CN111507147A - Intelligent inspection method and device, computer equipment and storage medium - Google Patents
Intelligent inspection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111507147A CN111507147A CN201911031275.0A CN201911031275A CN111507147A CN 111507147 A CN111507147 A CN 111507147A CN 201911031275 A CN201911031275 A CN 201911031275A CN 111507147 A CN111507147 A CN 111507147A
- Authority
- CN
- China
- Prior art keywords
- inspection
- image
- equipment
- target
- identification model
- 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.)
- Pending
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 495
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims description 55
- 238000005299 abrasion Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 13
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 230000036541 health Effects 0.000 claims description 2
- 230000010365 information processing Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06V10/267—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 by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses an intelligent inspection method, which comprises the following steps: the method comprises the steps that inspection configuration information is obtained, wherein the inspection configuration information comprises inspection points and inspection indexes; calling camera equipment corresponding to the inspection point to shoot an image of equipment to be inspected in an area corresponding to the inspection point; extracting a target inspection image from an image of equipment to be inspected by adopting an image detection algorithm; and taking the target inspection image as the input of the inspection identification model, and acquiring the inspection result output by the inspection identification model. The intelligent inspection system has the advantages that the service end can efficiently inspect the equipment to be inspected in real time, the intelligent degree of inspection is improved, the inspection efficiency is greatly improved compared with the traditional manual inspection or magnetic stripe card inspection mode, furthermore, inspection results and target inspection images can be stored and subsequently acquired, and the inspection standardization is improved. The intelligent inspection method improves the inspection efficiency and the standardization of the equipment. In addition, an intelligent inspection device, computer equipment and a storage medium are also provided.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an intelligent inspection method, an intelligent inspection device, computer equipment and a storage medium.
Background
Along with the continuous development of information process of various industries, the types and the quantity of equipment are more and more, for example, equipment in the fields of railways, network power, petroleum and the like has certain requirements on the normative and the rapidity of the maintenance and the routing inspection of electronic and mechanical equipment in order to ensure the normal operation of the equipment. However, most of the existing inspection systems use magnetic sheets and magnetic strips for sensing to perform inspection confirmation and statistics, on one hand, because identification codes of articles such as magnetic strips of magnetic cards and the like can be copied, it is difficult to ensure that transmission information is true and reliable, and thus accuracy of inspection recording is affected. On the other hand, the magnetic sheets and the magnetic strips are used for sensing to perform routing inspection, field characteristics cannot be provided, so that effective statistics and adjustment cannot be performed on field problems, the management personnel cannot communicate with the field problems in real time after the problems occur in the routing inspection field, unnecessary disputes are easily caused after the problems occur in corresponding field records, the situation of equipment cannot be rapidly and comprehensively known, and therefore the problems are timely handled, and therefore an intelligent routing inspection scheme needs to be provided urgently.
Disclosure of Invention
In view of the above, it is necessary to provide a smart inspection method, an apparatus, a computer device and a storage medium, which can improve inspection accuracy and comprehensiveness.
An intelligent inspection method, characterized in that the method comprises:
acquiring patrol configuration information, wherein the patrol configuration information comprises patrol points and patrol indexes;
calling the camera equipment corresponding to the inspection point to shoot an image of the equipment to be inspected in the area corresponding to the inspection point;
extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm;
and taking the target inspection image as the input of an inspection identification model, and acquiring an inspection result output by the inspection identification model.
An intelligent inspection device, the device comprising:
the system comprises a configuration information acquisition module, a configuration information acquisition module and a configuration information processing module, wherein the configuration information acquisition module is used for acquiring patrol configuration information which comprises patrol points and patrol indexes;
the inspection image acquisition module is used for calling the camera equipment corresponding to the inspection point to shoot an image of the equipment to be inspected in the area corresponding to the inspection point;
the target image extraction module is used for extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm;
and the inspection result acquisition module is used for taking the target inspection image as the input of the inspection identification model and acquiring the inspection result output by the inspection identification model.
A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of:
acquiring patrol configuration information, wherein the patrol configuration information comprises patrol points and patrol indexes;
calling the camera equipment corresponding to the inspection point to shoot an image of the equipment to be inspected in the area corresponding to the inspection point;
extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm;
and taking the target inspection image as the input of an inspection identification model, and acquiring an inspection result output by the inspection identification model.
A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
acquiring patrol configuration information, wherein the patrol configuration information comprises patrol points and patrol indexes;
calling the camera equipment corresponding to the inspection point to shoot an image of the equipment to be inspected in the area corresponding to the inspection point;
extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm;
and taking the target inspection image as the input of an inspection identification model, and acquiring an inspection result output by the inspection identification model.
According to the intelligent inspection method, the intelligent inspection device, the computer equipment and the storage medium, the inspection configuration information is obtained, and the inspection configuration information comprises inspection points and inspection indexes; calling the camera equipment corresponding to the inspection point to shoot an image of the equipment to be inspected in the area corresponding to the inspection point; extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm; and taking the target inspection image as the input of an inspection identification model, and acquiring an inspection result output by the inspection identification model. The intelligent inspection system has the advantages that the service end can efficiently inspect the equipment to be inspected in real time, the intelligent degree of inspection is improved, the inspection efficiency is greatly improved compared with the traditional manual inspection or magnetic stripe card inspection mode, furthermore, inspection results and target inspection images can be stored and subsequently acquired, and the inspection standardization is improved. The intelligent inspection method improves the inspection efficiency and the standardization of the equipment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
FIG. 1 is a flow diagram of a smart routing inspection method in one embodiment;
FIG. 2 is a flow chart of a smart routing inspection method in another embodiment;
FIG. 3 is a flow chart of a smart routing inspection method in yet another embodiment;
FIG. 4 is a flow diagram of a method for training a tour inspection recognition model in one embodiment;
FIG. 5 is a block diagram of the intelligent inspection device in one embodiment;
FIG. 6 is a block diagram of a computer device in one embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, in an embodiment, a smart inspection method is provided, which may be applied to a terminal or a server, and specifically includes the following steps:
102, acquiring patrol configuration information, wherein the patrol configuration information comprises patrol points and patrol indexes.
The inspection configuration information refers to information which is configured in advance for equipment needing inspection, and is used for determining an inspection object and an inspection index based on the inspection configuration information. The inspection configuration information comprises inspection points and inspection indexes, the inspection points refer to the positions of equipment needing inspection, such as a certain section of rail, and the inspection indexes refer to standards for determining whether the inspection equipment is normal, such as whether train wheels are worn or not. Specifically, an inspection configuration information template may be established in advance, and when the service end receives the inspection instruction, the inspection configuration information is obtained from the inspection configuration information template.
And 104, calling the camera equipment corresponding to the inspection point to shoot the image of the equipment to be inspected in the area corresponding to the inspection point.
The equipment image to be patrolled and examined is the image that contains the equipment to be patrolled and examined, specifically, calls the camera equipment that the point is corresponded to patrolling and examining and shoots the corresponding region of patrolling and examining, can obtain this equipment image to be patrolled and examined. The image to be inspected is obtained through shooting of the camera equipment, so that information of the image to be inspected can be prevented from being tampered, the real reliability of the image to be inspected is guaranteed, and the inspection accuracy is improved based on the image of the image to be inspected.
It should be noted that the image capturing device may be an industrial camera, and the industrial camera is a key component in a machine vision system, and its most essential function is to convert an optical signal into an ordered electrical signal, and the resolution and image quality of an image acquired by a server can be improved to a certain extent by the industrial camera.
And 106, extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm.
The target inspection image is an image of equipment to be inspected, and understandably, the image of the equipment to be inspected contains the image of the equipment to be inspected, but also contains some background information, which interferes the inspection and influences the inspection accuracy. Therefore, in the embodiment, the target inspection image is extracted from the to-be-inspected device image by adopting an image detection algorithm, so that the interference of background information in the to-be-inspected device image is reduced, and the inspection accuracy is improved subsequently. The image detection algorithm is a method for extracting a target image by removing background information based on computational vision, and can be an image detection algorithm based on a shape profile, a detection method based on target characteristics, or an image detection algorithm based on deep learning.
And step 108, taking the target inspection image as the input of an inspection identification model, and acquiring an inspection result output by the inspection identification model.
The inspection recognition model is used for recognizing an input target inspection image to obtain whether the equipment corresponding to the target inspection image is normal or not, the inspection recognition model can be obtained by training in a deep learning mode, and the inspection result is information used for determining whether the equipment to be inspected is normal or not, and the equipment is normal and equipment faults are avoided. Specifically, training in advance obtains the recognition model of patrolling and examining, patrols and examines the image as the input of patrolling and examining the recognition model with the target to directly acquire the result of patrolling and examining recognition model output, realized that the service end is to waiting to patrol and examine equipment high-efficiently in real time and patrol and examine, compare in traditional manual patrol and examine or the mode of patrolling and examining of magnetic stripe magnetic card, improved the efficiency of patrolling and examining greatly, improved the intelligent degree of patrolling and examining, furtherly, can also be with patrolling and examining result and target and patrolling and examining the image and preserving and.
According to the intelligent inspection method, inspection configuration information is obtained, and the inspection configuration information comprises inspection points and inspection indexes; calling the camera equipment corresponding to the inspection point to shoot an image of the equipment to be inspected in the area corresponding to the inspection point; extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm; and taking the target inspection image as the input of an inspection identification model, and acquiring an inspection result output by the inspection identification model. The intelligent inspection system has the advantages that the service end can efficiently inspect the equipment to be inspected in real time, the intelligent degree of inspection is improved, the inspection efficiency is greatly improved compared with the traditional manual inspection or magnetic stripe card inspection mode, furthermore, inspection results and target inspection images can be stored and subsequently acquired, and the inspection standardization is improved. The intelligent inspection method improves the inspection efficiency and the standardization of the equipment.
In one embodiment, the tour identification model includes: a fault classifier to identify a type of equipment fault;
in this embodiment, the fault classifier is used to identify the type of the equipment fault, that is, the type of the equipment fault is determined by performing identification and analysis on a target inspection image corresponding to the faulty equipment in an inspection result of the fault classifier.
The target inspection image is used as the input of an inspection identification model, and the inspection result obtained by the inspection identification model comprises the following steps:
when the equipment in the target inspection image is identified to be fault equipment, taking the target inspection image as the input of the fault classifier, and acquiring the fault type output by the fault classifier, wherein the fault type comprises: part drop out and part wear.
The fault type includes component falling and component abrasion, the component falling refers to component falling in equipment, such as screw falling, and the component abrasion refers to component abrasion in the equipment. According to the intelligent routing inspection system, the fault type of the fault equipment is identified and analyzed through the fault classifier, intelligent routing inspection analysis is achieved, the efficiency of routing inspection analysis is improved, and therefore the convenience of routing inspection of the equipment is improved.
In the above embodiment, when the equipment in the target inspection image is identified to be fault equipment, the target inspection image is used as the input of the fault classifier, the fault type output by the fault classifier is obtained, intelligent inspection analysis is realized, the efficiency of the inspection analysis is improved, and therefore the convenience of equipment inspection is improved.
As shown in fig. 2, in an embodiment, after the inspection result output by the inspection recognition model is obtained by taking the target inspection image as an input of the inspection recognition model, the method further includes:
and step 110, when the inspection result is the fault equipment, taking the target inspection image as the input of the fault classifier, and acquiring the fault type output by the fault classifier.
Specifically, for the equipment with the fault inspection result, the target inspection image is identified and classified through a fault classifier, and the fault type is determined, so that corresponding processing can be performed according to the fault type in the following process.
And 112, when the fault type is that the component falls off, sending the target inspection image to an equipment management end for re-inspection to obtain a secondary inspection result.
Specifically, when the fault type is that the component falls off, the server sends the corresponding target inspection image to the equipment management end, so that the management end carries out manual inspection to obtain a secondary inspection result, and the inspection accuracy is further improved.
It should be noted that when the server detects that the secondary inspection result is that the component falls off, the server sends the secondary inspection result and the inspection configuration information corresponding to the target object to the manager in the form of a mail or a short message, so that the manager can perform maintenance processing in time, and normal operation of the device is guaranteed.
And step 114, when the fault type is component abrasion, identifying the abrasion part of the target inspection image through an image identification technology and identifying the abrasion part.
The image recognition technology refers to a technology for processing, analyzing and understanding an image by using a computer to recognize various targets and objects in different modes. The specific process of identifying the worn part is as follows: and extracting the characteristics of the target inspection image, matching and identifying the characteristics of the target inspection image and the characteristics of the reference equipment image, and determining the worn part. And marking the identified worn part after detecting the edge position of the worn part by an edge algorithm. Specifically, when the fault type is component abrasion, the server side analyzes and recognizes the abraded part by adopting an image recognition algorithm, and identifies the identified part, so that a manager can carry out targeted maintenance according to the identified part, the manager is guided to maintain, the equipment maintenance efficiency is improved, and the normal work of the equipment is guaranteed.
In the embodiment, when the inspection result is the fault equipment, the target inspection image is used as the input of the fault classifier, and the fault type output by the fault classifier is obtained; when the fault type is that the component falls off, the target inspection image is sent to an equipment management end for re-inspection, and a secondary inspection result is obtained; when the fault type is component abrasion, the abrasion part of the target inspection image is identified through an image identification technology and is identified, so that managers can conveniently conduct targeted maintenance and repair according to the fault type, the managers are guided to conduct maintenance, the equipment maintenance and repair efficiency is improved, and normal operation of equipment is guaranteed.
As shown in fig. 3, in one embodiment, the inspection indexes include at least one reference inspection image and an inspection portion corresponding to each reference inspection image.
The reference inspection image is an image of normal equipment stored in advance by a server and used as a standard for determining an inspection result, each reference inspection image comprises a plurality of inspection positions, and the inspection positions are distinguished according to the structure of the normal equipment and components needing inspection.
After the target inspection image is used as the input of the inspection identification model and the inspection result output by the inspection identification model is obtained, the method further comprises the following steps:
and step 116, extracting inspection sub-images corresponding to each inspection part from the target inspection image.
Specifically, the target inspection image is segmented according to inspection positions corresponding to the reference inspection image through an image segmentation method, and inspection sub-images corresponding to each inspection position are obtained. It can be understood that, by dividing the whole target inspection image into corresponding inspection subimages, the accuracy of the equipment inspection is improved based on the inspection subimages,
and step 118, comparing the inspection subimages with the reference inspection image corresponding to the inspection part to obtain an inspection result corresponding to the inspection part.
Specifically, the inspection subimages are compared with the reference inspection image corresponding to the inspection part through an image comparison algorithm to obtain an inspection result corresponding to the inspection part. The image comparison algorithm can be a similarity comparison algorithm or a difference image detection algorithm. The method has the advantages that the global target inspection image is divided into the local inspection sub-images, the effective information contained in the inspection sub-images is richer, the local inspection sub-images are compared with the reference inspection images corresponding to the inspection parts one by one, the accuracy of the inspection result is obviously improved, and the inspection efficiency is improved.
In the embodiment, the inspection subimages corresponding to each inspection part are extracted from the target inspection image; the inspection subimage is compared with the reference inspection image corresponding to the inspection part to obtain an inspection result corresponding to the inspection part, so that the accuracy of the inspection result is improved, and the inspection efficiency is improved.
As shown in fig. 4, in one embodiment, the patrol inspection recognition model is obtained by training a convolutional neural network model.
The convolutional neural network model is a deep feedforward artificial neural network model, and the images are identified in a machine learning mode.
The inspection identification model is obtained by adopting the following method:
Specifically, the server acquires a pre-stored training sample set, where the training sample set includes an image corresponding to normal equipment and an image corresponding to faulty equipment.
And step 108B, obtaining a label corresponding to each training sample.
The label is a preset label for identifying the training result. In this embodiment, the label corresponding to the training sample corresponds to the inspection result, that is, two labels of equipment normal and equipment fault are provided.
And 108C, taking the training sample as the input of the inspection recognition model to be trained, and taking the label corresponding to the training sample as the expected output for training to obtain the trained inspection recognition model.
Specifically, the training sample is used as the input of the inspection recognition model to be trained, and the label corresponding to the training sample is used as the expected output to be trained, so that the trained inspection recognition model is obtained. Understandably, the routing inspection identification model is obtained by training the convolutional neural network model, so that the identification efficiency of the routing inspection identification model is improved, and the routing inspection efficiency is improved based on the routing inspection identification model.
In the above embodiment, first, a training sample set is obtained, where the training sample set includes an image corresponding to a normal device and an image corresponding to a faulty device; then, acquiring a label corresponding to each training sample; and finally, the training sample is used as the input of the inspection identification model to be trained, the label corresponding to the training sample is used as the expected output to be trained, the inspection identification model after training is obtained, the identification efficiency of the inspection identification model is improved, and the inspection efficiency is improved based on the inspection identification model in the following process.
In one embodiment, the inspection result includes equipment health and equipment failure.
After the target inspection image is used as the input of the inspection identification model and the inspection result output by the inspection identification model is obtained, the method further comprises the following steps:
and sending an operation task to an operator corresponding to the equipment according to the inspection result of the equipment fault so that the operator can overhaul the equipment.
Specifically, the inspection result of the equipment fault is sent to the operation personnel corresponding to the equipment to enable the operation personnel to overhaul the equipment, so that the equipment inspection can be timely processed, and the on-time rate of the equipment can be favorably guaranteed.
In the above embodiment, the operation task is sent to the operating personnel that equipment corresponds with the result of patrolling and examining of equipment trouble to make the operating personnel overhaul the equipment, realized patrolling and examining the equipment in time and handle, be favorable to guaranteeing the rate of opening of equipment.
In an embodiment, after the performing image recognition on the target inspection image by using a preset image recognition model to obtain an inspection result, the method further includes:
and storing the image of the equipment to be inspected and the inspection result in a database for archiving.
Specifically, the image of the equipment to be inspected and the inspection result are stored in a database for archiving. Therefore, the service end can store the images, namely the images of the equipment to be patrolled and examined and the patrolling results, of the patrolling records in the database, and the on-site patrolling records are stored, so that unnecessary disputes caused by problems in patrolling and examining processing are avoided, and the patrolling and examining efficiency is further guaranteed.
In the embodiment, the image of the equipment to be patrolled and examined and the patrolling result are stored in the database for archiving, the field patrolling record is saved, and unnecessary disputes caused by problems in patrolling and examining processing are avoided, so that the patrolling and examining efficiency is further ensured.
As shown in fig. 5, in one embodiment, a smart inspection device is provided, including:
a configuration information obtaining module 502, configured to obtain patrol configuration information, where the patrol configuration information includes patrol points and patrol indexes;
a patrol image acquisition module 504, configured to call the camera device corresponding to the patrol point to shoot an image of the device to be patrolled in the region corresponding to the patrol point;
a target image extraction module 506, configured to extract a target inspection image from the to-be-inspected device image by using an image detection algorithm;
and the inspection result obtaining module 508 is configured to use the target inspection image as an input of the inspection identification model, and obtain an inspection result output by the inspection identification model.
In one embodiment, the tour identification model includes: a fault classifier to identify a type of equipment fault;
the inspection result obtaining module comprises a fault classification unit, and is used for identifying that the target inspection image is taken as the input of the fault classifier when the target inspection image is taken as a fault device, and obtaining the fault type output by the fault classifier, wherein the fault type comprises: part drop out and part wear.
In one embodiment, the intelligent inspection device further comprises a type determination module, a first processing module and a second processing module.
The type determining module is used for taking the target inspection image as the input of the fault classifier and acquiring the fault type output by the fault classifier when the inspection result is the fault equipment;
the first processing module is used for sending the target inspection image to an equipment management end for re-inspection when the fault type is that the component falls off, so as to obtain a secondary inspection result;
and the second processing module is used for identifying the worn part of the target inspection image through an image identification technology and identifying when the fault type is component wear.
In one embodiment, the inspection indexes comprise at least one reference inspection image and an inspection part corresponding to each reference inspection image;
the intelligent inspection device also comprises a subimage extraction module and a subimage comparison module.
The subimage extraction module is used for extracting the routing inspection subimage corresponding to each routing inspection part from the target routing inspection image;
and the subimage comparison module is used for comparing the inspection subimage with the reference inspection image corresponding to the inspection part to obtain an inspection result corresponding to the inspection part.
In one embodiment, the inspection result obtaining module comprises a sample set obtaining unit, a label obtaining unit and a model training unit.
The device comprises a sample set acquisition unit, a failure device acquisition unit and a failure device acquisition unit, wherein the sample set acquisition unit is used for acquiring a training sample set which comprises images corresponding to normal devices and images corresponding to failure devices;
the label acquisition unit is used for acquiring a label corresponding to each training sample;
and the model training unit is used for taking the training sample as the input of the inspection recognition model to be trained, taking the label corresponding to the training sample as the expected output for training, and obtaining the inspection recognition model after training.
In one embodiment, the intelligent inspection device further comprises a job sending module, which is used for sending the inspection result of the equipment fault to a job task of a worker corresponding to the equipment, so that the worker can overhaul the equipment.
In one embodiment, the intelligent inspection device further comprises a record archiving module, which is used for storing the image of the equipment to be inspected and the inspection result in a database for archiving.
FIG. 6 is a diagram illustrating an internal structure of a computer device in one embodiment. The computer device may specifically be a server including, but not limited to, a high performance computer and a cluster of high performance computers. As shown in fig. 6, the computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program that, when executed by the processor, causes the processor to implement the intelligent tour inspection method. The internal memory may also have a computer program stored therein, which when executed by the processor, causes the processor to perform the smart polling method. Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the intelligent tour inspection method provided by the present application may be implemented in the form of a computer program that is executable on a computer device such as that shown in fig. 6. The memory of the computer equipment can store various program templates forming the intelligent inspection device. For example, the configuration information obtaining module 502, the inspection image obtaining module 504, the target image extracting module 506, and the inspection result obtaining module 508 may be used.
A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring patrol configuration information, wherein the patrol configuration information comprises patrol points and patrol indexes; calling the camera equipment corresponding to the inspection point to shoot an image of the equipment to be inspected in the area corresponding to the inspection point; extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm; and taking the target inspection image as the input of an inspection identification model, and acquiring an inspection result output by the inspection identification model.
In one embodiment, the tour identification model includes: a fault classifier to identify a type of equipment fault; the target inspection image is used as the input of an inspection identification model, and the inspection result obtained by the inspection identification model comprises the following steps: when the equipment in the target inspection image is identified to be fault equipment, taking the target inspection image as the input of the fault classifier, and acquiring the fault type output by the fault classifier, wherein the fault type comprises: part drop out and part wear.
In one embodiment, after the target inspection image is used as an input of an inspection identification model and an inspection result output by the inspection identification model is obtained, the method further includes: when the inspection result is the fault equipment, the target inspection image is used as the input of the fault classifier, and the fault type output by the fault classifier is obtained; when the fault type is that the component falls off, the target inspection image is sent to an equipment management end for re-inspection, and a secondary inspection result is obtained; and when the fault type is component abrasion, identifying the abrasion part of the target inspection image through an image identification technology and identifying the abrasion part.
In one embodiment, the inspection indexes comprise at least one reference inspection image and an inspection part corresponding to each reference inspection image; after the target inspection image is used as the input of the inspection identification model and the inspection result output by the inspection identification model is obtained, the method further comprises the following steps: extracting inspection subimages corresponding to each inspection part from the target inspection image; and comparing the inspection subimages with the reference inspection image corresponding to the inspection part to obtain an inspection result corresponding to the inspection part.
In one embodiment, the patrol inspection identification model is obtained by training a convolutional neural network model; the inspection identification model is obtained by adopting the following method: acquiring a training sample set, wherein the training sample set comprises images corresponding to normal equipment and images corresponding to fault equipment; acquiring a label corresponding to each training sample; and taking the training sample as the input of the inspection recognition model to be trained, and taking the label corresponding to the training sample as the expected output for training to obtain the inspection recognition model after training.
In one embodiment, the inspection result comprises equipment normality and equipment failure; after the target inspection image is used as the input of the inspection identification model and the inspection result output by the inspection identification model is obtained, the method further comprises the following steps: and sending an operation task to an operator corresponding to the equipment according to the inspection result of the equipment fault so that the operator can overhaul the equipment.
In an embodiment, after the performing image recognition on the target inspection image by using a preset image recognition model to obtain an inspection result, the method further includes: and storing the image of the equipment to be inspected and the inspection result in a database for archiving.
A computer-readable storage medium storing a computer program, the computer program when executed by a processor implementing the steps of: acquiring patrol configuration information, wherein the patrol configuration information comprises patrol points and patrol indexes; calling the camera equipment corresponding to the inspection point to shoot an image of the equipment to be inspected in the area corresponding to the inspection point; extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm; and taking the target inspection image as the input of an inspection identification model, and acquiring an inspection result output by the inspection identification model.
In one embodiment, the tour identification model includes: a fault classifier to identify a type of equipment fault; the target inspection image is used as the input of an inspection identification model, and the inspection result obtained by the inspection identification model comprises the following steps: when the equipment in the target inspection image is identified to be fault equipment, taking the target inspection image as the input of the fault classifier, and acquiring the fault type output by the fault classifier, wherein the fault type comprises: part drop out and part wear.
In one embodiment, after the target inspection image is used as an input of an inspection identification model and an inspection result output by the inspection identification model is obtained, the method further includes: when the inspection result is the fault equipment, the target inspection image is used as the input of the fault classifier, and the fault type output by the fault classifier is obtained; when the fault type is that the component falls off, the target inspection image is sent to an equipment management end for re-inspection, and a secondary inspection result is obtained; and when the fault type is component abrasion, identifying the abrasion part of the target inspection image through an image identification technology and identifying the abrasion part.
In one embodiment, the inspection indexes comprise at least one reference inspection image and an inspection part corresponding to each reference inspection image; after the target inspection image is used as the input of the inspection identification model and the inspection result output by the inspection identification model is obtained, the method further comprises the following steps: extracting inspection subimages corresponding to each inspection part from the target inspection image; and comparing the inspection subimages with the reference inspection image corresponding to the inspection part to obtain an inspection result corresponding to the inspection part.
In one embodiment, the patrol inspection identification model is obtained by training a convolutional neural network model; the inspection identification model is obtained by adopting the following method: acquiring a training sample set, wherein the training sample set comprises images corresponding to normal equipment and images corresponding to fault equipment; acquiring a label corresponding to each training sample; and taking the training sample as the input of the inspection recognition model to be trained, and taking the label corresponding to the training sample as the expected output for training to obtain the inspection recognition model after training.
In one embodiment, the inspection result comprises equipment normality and equipment failure; after the target inspection image is used as the input of the inspection identification model and the inspection result output by the inspection identification model is obtained, the method further comprises the following steps: and sending an operation task to an operator corresponding to the equipment according to the inspection result of the equipment fault so that the operator can overhaul the equipment.
In an embodiment, after the performing image recognition on the target inspection image by using a preset image recognition model to obtain an inspection result, the method further includes: and storing the image of the equipment to be inspected and the inspection result in a database for archiving.
It should be noted that the intelligent inspection method, the intelligent inspection device, the computer device and the computer readable storage medium belong to a general inventive concept, and the contents in the embodiments of the intelligent inspection method, the intelligent inspection device, the computer device and the computer readable storage medium are mutually applicable.
Those skilled in the art will appreciate that all or a portion of the processes in the methods of the embodiments described above may be implemented by computer programs that may be stored in a non-volatile computer-readable storage medium, which when executed, may include the processes of the embodiments of the methods described above, wherein any reference to memory, storage, database or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, non-volatile memory may include read-only memory (ROM), programmable ROM (prom), electrically programmable ROM (eprom), electrically erasable programmable ROM (eeprom), or flash memory, volatile memory may include Random Access Memory (RAM) or external cache memory, RAM is available in a variety of forms, such as static RAM (sram), Dynamic RAM (DRAM), synchronous sdram (sdram), double data rate sdram (ddr sdram), enhanced sdram (sdram), synchronous link (sdram), dynamic RAM (rdram) (rdram L), direct dynamic RAM (rdram), and the like, and/or external cache memory.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An intelligent inspection method, characterized in that the method comprises:
acquiring patrol configuration information, wherein the patrol configuration information comprises patrol points and patrol indexes;
calling the camera equipment corresponding to the inspection point to shoot an image of the equipment to be inspected in the area corresponding to the inspection point;
extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm;
and taking the target inspection image as the input of an inspection identification model, and acquiring an inspection result output by the inspection identification model.
2. The method of claim 1, wherein the routing inspection identification model comprises: a fault classifier to identify a type of equipment fault;
the target inspection image is used as the input of an inspection identification model, and the inspection result obtained by the inspection identification model comprises the following steps:
when the equipment in the target inspection image is identified to be fault equipment, taking the target inspection image as the input of the fault classifier, and acquiring the fault type output by the fault classifier, wherein the fault type comprises: part drop out and part wear.
3. The method according to claim 1, after the inspection result output by the inspection identification model is obtained by taking the target inspection image as an input of the inspection identification model, the method further comprises the following steps:
when the inspection result is the fault equipment, the target inspection image is used as the input of the fault classifier, and the fault type output by the fault classifier is obtained;
when the fault type is that the component falls off, the target inspection image is sent to an equipment management end for re-inspection, and a secondary inspection result is obtained;
and when the fault type is component abrasion, identifying the abrasion part of the target inspection image through an image identification technology and identifying the abrasion part.
4. The method of claim 1, wherein the inspection metrics include at least one reference inspection image and an inspection location corresponding to each reference inspection image;
after the target inspection image is used as the input of the inspection identification model and the inspection result output by the inspection identification model is obtained, the method further comprises the following steps:
extracting inspection subimages corresponding to each inspection part from the target inspection image;
and comparing the inspection subimages with the reference inspection image corresponding to the inspection part to obtain an inspection result corresponding to the inspection part.
5. The method according to claim 1, wherein the patrol inspection recognition model is obtained by training a convolutional neural network model;
the inspection identification model is obtained by adopting the following method:
acquiring a training sample set, wherein the training sample set comprises images corresponding to normal equipment and images corresponding to fault equipment;
acquiring a label corresponding to each training sample;
and taking the training sample as the input of the inspection recognition model to be trained, and taking the label corresponding to the training sample as the expected output for training to obtain the inspection recognition model after training.
6. The method of claim 1, wherein the inspection results include equipment health and equipment failure;
after the target inspection image is used as the input of the inspection identification model and the inspection result output by the inspection identification model is obtained, the method further comprises the following steps:
and sending an operation task to an operator corresponding to the equipment according to the inspection result of the equipment fault so that the operator can overhaul the equipment.
7. The method according to claim 1, wherein after the image recognition is performed on the target inspection image by using a preset image recognition model to obtain an inspection result, the method further comprises:
and storing the image of the equipment to be inspected and the inspection result in a database for archiving.
8. An intelligent inspection device, the device comprising:
the system comprises a configuration information acquisition module, a configuration information acquisition module and a configuration information processing module, wherein the configuration information acquisition module is used for acquiring patrol configuration information which comprises patrol points and patrol indexes;
the inspection image acquisition module is used for calling the camera equipment corresponding to the inspection point to shoot an image of the equipment to be inspected in the area corresponding to the inspection point;
the target image extraction module is used for extracting a target inspection image from the equipment image to be inspected by adopting an image detection algorithm;
and the inspection result acquisition module is used for taking the target inspection image as the input of the inspection identification model and acquiring the inspection result output by the inspection identification model.
9. A computer arrangement comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program performs the steps of the intelligent tour inspection method according to any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the smart routing inspection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911031275.0A CN111507147A (en) | 2019-10-28 | 2019-10-28 | Intelligent inspection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911031275.0A CN111507147A (en) | 2019-10-28 | 2019-10-28 | Intelligent inspection method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111507147A true CN111507147A (en) | 2020-08-07 |
Family
ID=71863829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911031275.0A Pending CN111507147A (en) | 2019-10-28 | 2019-10-28 | Intelligent inspection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111507147A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112184678A (en) * | 2020-09-30 | 2021-01-05 | 国网北京市电力公司 | Image recognition method, image recognition device, computer-readable storage medium and processor |
| CN112257610A (en) * | 2020-10-23 | 2021-01-22 | 岭东核电有限公司 | Nuclear power equipment monitoring method and device, computer equipment and storage medium |
| CN112364716A (en) * | 2020-10-23 | 2021-02-12 | 岭东核电有限公司 | Nuclear power equipment abnormal information detection method and device and computer equipment |
| CN112580832A (en) * | 2020-11-23 | 2021-03-30 | 深圳市海洋王照明工程有限公司 | Inspection method and device and electronic equipment |
| CN113129303A (en) * | 2021-05-18 | 2021-07-16 | 广州市吉华勘测股份有限公司 | Automatic marking method and device for inspection pictures, storage medium and electronic equipment |
| CN113538370A (en) * | 2021-07-14 | 2021-10-22 | 宁波旗芯电子科技有限公司 | Power grid inspection method and device, computer equipment and storage medium |
| CN113554777A (en) * | 2021-06-24 | 2021-10-26 | 国网山东省电力公司济宁市任城区供电公司 | Intelligent power supply equipment inspection method and system |
| CN113743235A (en) * | 2021-08-11 | 2021-12-03 | 中国南方电网有限责任公司超高压输电公司广州局 | Electric power inspection image processing method, device and equipment based on edge calculation |
| CN113793428A (en) * | 2021-09-14 | 2021-12-14 | 国网江苏省电力有限公司常州供电分公司 | Handheld terminal inspection method and system |
| CN113852915A (en) * | 2021-09-26 | 2021-12-28 | 上海上实龙创智能科技股份有限公司 | Subway station equipment control method and device, electronic equipment and storage medium |
| CN113920449A (en) * | 2021-08-26 | 2022-01-11 | 中国电建集团江西省电力建设有限公司 | Photovoltaic power station inspection method and system, computer equipment and storage medium |
| CN113919692A (en) * | 2021-10-11 | 2022-01-11 | 北京京东乾石科技有限公司 | Equipment inspection method and device, electronic equipment and computer readable medium |
| CN115908871A (en) * | 2022-10-27 | 2023-04-04 | 广州城轨科技有限公司 | Wearable equipment track equipment data detection method, device, equipment and medium |
| CN113727022B (en) * | 2021-08-30 | 2023-06-20 | 杭州申昊科技股份有限公司 | Method and device for collecting inspection image, electronic equipment and storage medium |
| CN117523501A (en) * | 2024-01-04 | 2024-02-06 | 四川省铁路建设有限公司 | Control method and system for pipeline inspection robot |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832770A (en) * | 2017-11-08 | 2018-03-23 | 浙江国自机器人技术有限公司 | A kind of equipment routing inspection method, apparatus, system, storage medium and crusing robot |
| CN109299758A (en) * | 2018-07-27 | 2019-02-01 | 深圳市中兴系统集成技术有限公司 | A kind of intelligent polling method, electronic equipment, intelligent inspection system and storage medium |
| CN109658397A (en) * | 2018-12-12 | 2019-04-19 | 广州地铁集团有限公司 | A kind of rail polling method and system |
-
2019
- 2019-10-28 CN CN201911031275.0A patent/CN111507147A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832770A (en) * | 2017-11-08 | 2018-03-23 | 浙江国自机器人技术有限公司 | A kind of equipment routing inspection method, apparatus, system, storage medium and crusing robot |
| CN109299758A (en) * | 2018-07-27 | 2019-02-01 | 深圳市中兴系统集成技术有限公司 | A kind of intelligent polling method, electronic equipment, intelligent inspection system and storage medium |
| CN109658397A (en) * | 2018-12-12 | 2019-04-19 | 广州地铁集团有限公司 | A kind of rail polling method and system |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112184678A (en) * | 2020-09-30 | 2021-01-05 | 国网北京市电力公司 | Image recognition method, image recognition device, computer-readable storage medium and processor |
| CN112257610A (en) * | 2020-10-23 | 2021-01-22 | 岭东核电有限公司 | Nuclear power equipment monitoring method and device, computer equipment and storage medium |
| CN112364716A (en) * | 2020-10-23 | 2021-02-12 | 岭东核电有限公司 | Nuclear power equipment abnormal information detection method and device and computer equipment |
| CN112257610B (en) * | 2020-10-23 | 2024-05-07 | 岭东核电有限公司 | Nuclear power equipment monitoring method and device, computer equipment and storage medium |
| CN112580832A (en) * | 2020-11-23 | 2021-03-30 | 深圳市海洋王照明工程有限公司 | Inspection method and device and electronic equipment |
| CN113129303B (en) * | 2021-05-18 | 2022-01-18 | 广州市吉华勘测股份有限公司 | Automatic marking method and device for inspection pictures, storage medium and electronic equipment |
| CN113129303A (en) * | 2021-05-18 | 2021-07-16 | 广州市吉华勘测股份有限公司 | Automatic marking method and device for inspection pictures, storage medium and electronic equipment |
| CN113554777A (en) * | 2021-06-24 | 2021-10-26 | 国网山东省电力公司济宁市任城区供电公司 | Intelligent power supply equipment inspection method and system |
| CN113538370A (en) * | 2021-07-14 | 2021-10-22 | 宁波旗芯电子科技有限公司 | Power grid inspection method and device, computer equipment and storage medium |
| CN113743235A (en) * | 2021-08-11 | 2021-12-03 | 中国南方电网有限责任公司超高压输电公司广州局 | Electric power inspection image processing method, device and equipment based on edge calculation |
| CN113743235B (en) * | 2021-08-11 | 2024-04-05 | 中国南方电网有限责任公司超高压输电公司广州局 | Electric power inspection image processing method, device and equipment based on edge calculation |
| CN113920449A (en) * | 2021-08-26 | 2022-01-11 | 中国电建集团江西省电力建设有限公司 | Photovoltaic power station inspection method and system, computer equipment and storage medium |
| CN113727022B (en) * | 2021-08-30 | 2023-06-20 | 杭州申昊科技股份有限公司 | Method and device for collecting inspection image, electronic equipment and storage medium |
| CN113793428A (en) * | 2021-09-14 | 2021-12-14 | 国网江苏省电力有限公司常州供电分公司 | Handheld terminal inspection method and system |
| CN113852915A (en) * | 2021-09-26 | 2021-12-28 | 上海上实龙创智能科技股份有限公司 | Subway station equipment control method and device, electronic equipment and storage medium |
| CN113919692A (en) * | 2021-10-11 | 2022-01-11 | 北京京东乾石科技有限公司 | Equipment inspection method and device, electronic equipment and computer readable medium |
| CN115908871A (en) * | 2022-10-27 | 2023-04-04 | 广州城轨科技有限公司 | Wearable equipment track equipment data detection method, device, equipment and medium |
| CN117523501A (en) * | 2024-01-04 | 2024-02-06 | 四川省铁路建设有限公司 | Control method and system for pipeline inspection robot |
| CN117523501B (en) * | 2024-01-04 | 2024-03-15 | 四川省铁路建设有限公司 | Control method and system for pipeline inspection robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111507147A (en) | Intelligent inspection method and device, computer equipment and storage medium | |
| CN113962274B (en) | Abnormity identification method and device, electronic equipment and storage medium | |
| CN112990870B (en) | Inspection file generation method and device based on nuclear power equipment and computer equipment | |
| CN113822385B (en) | Coal conveying abnormity monitoring method, device and equipment based on image and storage medium | |
| CN112115927A (en) | Intelligent machine room equipment identification method and system based on deep learning | |
| CN111566493A (en) | Method and system for circuit breaker condition monitoring | |
| CN115795021A (en) | Big data risk monitoring, recognizing and early warning device and system | |
| CN112985515B (en) | Method and system for detecting assembly qualification of product fastener and storage medium | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN117314921B (en) | RFID-based starting point detection and treatment method for track inspection equipment | |
| CN113469137A (en) | Abnormal behavior recognition method and device, storage medium and electronic device | |
| CN114140684A (en) | Method, device and equipment for detecting coal blockage and coal leakage and storage medium | |
| CN113778091A (en) | Method for inspecting equipment of wind power plant booster station | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN110826473A (en) | Neural network-based automatic insulator image identification method | |
| CN113205479A (en) | System and method for assessing asset health | |
| CN110992299B (en) | Method and device for detecting browser compatibility | |
| CN111460198A (en) | Method and device for auditing picture timestamp | |
| CN115965625A (en) | Instrument detection device based on visual identification and detection method thereof | |
| CN116002480A (en) | Automatic detection method and system for accidental falling of passengers in elevator car | |
| CN113727022B (en) | Method and device for collecting inspection image, electronic equipment and storage medium | |
| CN110472656B (en) | Vehicle image classification method, device, computer equipment and storage medium | |
| CN111610205A (en) | X-ray image defect detection device for metal parts | |
| CN118096747B (en) | Automatic PCBA (printed circuit board assembly) board detection method and system based on deep learning | |
| CN114596439A (en) | Image-based intelligent damage assessment and check method and device for car insurance and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200807 |
|
| RJ01 | Rejection of invention patent application after publication |