-dimensional point cloud data;
the global quality inspection module 402 is configured to perform point cloud data segmentation on the three-dimensional point cloud data in the three-dimensional point cloud model to obtain segmented point cloud data, calculate a point cloud difference value between the segmented point cloud data and preset standard point cloud data, remove an error difference value in the difference value to obtain a screened difference value, and determine a global quality detection result of the power device based on the screened difference value;
The local quality inspection module 403 is configured to divide interference information in the device image to obtain a divided device image, and perform local quality inspection on the power device based on the divided device image to obtain a local quality inspection result of the power device;
the anomaly selection module 404 is configured to obtain historical operation data of the electrical equipment, perform normalization processing on the historical operation data to obtain normalized data, identify candidate anomaly data in the normalized data, and extract an anomaly data set of each candidate anomaly data in the candidate anomaly data from the normalized data based on a time scale of the candidate anomaly data, where the identifying the candidate anomaly data in the normalized data includes:
sequencing the standardized data according to a time sequence to obtain a historical data sequence; calculating the surrounding values of the historical operating data in the historical data sequence by using the following formula:
wherein ,representing the surrounding values +.>Represents +.>Distance between the data point and the data point at the centre instant in the p-time period,/v>，/>Representation ofMean value of middle distance,/" >The absolute difference between the distance at time p and the distance at time p-1,
when the absolute difference value between the surrounding numerical value and the current numerical value in the historical data sequence is larger than a preset difference value, the current numerical value in the historical data sequence is used as the candidate abnormal data;
the result determining module 405 is configured to take the global quality detection result, the local quality detection result, and the abnormal data set as a quality inspection result of the power device.
In detail, the modules in the power equipment inspection device 400 in the embodiment of the present invention use the same technical means as the power equipment inspection method described in fig. 1 to 3, and can produce the same technical effects, which are not described herein.
Fig. 5 is a schematic structural diagram of an electronic device for implementing the inspection method of the power device according to the present invention.
The electronic device may comprise a processor 50, a memory 51, a communication bus 52 and a communication interface 53, and may further comprise a computer program, such as a power device patrol program, stored in the memory 51 and executable on the processor 50.
The processor 50 may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing unit, CPU), a microprocessor, a digital processing chip, a graphics processor, a combination of various control chips, and so on. The processor 50 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, and executes various functions of the electronic device and processes data by running or executing programs or modules (e.g., executing a power device inspection program, etc.) stored in the memory 51, and calling data stored in the memory 51.
The memory 51 includes at least one type of readable storage medium including flash memory, a removable hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 51 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 51 may also be an external storage device of the electronic device in other embodiments, for example, a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like. Further, the memory 51 may also include both an internal storage unit and an external storage device of the electronic device. The memory 51 may be used not only for storing application software installed in an electronic device and various types of data, such as codes of a database-configured connection program, but also for temporarily storing data that has been output or is to be output.
The communication bus 52 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 51 and at least one processor 50 etc.
The communication interface 53 is used for communication between the electronic device 5 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Fig. 5 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 5 is not limiting of the electronic device and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and the power source may be logically connected to the at least one processor 50 through a power management device, so that functions of charge management, discharge management, and power consumption management are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited in scope by this configuration.
The database-configured connection program stored in the memory 51 in the electronic device is a combination of a plurality of computer programs, which, when run in the processor 50, can implement:
acquiring equipment information of electric equipment, acquiring equipment images of the electric equipment, extracting equipment characteristic points from the equipment images, converting the equipment characteristic points into three-dimensional point cloud data, and constructing a three-dimensional point cloud model of the three-dimensional point cloud data;
Performing point cloud data segmentation on the three-dimensional point cloud data in the three-dimensional point cloud model to obtain segmented point cloud data, calculating point cloud difference values between the segmented point cloud data and preset standard point cloud data, removing error difference values in the difference values to obtain screened difference values, and determining a global quality detection result of the power equipment based on the screened difference values;
dividing the interference information in the equipment image to obtain a divided equipment image, and carrying out local quality detection on the power equipment based on the divided equipment image to obtain a local quality detection result of the power equipment;
acquiring historical operation data of the power equipment, carrying out standardization processing on the historical operation data to obtain standardized data, identifying candidate abnormal data in the standardized data, and extracting an abnormal data set of each candidate abnormal data in the candidate abnormal data from the standardized data based on a time scale of the candidate abnormal data, wherein the identifying the candidate abnormal data in the standardized data comprises the following steps:
sequencing the standardized data according to a time sequence to obtain a historical data sequence; calculating the surrounding values of the historical operating data in the historical data sequence by using the following formula:
wherein ,representing the surrounding values +.>Represents +.>Distance between the data point and the data point at the centre instant in the p-time period,/v>，/>Representation ofMean value of middle distance,/">The absolute difference between the distance at time p and the distance at time p-1,
when the absolute difference value between the surrounding numerical value and the current numerical value in the historical data sequence is larger than a preset difference value, the current numerical value in the historical data sequence is used as the candidate abnormal data;
and taking the global quality detection result, the local quality detection result and the abnormal data set as quality inspection results of the power equipment.
In particular, the specific implementation method of the processor 50 on the computer program may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
Further, the electronic device integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a non-volatile computer readable storage medium. The storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
acquiring equipment information of electric equipment, acquiring equipment images of the electric equipment, extracting equipment characteristic points from the equipment images, converting the equipment characteristic points into three-dimensional point cloud data, and constructing a three-dimensional point cloud model of the three-dimensional point cloud data;
performing point cloud data segmentation on the three-dimensional point cloud data in the three-dimensional point cloud model to obtain segmented point cloud data, calculating point cloud difference values between the segmented point cloud data and preset standard point cloud data, removing error difference values in the difference values to obtain screened difference values, and determining a global quality detection result of the power equipment based on the screened difference values;
dividing the interference information in the equipment image to obtain a divided equipment image, and carrying out local quality detection on the power equipment based on the divided equipment image to obtain a local quality detection result of the power equipment;
acquiring historical operation data of the power equipment, carrying out standardization processing on the historical operation data to obtain standardized data, identifying candidate abnormal data in the standardized data, and extracting an abnormal data set of each candidate abnormal data in the candidate abnormal data from the standardized data based on a time scale of the candidate abnormal data, wherein the identifying the candidate abnormal data in the standardized data comprises the following steps:
Sequencing the standardized data according to a time sequence to obtain a historical data sequence; calculating the surrounding values of the historical operating data in the historical data sequence by using the following formula:
wherein ,representing the surrounding values +.>Represents +.>Distance between the data point and the data point at the centre instant in the p-time period,/v>，/>Representation ofMean value of middle distance,/">The absolute difference between the distance at time p and the distance at time p-1,
when the absolute difference value between the surrounding numerical value and the current numerical value in the historical data sequence is larger than a preset difference value, the current numerical value in the historical data sequence is used as the candidate abnormal data;
and taking the global quality detection result, the local quality detection result and the abnormal data set as quality inspection results of the power equipment.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, system and method may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A method for inspecting electrical equipment, the method comprising:
acquiring equipment information of electric equipment, acquiring equipment images of the electric equipment, extracting equipment characteristic points from the equipment images, converting the equipment characteristic points into three-dimensional point cloud data, and constructing a three-dimensional point cloud model of the three-dimensional point cloud data;
performing point cloud data segmentation on the three-dimensional point cloud data in the three-dimensional point cloud model to obtain segmented point cloud data, calculating point cloud difference values between the segmented point cloud data and preset standard point cloud data, removing error difference values in the difference values to obtain screened difference values, and determining a global quality detection result of the power equipment based on the screened difference values;
Dividing the interference information in the equipment image to obtain a divided equipment image, and carrying out local quality detection on the power equipment based on the divided equipment image to obtain a local quality detection result of the power equipment;
acquiring historical operation data of the power equipment, carrying out standardization processing on the historical operation data to obtain standardized data, identifying candidate abnormal data in the standardized data, and extracting an abnormal data set of each candidate abnormal data in the candidate abnormal data from the standardized data based on a time scale of the candidate abnormal data, wherein the identifying the candidate abnormal data in the standardized data comprises the following steps:
sequencing the standardized data according to a time sequence to obtain a historical data sequence; calculating the surrounding values of the historical operating data in the historical data sequence by using the following formula:
wherein ,representing the surrounding values +.>Represents +.>Distance between the data point and the data point at the centre instant in the p-time period,/v>，/>Representation ofMean value of middle distance,/">Representing the absolute difference between the distance at time p and the distance at time p-1,/o >Represents a period of time less than p, +.>，/>Representation ofThe average value of the absolute difference values of (c),
when the absolute difference value between the surrounding numerical value and the current numerical value in the historical data sequence is larger than a preset difference value, the current numerical value in the historical data sequence is used as the candidate abnormal data;
and taking the global quality detection result, the local quality detection result and the abnormal data set as quality inspection results of the power equipment.
2. The method of claim 1, wherein the converting the device feature points into three-dimensional point cloud data comprises:
performing feature point matching on the equipment feature points to obtain matching feature point pairs;
calculating a position migration matrix between two feature points matched with each other in the matched feature point pair by using the following formula:
wherein ,representing the position transition matrix, i.e. the rotation change matrix from the image in which feature point a is located to the image in which feature point b is located,/o>A vector of coordinates representing a feature point of two feature points each of which matches the matching feature point pair,/->Representing the coordinates of feature point a in its corresponding image, < >>Vector of coordinates representing feature point b matching feature point a +. >Representing coordinates of the feature point b in its corresponding image;
according to the position migration matrix, calculating the three-dimensional coordinates of the equipment characteristic points in a preset three-dimensional space by using the following formula:
wherein ,representing the three-dimensional coordinates->Representing the position transition matrix, i.e. the rotation change matrix from the image in which feature point a is located to the image in which feature point b is located,/o>Vector of coordinates representing feature point b matching feature point a +.>Representing the coordinates of feature point b in its corresponding image,/->Representing the presentation to beMapping the coordinate vector to a mapping relation matrix in a preset three-dimensional space;
and screening the characteristic points at the three-dimensional coordinates, and taking the characteristic points obtained by screening as the three-dimensional point cloud data.
3. The method of claim 1, wherein the performing point cloud data segmentation on the three-dimensional point cloud data in the three-dimensional point cloud model to obtain segmented point cloud data comprises:
and gridding the three-dimensional point cloud data in the three-dimensional point cloud model to obtain a grid surface of the three-dimensional point cloud data, and taking the point cloud data in the grid surface as the segmentation point cloud data.
4. The method of claim 1, wherein the calculating the point cloud difference value between the partitioned point cloud data and the preset standard point cloud data comprises:
calculating the point cloud distance between the partitioned point cloud data and the preset standard point cloud data by using the following formula:
wherein ,representing the point cloud distance,/->Representing the ith point cloud in the partitioned point cloud data,/and->Representing the j-th point cloud in the preset standard point cloud data, and n represents the number of point clouds in the preset standard point cloud data;
selecting a shortest distance from the point cloud distances, and taking the shortest distance as a first point cloud difference value;
obtaining a grid surface corresponding to the grid surface where the segmentation point cloud data is located in the preset standard point cloud data, obtaining a target grid surface, and calculating the point-surface distance between the segmentation point cloud data and the target grid surface by using the following formula:
wherein ,representing the dot-plane distance,/->Representing the ith point cloud in the partitioned point cloud data,/and->Representing the t-th mesh node in the target mesh plane s, a +.>Representing the number of mesh nodes in the target mesh surface s;
and taking the point-to-surface distance as a second point cloud difference value.
5. The method of claim 1, wherein the removing the erroneous difference value from the difference values to obtain the filtered difference value comprises:
acquiring target point clouds corresponding to the difference values from preset standard point cloud data, and identifying target positions of the target point clouds in the preset standard point cloud data;
judging whether the target part is a preset part or not;
and when the target part is the preset part, taking the difference value corresponding to the target part as an error difference value, and removing the error difference value to obtain the screened difference value.
6. The method of claim 1, wherein determining a global quality detection result for the power device based on the filtered difference values comprises:
when the screened difference value is larger than a preset difference threshold value, acquiring point cloud data corresponding to the screened difference value from the segmented point cloud data, and taking the position of the acquired point cloud data in the power equipment as a first global quality detection result;
and when the screened difference value is not greater than the preset difference threshold value, obtaining a second global quality detection result.
7. The method of claim 1, wherein the segmenting the interference information in the device image to obtain a segmented device image comprises:
calculating an edge detection value in the device image using the following formula:
wherein ,representing the edge detection value,/->Represents the gradient value in the horizontal direction +.>Represents the vertical gradient value +_>Representing the arrangementStandby image->、/>、/>、/>、/>、/>、/>Representing pixel values of the device image within a convolution kernel when the device image is convolved with a Sobel operator,/->Indicates the horizontal direction +.>Representing the vertical direction;
taking the pixel position when the edge detection value is larger than a preset edge threshold value as an edge position in the equipment image;
measuring the length and width of the edge part;
identifying an interference area in the device image based on the length and width of the edge portion;
and dividing the interference area in the equipment image to obtain the divided equipment image.
8. The method according to claim 1, wherein the performing local quality detection on the power device based on the segmented device image to obtain a local quality detection result of the power device includes:
Acquiring a local detection template of the power equipment, and acquiring an area with the same size as the local detection template in the segmented equipment image to obtain a local area to be detected;
calculating the region similarity between the local region to be detected and the local detection template by using the following formula:
wherein ,representing the similarity of the regions>* N represents the size of the local detection template, < >>Representing the upper left corner coordinates of said local detection template,/->Expressed as +.>Said local detection template with coordinates in upper left corner,>and->Representing the upper left corner coordinates of said local area to be detected,/->Expressed as +.>The coordinates are the local area to be detected in the upper left corner;
determining a target local area from the local areas to be detected based on the area similarity;
and performing defect detection on the target local area to obtain the local quality detection result.
9. The method of claim 1, wherein the extracting the anomaly data set for each of the candidate anomaly data from the normalized data based on the time scale of the candidate anomaly data comprises:
performing cluster analysis on the standardized data to obtain data clusters;
Inquiring a data cluster corresponding to the time scale of the candidate abnormal data from the data cluster based on the time scale of the candidate abnormal data and the time scale of the data cluster to obtain a target data cluster;
and clustering the target data as the abnormal data set.
10. An electrical equipment inspection device, the device comprising:
the three-dimensional construction module is used for acquiring equipment information of the power equipment, acquiring equipment images of the power equipment, extracting equipment characteristic points from the equipment images, converting the equipment characteristic points into three-dimensional point cloud data, and constructing a three-dimensional point cloud model of the three-dimensional point cloud data;
the global quality inspection module is used for carrying out point cloud data segmentation on the three-dimensional point cloud data in the three-dimensional point cloud model to obtain segmented point cloud data, calculating point cloud difference values between the segmented point cloud data and preset standard point cloud data, removing error difference values in the difference values to obtain screened difference values, and determining a global quality detection result of the power equipment based on the screened difference values;
the local quality inspection module is used for dividing the interference information in the equipment image to obtain a divided equipment image, and carrying out local quality inspection on the power equipment based on the divided equipment image to obtain a local quality inspection result of the power equipment;
The abnormal selection module is used for acquiring historical operation data of the power equipment, carrying out standardization processing on the historical operation data to obtain standardized data, identifying candidate abnormal data in the standardized data, and extracting an abnormal data set of each candidate abnormal data in the candidate abnormal data from the standardized data based on the time scale of the candidate abnormal data, wherein the identification of the candidate abnormal data in the standardized data comprises the following steps:
sequencing the standardized data according to a time sequence to obtain a historical data sequence; calculating the surrounding values of the historical operating data in the historical data sequence by using the following formula:
wherein ,representing the surrounding values +.>Represents +.>Distance between the data point and the data point at the centre instant in the p-time period,/v>，/>Representation ofMean value of middle distance,/">Representing the absolute difference between the distance at time p and the distance at time p-1,/o>Represents a period of time less than p, +.>，/>Representation ofThe average value of the absolute difference values of (c),
when the absolute difference value between the surrounding numerical value and the current numerical value in the historical data sequence is larger than a preset difference value, the current numerical value in the historical data sequence is used as the candidate abnormal data;
And the result determining module is used for taking the global quality detection result, the local quality detection result and the abnormal data set as the quality inspection result of the power equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310460521.4A CN116168351B (en) | 2023-04-26 | 2023-04-26 | Inspection method and device for power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310460521.4A CN116168351B (en) | 2023-04-26 | 2023-04-26 | Inspection method and device for power equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116168351A CN116168351A (en) | 2023-05-26 |
| CN116168351B true CN116168351B (en) | 2023-09-08 |
Family
ID=86420464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310460521.4A Active CN116168351B (en) | 2023-04-26 | 2023-04-26 | Inspection method and device for power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116168351B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116645370B (en) * | 2023-07-27 | 2023-10-10 | 山东顺发重工有限公司 | Real-time detection method for surface defects of high-temperature forging based on three-dimensional point cloud data |
| CN116699428B (en) * | 2023-08-08 | 2023-10-10 | 深圳市杰成镍钴新能源科技有限公司 | Defect detection method and device for retired battery |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20210061875A (en) * | 2019-11-20 | 2021-05-28 | 국민대학교산학협력단 | Method for detecting defects in the 3d lidar sensor using point cloud data |
| CN114373138A (en) * | 2021-12-28 | 2022-04-19 | 北京交通大学 | Full-automatic unmanned aerial vehicle inspection method and system for high-speed railway |
| CN115549303A (en) * | 2022-09-30 | 2022-12-30 | 国网四川省电力公司广安供电公司 | Power equipment inspection monitoring system |
| CN115861927A (en) * | 2022-12-01 | 2023-03-28 | 中国南方电网有限责任公司超高压输电公司大理局 | Image identification method and device for power equipment inspection image and computer equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018148628A1 (en) * | 2017-02-10 | 2018-08-16 | Seecure Systems, Inc. | Detection of risky objects in image frames |
| CN114037675B (en) * | 2021-11-05 | 2022-12-06 | 南京航空航天大学 | Airplane sample plate defect detection method and device |
-
2023
- 2023-04-26 CN CN202310460521.4A patent/CN116168351B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20210061875A (en) * | 2019-11-20 | 2021-05-28 | 국민대학교산학협력단 | Method for detecting defects in the 3d lidar sensor using point cloud data |
| CN114373138A (en) * | 2021-12-28 | 2022-04-19 | 北京交通大学 | Full-automatic unmanned aerial vehicle inspection method and system for high-speed railway |
| CN115549303A (en) * | 2022-09-30 | 2022-12-30 | 国网四川省电力公司广安供电公司 | Power equipment inspection monitoring system |
| CN115861927A (en) * | 2022-12-01 | 2023-03-28 | 中国南方电网有限责任公司超高压输电公司大理局 | Image identification method and device for power equipment inspection image and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 基于空间相似聚类的点云数据分割方法研究与实验;马进全;李玉忠;穆文龙;;地理信息世界(第02期);134-138 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116168351A (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229509B (en) | Method and device for identifying object class and electronic equipment | |
| CN116168351B (en) | Inspection method and device for power equipment | |
| CN112418216B (en) | Text detection method in complex natural scene image | |
| CN109344864B (en) | Image processing method and device for dense object | |
| CN110390327B (en) | Foreground extraction method and device, computer equipment and storage medium | |
| CN112651953B (en) | Picture similarity calculation method and device, computer equipment and storage medium | |
| CN115909059A (en) | Natural resource sample library establishing method and device | |
| CN111950523A (en) | Ship detection optimization method and device based on aerial photography, electronic equipment and medium | |
| CN113409296A (en) | Core-pulling detection method of winding battery cell, electronic equipment and storage medium | |
| CN113554008A (en) | Method and device for detecting static object in area, electronic equipment and storage medium | |
| CN110288040B (en) | Image similarity judging method and device based on topology verification | |
| CN112966687B (en) | Image segmentation model training method and device and communication equipment | |
| CN111523423B (en) | Power equipment identification method and device | |
| CN112528903B (en) | Face image acquisition method and device, electronic equipment and medium | |
| CN112883827A (en) | Method and device for identifying designated target in image, electronic equipment and storage medium | |
| CN111079752A (en) | Method and device for identifying circuit breaker in infrared image and readable storage medium | |
| CN115601684A (en) | Emergency early warning method and device, electronic equipment and storage medium | |
| CN115760854A (en) | Deep learning-based power equipment defect detection method and device and electronic equipment | |
| CN115374517A (en) | Testing method and device for wiring software, electronic equipment and storage medium | |
| CN115272262A (en) | Outdoor insulator surface defect identification method and device and electronic equipment | |
| CN114240924A (en) | Power grid equipment quality evaluation method based on digitization technology | |
| CN114299007A (en) | Flame detection method and system and computer readable storage medium | |
| CN111986169A (en) | Door and window detection method, system, terminal and medium | |
| CN117218162B (en) | Panoramic tracking vision control system based on ai | |
| CN114708230B (en) | Vehicle frame quality detection method, device, equipment and medium based on image analysis |
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 |