Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide the equipment fault alarm method and the equipment fault alarm system, which can replace manual work to judge and process information, overcome the problems of low manual monitoring efficiency and the like, solve the problem of positioning of a plurality of equipment in a machine room and improve the automatic monitoring capability of the machine room.
In a first aspect, the present invention provides an apparatus failure alarm method, including the following steps:
acquiring a picture containing equipment, wherein information patterns which can be identified are arranged on the equipment;
identifying information patterns in the picture to obtain equipment information, and detecting an indicator light in the picture to obtain indicator light information, wherein the method comprises the following steps:
-constructing a training sample set of information patterns and indicator lights, the training sample set comprising a plurality of pictures of marked information patterns and indicator light positions, the pictures being pre-collected by the robot in the tour inspection;
-training a plurality of pictures in the training sample set using a yolo algorithm, resulting in respective model parameters of a deep learning algorithm model;
-identifying an information pattern and indicator light information of a picture containing the device from the obtained deep learning algorithm model;
judging the working state of an indicator lamp on the equipment according to the information pattern and the indicator lamp information;
determining whether the device is malfunctioning based on the determination result.
Wherein the equipment information comprises equipment name information and relative position information of the equipment in the machine room.
The identifying information patterns in the picture to obtain device information, and detecting the indicator light in the picture to obtain indicator light information specifically include:
identifying an information pattern on the picture by using a deep learning algorithm model to obtain an equipment name and the equipment position information;
and detecting the indicator lights on the pictures by using a deep learning algorithm model to obtain indicator light information containing the positions of the indicator lights.
Wherein, judge the pilot lamp operating condition on the equipment according to information pattern and pilot lamp information, specifically include:
correspondingly converting coordinate position information of the equipment on the picture according to the equipment position information;
and judging the working state of the indicator light on the equipment according to the detected indicator light information and the coordinate position of the equipment on the picture.
Wherein the information pattern is disposed at an upper left position and a lower right position of the apparatus.
The correspondingly converting the coordinate information of the device on the picture according to the device position information specifically includes:
identifying information patterns based on a deep learning algorithm model;
judging whether the corresponding information pattern is positioned at the upper left position or the lower right position;
and determining the position and the coordinates of the equipment on the picture according to the corresponding position of the identified information pattern on the picture.
Wherein, the judging the working state of the indicator light on the equipment according to the detected indicator light information and the coordinate position of the equipment on the picture comprises the following steps:
according to the indicator light information detected by the deep learning algorithm model, obtaining the position information and the working state of the indicator light;
judging whether the position of the indicator light is within the position range of the equipment or not according to the position information of the indicator light and the coordinate position of the equipment on the picture;
and if the position of the indicator light is within the position range of the equipment, outputting the working state of the indicator light on the corresponding equipment.
Wherein, the information pattern is a two-dimensional code or a bar code.
In a second aspect, the present invention further provides an equipment failure alarm system, including:
the image acquisition module is used for acquiring an image containing the equipment;
the identification detection module is used for identifying the information pattern in the picture to obtain equipment information and detecting the indicator lamp in the picture to obtain indicator lamp information;
the state judgment module is used for judging the working state of the indicator lamp on the equipment according to the information pattern and the indicator lamp information;
a status output module for determining whether the device is malfunctioning based on the determination result.
Wherein the identification detection module comprises:
the construction module is used for constructing a training sample set of the information patterns and the indicating lamps, the training sample set comprises a plurality of marked information patterns and pictures of the positions of the indicating lamps, and the pictures are collected by the robot in the inspection process in advance;
the training module trains a plurality of pictures in the training sample set by adopting a yolo algorithm to obtain each model parameter of the deep learning algorithm model;
and the equipment identification module is used for identifying the information pattern and the indicator light information of the picture containing the equipment according to the obtained deep learning algorithm model.
Compared with the prior art, the method is based on the deep learning YOLO target detection algorithm, the inspection robot can be used for collecting the characteristics of the two-dimensional codes and the indicator lamps in the machine room, then the positions of the two-dimensional codes and the indicator lamps are detected, the corresponding equipment names are judged according to the two-dimensional codes, the equipment models and the indicator lamp detection results on the equipment are judged and generated on the basis, and finally the alarm signals of the equipment faults are output. Therefore, the invention can replace manual work to judge and process information, overcomes the problems of low efficiency of manual monitoring and the like, can solve the problem of positioning of a plurality of devices in the machine room, simultaneously corresponds different devices and the states of the indicator lights on the devices one by one, and improves the automatic monitoring capability of the machine room.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a plurality" typically includes at least two.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that an article or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such article or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in the article or device in which the element is included.
Alternative embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Example one
Referring to fig. 1, an embodiment of the present invention provides an apparatus fault alarm method, including the following steps:
acquiring a picture containing equipment, wherein information patterns which can be identified are arranged on the equipment;
identifying information patterns in the picture based on a deep learning algorithm model to obtain equipment information, and detecting an indicator light in the picture to obtain indicator light information;
judging the working state of an indicator lamp on the equipment according to the information pattern and the indicator lamp information;
determining whether the device is malfunctioning based on the determination result.
Wherein, pilot lamp information can include pilot lamp position, colour and quantity, and the different kinds of bright lamp quantity judgement operating condition that different equipment corresponds is counted. The indicator operating status may include whether the indicator is detected to be lit, and the color of the indicator (e.g., the color may be red, yellow, blue, green).
Example two
On the basis of the first embodiment, the present embodiment may include the following:
in the embodiment of the present invention, the information pattern arranged on the device may be an identifiable information pattern such as a two-dimensional code or a barcode. In addition, the mode of arranging the information pattern on the equipment can be selected according to the requirement, in one application scene, the information pattern is directly pasted on the equipment, and in another application scene, the information pattern is sprayed or engraved on the equipment. Further, in order to avoid the occurrence of a situation where the information pattern on the device is damaged and cannot be recognized, a plurality of information patterns may be arranged on each device, and the plurality of information patterns may be one or both of a two-dimensional code and a barcode. In addition, the device information obtained by recognizing the information pattern in the picture may include device name information and device relative position information within the room.
Referring to fig. 2, in some application scenarios, the identifying an information pattern in the picture to obtain device information, and detecting an indicator light in the picture to obtain indicator light information may include:
identifying an information pattern on the picture by using a deep learning algorithm model to obtain an equipment name and the equipment position information;
and detecting the indicator lights on the pictures by using a deep learning algorithm model to obtain indicator light information containing the positions of the indicator lights.
Further, the determining the operating state of the indicator light on the device according to the information pattern and the indicator light information according to the embodiment of the present invention may include:
correspondingly converting coordinate position information of the equipment on the picture according to the equipment position information;
and judging the working state of the indicator light on the equipment according to the detected indicator light information and the coordinate position of the equipment on the picture.
The detected indicating lamp information comprises the coordinate position of the indicating lamp on the picture, and the number and the color of the indicating lamps on the equipment can be obtained by judging whether the position of the indicating lamp is in the coordinate position of the equipment or not and the detected indicating lamp information.
In the embodiment of the present invention, the position where the information pattern is arranged on the device may be selected as needed, and in one application scenario, the information pattern is arranged at the upper left position and/or the lower right position of the device. In another application scenario, the information patterns are disposed on a plurality of corners of the photographed side of the device. The embodiment of the invention can directly determine the position and the coordinate of the equipment on the picture through the arrangement position of the information pattern when the information pattern is identified through the deep learning algorithm model. Correspondingly, the correspondingly converting the coordinate information of the device on the picture according to the device location information may include:
identifying information patterns based on a deep learning algorithm model;
judging whether the corresponding information pattern is positioned at the upper left position or the lower right position;
and determining the position and the coordinates of the equipment on the picture according to the corresponding position of the identified information pattern on the picture.
Referring to fig. 3, after the coordinate position information of the device on the picture is correspondingly calculated according to the device position information, the determining the operating state of the indicator light on the device according to the detected indicator light information and the coordinate position of the device on the picture in the embodiment of the present invention may specifically include:
according to the indicator light information detected by the deep learning algorithm model, obtaining the position information and the working state of the indicator light;
judging whether the position of the indicator light is within the position range of the equipment or not according to the position information of the indicator light and the coordinate position of the equipment on the picture;
and if the position of the indicator light is within the position range of the equipment, outputting the working state of the indicator light on the corresponding equipment.
In the embodiment of the present invention, after obtaining a picture including a device, identifying an information pattern in the picture based on a deep learning algorithm model to obtain device information, and detecting an indicator light in the picture to obtain indicator light information, which may specifically include:
constructing a training sample set of information patterns and indicator lights, wherein the sample set comprises a plurality of marked information patterns and images of the positions of the indicator lights, and the images are collected by the robot in the inspection process in advance;
training a plurality of pictures in the training sample set by adopting a yolo algorithm (deep learning algorithm) to obtain each model parameter of a deep learning algorithm model for equipment identification;
and identifying the information pattern and the indicator light information of the picture containing the equipment according to the obtained deep learning algorithm model.
The training process of the YOLO algorithm may include:
collecting a plurality of (for example 7000) pictures containing equipment information patterns and indicator lights in a machine room, and marking the information patterns and the indicator lights in the pictures in a manual mode;
establishing a folder, and putting the labeled files and pictures into the folder according to the training requirements;
downloading a pre-training weight file yolov3.weights in a YoLO official website, converting a marking file into a file in a YOLO format according to a conversion script, and dividing the file into a training set, a testing set and a verification set;
and executing the training script to start training, testing the generated deep learning algorithm model after the training is finished, and obtaining the information patterns of the equipment in the machine room and all the parameters of the deep learning algorithm model for identifying the indicator light after the identification accuracy is determined to meet the requirement.
EXAMPLE III
On the basis of the above embodiment, the present embodiment may include the following:
referring to fig. 4, an embodiment of the present invention takes an information pattern arranged on a device as a two-dimensional code for example, and provides a machine room device fault alarm method based on a two-dimensional code and deep learning, which may include the following steps:
attaching two-dimensional codes at the upper left position and the lower right position of the key equipment of the machine room and writing corresponding equipment names and relative position information of the equipment in the machine room;
when the robot patrols and examines in the machine room, pictures containing key equipment of the machine room are shot;
detecting a two-dimensional code and an indicator light on a picture by using a deep learning algorithm;
identifying the two-dimensional code information to obtain the name of the equipment and the corresponding position information of the equipment in the picture;
correspondingly converting coordinate information of the equipment on the picture according to the position information of the equipment in the picture;
judging the working state of the indicator light on the equipment according to the detected indicator light information and the coordinate position of the equipment on the picture;
and outputting whether the corresponding equipment in the machine room has a fault according to the working state of the indicator lamp.
In some application scenarios, detecting the two-dimensional code and the indicator light on the picture using the deep learning algorithm may include:
constructing a training sample set of the two-dimensional codes and the indicating lamps, wherein the sample set comprises a plurality of pictures marked with the two-dimensional codes and the indicating lamps, and the pictures are collected by the robot in the inspection process in advance;
training the multiple pictures in the training sample set by adopting a yolo algorithm to obtain each model parameter of the machine room key equipment recognition deep learning algorithm model, and then detecting the two-dimensional codes and the indicator light information of the corresponding pictures by using the obtained deep learning algorithm model.
In addition, in the embodiment of the present invention, the converting the coordinate information of the device on the picture according to the position information of the device in the picture may include:
recognizing the two-dimensional code information, and reading whether the corresponding information is the upper left position or the lower right position;
and according to the corresponding position of the two-dimensional code identified by the deep learning algorithm model on the picture, the position and the coordinates of the equipment on the picture are sketched.
The embodiment of the invention is based on the current mainstream deep learning YOLO target detection algorithm, uses an inspection robot to carry out feature acquisition on a two-dimensional code and an indicator lamp in a machine room, then detects the positions of the two-dimensional code and the indicator lamp, judges the corresponding equipment name according to the two-dimensional code, judges and generates the equipment model and the indicator lamp detection result on the equipment on the basis, and finally outputs the alarm signal of the equipment with fault.
Example four
On the basis of the above embodiment, the present embodiment may include the following:
referring to fig. 5, an embodiment of the present invention provides an apparatus failure alarm system, including:
the image acquisition module is used for acquiring an image containing the equipment;
the identification detection module is used for identifying the information pattern in the picture to obtain equipment information and detecting the indicator lamp in the picture to obtain indicator lamp information;
the state judgment module is used for judging the working state of the indicator lamp on the equipment according to the information pattern and the indicator lamp information;
a status output module for determining whether the device is malfunctioning based on the determination result.
Wherein the identification detection module may include:
the construction module is used for constructing a training sample set of the information patterns and the indicating lamps, the training sample set comprises a plurality of marked information patterns and pictures of the positions of the indicating lamps, and the pictures are collected by the robot in the inspection process in advance;
the training module trains a plurality of pictures in the training sample set by adopting a yolo algorithm to obtain each model parameter of the deep learning algorithm model;
and the equipment identification module is used for identifying the information pattern and the indicator light information of the picture containing the equipment according to the obtained deep learning algorithm model.
EXAMPLE five
On the basis of the above embodiment, the present embodiment may include the following:
the embodiment of the invention provides a machine room equipment intelligent identification and fault alarm system based on two-dimensional codes and deep learning, which comprises:
the acquisition module is used for acquiring the image characteristics of the two-dimensional code and the indicator lamp in the machine room by adopting the inspection robot according to the preset coordinate position;
the recognition module is used for recognizing equipment pictures collected by the robot by adopting a pre-trained machine room two-dimensional code and a depth learning algorithm model recognized by an indicator lamp and outputting the coordinate positions of the two-dimensional code and the indicator lamp in the pictures;
and the judging module is used for comparing the identified positions of the indicating lamps with the coordinate position of the equipment and judging the number of the working indicating lamps on the equipment.
EXAMPLE six
As shown in fig. 6, this embodiment further provides an electronic device 600, where the electronic device 600 includes: at least one processor 601; and a memory 602 communicatively coupled to the at least one processor 601; wherein the content of the first and second substances,
the memory 602 stores instructions executable by the one processor 601 to be executed by the at least one processor 601 to enable the at least one processor 601 to perform the method steps as described in the above embodiments.
EXAMPLE seven
The disclosed embodiments provide a non-volatile computer storage medium having stored thereon computer-executable instructions that may perform the method steps as described in the embodiments above.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local Area Network (AN) or a Wide Area Network (WAN), or the connection may be made to AN external computer (for example, through the internet using AN internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.
The foregoing describes preferred embodiments of the present invention, and is intended to provide a clear and concise description of the spirit and scope of the invention, and not to limit the same, but to include all modifications, substitutions, and alterations falling within the spirit and scope of the invention as defined by the appended claims.