CN107784310A - Status information of equipment acquisition methods, device, system, storage medium and robot - Google Patents
Status information of equipment acquisition methods, device, system, storage medium and robot Download PDFInfo
- Publication number
- CN107784310A CN107784310A CN201711108306.9A CN201711108306A CN107784310A CN 107784310 A CN107784310 A CN 107784310A CN 201711108306 A CN201711108306 A CN 201711108306A CN 107784310 A CN107784310 A CN 107784310A
- Authority
- CN
- China
- Prior art keywords
- equipment
- recognition
- information
- feature vector
- identified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
- G06V10/443—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 by matching or filtering
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G07C3/005—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles during manufacturing process
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Image Analysis (AREA)
- Manipulator (AREA)
Abstract
The embodiment of the invention discloses a kind of status information of equipment acquisition methods, device, system, computer-readable recording medium and indoor extension rail intelligent inspection robot.Wherein, method includes obtaining the target image of the equipment to be identified of robot itself camera collection；According to the recognition feature vector of the target property information of equipment to be identified, in the target image extraction corresponding types；According to target property information in the feature recognition model library pre-established, corresponding feature recognition submodel is matched；The recognition feature vector of feature recognition submodeling analysis extraction is called, obtains the running state information of equipment to be identified.The technical scheme that the application provides can obtain the running state information of current device, so as to the equipment that timely back-to-back running is abnormal, effectively solve the problems, such as that manpower inspection efficiency is low and easily causes careless omission, have higher stability and accuracy.
Description
Technical field
The present embodiments relate to technical field of machine vision, more particularly to a kind of status information of equipment acquisition methods,
Device, system, calculate readable machine storage medium and indoor extension rail intelligent inspection robot.
Background technology
During production or management, the working condition of equipment operation directly affects global development, such as in production process
In, if relevant production units are constantly in the bad shutdown of performance state to be repaired, the quantum of output of enterprise will be directly affected, caused
The insufficient supply of product, the economic benefit and social benefit of difference are brought to whole enterprise.It can be seen that the operation shape of equipment is paid close attention in real time
State, it is very important, equipment routing inspection is just applied and given birth to.
For example, in railway or the control room of transformer station, color change or change in shape instruction equipment are passed through
State, such as unit exception or normal is indicated respectively using the red and green of indicator lamp, if unit exception is, it is necessary to staff
Maintenance in time；Indicate whether to be struck by lightning using the red and green of arrester, if after being struck by lightning, that is, be changed into it is red, it is necessary to
Arrester is changed in time, and otherwise next time, thunderbolt will injury device.Common a kind of plate pressing equipment in the control room of transformer station, lead to
Cross length-width ratio 3：1 rectangular block represents whether it works, if rectangular block represents work perpendicular to horizontal plane, i.e., " throws ", if same water
" moved back " into 30 degree or so (fixed gears) plane included angle, then it represents that do not work, if because operation or unit exception, it is impossible to
Normal power supply.
Existing equipment routing inspection, namely obtain the status information of equipment, the typically sense organ using people or simple instrument
Table instrument, according to codes and standards, pinpoint and periodically carry out equipment inspection, find out unit exception place.But manpower is patrolled, not only
Efficiency is low, and easily causes careless omission, and the degree of accuracy is relatively low.
Therefore how inspection accurately and efficiently to be carried out to equipment, the running status of timely feedback device, it is art technology
Personnel's urgent problem to be solved.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of status information of equipment acquisition methods, device, system, the readable machine of calculating
Storage medium and indoor extension rail intelligent inspection robot, accurate and inspection efficiently is carried out to equipment, timely feedback device
Operation conditions, to take measures in time, remove a hidden danger as early as possible, avoid unnecessary loss.
In order to solve the above technical problems, the embodiment of the present invention provides following technical scheme：
On the one hand the embodiment of the present invention provides a kind of status information of equipment acquisition methods, intelligently patrolled applied to indoor extension rail
Robot is examined, including：
Obtain the target image of the equipment to be identified of camera collection；
According to the target property information of the equipment to be identified, the identification that corresponding types are extracted in the target image is special
Sign vector, the type of the recognition feature vector is color feature vector or shape eigenvectors；
According to the target property information in the feature recognition model library pre-established, corresponding feature recognition is matched
Submodel；
Recognition feature vector described in calling the feature recognition submodeling analysis, obtain the operation shape of the equipment to be identified
State information；
Wherein, the feature recognition model library includes multiple feature recognition submodels, and each feature recognition submodel utilizes branch
Vector machine is held, is formed according to the multiple sample informations training for gathering each equipment, sample information includes the attribute information of equipment, color
The corresponding relation of the running state information of characteristic vector and equipment or pair of the running state information of shape eigenvectors and equipment
It should be related to.
Optionally, in addition to：
According to the running state information, and prestore equipment operation exception when correspond to running state information, judge
It is described to treat whether equipment operation is normal.
Optionally, in addition to：
When the equipment operation exception to be identified, alarm is carried out, and the positional information of the equipment to be identified is anti-
It is fed to user terminal.
Optionally, the feature recognition submodel is that device type identifies submodel, and device type identifies submodel with setting
Standby type corresponds, and each device type identification submodel includes attribute information, equipment running status and the identification feature of equipment
The corresponding relation of vector；Or
The feature recognition submodel includes color characteristic identification model and shape facility identification model, the color characteristic
Identification model and the shape facility identification model include multiple corresponding characteristic type identification submodels respectively；Each feature class
Type identifies that submodel corresponds with equipment, and each characteristic type identification submodel includes the attribute information of equipment, equipment operation shape
The corresponding relation of state and recognition feature vector.
Optionally, after the target image of the equipment to be identified of the acquisition camera collection, in addition to：
The target image is normalized to the image of default size.
Optionally, the target property information according to the equipment to be identified, extracted in the target image corresponding
The recognition feature vector of type includes：
According to the target property information of the equipment to be identified, the type of recognition feature vector extracted is judged；
When judge extraction recognition feature vector type for color feature vector when, by the color class of the target image
Type is converted into hsv color space type, and calculates the color histogram of each passage respectively, and each color histogram is connected as into one
Dimension group, using the color feature vector as the target image；
When judge the type of recognition feature vector of extraction for shape eigenvectors when, extract the accumulative of the target image
Histogram of gradients, using the shape eigenvectors as the target image.
On the other hand the embodiment of the present invention provides a kind of status information of equipment acquisition device, applied to indoor extension rail intelligence
Crusing robot, including：
Image module is obtained, the target image of the equipment to be identified for obtaining camera collection；
Characteristic extracting module, for the target property information according to the equipment to be identified, carried in the target image
The recognition feature vector of corresponding types is taken, the type of the recognition feature vector is color feature vector or shape eigenvectors；
Model fitting module, for according to the target property information in the feature recognition model library pre-established,
With corresponding feature recognition submodel；The feature recognition model library includes multiple feature recognition submodels, each feature recognition
Submodel utilizes SVMs, is formed according to the multiple sample informations training for gathering each equipment, sample information includes equipment
The corresponding relation or shape eigenvectors of the running state information of attribute information, color feature vector and equipment and the operation of equipment
The corresponding relation of status information；
State information acquisition module, for recognition feature vector described in calling the feature recognition submodeling analysis, obtain
The running state information of the equipment to be identified.
The embodiment of the present invention additionally provides a kind of status information of equipment and obtains system, including processor and memory, described
Realize that the status information of equipment as described in preceding any one obtains when processor is used to perform the computer program stored in the memory
The step of taking method.
The embodiment of the present invention additionally provides a kind of computer-readable recording medium, is deposited on the computer-readable recording medium
Contain status information of equipment and obtain program, the status information of equipment, which obtains, to be realized when program is executed by processor as any one of preceding
The step of status information of equipment acquisition methods.
The embodiment of the present invention finally additionally provides a kind of indoor extension rail intelligent inspection robot, including image capture device and
Computer-readable recording medium as previously described.
The embodiments of the invention provide a kind of status information of equipment acquisition methods, applied to indoor extension rail intelligent inspection machine
People, obtain the target image of the equipment to be identified of robot itself camera collection；Believed according to the objective attribute target attribute of equipment to be identified
Breath, the recognition feature vector of corresponding types is extracted in the target image；Known according to target property information in the feature pre-established
In other model library, corresponding feature recognition submodel is matched；Feature recognition model library includes multiple feature recognition submodels, respectively
Feature recognition submodel utilizes SVMs, is formed according to the multiple sample informations training for gathering each equipment, sample information bag
Include the running state information of the attribute information of equipment, color feature vector and equipment corresponding relation or shape eigenvectors with setting
The corresponding relation of standby running state information；Feature recognition submodeling analysis recognition feature vector is called, obtains equipment to be identified
Running state information.
The advantages of technical scheme that the application provides, is, using hanging rail intelligent inspection robot autonomous operation indoors,
By the camera collection image of itself, it is identified using the recognition feature vector of equipment of the model of structure to extracting,
So as to fast and accurately obtain the running state information of current device, so as to the equipment that timely back-to-back running is abnormal, effective solution
Manpower of having determined inspection efficiency is low and the problem of easily causing careless omission, has higher stability, accuracy and efficiency, can be effective
Potential faults are taken precautions against, the information at initial stage of equipment fault is grasped, to take measures in time, removes a hidden danger as early as possible, it is unnecessary to avoid
Loss.
In addition, the embodiment of the present invention also directed to status information of equipment acquisition methods provide corresponding realization device, equipment,
Computer-readable recording medium and indoor extension rail intelligent inspection robot, further such that methods described has more practicality, institute
Stating device, equipment and computer-readable recording medium has the advantages of corresponding.
Brief description of the drawings
, below will be to embodiment or existing for the clearer explanation embodiment of the present invention or the technical scheme of prior art
The required accompanying drawing used is briefly described in technology description, it should be apparent that, drawings in the following description are only this hair
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of status information of equipment acquisition methods provided in an embodiment of the present invention；
Fig. 2 is the schematic flow sheet of another status information of equipment acquisition methods provided in an embodiment of the present invention；
Fig. 3 is a kind of embodiment structure chart of status information of equipment acquisition device provided in an embodiment of the present invention；
Fig. 4 is another embodiment structure of status information of equipment acquisition device provided in an embodiment of the present invention
Figure.
Embodiment
In order that those skilled in the art more fully understand the present invention program, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiment is only part of the embodiment of the present invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
Term " first ", " second ", " the 3rd " " in the description and claims of this application and above-mentioned accompanying drawing
Four " etc. be for distinguishing different objects, rather than for describing specific order.In addition term " comprising " and " having " and
Their any deformations, it is intended that cover non-exclusive include.Such as contain the process of series of steps or unit, method,
The step of system, product or equipment are not limited to list or unit, but the step of may include not list or unit.
After the technical scheme of the embodiment of the present invention is described, the various non-limiting realities of detailed description below the application
Apply mode.
Referring first to Fig. 1, Fig. 1 is that a kind of flow of status information of equipment acquisition methods provided in an embodiment of the present invention is illustrated
Figure, applied to indoor extension rail intelligent inspection robot, the embodiment of the present invention may include herein below：
S101：Obtain the target image of the equipment to be identified of camera collection.
The indoor self-contained image capture device of extension rail intelligent inspection robot, such as camera, robot are sharp indoors
With hang rail technology can autonomous operation, at equipment set in advance suspend, using camera gather current device image, pass through
The special characteristic for extracting image obtains the equipment running status information.
S102：According to the identification feature of the target property information of equipment to be identified, in the target image extraction corresponding types
Vector, the type of recognition feature vector is color feature vector or shape eigenvectors.
The attribute information of equipment may include the title of equipment, the positional information of equipment, the expression feature of equipment running status,
The recognition feature vector type to be extracted, such as unit exception or normal is represented using the color of indicator lamp, if unit exception,
It is then red light, it is necessary to which staff overhauls in time；Indicate whether to be struck by lightning using the red and green of arrester, if by thunder
After hitting, that is, it is changed into red, it is necessary to change arrester in time；Plate pressing equipment, pass through length-width ratio 3：1 rectangular block represent its whether work
Make, if rectangular block represents work perpendicular to horizontal plane, i.e., " throw ", if same level face angle into 30 degree or so (fixations gears), i.e.,
" moving back ", then it represents that do not work.First two equipment utilization color represents the running status of equipment, and plate pressing equipment can be transported with shape characterization
Row state.
Specifically characteristic extraction procedure can be：
According to the target property information of equipment to be identified, the type of recognition feature vector extracted is judged；
When judge extraction recognition feature vector type for color feature vector when, by the color type of target image turn
Hsv color space type is turned to, and calculates the color histogram of each passage respectively, each color histogram is connected as a dimension
Group, using the color feature vector as target image；
When judge the type of recognition feature vector of extraction for shape eigenvectors when, extract the accumulative gradient of target image
Histogram, using the shape eigenvectors as target image.
, it is necessary to the information such as hue, saturation, intensity be carried out individually separated for color feature vector.Specifically,
The RGB color of current target image can be converted into hsv color space, H represents tone, and S represents saturation degree, and V represents bright
Degree.Calculate the color histogram of target image respectively in H passages, channel S, V passages, be then connected as one-dimension array.
S103：According to target property information in the feature recognition model library pre-established, match corresponding feature and know
Small pin for the case model.
Feature recognition model library includes multiple feature recognition submodels, and each feature recognition submodel utilizes SVMs,
Multiple sample informations training according to each equipment is gathered forms, and sample information includes the attribute information of equipment, color feature vector
With the corresponding relation or shape eigenvectors of the running state information of equipment and the corresponding relation of the running state information of equipment.
Each feature recognition submodel utilizes SVMs, and tool is formed according to the multiple sample informations training for gathering each equipment
Body process can be：
Multiple equipment drawing pictures are gathered as training sample image, comprising equipment in each running status in multiple sample images
Under equipment drawing picture, running status of the every sample image all comprising the attribute information of equipment, color feature vector and equipment believe
The corresponding relation of the corresponding relation or shape eigenvectors of breath and the running state information of equipment.Different equipment will correspondingly be extracted
Characteristic vector type it is different, when equipment extraction for color feature vector when, including for color feature vector and equipment
Running state information corresponding relation；When equipment extraction for color feature vector when, including be shape eigenvectors with
The corresponding relation of the running state information of equipment；When equipment extraction for color feature vector and shape eigenvectors when, including
The corresponding relation and the running state information of shape eigenvectors and equipment of the running state information of color feature vector and equipment
Corresponding relation.
For example, for arrester equipment, the sample image of collection be image under multiple arrester red status and
Image under green state, the attribute information for the equipment that each training sample image includes is the title of arrester and position letter
Breath；Arrester corresponding to the color feature vector and the vector extracted in the image of arrester under from red status is thunderbolt
State；The color feature vector extracted in the image of arrester under green state, the operation shape of arrester corresponding to the vector
State is normal.
The corresponding recognition feature vector of the training sample image of collection is extracted respectively, according to sample information and extraction
Recognition feature vector, using SVMs, based on RBF, it is trained.
According to the difference of the training process of training, following two kinds of situations can be divided into：
Feature recognition submodel is that device type identifies submodel, a pair of device type identification submodel and device type 1
Should, attribute information, the equipment running status pass corresponding with recognition feature vector that each device type identification submodel includes equipment
System；Or
Feature recognition submodel includes color characteristic identification model and shape facility identification model, color characteristic identification model
Include multiple corresponding characteristic type identification submodels respectively with shape facility identification model；Each characteristic type identification submodel
Corresponded with equipment, each characteristic type identification submodel includes attribute information, equipment running status and the identification feature of equipment
The corresponding relation of vector.
The first situation can be trained for each equipment, and second of situation is for the recognition feature vector of extraction
Type is trained, and this does not influence the realization of the application, and the application does not do any restriction to this.
S104：Feature recognition submodeling analysis recognition feature vector is called, obtains the running state information of equipment to be identified.
The recognition feature vector that will be extracted, it is input in the feature recognition submodel matched, can exports and currently set
Standby running state information.
According to running state information, and prestore equipment operation exception when correspond to running state information, judge to wait to set
Whether received shipment row is normal.
Such as prestore and represent to be struck by lightning under the red status of arrester, represent normal under green state.Ought
The IMAQ of preceding arrester and extract color feature vector be input to corresponding in feature recognition submodel, output is lightning-arrest
The indicator lamp of device is red, then confirms that current arrester is struck by lightning.
It should be noted that for the accuracy of whole equipment state information acquisition process, can be by the image of collection, training
Equipment sample image during model is normalized to formed objects, such as a height of 1330*1040 of wide *, unit are resolution ratio.
In technical scheme provided in an embodiment of the present invention, using hanging rail intelligent inspection robot autonomous operation indoors,
By the camera collection image of itself, it is identified using the recognition feature vector of equipment of the model of structure to extracting,
So as to fast and accurately obtain the running state information of current device, so as to the equipment that timely back-to-back running is abnormal, effective solution
Manpower of having determined inspection efficiency is low and the problem of easily causing careless omission, has higher stability, accuracy and efficiency, can be effective
Potential faults are taken precautions against, the information at initial stage of equipment fault is grasped, to take measures in time, removes a hidden danger as early as possible, it is unnecessary to avoid
Loss.
For the equipment for allowing staff or user to find operation exception as early as possible, based on above-described embodiment, referring to Fig. 2,
It may also include：
S105：When equipment operation exception to be identified, alarm is carried out, and the positional information of equipment to be identified is fed back to
User terminal.
By carrying out alarm, or directly by the device location information to break down feed back to upper layer application system or
Person is user terminal, the equipment that can find operation exception in time, and the very first time grasps the information at initial stage of equipment fault, to adopt in time
Measure is taken, is removed a hidden danger as early as possible, avoids unnecessary loss.
The embodiment of the present invention provides corresponding realization device also directed to status information of equipment acquisition methods, further such that
Methods described has more practicality.Status information of equipment acquisition device provided in an embodiment of the present invention is introduced below, under
The status information of equipment acquisition device of text description can be mutually to should refer to devices described above status information acquiring method.
Referring to Fig. 3, Fig. 3 is status information of equipment acquisition device provided in an embodiment of the present invention in a kind of embodiment
Under structure chart, applied to indoor extension rail intelligent inspection robot, the device may include：
Image module 301 is obtained, the target image of the equipment to be identified for obtaining camera collection.
Characteristic extracting module 302, for the target property information according to equipment to be identified, extraction is corresponding in the target image
The recognition feature vector of type, the type of recognition feature vector is color feature vector or shape eigenvectors.
Model fitting module 303, in the feature recognition model library pre-established, being matched according to target property information
Corresponding feature recognition submodel；Feature recognition model library includes multiple feature recognition submodels, each feature recognition submodel
Using SVMs, formed according to the multiple sample informations training for gathering each equipment, the attribute that sample information includes equipment is believed
The corresponding relation or the running status of shape eigenvectors and equipment of the running state information of breath, color feature vector and equipment are believed
The corresponding relation of breath.
State information acquisition module 304, for calling feature recognition submodeling analysis recognition feature vector, obtain to be identified
The running state information of equipment.
Optionally, in some embodiments of the present embodiment, referring to Fig. 4, described device can include：
Judge module 305, for according to running state information, and prestore equipment operation exception when correspondingly run shape
State information, judgement treat whether equipment operation is normal.
In other embodiments of the present embodiment, described device can also for example include：
Alarm module 306, for when judging the equipment operation exception of point to be inspected, carrying out alarm, and will be corresponding
Dot position information to be inspected feed back to user terminal.
In addition, described device can also for example include：
Module 307 is normalized, for target image to be normalized to the image of default size.
Optionally, under some specific embodiments, the characteristic extracting module 302 may include：
Judging unit, for the target property information according to equipment to be identified, judge the class of recognition feature vector extracted
Type；
Fisrt feature extraction unit, for when judge extraction recognition feature vector type for color feature vector when,
The color type of target image is converted into hsv color space type, and calculates the color histogram of each passage respectively, will be each
Color histogram is connected as one-dimension array, using the color feature vector as target image；
Second feature extraction unit, for when judge extraction recognition feature vector type for shape eigenvectors when,
The accumulative histogram of gradients of target image is extracted, using the shape eigenvectors as target image.
The function of each functional module of status information of equipment acquisition device described in the embodiment of the present invention can be according to the above method
Method specific implementation in embodiment, its specific implementation process are referred to the associated description of above method embodiment, herein not
Repeat again.
From the foregoing, it will be observed that the embodiment of the present invention is using hanging rail intelligent inspection robot autonomous operation indoors, by itself
Camera collection image, it is identified using the recognition feature vector of equipment of the model of structure to extracting, so as to quick, accurate
The running state information of true acquisition current device, so as to the equipment that timely back-to-back running is abnormal, effectively solves manpower and patrols
The problem of looking into efficiency lowly and easily causing careless omission, has higher stability, accuracy and efficiency, it is hidden can effectively to take precautions against failure
Suffer from, grasp the information at initial stage of equipment fault, to take measures in time, remove a hidden danger as early as possible, avoid unnecessary loss.
The embodiment of the present invention additionally provides a kind of status information of equipment and obtains system, it may include：
Memory, for storing computer program；
Processor, for performing computer program to realize as above status information of equipment acquisition side described in any one embodiment
The step of method.
The function that status information of equipment described in the embodiment of the present invention obtains each functional module of system can be according to the above method
Method specific implementation in embodiment, its specific implementation process are referred to the associated description of above method embodiment, herein not
Repeat again.
From the foregoing, it will be observed that the embodiment of the present invention fast and accurately obtains the running state information of current device, so as to anti-in time
The equipment for presenting operation exception, effectively solve the problems, such as that manpower inspection efficiency is low and easily causes careless omission, have higher
Stability, accuracy and efficiency, potential faults can be effectively taken precautions against, grasp the information at initial stage of equipment fault, arranged to take in time
Apply, remove a hidden danger as early as possible, avoid unnecessary loss.
The embodiment of the present invention additionally provides a kind of computer-readable recording medium, is stored with status information of equipment and obtains journey
Sequence, the status information of equipment obtain as above status information of equipment acquisition described in any one embodiment when program is executed by processor
The step of method.
The function of each functional module of computer-readable recording medium described in the embodiment of the present invention can be real according to the above method
The method specific implementation in example is applied, its specific implementation process is referred to the associated description of above method embodiment, herein no longer
Repeat.
From the foregoing, it will be observed that the embodiment of the present invention fast and accurately obtains the running state information of current device, so as to anti-in time
The equipment for presenting operation exception, effectively solve the problems, such as that manpower inspection efficiency is low and easily causes careless omission, have higher
Stability, accuracy and efficiency, potential faults can be effectively taken precautions against, grasp the information at initial stage of equipment fault, arranged to take in time
Apply, remove a hidden danger as early as possible, avoid unnecessary loss.
The embodiment of the present invention additionally provides a kind of indoor extension rail intelligent inspection robot, including image capture device and as before
Computer-readable recording medium described in any one embodiment.
The function of each functional module of indoor extension rail intelligent inspection robot can be according to above-mentioned side described in the embodiment of the present invention
Method specific implementation in method embodiment, its specific implementation process are referred to the associated description of above method embodiment, herein
Repeat no more.
From the foregoing, it will be observed that the embodiment of the present invention fast and accurately obtains the running state information of current device, so as to anti-in time
The equipment for presenting operation exception, effectively solve the problems, such as that manpower inspection efficiency is low and easily causes careless omission, have higher
Stability, accuracy and efficiency, potential faults can be effectively taken precautions against, grasp the information at initial stage of equipment fault, arranged to take in time
Apply, remove a hidden danger as early as possible, avoid unnecessary loss.
Each embodiment is described by the way of progressive in this specification, what each embodiment stressed be with it is other
The difference of embodiment, between each embodiment same or similar part mutually referring to.For dress disclosed in embodiment
For putting, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is referring to method part
Explanation.
Professional further appreciates that, with reference to the unit of each example of the embodiments described herein description
And algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software, the composition and step of each example are generally described according to function in the above description.These
Function is performed with hardware or software mode actually, application-specific and design constraint depending on technical scheme.Specialty
Technical staff can realize described function using distinct methods to each specific application, but this realization should not
Think beyond the scope of this invention.
Directly it can be held with reference to the step of method or algorithm that the embodiments described herein describes with hardware, processor
Capable software module, or the two combination are implemented.Software module can be placed in random access memory (RAM), internal memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Above to a kind of status information of equipment acquisition methods provided by the present invention, device, system, computer-readable storage
Medium and indoor extension rail intelligent inspection robot are described in detail.Principle of the specific case used herein to the present invention
And embodiment is set forth, the explanation of above example is only intended to help method and its core think of for understanding the present invention
Think.It should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention, may be used also
To carry out some improvement and modification to the present invention, these are improved and modification is also fallen into the protection domain of the claims in the present invention.
Claims (10)
- A kind of 1. status information of equipment acquisition methods, it is characterised in that applied to indoor extension rail intelligent inspection robot, including：Obtain the target image of the equipment to be identified of camera collection；According to the target property information of the equipment to be identified, extracted in the target image identification features of corresponding types to Amount, the type of the recognition feature vector is color feature vector or shape eigenvectors；According to the target property information in the feature recognition model library pre-established, corresponding feature recognition submodule is matched Type；Recognition feature vector described in calling the feature recognition submodeling analysis, obtain the running status letter of the equipment to be identified Breath；Wherein, the feature recognition model library includes multiple feature recognition submodels, each feature recognition submodel using support to Amount machine, formed according to the multiple sample informations training for gathering each equipment, sample information includes attribute information, the color characteristic of equipment Vector closes with the corresponding relation or shape eigenvectors of the running state information of equipment and the corresponding of running state information of equipment System.
- 2. status information of equipment acquisition methods according to claim 1, it is characterised in that also include：According to the running state information, and prestore equipment operation exception when correspond to running state information, described in judgement Treat whether equipment operation is normal.
- 3. status information of equipment acquisition methods according to claim 2, it is characterised in that also include：When the equipment operation exception to be identified, alarm is carried out, and the positional information of the equipment to be identified is fed back to User terminal.
- 4. status information of equipment acquisition methods according to claim 1, it is characterised in that the feature recognition submodel is Device type identifies submodel, and device type identification submodel corresponds with device type, and each device type identifies submodel The corresponding relation of attribute information, equipment running status and recognition feature vector including equipment；OrThe feature recognition submodel includes color characteristic identification model and shape facility identification model, the color characteristic identification Model and the shape facility identification model include multiple corresponding characteristic type identification submodels respectively；Each characteristic type is known Small pin for the case model and equipment correspond, each characteristic type identification submodel include the attribute information of equipment, equipment running status with The corresponding relation of recognition feature vector.
- 5. status information of equipment acquisition methods according to claim 1, it is characterised in that in the acquisition camera collection Equipment to be identified target image after, in addition to：The target image is normalized to the image of default size.
- 6. the status information of equipment acquisition methods according to claim 1 to 5 any one, it is characterised in that the basis The target property information of the equipment to be identified, the recognition feature vector of corresponding types is extracted in the target image to be included：According to the target property information of the equipment to be identified, the type of recognition feature vector extracted is judged；When judge extraction recognition feature vector type for color feature vector when, by the color type of the target image turn Hsv color space type is turned to, and calculates the color histogram of each passage respectively, each color histogram is connected as a dimension Group, using the color feature vector as the target image；When judge the type of recognition feature vector of extraction for shape eigenvectors when, extract the accumulative gradient of the target image Histogram, using the shape eigenvectors as the target image.
- A kind of 7. status information of equipment acquisition device, it is characterised in that applied to indoor extension rail intelligent inspection robot, including：Image module is obtained, the target image of the equipment to be identified for obtaining camera collection；Characteristic extracting module, for the target property information according to the equipment to be identified, the extraction pair in the target image The recognition feature vector of type is answered, the type of the recognition feature vector is color feature vector or shape eigenvectors；Model fitting module, in the feature recognition model library pre-established, matching phase according to the target property information Corresponding feature recognition submodel；The feature recognition model library includes multiple feature recognition submodels, each feature recognition submodule Type utilizes SVMs, is formed according to the multiple sample informations training for gathering each equipment, sample information includes the attribute of equipment The corresponding relation or shape eigenvectors of the running state information of information, color feature vector and equipment and the running status of equipment The corresponding relation of information；State information acquisition module, for recognition feature vector described in calling the feature recognition submodeling analysis, obtain described The running state information of equipment to be identified.
- 8. a kind of status information of equipment obtains system, it is characterised in that including processor and memory, the processor is used to hold Realize that status information of equipment obtains as described in any one of claim 1 to 6 during the computer program stored in the row memory The step of method.
- 9. a kind of computer-readable recording medium, it is characterised in that equipment shape is stored with the computer-readable recording medium State information acquiring program, the status information of equipment are obtained when program is executed by processor and realized such as any one of claim 1 to 6 The step of status information of equipment acquisition methods.
- 10. a kind of indoor extension rail intelligent inspection robot, it is characterised in that including image capture device and such as claim 9 institute State computer-readable recording medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711108306.9A CN107784310B (en) | 2017-11-08 | 2017-11-08 | Equipment state information acquisition method, device and system, storage medium and robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711108306.9A CN107784310B (en) | 2017-11-08 | 2017-11-08 | Equipment state information acquisition method, device and system, storage medium and robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107784310A true CN107784310A (en) | 2018-03-09 |
| CN107784310B CN107784310B (en) | 2021-03-23 |
Family
ID=61431815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711108306.9A Active CN107784310B (en) | 2017-11-08 | 2017-11-08 | Equipment state information acquisition method, device and system, storage medium and robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107784310B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108347554A (en) * | 2018-03-20 | 2018-07-31 | 浙江国自机器人技术有限公司 | A kind of industrial camera |
| CN108846487A (en) * | 2018-05-29 | 2018-11-20 | 长乐壹中正和信息科技有限公司 | A kind of method and terminal of efficient inspection Weaving device |
| CN108890652A (en) * | 2018-06-28 | 2018-11-27 | 全球能源互联网研究院有限公司 | A kind of Intelligent Mobile Robot and method for inspecting substation equipment |
| CN109063670A (en) * | 2018-08-16 | 2018-12-21 | 大连民族大学 | Block letter language of the Manchus word recognition methods based on prefix grouping |
| CN109271407A (en) * | 2018-09-27 | 2019-01-25 | 西安银石科技发展有限责任公司 | A kind of equipment routing inspection method based on machine learning |
| CN109389182A (en) * | 2018-10-31 | 2019-02-26 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
| CN109491875A (en) * | 2018-11-09 | 2019-03-19 | 浙江国自机器人技术有限公司 | A kind of robot information display method, system and equipment |
| CN109664301A (en) * | 2019-01-17 | 2019-04-23 | 中国石油大学(北京) | Method for inspecting, device, equipment and computer readable storage medium |
| CN109683618A (en) * | 2018-12-28 | 2019-04-26 | 广州中国科学院沈阳自动化研究所分所 | A kind of navigational signals identifying system and its recognition methods |
| CN109783671A (en) * | 2019-01-30 | 2019-05-21 | 京东方科技集团股份有限公司 | A kind of method, computer-readable medium and server to scheme to search figure |
| CN110363169A (en) * | 2019-07-19 | 2019-10-22 | 南方电网科学研究院有限责任公司 | Identification device, equipment and the system of a kind of power grid key equipment and component |
| CN110383274A (en) * | 2018-09-27 | 2019-10-25 | 西门子股份公司 | Identify method, apparatus, system, storage medium, processor and the terminal of equipment |
| CN110471376A (en) * | 2019-07-10 | 2019-11-19 | 深圳市乾行达科技有限公司 | A kind of industry spot fault detection method and equipment |
| CN110555585A (en) * | 2019-07-19 | 2019-12-10 | 云南昆钢电子信息科技有限公司 | Automatic hidden danger level identification and alarm system for steel production equipment |
| CN110738179A (en) * | 2019-10-18 | 2020-01-31 | 国家电网有限公司 | electric power equipment identification method and related device |
| CN111079482A (en) * | 2019-03-29 | 2020-04-28 | 新华三技术有限公司 | Information acquisition method and device |
| CN111082530A (en) * | 2020-01-03 | 2020-04-28 | 国家电网有限公司 | Lightning conductor equipment abnormity alarm method based on Internet of things |
| CN111191721A (en) * | 2019-12-30 | 2020-05-22 | 国网浙江省电力有限公司宁波供电公司 | Protection pressing plate state identification method based on AI technology |
| CN112257740A (en) * | 2020-09-05 | 2021-01-22 | 赛飞特工程技术集团有限公司 | Knowledge graph-based image hidden danger identification method and system |
| CN112541543A (en) * | 2020-12-11 | 2021-03-23 | 深圳市优必选科技股份有限公司 | Image recognition method and device, terminal equipment and storage medium |
| CN113743454A (en) * | 2021-07-22 | 2021-12-03 | 南方电网深圳数字电网研究院有限公司 | Detection method, device and equipment of oil-immersed transformer and storage medium |
| CN114554152A (en) * | 2022-02-22 | 2022-05-27 | 正泰电气股份有限公司 | Intelligent monitoring method for transformer substation |
| CN115862833A (en) * | 2023-02-16 | 2023-03-28 | 成都与睿创新科技有限公司 | Detection system and method for instrument loss |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103324943A (en) * | 2013-06-18 | 2013-09-25 | 中国人民解放军第二炮兵工程大学 | Identification method of complex device panel image multi-sub zone state |
| US20140358601A1 (en) * | 2013-06-03 | 2014-12-04 | Abb Research Ltd. | Industrial asset health profile |
| CN104318198A (en) * | 2014-02-28 | 2015-01-28 | 郑州金惠计算机系统工程有限公司 | Identification method and device suitable for substation robot patrolling |
| CN106514654A (en) * | 2016-11-11 | 2017-03-22 | 国网浙江宁海县供电公司 | Patrol method of robot and patrol robot |
| CN106679813A (en) * | 2016-11-21 | 2017-05-17 | 深圳供电局有限公司 | Intelligent detection system for tunnel power equipment |
-
2017
- 2017-11-08 CN CN201711108306.9A patent/CN107784310B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140358601A1 (en) * | 2013-06-03 | 2014-12-04 | Abb Research Ltd. | Industrial asset health profile |
| CN103324943A (en) * | 2013-06-18 | 2013-09-25 | 中国人民解放军第二炮兵工程大学 | Identification method of complex device panel image multi-sub zone state |
| CN104318198A (en) * | 2014-02-28 | 2015-01-28 | 郑州金惠计算机系统工程有限公司 | Identification method and device suitable for substation robot patrolling |
| CN106514654A (en) * | 2016-11-11 | 2017-03-22 | 国网浙江宁海县供电公司 | Patrol method of robot and patrol robot |
| CN106679813A (en) * | 2016-11-21 | 2017-05-17 | 深圳供电局有限公司 | Intelligent detection system for tunnel power equipment |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108347554A (en) * | 2018-03-20 | 2018-07-31 | 浙江国自机器人技术有限公司 | A kind of industrial camera |
| CN108846487A (en) * | 2018-05-29 | 2018-11-20 | 长乐壹中正和信息科技有限公司 | A kind of method and terminal of efficient inspection Weaving device |
| CN108890652A (en) * | 2018-06-28 | 2018-11-27 | 全球能源互联网研究院有限公司 | A kind of Intelligent Mobile Robot and method for inspecting substation equipment |
| CN109063670A (en) * | 2018-08-16 | 2018-12-21 | 大连民族大学 | Block letter language of the Manchus word recognition methods based on prefix grouping |
| CN110383274B (en) * | 2018-09-27 | 2023-10-27 | 西门子股份公司 | Method, device, system, storage medium, processor and terminal for identifying equipment |
| CN109271407A (en) * | 2018-09-27 | 2019-01-25 | 西安银石科技发展有限责任公司 | A kind of equipment routing inspection method based on machine learning |
| CN110383274A (en) * | 2018-09-27 | 2019-10-25 | 西门子股份公司 | Identify method, apparatus, system, storage medium, processor and the terminal of equipment |
| CN109389182A (en) * | 2018-10-31 | 2019-02-26 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
| CN109491875A (en) * | 2018-11-09 | 2019-03-19 | 浙江国自机器人技术有限公司 | A kind of robot information display method, system and equipment |
| CN109683618A (en) * | 2018-12-28 | 2019-04-26 | 广州中国科学院沈阳自动化研究所分所 | A kind of navigational signals identifying system and its recognition methods |
| CN109664301A (en) * | 2019-01-17 | 2019-04-23 | 中国石油大学(北京) | Method for inspecting, device, equipment and computer readable storage medium |
| CN109664301B (en) * | 2019-01-17 | 2022-02-01 | 中国石油大学(北京) | Inspection method, inspection device, inspection equipment and computer readable storage medium |
| CN109783671A (en) * | 2019-01-30 | 2019-05-21 | 京东方科技集团股份有限公司 | A kind of method, computer-readable medium and server to scheme to search figure |
| US11763164B2 (en) | 2019-01-30 | 2023-09-19 | Boe Technology Group Co., Ltd. | Image-to-image search method, computer-readable storage medium and server |
| CN111079482A (en) * | 2019-03-29 | 2020-04-28 | 新华三技术有限公司 | Information acquisition method and device |
| CN110471376A (en) * | 2019-07-10 | 2019-11-19 | 深圳市乾行达科技有限公司 | A kind of industry spot fault detection method and equipment |
| CN110555585A (en) * | 2019-07-19 | 2019-12-10 | 云南昆钢电子信息科技有限公司 | Automatic hidden danger level identification and alarm system for steel production equipment |
| CN110363169A (en) * | 2019-07-19 | 2019-10-22 | 南方电网科学研究院有限责任公司 | Identification device, equipment and the system of a kind of power grid key equipment and component |
| CN110738179A (en) * | 2019-10-18 | 2020-01-31 | 国家电网有限公司 | electric power equipment identification method and related device |
| CN111191721A (en) * | 2019-12-30 | 2020-05-22 | 国网浙江省电力有限公司宁波供电公司 | Protection pressing plate state identification method based on AI technology |
| CN111082530A (en) * | 2020-01-03 | 2020-04-28 | 国家电网有限公司 | Lightning conductor equipment abnormity alarm method based on Internet of things |
| CN112257740A (en) * | 2020-09-05 | 2021-01-22 | 赛飞特工程技术集团有限公司 | Knowledge graph-based image hidden danger identification method and system |
| CN112541543A (en) * | 2020-12-11 | 2021-03-23 | 深圳市优必选科技股份有限公司 | Image recognition method and device, terminal equipment and storage medium |
| CN112541543B (en) * | 2020-12-11 | 2023-11-24 | 深圳市优必选科技股份有限公司 | Image recognition method, device, terminal equipment and storage medium |
| CN113743454A (en) * | 2021-07-22 | 2021-12-03 | 南方电网深圳数字电网研究院有限公司 | Detection method, device and equipment of oil-immersed transformer and storage medium |
| CN114554152A (en) * | 2022-02-22 | 2022-05-27 | 正泰电气股份有限公司 | Intelligent monitoring method for transformer substation |
| CN115862833A (en) * | 2023-02-16 | 2023-03-28 | 成都与睿创新科技有限公司 | Detection system and method for instrument loss |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107784310B (en) | 2021-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784310A (en) | Status information of equipment acquisition methods, device, system, storage medium and robot | |
| CN107832770A (en) | A kind of equipment routing inspection method, apparatus, system, storage medium and crusing robot | |
| CN111259892B (en) | Inspection method, inspection device, inspection equipment and inspection medium for state of indicator lamp | |
| CN111949809B (en) | Intelligent processing method for infrared inspection data of power transmission line | |
| CN110059694A (en) | The intelligent identification Method of lteral data under power industry complex scene | |
| CN108537154A (en) | Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning | |
| CN107103330A (en) | A kind of LED status recognition methods and device | |
| CN104438128A (en) | Method for detecting and sorting integrally-disassembled electric energy meter | |
| CN110059556A (en) | A kind of transformer substation switch division condition detection method based on deep learning | |
| CN107610128A (en) | The method for inspecting and device of a kind of oil level indicator | |
| CN109214280A (en) | Shop recognition methods, device, electronic equipment and storage medium based on streetscape | |
| CN109919925A (en) | Printed circuit board intelligent detecting method, system, electronic device and storage medium | |
| CN106454302A (en) | Method and device for detecting ripeness of fruits and vegetables | |
| CN112613339B (en) | Automatic identification and examination method and device for electrical drawing | |
| CN111709361A (en) | Unmanned aerial vehicle inspection data processing method for power transmission line | |
| CN111044149A (en) | Method and device for detecting temperature abnormal point of voltage transformer and readable storage medium | |
| CN105608703A (en) | Current transformer oil level detection method of intelligent substation inspection robot | |
| CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
| CN112687022A (en) | Intelligent building inspection method and system based on video | |
| CN108898187A (en) | A kind of method and device of automatic identification power distribution room indicating equipment image | |
| CN106803290A (en) | Transmission line makes an inspection tour recording method and device | |
| CN115578551A (en) | Household ammeter state checking method based on image recognition | |
| CN107316131A (en) | A kind of electric power meter mounting process quality detecting system based on image recognition | |
| CN111199250A (en) | Transformer substation air switch state checking method and device based on machine learning | |
| CN104391203B (en) | Electrical equipment test monitoring device and electrical equipment test monitoring method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Room 501-516, 518, 5 / F, building 4, No. 66, Dongxin Avenue, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Zhejiang Guozi Robot Technology Co., Ltd Address before: 310053 3 building, 2 six Binjiang District Road 309, Hangzhou, Zhejiang. Applicant before: ZHEJIANG GUOZI ROBOT TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20180309 Assignee: ZHEJIANG GUOZI INTELLIGENT EQUIPMENT Co.,Ltd. Assignor: Zhejiang Guozi Robot Technology Co., Ltd Contract record no.: X2021330000267 Denomination of invention: Equipment status information acquisition method, device, system, storage medium and robot Granted publication date: 20210323 License type: Exclusive License Record date: 20210907 |
|
| EE01 | Entry into force of recordation of patent licensing contract |