CN107784310B - Equipment state information acquisition method, device and system, storage medium and robot - Google Patents
Equipment state information acquisition method, device and system, storage medium and robot Download PDFInfo
- Publication number
- CN107784310B CN107784310B CN201711108306.9A CN201711108306A CN107784310B CN 107784310 B CN107784310 B CN 107784310B CN 201711108306 A CN201711108306 A CN 201711108306A CN 107784310 B CN107784310 B CN 107784310B
- Authority
- CN
- China
- Prior art keywords
- equipment
- feature
- identification
- color
- feature vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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 method, a device and a system for acquiring equipment state information, a computer readable storage medium and an indoor rail-mounted intelligent inspection robot. The method comprises the steps of obtaining a target image of equipment to be identified, which is acquired by a camera of the robot; extracting identification characteristic vectors of corresponding types from a target image according to target attribute information of equipment to be identified; matching a corresponding feature recognition sub-model in a pre-established feature recognition model library according to the target attribute information; and calling the feature recognition submodel to analyze the extracted recognition feature vector to obtain the running state information of the equipment to be recognized. The technical scheme that this application provided can acquire the running state information of current equipment to in time feed back the unusual equipment of operation, the effectual manpower of having solved patrols the inefficiency and causes the problem of careless omission easily, has higher stability and accuracy.
Description
Technical Field
The embodiment of the invention relates to the technical field of machine vision, in particular to a method, a device and a system for acquiring equipment state information, a computer readable storage medium and an indoor rail-mounted intelligent inspection robot.
Background
In the production or management process, the working state of the equipment operation directly affects the global development, for example, in the production process, if the relevant production equipment is always in a shutdown state with poor performance and is to be repaired, the output of an enterprise is directly affected, the supply of products is insufficient, and poor economic benefit and social benefit are brought to the whole enterprise. Therefore, the real-time attention to the running state of the equipment is very necessary, and equipment inspection is performed according to the application.
For example, in a control room of a railway or a substation, the state of the equipment is indicated through color change or shape change, for example, the red and green of an indicator light are used for indicating that the equipment is abnormal or normal respectively, and if the equipment is abnormal, a worker is required to overhaul the equipment in time; the red and green indication of the lightning arrester is used for indicating whether the lightning arrester is struck by lightning or not, if the lightning arrester is struck by lightning, the lightning arrester is changed into red, the lightning arrester needs to be replaced in time, and otherwise the equipment can be damaged by next lightning strike. In the control room of a substation, a pressure plate device is common, which is fixed by an aspect ratio of 3: the rectangular block of 1 indicates whether it works, if the rectangular block is vertical to the horizontal plane, it indicates working, i.e. "throw", if it forms an angle of about 30 degrees with the horizontal plane (fixed gear), it indicates not working, if it is abnormal because of operation or equipment, it will not supply power normally.
The existing equipment inspection, namely acquiring the state information of the equipment, generally utilizes the sense of a person or a simple instrument and tool to regularly check the equipment at fixed points according to a standard so as to find out the abnormal position of the equipment. However, the manual inspection is not only inefficient, but also easily causes careless omission and has lower accuracy.
Therefore, how to accurately and efficiently patrol the equipment and feed back the running state of the equipment in time is a problem to be solved urgently by technical personnel in the field.
Disclosure of Invention
The embodiment of the invention aims to provide a method, a device and a system for acquiring equipment state information, a computer-readable storage medium and an indoor rail-mounted intelligent inspection robot, which can accurately and efficiently inspect equipment and timely feed back the running state of the equipment so as to take measures in time, eliminate hidden dangers as early as possible and avoid unnecessary loss.
In order to solve the above technical problems, embodiments of the present invention provide the following technical solutions:
the embodiment of the invention provides an equipment state information acquisition method, which is applied to an indoor rail-mounted intelligent inspection robot and comprises the following steps:
acquiring a target image of equipment to be identified, which is acquired by a camera;
extracting corresponding types of identification feature vectors in the target image according to the target attribute information of the equipment to be identified, wherein the types of the identification feature vectors are color feature vectors or shape feature vectors;
matching a corresponding feature recognition sub-model in a pre-established feature recognition model library according to the target attribute information;
calling the feature identifier model to analyze the identification feature vector to obtain the running state information of the equipment to be identified;
the characteristic identification model library comprises a plurality of characteristic identification submodels, each characteristic identification submodel is formed by utilizing a support vector machine and training according to a plurality of pieces of sample information of each device, and the sample information comprises attribute information of the device, a corresponding relation between a color characteristic vector and running state information of the device or a corresponding relation between a shape characteristic vector and the running state information of the device.
Optionally, the method further includes:
and judging whether the equipment to be tested operates normally or not according to the operating state information and the prestored corresponding operating state information when the equipment operates abnormally.
Optionally, the method further includes:
and when the equipment to be identified runs abnormally, giving an alarm prompt, and feeding back the position information of the equipment to be identified to the user side.
Optionally, the feature recognition submodel is an equipment type recognition submodel, the equipment type recognition submodel corresponds to the equipment types one to one, and each equipment type recognition submodel includes attribute information of the equipment, and a corresponding relationship between an equipment running state and a recognition feature vector; or
The feature recognition sub-models comprise color feature recognition models and shape feature recognition models, and the color feature recognition models and the shape feature recognition models respectively comprise a plurality of corresponding feature type recognition sub-models; each feature type identification submodel corresponds to the equipment one by one, and each feature type identification submodel comprises the corresponding relation of the attribute information of the equipment, the running state of the equipment and the identification feature vector.
Optionally, after the target image of the device to be identified, acquired by the camera, is acquired, the method further includes:
and normalizing the target image into an image with a preset size.
Optionally, the extracting, according to the target attribute information of the device to be identified, the identification feature vector of the corresponding type in the target image includes:
judging the type of the extracted identification feature vector according to the target attribute information of the equipment to be identified;
when the type of the extracted identification feature vector is judged to be a color feature vector, converting the color type of the target image into an HSV color space type, respectively calculating a color histogram of each channel, and connecting the color histograms into a one-dimensional array to serve as the color feature vector of the target image;
when the type of the extracted identification feature vector is judged to be a shape feature vector, extracting the cumulative gradient histogram of the target image as the shape feature vector of the target image.
Another aspect of the embodiments of the present invention provides an apparatus state information acquiring device, which is applied to an indoor rail-mounted intelligent inspection robot, and includes:
the image acquisition module is used for acquiring a target image of the equipment to be identified, which is acquired by the camera;
the characteristic extraction module is used for extracting corresponding types of identification characteristic vectors from the target image according to the target attribute information of the equipment to be identified, wherein the types of the identification characteristic vectors are color characteristic vectors or shape characteristic vectors;
the model matching module is used for matching a corresponding feature recognition sub-model in a pre-established feature recognition model library according to the target attribute information; the characteristic identification model library comprises a plurality of characteristic identification submodels, each characteristic identification submodel is trained by utilizing a support vector machine according to a plurality of pieces of sample information of each device, and the sample information comprises attribute information of the device, a corresponding relation between a color characteristic vector and running state information of the device or a corresponding relation between a shape characteristic vector and the running state information of the device;
and the state information acquisition module is used for calling the feature identifier model to analyze the identification feature vector to obtain the running state information of the equipment to be identified.
The embodiment of the present invention further provides an apparatus status information acquiring system, which includes a processor and a memory, where the processor is configured to implement the steps of the apparatus status information acquiring method according to any one of the foregoing embodiments when executing the computer program stored in the memory.
An embodiment of the present invention further provides a computer-readable storage medium, where an apparatus status information obtaining program is stored on the computer-readable storage medium, and when the apparatus status information obtaining program is executed by a processor, the method for obtaining apparatus status information according to any of the foregoing embodiments is implemented.
The embodiment of the invention finally provides an indoor rail hanging intelligent inspection robot which comprises image acquisition equipment and the computer readable storage medium.
The embodiment of the invention provides an equipment state information acquisition method, which is applied to an indoor rail-mounted intelligent inspection robot and is used for acquiring a target image of equipment to be identified, which is acquired by a camera of the robot; extracting identification characteristic vectors of corresponding types from a target image according to target attribute information of equipment to be identified; matching a corresponding feature recognition sub-model in a pre-established feature recognition model library according to the target attribute information; the characteristic recognition model library comprises a plurality of characteristic recognition submodels, each characteristic recognition submodel is trained by utilizing a support vector machine according to a plurality of pieces of sample information of each device, and the sample information comprises attribute information of the device, a corresponding relation between a color characteristic vector and running state information of the device or a corresponding relation between a shape characteristic vector and the running state information of the device; and calling a feature identifier model to analyze and identify the feature vector to obtain the running state information of the equipment to be identified.
The utility model provides a technical scheme's advantage lies in, utilize and hang rail intelligence and patrol and examine the robot at indoor autonomous operation, gather the image through the camera of self, the model that utilizes to establish discerns the discernment eigenvector of the equipment of extraction, thereby it is quick, the accurate running state information who obtains current equipment, thereby the unusual equipment of timely feedback operation, the effectual manpower of having solved patrols and examines inefficiency and cause the problem of careless omission easily, higher stability has, accuracy and efficiency, can effectively take precautions against the hidden danger, master the initial stage information of equipment trouble, so that in time take measures, eliminate hidden danger as early as possible, avoid unnecessary loss.
In addition, the embodiment of the invention also provides a corresponding implementation device, equipment, a computer readable storage medium and an indoor rail-mounted intelligent inspection robot aiming at the equipment state information acquisition method, so that the method has higher practicability, and the device, the equipment and the computer readable storage medium have corresponding advantages.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for acquiring device status information according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of another method for acquiring device status information according to an embodiment of the present invention;
fig. 3 is a structural diagram of an embodiment of an apparatus for acquiring device status information according to an embodiment of the present invention;
fig. 4 is a structural diagram of another specific embodiment of an apparatus for acquiring device status information according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. 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.
The terms "first," "second," "third," "fourth," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may include other steps or elements not expressly listed.
Having described the technical solutions of the embodiments of the present invention, various non-limiting embodiments of the present application are described in detail below.
Referring to fig. 1, fig. 1 is a schematic flow chart of an apparatus state information obtaining method provided by an embodiment of the present invention, and the method is applied to an indoor rail-mounted intelligent inspection robot, and the embodiment of the present invention may include the following contents:
s101: and acquiring a target image of the equipment to be identified, which is acquired by the camera.
The indoor rail hanging intelligent inspection robot carries image acquisition equipment, such as a camera, can autonomously operate indoors by using a rail hanging technology, pauses at preset equipment, acquires images of current equipment by using the camera, and acquires running state information of the equipment by extracting specific characteristics of the images.
S102: and extracting the corresponding type of identification feature vector from the target image according to the target attribute information of the equipment to be identified, wherein the type of the identification feature vector is a color feature vector or a shape feature vector.
The attribute information of the equipment can include the name of the equipment, the position information of the equipment and the representation characteristics of the running state of the equipment, namely the type of the identification characteristic vector to be extracted, for example, the color of an indicator light is used for representing that the equipment is abnormal or normal, if the equipment is abnormal, the equipment is a red light, and the equipment needs to be overhauled by workers in time; the red and green of the lightning arrester are used for indicating whether the lightning arrester is struck by lightning or not, if the lightning arrester is struck by lightning, the lightning arrester is changed into red, and the lightning arrester needs to be replaced in time; platen apparatus, with aspect ratio 3: the rectangular block of 1 indicates whether the rectangular block works or not, if the rectangular block is vertical to the horizontal plane, the rectangular block works, namely, throw, and if the rectangular block forms an angle of about 30 degrees with the horizontal plane (fixed gear), namely, retreat, the rectangular block does not work. The former two devices represent the operating state of the device by color, and the platen device can represent the operating state in shape.
The specific feature extraction process may be:
judging the type of the extracted identification characteristic vector according to the target attribute information of the equipment to be identified;
when the type of the extracted identification feature vector is judged to be a color feature vector, converting the color type of the target image into an HSV color space type, respectively calculating a color histogram of each channel, and connecting the color histograms into a one-dimensional array to serve as the color feature vector of the target image;
when it is determined that the type of the extracted recognition feature vector is a shape feature vector, a cumulative gradient histogram of the target image is extracted as the shape feature vector of the target image.
For the color feature vector, information such as hue, saturation, and brightness needs to be separated. Specifically, the RGB color space of the current target image may be converted into HSV color space, H represents hue, S represents saturation, and V represents brightness. And respectively calculating color histograms of the target image in an H channel, an S channel and a V channel, and then connecting the color histograms into a one-dimensional array.
S103: and matching the corresponding feature recognition submodels in a pre-established feature recognition model library according to the target attribute information.
The feature recognition model library comprises a plurality of feature recognition submodels, each feature recognition submodel is trained by a support vector machine according to a plurality of pieces of sample information of each device, and the sample information comprises attribute information of the device, a corresponding relation between a color feature vector and running state information of the device or a corresponding relation between a shape feature vector and the running state information of the device.
Each feature identifier sub-model is trained by using a support vector machine according to a plurality of pieces of sample information of each device, and the specific process can be as follows:
acquiring a plurality of device images as training sample images, wherein the plurality of sample images comprise device images of the device in each running state, and each sample image comprises attribute information of the device, a corresponding relation between a color feature vector and running state information of the device or a corresponding relation between a shape feature vector and the running state information of the device. Different devices correspond to different types of feature vectors to be extracted, and when the device extracts color feature vectors, the color feature vectors comprise the corresponding relation between the color feature vectors and the running state information of the device; when the color feature vector is extracted by the equipment, the corresponding relation between the shape feature vector and the running state information of the equipment is included; when the color feature vector and the shape feature vector are extracted by the equipment, the corresponding relation between the color feature vector and the running state information of the equipment and the corresponding relation between the shape feature vector and the running state information of the equipment are included.
For example, for lightning arrester equipment, the collected sample images are images of multiple lightning arresters in a red state and images of multiple lightning arresters in a green state, and the attribute information of the equipment included in each training sample image is the name and position information of the lightning arrester; extracting a color characteristic vector from an image of the lightning arrester in a red state and enabling the lightning arrester corresponding to the vector to be in a lightning stroke state; the color characteristic vector is extracted from the image of the lightning arrester in the green state, and the running state of the lightning arrester corresponding to the vector is normal.
And respectively extracting corresponding recognition characteristic vectors of the acquired training sample images, and training by using a support vector machine based on a radial basis function according to the sample information and the extracted recognition characteristic vectors.
According to the different training processes of training, the following two cases can be divided:
the characteristic identification submodel is an equipment type identification submodel, the equipment type identification submodel corresponds to the equipment types one by one, and each equipment type identification submodel comprises the corresponding relation of the attribute information of the equipment, the running state of the equipment and the identification characteristic vector; or
The characteristic identification submodels comprise a color characteristic identification model and a shape characteristic identification model, and the color characteristic identification model and the shape characteristic identification model respectively comprise a plurality of corresponding characteristic type identification submodels; each feature type identification submodel corresponds to the equipment one by one, and each feature type identification submodel comprises the corresponding relation of the attribute information of the equipment, the running state of the equipment and the identification feature vector.
The first case may be trained for each device, and the second case is trained for the type of the extracted recognition feature vector, which does not affect the implementation of the present application, and the present application is not limited in this respect.
S104: and calling a feature identifier model to analyze and identify the feature vector to obtain the running state information of the equipment to be identified.
And inputting the extracted identification feature vector into the matched feature identification submodel, and outputting the running state information of the current equipment.
And judging whether the equipment to be treated normally operates according to the operation state information and the prestored corresponding operation state information when the equipment operates abnormally.
For example, the red state of the arrester is stored in advance to indicate that a lightning stroke has been made, and the green state indicates normal. And acquiring an image of the current lightning arrester, extracting a color feature vector, inputting the color feature vector into a corresponding feature recognition sub-model, and if the output indicator light of the lightning arrester is red, confirming that the current lightning arrester is struck by lightning.
It should be noted that, for the accuracy of the whole device status information obtaining process, the collected images and the device sample images during model training can be normalized to the same size, for example, 1330 × 1040 in width and 1040 in resolution.
According to the technical scheme provided by the embodiment of the invention, the intelligent rail-mounted inspection robot autonomously runs indoors, images are acquired through the camera of the intelligent rail-mounted inspection robot, the extracted identification characteristic vector of the equipment is identified by using the constructed model, so that the running state information of the current equipment is quickly and accurately acquired, the equipment with abnormal running is fed back in time, the problems of low manpower inspection efficiency and easiness in causing careless omission are effectively solved, the intelligent rail-mounted inspection robot has higher stability, accuracy and efficiency, the hidden trouble can be effectively prevented, the initial information of equipment faults is mastered, measures are taken in time, the hidden trouble is eliminated as soon as possible, and unnecessary loss is avoided.
In order to enable the staff or the user to find the device with abnormal operation as soon as possible, according to the above embodiment, please refer to fig. 2, which may further include:
s105: and when the equipment to be identified runs abnormally, alarming and prompting are carried out, and the position information of the equipment to be identified is fed back to the user side.
Through carrying out the suggestion of reporting to the police, or directly feed back the equipment position information that breaks down to upper application system or user, can in time discover the equipment of abnormal operation, the initial information of the very first time grasp equipment trouble to in time take measures, eliminate hidden danger as early as possible, avoid unnecessary loss.
The embodiment of the invention also provides a corresponding implementation device for the equipment state information acquisition method, so that the method has higher practicability. In the following, the device status information acquiring apparatus provided by the embodiment of the present invention is introduced, and the device status information acquiring apparatus described below and the device status information acquiring method described above may be referred to in correspondence with each other.
Referring to fig. 3, fig. 3 is a structural diagram of an apparatus state information obtaining device according to an embodiment of the present invention, in a specific implementation manner, and the apparatus is applied to an indoor rail-mounted intelligent inspection robot, and the apparatus may include:
an image obtaining module 301, configured to obtain a target image of the device to be identified, where the target image is acquired by a camera.
The feature extraction module 302 is configured to extract, according to the target attribute information of the device to be identified, an identification feature vector of a corresponding type from the target image, where the type of the identification feature vector is a color feature vector or a shape feature vector.
The model matching module 303 is configured to match a corresponding feature recognition submodel in a pre-established feature recognition model library according to the target attribute information; the feature recognition model library comprises a plurality of feature recognition submodels, each feature recognition submodel is trained by a support vector machine according to a plurality of pieces of collected sample information of each device, and the sample information comprises attribute information of the device, a corresponding relation between a color feature vector and running state information of the device or a corresponding relation between a shape feature vector and the running state information of the device.
And the state information acquisition module 304 is configured to invoke the feature identifier sub-model to analyze and identify the feature vector, so as to obtain the running state information of the device to be identified.
Optionally, in some embodiments of this embodiment, referring to fig. 4, the apparatus may include:
the determining module 305 is configured to determine whether the device to be tested operates normally according to the operating state information and the pre-stored operating state information corresponding to the abnormal operation of the device.
In other embodiments of this embodiment, the apparatus may further include:
and the alarm module 306 is used for giving an alarm prompt when judging that the equipment at the point to be patrolled operates abnormally, and feeding back the corresponding point position information to be patrolled to the user side.
Further, the apparatus may further include, for example:
a normalization module 307, configured to normalize the target image to an image with a preset size.
Optionally, in some specific embodiments, the feature extraction module 302 may include:
the judging unit is used for judging the type of the extracted identification feature vector according to the target attribute information of the equipment to be identified;
the first feature extraction unit is used for converting the color type of the target image into an HSV color space type when the type of the extracted identification feature vector is judged to be the color feature vector, respectively calculating a color histogram of each channel, and connecting the color histograms into a one-dimensional array to serve as the color feature vector of the target image;
and a second feature extraction unit configured to extract the cumulative gradient histogram of the target image as the shape feature vector of the target image when it is determined that the type of the extracted recognition feature vector is the shape feature vector.
The functions of each functional module of the device state information acquiring apparatus according to the embodiment of the present invention may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the related description of the foregoing method embodiment, which is not described herein again.
Therefore, the embodiment of the invention utilizes the hanging rail intelligent inspection robot to autonomously operate indoors, acquires images through the camera of the robot, and identifies the extracted identification characteristic vector of the equipment by utilizing the constructed model, so that the current running state information of the equipment is quickly and accurately acquired, the abnormal running equipment is fed back in time, the problems of low manpower inspection efficiency and easiness in causing careless leakage are effectively solved, the stability, the accuracy and the efficiency are higher, the hidden trouble can be effectively prevented, the initial information of equipment failure is mastered, measures are taken in time, the hidden trouble is eliminated as soon as possible, and unnecessary loss is avoided.
An embodiment of the present invention further provides a system for acquiring device status information, which may include:
a memory for storing a computer program;
a processor for executing a computer program to implement the steps of the device status information acquisition method according to any one of the above embodiments.
The functions of each functional module of the device state information acquisition system according to the embodiment of the present invention may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the related description of the foregoing method embodiment, which is not described herein again.
Therefore, the method and the device for acquiring the operation state information of the current equipment quickly and accurately acquire the operation state information of the current equipment, so that the equipment with abnormal operation is fed back in time, the problems that the manpower inspection efficiency is low and careless omission is easily caused are effectively solved, the method and the device have higher stability, accuracy and efficiency, the hidden trouble can be effectively prevented, the initial information of the equipment fault is mastered, measures can be taken in time, the hidden trouble is eliminated as soon as possible, and unnecessary loss is avoided.
An embodiment of the present invention further provides a computer-readable storage medium, in which an apparatus status information acquisition program is stored, and the apparatus status information acquisition program is executed by a processor, and the steps of the apparatus status information acquisition method according to any one of the above embodiments are performed.
The functions of the functional modules of the computer-readable storage medium according to the embodiment of the present invention may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the related description of the foregoing method embodiment, which is not described herein again.
Therefore, the method and the device for acquiring the operation state information of the current equipment quickly and accurately acquire the operation state information of the current equipment, so that the equipment with abnormal operation is fed back in time, the problems that the manpower inspection efficiency is low and careless omission is easily caused are effectively solved, the method and the device have higher stability, accuracy and efficiency, the hidden trouble can be effectively prevented, the initial information of the equipment fault is mastered, measures can be taken in time, the hidden trouble is eliminated as soon as possible, and unnecessary loss is avoided.
The embodiment of the invention also provides an indoor rail hanging intelligent inspection robot which comprises image acquisition equipment and the computer readable storage medium according to any one of the embodiments.
The functions of the functional modules of the indoor rail-mounted intelligent inspection robot in the embodiment of the invention can be specifically realized according to the method in the embodiment of the method, and the specific realization process can refer to the related description of the embodiment of the method, which is not described herein again.
Therefore, the method and the device for acquiring the operation state information of the current equipment quickly and accurately acquire the operation state information of the current equipment, so that the equipment with abnormal operation is fed back in time, the problems that the manpower inspection efficiency is low and careless omission is easily caused are effectively solved, the method and the device have higher stability, accuracy and efficiency, the hidden trouble can be effectively prevented, the initial information of the equipment fault is mastered, measures can be taken in time, the hidden trouble is eliminated as soon as possible, and unnecessary loss is avoided.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The method, the device, the system, the computer readable storage medium and the indoor rail-mounted intelligent inspection robot for acquiring the equipment state information provided by the invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (9)
1. The equipment state information acquisition method is applied to an indoor rail-mounted intelligent inspection robot and comprises the following steps:
acquiring a target image of equipment to be identified, which is acquired by a camera;
extracting corresponding types of identification feature vectors in the target image according to the target attribute information of the equipment to be identified; the target attribute information comprises the name, the position information and the representation characteristics of the running state of the equipment to be identified, and the type of the identification characteristic vector is a color characteristic vector or a shape characteristic vector;
matching a corresponding feature recognition sub-model in a pre-established feature recognition model library according to the target attribute information; the characteristic identification model library comprises a plurality of characteristic identification submodels, each characteristic identification submodel is trained by utilizing a support vector machine according to a plurality of pieces of sample information of each device, and the sample information comprises attribute information of the device, a corresponding relation between a color characteristic vector and running state information of the device or a corresponding relation between a shape characteristic vector and the running state information of the device;
calling the feature identifier model to analyze the identification feature vector to obtain the running state information of the equipment to be identified;
wherein, the extracting the corresponding type of the identification feature vector in the target image according to the target attribute information of the device to be identified comprises:
judging the type of the extracted identification feature vector according to the target attribute information of the equipment to be identified;
when the type of the extracted identification feature vector is judged to be a color feature vector, converting the color type of the target image into an HSV color space type, respectively calculating a color histogram of each channel, and connecting the color histograms into a one-dimensional array to serve as the color feature vector of the target image;
when the type of the extracted identification feature vector is judged to be a shape feature vector, extracting the cumulative gradient histogram of the target image as the shape feature vector of the target image.
2. The device status information acquisition method according to claim 1, further comprising:
and judging whether the equipment to be identified runs normally or not according to the running state information and the prestored corresponding running state information when the equipment runs abnormally.
3. The device status information acquisition method according to claim 2, further comprising:
and when the equipment to be identified runs abnormally, giving an alarm prompt, and feeding back the position information of the equipment to be identified to the user side.
4. The device state information acquisition method according to claim 1, wherein the feature recognition submodel is a device type recognition submodel, the device type recognition submodel corresponds to the device types one to one, and each device type recognition submodel includes correspondence between attribute information of the device, a device operating state, and a recognition feature vector; or
The feature recognition sub-models comprise color feature recognition models and shape feature recognition models, and the color feature recognition models and the shape feature recognition models respectively comprise a plurality of corresponding feature type recognition sub-models; each feature type identification submodel corresponds to the equipment one by one, and each feature type identification submodel comprises the corresponding relation of the attribute information of the equipment, the running state of the equipment and the identification feature vector.
5. The device status information acquiring method according to claim 1, further comprising, after acquiring the target image of the device to be recognized acquired by the camera:
and normalizing the target image into an image with a preset size.
6. The utility model provides an equipment status information acquisition device which characterized in that is applied to indoor string rail intelligence and patrols and examines robot, includes:
the image acquisition module is used for acquiring a target image of the equipment to be identified, which is acquired by the camera;
the characteristic extraction module is used for extracting corresponding types of identification characteristic vectors from the target image according to the target attribute information of the equipment to be identified, wherein the types of the identification characteristic vectors are color characteristic vectors or shape characteristic vectors;
the model matching module is used for matching a corresponding feature recognition sub-model in a pre-established feature recognition model library according to the target attribute information; the characteristic identification model library comprises a plurality of characteristic identification submodels, each characteristic identification submodel is trained by utilizing a support vector machine according to a plurality of pieces of sample information of each device, and the sample information comprises attribute information of the device, a corresponding relation between a color characteristic vector and running state information of the device or a corresponding relation between a shape characteristic vector and the running state information of the device;
the state information acquisition module is used for calling the feature identifier model to analyze the identification feature vector to obtain the running state information of the equipment to be identified;
wherein the feature extraction module comprises:
the judging unit is used for judging the type of the extracted identification feature vector according to the target attribute information of the equipment to be identified;
the first feature extraction unit is used for converting the color type of the target image into an HSV color space type when the type of the extracted identification feature vector is judged to be the color feature vector, respectively calculating a color histogram of each channel, and connecting the color histograms into a one-dimensional array to serve as the color feature vector of the target image;
and a second feature extraction unit configured to extract, when it is determined that the type of the extracted recognition feature vector is a shape feature vector, an accumulated gradient histogram of the target image as the shape feature vector of the target image.
7. A device state information acquisition system comprising a processor and a memory, the processor being configured to implement the steps of the device state information acquisition method according to any one of claims 1 to 5 when executing a computer program stored in the memory.
8. A computer-readable storage medium, characterized in that a device-state-information acquisition program is stored thereon, which when executed by a processor, implements the steps of the device-state-information acquisition method according to any one of claims 1 to 5.
9. An indoor rail-mounted intelligent inspection robot, characterized by comprising an image acquisition device and the computer-readable storage medium of claim 8.
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 CN107784310A (en) | 2018-03-09 |
| CN107784310B true 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) |
Families Citing this family (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108347554B (en) * | 2018-03-20 | 2024-06-14 | 浙江国自机器人技术有限公司 | 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 |
| CN108890652B (en) * | 2018-06-28 | 2021-02-09 | 全球能源互联网研究院有限公司 | Transformer substation inspection robot and transformer substation equipment inspection method |
| 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 | Methods, devices, systems, storage media, processors and terminals 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 |
| 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 |
| 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 |
| CN109783671B (en) | 2019-01-30 | 2021-10-08 | 京东方科技集团股份有限公司 | A method, computer readable medium and server for searching images by image |
| 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 | An identification device, device and system for key equipment and components of a power grid |
| 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 | Status recognition method of protection platen based on AI technology |
| CN111082530A (en) * | 2020-01-03 | 2020-04-28 | 国家电网有限公司 | An abnormal alarm method for lightning protection line equipment based on the Internet of Things |
| CN112257740B (en) * | 2020-09-05 | 2022-09-09 | 赛飞特工程技术集团有限公司 | Knowledge graph-based image hidden danger identification method and system |
| 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 |
| CN113743454B (en) * | 2021-07-22 | 2024-08-20 | 南方电网数字平台科技(广东)有限公司 | Detection method, device, equipment and storage medium of oil-immersed transformer |
| 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 |
| CN116661400B (en) * | 2023-07-14 | 2024-12-06 | 广船国际有限公司 | Control method, device, equipment and medium of target device based on machine vision |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9665843B2 (en) * | 2013-06-03 | 2017-05-30 | Abb Schweiz Ag | 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 |
| CN104318198B (en) * | 2014-02-28 | 2018-03-27 | 郑州金惠计算机系统工程有限公司 | Recognition methods and device suitable for transformer substation robot inspection |
| 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
Also Published As
| Publication number | Publication date |
|---|---|
| CN107784310A (en) | 2018-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784310B (en) | Equipment state information acquisition method, device and system, storage medium and robot | |
| CN107832770B (en) | Equipment inspection method, device and system, storage medium and inspection robot | |
| CN111259892B (en) | Inspection method, inspection device, inspection equipment and inspection medium for state of indicator lamp | |
| CN118449277A (en) | High-low voltage power distribution cabinet abnormal fault information remote monitoring system | |
| CN111401314A (en) | Dressing information detection method, device, equipment and storage medium | |
| CN104280668B (en) | Distribution network failure kind identification method and system | |
| CN111507147A (en) | Intelligent inspection method and device, computer equipment and storage medium | |
| CN112464995A (en) | Power grid distribution transformer fault diagnosis method and system based on decision tree algorithm | |
| US7872584B2 (en) | Analyzing smoke or other emissions with pattern recognition | |
| CN112613454A (en) | Electric power infrastructure construction site violation identification method and system | |
| CN112100039B (en) | Equipment fault alarm method and system | |
| US10460268B2 (en) | System and method for generating device work orders based on work patterns and plant location | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN111127445A (en) | Distribution network line high-temperature area detection method and system based on deep learning | |
| CN104156819A (en) | Method and device used for automatically observing and correcting unsafe behaviors at important posts | |
| CN112147438A (en) | A high-voltage inverter fault pre-diagnosis system | |
| CN115296193A (en) | Intelligent inspection system and method for transformer substation | |
| CN118172693A (en) | Method for intelligently identifying illegal filling of liquefied gas cylinder through video | |
| CN115965625A (en) | Instrument detection device based on visual identification and detection method thereof | |
| CN116863196A (en) | Distance measurement and alarm method and system for electric power operation training and production safety supervision | |
| CN107657682A (en) | A kind of power transformation method for inspecting based on augmented reality | |
| CN114663820A (en) | Power distribution station room storage battery abnormity identification method | |
| CN114387636A (en) | Industrial safety operation standard system based on action recognition | |
| CN106600168A (en) | Power grid responsibility area information verification method, device and system | |
| CN113591909B (en) | Abnormality detection method, abnormality detection device and storage medium of power system |
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 |