CN111935458A - Control method, device and system of belt conveyor - Google Patents
Control method, device and system of belt conveyor Download PDFInfo
- Publication number
- CN111935458A CN111935458A CN202010837514.8A CN202010837514A CN111935458A CN 111935458 A CN111935458 A CN 111935458A CN 202010837514 A CN202010837514 A CN 202010837514A CN 111935458 A CN111935458 A CN 111935458A
- Authority
- CN
- China
- Prior art keywords
- belt conveyor
- current
- deviation
- monitoring result
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Control Of Conveyors (AREA)
Abstract
The application provides a control method, a device and a system of a belt conveyor, wherein the method comprises the steps of acquiring a current operation picture of the belt conveyor, which is obtained by real-time shooting of camera equipment when the belt conveyor operates; analyzing the current operation picture of the belt conveyor by using a pre-trained state detection model to obtain a current state monitoring result of the belt conveyor; the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state, a load degree and a belt conveyor running position; and controlling the belt conveyor to operate according to the current state monitoring result of the belt conveyor. The running picture that this scheme was gathered through analysis camera equipment realizes the control and corresponding control to the state of belt feeder, compares in the sensor of installing at the belt feeder, and camera equipment more can resist adverse circumstances's interference, is difficult for breaking down with the sensor contrast, and consequently, this scheme has higher reliability for prior art.
Description
Technical Field
The invention relates to the technical field of automation, in particular to a control method, a device and a system of a belt conveyor.
Background
The belt feeder is all by a transportation equipment of wide use in various production environment, when using the belt feeder, only need to place the material that will wait to transport on the belt, just can transport the material to the other end from the one end of belt feeder through the removal of belt.
The belt feeder is in the operation process, multiple abnormal state probably appears, for example, the belt off tracking (the belt is skew the track of belt feeder promptly), the belt skids, and the material is too little or too much, and motor trouble leads to the belt to stop moving etc. in order to discover in time and maintain when the abnormal state appears in the belt feeder, it is necessary to monitor the operation of belt feeder and carry out corresponding control according to the control result.
The existing control method of the belt conveyor generally installs various sensors, such as a speed sensor, a current sensor and the like, on the belt conveyor, analyzes whether the belt conveyor is in an abnormal state according to various running parameters of the belt conveyor measured by the sensors in real time, and controls the belt conveyor to stop once the abnormal state is detected.
The problem of prior art lies in, in the more abominable production environment, for example the dust is more, in the great production environment of air humidity, the multiple sensor of direct mount on the belt feeder appears the detection accuracy low easily, even direct fault shutdown scheduling problem, leads to the reliability of system lower.
Disclosure of Invention
Based on the problems in the prior art, the invention provides a method, a device and a system for controlling a belt conveyor, so as to provide a belt conveyor control scheme with higher reliability.
The invention provides a control method of a belt conveyor, which comprises the following steps:
when the belt conveyor runs, acquiring a current running picture of the belt conveyor, which is obtained by real-time shooting of camera equipment;
analyzing the current operation picture of the belt conveyor by using a pre-trained state detection model to obtain the current state monitoring result of the belt conveyor; the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state, a load degree and a belt conveyor running position;
and controlling the belt conveyor to operate according to the current state monitoring result of the belt conveyor.
Optionally, when the belt conveyor runs, acquiring a current running picture of the belt conveyor, which is obtained by real-time shooting by the camera device, includes:
and extracting a frame of image closest to the current moment from the running video of the belt conveyor shot by the camera equipment in real time to be used as the current running picture of the belt conveyor.
Optionally, the controlling the operation of the belt conveyor according to the current state monitoring result of the belt conveyor includes:
generating a corresponding state word according to the current state monitoring result of the belt conveyor;
and controlling the belt conveyor to operate according to the state words.
Optionally, the state detection model includes a deviation detection model, and the state monitoring result includes a deviation degree of the belt conveyor;
wherein, the controlling the operation of the belt conveyor according to the current state monitoring result of the belt conveyor comprises:
if the deviation degree of the belt conveyor is not deviation, controlling the belt conveyor to continuously operate at the current power;
if the deviation degree of the belt conveyor is slight deviation or moderate deviation, controlling the belt conveyor to continuously operate at a first power, and outputting belt conveyor deviation prompt information; wherein the first power is lower than the current power of the belt conveyor;
and if the deviation degree of the belt conveyor is severe deviation, controlling the belt conveyor to stop running.
Optionally, the state detection model includes a load detection model, and the state monitoring result includes a load degree of the belt conveyor;
wherein, the controlling the operation of the belt conveyor according to the current state monitoring result of the belt conveyor comprises:
if the load degree of the belt conveyor is that the material quantity is normal, controlling the belt conveyor to continuously operate at the current power;
if the load degree of the belt conveyor is that the material quantity is too large, controlling the belt conveyor to continuously operate at a second power; wherein the second power is higher than the current power of the belt conveyor;
if the load degree of the belt conveyor is that the material quantity is too small, controlling the belt conveyor to continuously operate at a third power; and the third power is lower than the current power of the belt conveyor.
The present application provides in a second aspect a control device for a belt conveyor, including:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring a current operation picture of the belt conveyor, which is obtained by real-time shooting of camera equipment when the belt conveyor operates;
the analysis unit is used for analyzing the current running picture of the belt conveyor by utilizing a pre-trained state detection model to obtain the current state monitoring result of the belt conveyor; the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state, a load degree and a belt conveyor running position;
and the control unit is used for controlling the operation of the belt conveyor according to the current state monitoring result of the belt conveyor.
Optionally, when the belt conveyor runs, the acquiring unit acquires a current running picture of the belt conveyor, which is obtained by real-time shooting by the camera device, and is specifically configured to:
and extracting a frame of image closest to the current moment from the running video of the belt conveyor shot by the camera equipment in real time to be used as the current running picture of the belt conveyor.
Optionally, the control unit includes:
the generating unit is used for generating a corresponding state word according to the current state monitoring result of the belt conveyor;
and the sub-control unit is used for controlling the belt conveyor to operate according to the state words.
Optionally, the state detection model includes a deviation detection model, and the state monitoring result includes a deviation degree of the belt conveyor;
the control unit is used for controlling the operation of the belt conveyor according to the current state monitoring result of the belt conveyor, and is specifically used for:
if the deviation degree of the belt conveyor is not deviation, controlling the belt conveyor to continuously operate at the current power;
if the deviation degree of the belt conveyor is slight deviation or moderate deviation, controlling the belt conveyor to continuously operate at a first power, and outputting belt conveyor deviation prompt information; wherein the first power is lower than the current power of the belt conveyor;
and if the deviation degree of the belt conveyor is severe deviation, controlling the belt conveyor to stop running.
A third aspect of the present application provides a control system of a belt conveyor, including:
the system comprises a camera device, a video identification server and a belt conveyor controller;
the camera device is used for shooting in real time to obtain a current operation picture of the belt conveyor when the belt conveyor operates;
the video recognition server is configured to:
acquiring a current running picture of the belt conveyor, which is obtained by real-time shooting of the camera equipment;
analyzing the current operation picture of the belt conveyor by using a pre-trained state detection model to obtain the current state monitoring result of the belt conveyor; the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state, a load degree and a belt conveyor running position;
the belt feeder controller is used for:
and controlling the belt conveyor to operate according to the current state monitoring result of the belt conveyor.
The application provides a control method, a device and a system of a belt conveyor, wherein the method comprises the steps of acquiring a current operation picture of the belt conveyor, which is obtained by real-time shooting of camera equipment when the belt conveyor operates; analyzing the current operation picture of the belt conveyor by using a pre-trained state detection model to obtain a current state monitoring result of the belt conveyor; the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state and a load degree; and controlling the belt conveyor to operate according to the current state monitoring result of the belt conveyor. The running picture that this scheme was gathered through analysis camera equipment realizes the control and corresponding control to the state of belt feeder, compares in the sensor of installing at the belt feeder, and camera equipment more can resist adverse circumstances's interference, is difficult for breaking down with the sensor contrast, and consequently, this scheme has higher reliability for prior art.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a control system of a belt conveyor according to an embodiment of the present disclosure;
fig. 2 is a schematic diagram of an apparatus connection relationship of a control system of a belt conveyor according to an embodiment of the present disclosure;
fig. 3 is a flowchart of a control method of a belt conveyor according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a control device of a belt conveyor according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to facilitate understanding of a control method of a belt conveyor provided in an embodiment of the present application, an architecture of a control system of a belt conveyor provided in an embodiment of the present application is first described with reference to fig. 1.
As shown in fig. 1, a control system of a belt conveyor provided in an embodiment of the present application may include:
the camera device 101, the video identification server (i.e. Vxidentify)102 and the belt conveyor controller 103 can communicate with each other through a network.
The camera device is used for shooting in real time to obtain a current running picture of the belt conveyor when the belt conveyor runs.
It should be noted that the control system provided in the embodiment of the present application may be configured to monitor and control a plurality of belt conveyors simultaneously, and when a plurality of running belt conveyors need to be monitored, the image capturing apparatus includes a plurality of cameras in a corresponding number, each camera corresponds to one running belt conveyor, and is configured to collect an operation picture of the belt conveyor.
Specifically, for each belt conveyor, the camera corresponding to the belt conveyor can start to work after the switch of the belt conveyor is turned on, the running video of the belt conveyor is shot in real time during the running period of the belt conveyor, the running video is uploaded to the video identification server 102 through the network, after the video identification server 102 obtains the running video, one frame of image closest to the current moment is extracted from the running video, and the extracted frame of image is equivalent to the current running picture of the belt conveyor.
And the video identification server 102 is configured to obtain an operation picture of the belt machine, which is obtained by shooting by the camera device 101, and analyze the current operation picture of the belt machine by using a pre-trained state detection model to obtain a current state monitoring result of the belt machine.
As described above, the camera device may include a plurality of cameras, and may correspondingly upload current operation pictures of a plurality of belt conveyors to the video recognition server at the same time, and the video recognition server may analyze the current operation pictures of each belt conveyor one by using the state detection model to obtain a state monitoring result of each belt conveyor.
The state detection model configured by the video recognition server can be understood as a combination of one or more pre-trained neural network models, wherein each neural network model is used for analyzing a certain state monitoring result of the belt conveyor displayed in the picture according to the running picture of the belt conveyor input with the model.
The state monitoring results of the belt conveyor include, but are not limited to, the following five types: the running deviation degree, the state of skidding, open and stop state, load degree and belt feeder running position.
And aiming at each state monitoring result, a neural network model which is specially used for analyzing and obtaining the corresponding state monitoring result from the running picture of the belt conveyor can be trained. That is to say, a deviation detection model for analyzing the deviation degree of the belt conveyor, a slip detection model for analyzing the slip state of the belt conveyor, a start-stop detection model for analyzing the start-stop state of the belt conveyor, a load detection model for analyzing the load degree of the belt conveyor, and a position detection model for detecting whether people approach near the running position of the belt conveyor can be obtained through training respectively.
The deviation refers to the phenomenon that a belt deviates from a mechanical track installed on the belt conveyor in the running process of the belt conveyor, and the deviation degree of the belt deviates from the track after deviation occurs according to whether deviation occurs or not, wherein the deviation degree specifically comprises four labels which are respectively non-deviation, slight deviation, moderate deviation and severe deviation.
The slipping is a phenomenon that a belt slides relative to a belt pulley of the belt conveyor (the belt pulley drives the belt to move through rotation) when the belt conveyor runs. The slip condition may include no slip, two tags slip.
And the start-stop state is used for indicating whether the belt conveyor is suddenly stopped to run due to sudden mechanical or electrical faults after the belt conveyor starts to run, and the start-stop state can comprise two labels of normal running and operation stopping.
The load is used for reflecting the amount of the materials carried by the belt conveyor in the operation picture, specifically, three continuous intervals can be set according to the quantity or quality of the materials to be conveyed, and correspondingly, the load degree can comprise the following four labels, and no load is used for indicating that the belt conveyor does not convey the materials at all currently; the material quantity is too small and is used for indicating that the quantity (or quality) of the materials transported by the belt conveyor detected from the current operation picture is in the smallest interval in the set intervals; the material quantity is excessive and is used for indicating that the quantity (or quality) of the materials transported by the belt conveyor detected from the current operation picture is in the largest interval in the set intervals; the material quantity is normal and is used for indicating that the quantity (or quality) of the materials transported by the belt conveyor detected from the current operation picture is in the middle of the three set intervals.
The belt conveyor operation position is mainly used for indicating whether a person approaches the vicinity of the belt conveyor operation area when the belt conveyor operates.
According to the needs of actual conditions, any one or combination of more than one of the five detection models can be configured on the video identification server as a state detection model, so that a corresponding state monitoring result can be detected from the current running picture of the belt conveyor.
It should be noted that the state detection model of the video recognition server may also include the above five detection models at the same time, and the above five detection models may be used at the same time when the video recognition server analyzes the running screen, so as to analyze the above five detection results at the same time. In addition, the video recognition server may call any one or more of the five detection models included in the state detection model at different frequencies as needed.
For example, the video recognition server may analyze each frame of running picture of the belt conveyor by using the deviation detection model, the slip detection model and the start-stop detection model to obtain the corresponding state detection result, and the frequency of use of the load detection model may be relatively low, for example, for a running video uploaded by the image pickup apparatus, the video server calls the load detection model to analyze the latest frame of running picture only every 10 frames, that is, for a first frame of running picture in the running video, the video recognition server analyzes the four detection models simultaneously to obtain four state monitoring results, for second to tenth frame of running pictures, the video recognition server only calls the other three detection models except the load detection model to analyze to obtain three state monitoring results, for an eleventh frame of running picture, and the video identification server analyzes the four detection models simultaneously again to obtain four state monitoring results, and so on.
For any belt conveyor, after the video identification server analyzes the state monitoring result of the belt conveyor, the running belt conveyor can be controlled according to the state monitoring result. The specific control mode may include controlling the belt conveyor to continue to operate in the current state, adjusting the operating power of the belt conveyor, closing the belt conveyor in operation, and the like.
It should be noted that the video identification server described in the present application may be a single server, or may be a server cluster formed by a plurality of servers.
Each video server may be equipped with multiple GPUs (image processors) to increase the speed at which each video recognition server analyzes the running picture.
In the system provided by this embodiment, the control of the belt by the video identification server is mainly realized by the belt controller 103 of the system. As described above, the belt controller 103 and the video recognition server 102 are connected via a network. After analyzing the state monitoring result of the belt conveyor from the operation picture, the video recognition server may generate a state word of the belt conveyor according to the state monitoring result, where the state word may be regarded as an identifier for indicating a state of a certain aspect of the belt conveyor, and according to a difference of values of the identifier, the belt conveyor controller may determine a state of the belt conveyor and perform corresponding control, where each state monitoring result has a corresponding state word, and reference may be specifically made to subsequent embodiments.
The video recognition server can send the generated status words to the belt conveyor controller, so that the belt conveyor controller is triggered to control the operation of the belt conveyor according to the received status words.
Optionally, in other embodiments of the application, the operation video of the belt conveyor captured by the camera device may also be directly transmitted to the belt conveyor controller through a network, and the belt conveyor controller may play the operation video of the belt conveyor on a corresponding terminal in real time, so that related personnel may manually monitor the operation of the belt conveyor.
In the above embodiment, the image pickup device, the video recognition server, and the belt conveyor controller are a plurality of modules divided according to functions and connection relationships of each device in the control system, and it is described below with reference to fig. 2 that in a specific embodiment, the control system of the belt conveyor described in this application may be composed of real devices.
Referring to fig. 2, as described in the foregoing embodiment, the image capturing apparatus in the control system may include a plurality of cameras, each camera is used to correspondingly monitor one belt conveyor, further, the image capturing apparatus may further be configured with a network hard disk, the network hard disk may understand a cache server directly connected to each camera, and the network hard disk may be configured to cache videos captured by each camera when a network connection between the image capturing apparatus and the video recognition server is interrupted, and send the cached videos to the video recognition server again after the network connection is restored.
The image capturing apparatus accesses a network formed by the video identification server and the belt conveyor controller through the network switch, wherein, as described above, the video identification server may be a server cluster formed by a plurality of servers.
Optionally, the video identification server may be further connected to one or more video terminals through a network, and related personnel may monitor the operation of the state detection model through the state detection model of the video identification server at the video terminal.
The video recognition server can generate corresponding state words according to the state monitoring results obtained through analysis, and then sends the state words to the belt conveyor controller through the network. On the other hand, the belt conveyor controller and the video identification server can also be directly connected through the bus system, and in this case, the video identification server can directly send the status word to the belt conveyor controller through the bus system.
The video recognition server may send the status word to the belt controller via an OPC-DA communication protocol, or an OPC-UA communication protocol.
The belt conveyor controller in the embodiment of the application may be an ECS-700 control system. The belt conveyor controller can comprise one or more configuration servers used for controlling the belt conveyor to operate according to the state words sent by the video identification server, meanwhile, the configuration servers can be connected with one or more control terminals, the control terminals can play the operation video of the belt conveyor shot by the camera shooting equipment in real time so as to be convenient for relevant personnel to check, and the relevant personnel can realize manual control over the belt conveyor in operation through operating the control terminals. In addition, the prompt information output by any link of the control system and the corresponding method in the embodiment of the application can be displayed in the control terminal.
In the following, a control method of a belt conveyor provided in an embodiment of the present application is described with reference to a belt conveyor control system shown in fig. 1 and fig. 2, and an execution main body of the control method may be regarded as the belt conveyor control system shown in fig. 1.
Referring to fig. 3, a method for controlling a belt conveyor provided in an embodiment of the present application may include the following steps:
s301, when the belt conveyor runs, acquiring a current running picture of the belt conveyor, which is obtained by real-time shooting of the camera device.
As described above, the camera device may obtain the running video of the belt conveyor through shooting by the camera, and then the video recognition server may extract one frame of image closest to the current time from the running video as the current running picture of the belt conveyor.
S302, analyzing a current running picture of the belt conveyor by using a pre-trained state detection model to obtain a current state monitoring result of the belt conveyor.
Wherein, the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state, a load degree and a belt conveyor running position.
Correspondingly, the state detection model may include any one or a combination of a deviation detection model for analyzing the deviation degree of the belt conveyor, a slip detection model for analyzing the slip state of the belt conveyor, a start-stop detection model for analyzing the start-stop state of the belt conveyor, a load detection model for analyzing the load degree of the belt conveyor, and a position detection model for detecting whether people approach near the running position of the belt conveyor.
The training method of the deviation detection model comprises the steps of firstly collecting a large number of running pictures of the belt conveyor, then manually identifying the deviation degree of the belt conveyor in each running picture, configuring any one of four labels of non-deviation, slight deviation, moderate deviation and severe deviation for each running picture according to the identification result, configuring the running picture of the label, and forming a training sample of the deviation detection model.
After a large number of training samples are obtained, the operation pictures in the training samples can be input into a pre-constructed neural network model to be trained one by one, so that the neural network model to be trained outputs any one of the four labels corresponding to the deviation degree. On the basis, the label output by the neural network model aiming at the running picture of each training sample is taken as a training target, the label which is as close to the artificially labeled label as possible, the parameter of the neural network model to be trained is repeatedly adjusted until the loss of the neural network model to be trained (the loss reflects the deviation degree of the label output by the model and the artificially labeled label, the smaller the loss is, the closer the label output by the model is to the artificially labeled label) meets the preset convergence condition, and at the moment, the neural network model is a deviation detection model which can be used for analyzing the running picture of the belt conveyor and outputting the corresponding deviation degree.
Aiming at the slipping detection model, the training process of the start-stop detection model and the load detection model is basically consistent with the training process of the deviation detection model, the labels of the slipping state, the labels of the start-stop state and the labels of the load degree are manually configured on a plurality of operation pictures one by one, then the corresponding neural network model is trained by using the operation pictures configured with the labels until the loss of the model meets the convergence condition, in other words, the loss of the model is close to the labels manually marked, and the obtained model is the corresponding detection model.
The position detection model does not need to be trained specifically, any one of the existing face detection models can be directly used as the position detection model in the embodiment of the application, only the camera needs to be aligned to the area near the belt conveyor, then the position detection model is directly used for detecting whether a face image appears in the collected running picture, if the face image appears in the running picture, the situation that a person approaches the area near the belt conveyor is indicated, otherwise, if the face image does not appear in the picture, the situation that no person approaches the area near the belt conveyor is indicated.
And S303, controlling the belt conveyor to operate according to the current state monitoring result of the belt conveyor.
As described above, the specific implementation process of step S303 is:
and generating corresponding state words according to the current state monitoring result of the belt conveyor, and controlling the belt conveyor to operate according to the state words.
If the executing entity of the present embodiment is regarded as the belt conveyor control system shown in fig. 1, step S303 may be understood as that the status word is generated by the video recognition server and sent to the belt conveyor controller (i.e., the ECS-700 control system), and then the belt conveyor controller controls the belt conveyor to operate according to the status word.
If the executing body of this embodiment is regarded as the video recognition server of the belt conveyor control system shown in fig. 1, step S303 may be understood as that the video recognition server generates the status word and triggers the belt conveyor controller to control the belt conveyor to operate according to the status word by sending the status word to the belt conveyor controller.
The status word indicating the degree of deviation may be an integer variable (i.e. int type variable in a computer program), and the value of the variable may be 0,1,2 or 3, where 0 indicates no deviation, 1 corresponds to light deviation, 2 corresponds to medium deviation, and 3 corresponds to heavy deviation.
The status word indicating the start/stop status may be a boolean variable (i.e. a bol-type variable in a computer program), and the value of the variable may be true or false, where true indicates that the belt is operating normally, and false indicates that the belt is out of operation.
The state word representing the load state can be a shaping variable, the value of the variable can be 0,1,2, 3, 0 represents that the belt conveyor is unloaded, namely the belt conveyor does not transport materials, 1 represents that the material quantity of the belt conveyor is too small, 2 represents that the material quantity is normal, and 3 represents that the material quantity is too large.
The state word indicating the slip state may be a boolean variable and the variable value may be true or false, where true indicates belt slip and false indicates belt non-slip.
The state word representing the belt running position can be a boolean variable, and the variable value can be true or false, wherein true represents that the belt running area or the vicinity of the belt is occupied, and false represents that the belt is not occupied.
In summary, after the state monitoring result is analyzed, the video identification model may set variable values of the variables according to the state monitoring result, and then transmit the set variables to the belt conveyor controller, and the belt conveyor controller may determine the current state of the belt conveyor according to the rule and perform corresponding control.
It can be understood that the control method provided by the embodiment of the application can be used for monitoring the running states of a plurality of belt conveyors in real time and performing corresponding control according to the monitoring result.
Optionally, when a plurality of belt conveyors need to be controlled, a camera can be arranged for a plurality of belt conveyors close to each other for monitoring, and a corresponding camera can be arranged for each belt conveyor for monitoring.
The control method provided by the application only needs to shoot the running video of the monitored belt conveyor by installing a corresponding camera, and then automatic monitoring and control of the running state can be achieved. Therefore, the cost of hardware equipment required by the implementation scheme is low, and a large number of cameras and sensors do not need to be installed for each belt conveyor.
On the other hand, among the prior art, a plurality of precision sensors installed on the belt conveyor are generally difficult to be equipped with corresponding dustproof, moistureproof and other facilities, so that in a severe environment, the implementation of the scheme for realizing the state monitoring of the belt conveyor through the sensors can cause various sensors to frequently break down, the reliability of the whole system is low, and related personnel also need to frequently overhaul and maintain the sensors. The state monitoring and control scheme realized by the camera and the video identification service can be implemented in practice by easily adding various protective facilities to the camera according to specific environments, effectively reduces the probability of damage of the camera due to environmental influence, and greatly improves the reliability of the work of the control system under the corresponding environment.
For convenience in understanding the control method in the embodiment of the present application, the following description is made of a corresponding control method in combination with a specific operation state of the belt conveyor:
firstly, according to the detection result of the running position of the belt conveyor, if a person is detected in the running area of the belt conveyor, that is, if the value of the state word corresponding to the running position of the belt conveyor is true, the belt conveyor is controlled to stop running, otherwise, if no person is detected in the running area of the belt conveyor, that is, the value of the corresponding state word is false, the belt conveyor is controlled to continue running in the current state.
Optionally, after the operation of the belt conveyor is stopped by detecting that someone exists in the operation area of the belt conveyor, the control terminal of the ECS-700 control system may output the prompt message.
Secondly, aiming at the detection result of the deviation degree, if the belt conveyor is detected not to deviate, the belt conveyor is controlled to continue to operate in the current state, and if the deviation degree of the belt conveyor is detected to be slight deviation or moderate deviation, the power of the belt conveyor can be reduced, so that the belt conveyor continues to operate at a lower power, and meanwhile, belt conveyor deviation prompt information is output at a corresponding control terminal to prompt related personnel to overhaul.
In other words, in the case of light deviation or moderate deviation, a first power lower than the current power can be determined according to the current power of the belt conveyor, and then the belt conveyor is controlled to continue to operate at the first power.
And if the deviation degree of the belt conveyor is detected to be severe deviation, immediately controlling the belt conveyor to stop running, and outputting deviation prompt information at the control terminal.
Thirdly, according to the state monitoring result of the slipping state, if the belt conveyor is detected not to slip, namely the value of the corresponding state word is false, the belt conveyor is controlled to keep the current state to continue to operate, and if the belt conveyor is detected to slip, namely the value of the corresponding state word is true, the belt conveyor is controlled to stop operating, and belt conveyor slipping prompt information is output at the control terminal.
Fourthly, aiming at the detection result of the load degree, if the load degree of the belt conveyor is detected to be that the material quantity is normal, the belt conveyor can be controlled to continuously operate in the current state.
If the current load degree of the belt conveyor is detected to be excessive material quantity, the power of the belt conveyor can be improved, and the belt conveyor can continuously run at higher power. That is to say, when the material quantity is too small, a second power higher than the current power can be determined according to the current power of the belt conveyor, and then the belt conveyor is controlled to operate at the second power.
If the current load degree of the belt conveyor is detected to be that the material quantity is too small, or the belt conveyor is detected not to transport materials currently (namely the materials are not displayed in the current operation picture), the power of the belt conveyor can be reduced, and the belt conveyor can continuously operate at lower power. That is, when the material quantity is too small, a third power lower than the current power can be determined according to the current power of the belt conveyor, and then the belt conveyor is controlled to operate at the third power.
Fifthly, aiming at the detection result of the start-stop state, if the normal operation of the belt conveyor is detected, the belt conveyor is controlled to keep the current operation state, if the belt conveyor is detected to temporarily stop the operation due to unknown reasons, on one hand, prompt information of abnormal stop of the belt conveyor can be output at the control terminal, and on the other hand, the belt conveyor controller can try to restart the belt conveyor.
In any of the foregoing control manners, the output of the prompt message at the control terminal may have various forms, which may include, but are not limited to, popping up a running video of the corresponding belt machine at the control terminal, popping up a message prompt window, and emitting a warning sound.
Finally, in combination with the control method of the belt conveyor provided in any embodiment of the present application, an embodiment of the present application also provides a control device of the belt conveyor, where the control device may be regarded as a belt conveyor control system as shown in fig. 1, and each unit of the control device may be regarded as a program running on each hardware in the belt conveyor control system as shown in fig. 1.
Referring to fig. 4, the control device may include the following units:
the acquiring unit 401 is configured to acquire a current operation picture of the belt conveyor, which is obtained by real-time shooting by the image capturing device when the belt conveyor operates.
An analyzing unit 402, configured to analyze a current operation screen of the belt conveyor by using a pre-trained state detection model, so as to obtain a current state monitoring result of the belt conveyor.
Wherein, the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state, a load degree and a belt conveyor running position.
And a control unit 403, configured to control operation of the belt conveyor according to a current state monitoring result of the belt conveyor.
When the belt conveyor runs, the obtaining unit 401 is specifically configured to, when obtaining a current running picture of the belt conveyor, which is obtained by real-time shooting by the camera device, of the belt conveyor:
and extracting one frame of image closest to the current moment from the running video of the belt conveyor shot by the camera equipment in real time to be used as the current running picture of the belt conveyor.
The control unit 403 includes:
the generating unit is used for generating corresponding state words according to the current state monitoring result of the belt conveyor;
and the sub-control unit is used for controlling the belt conveyor to operate according to the status words.
Optionally, the state detection model includes a deviation detection model, and the state monitoring result includes a deviation degree of the belt conveyor.
The control unit 403 is configured to control the operation of the belt conveyor according to the current state monitoring result of the belt conveyor, and is specifically configured to:
if the deviation degree of the belt conveyor is not deviation, controlling the belt conveyor to continuously operate at the current power;
if the deviation degree of the belt conveyor is slight deviation or moderate deviation, controlling the belt conveyor to continuously operate at a first power, and outputting belt conveyor deviation prompt information; the first power is lower than the current power of the belt conveyor;
and if the deviation degree of the belt conveyor is severe deviation, controlling the belt conveyor to stop running.
Optionally, the state detection model includes a load detection model, and the state monitoring result includes a load degree of the belt conveyor.
The control unit 403 is configured to control the operation of the belt conveyor according to the current state monitoring result of the belt conveyor, and is specifically configured to:
if the load degree of the belt conveyor is that the material quantity is normal, controlling the belt conveyor to continuously operate at the current power;
if the load degree of the belt conveyor is that the material quantity is excessive, controlling the belt conveyor to continuously operate at a second power; the second power is higher than the current power of the belt conveyor;
if the load degree of the belt conveyor is that the material quantity is too small, controlling the belt conveyor to continuously operate at a third power; and the third power is lower than the current power of the belt conveyor.
The specific working principle of the control device of the belt conveyor provided by the embodiment of the application can refer to the control method of the belt conveyor provided by any embodiment of the application, and details are not described here.
The application provides a control device of a belt conveyor, which comprises an acquisition unit 401, a control unit and a control unit, wherein the acquisition unit is used for acquiring a current operation picture of the belt conveyor, which is obtained by real-time shooting of camera equipment when the belt conveyor operates; an analyzing unit 402, configured to analyze a current operation screen of the belt conveyor by using a pre-trained state detection model to obtain a current state monitoring result of the belt conveyor; the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state, a load degree and a belt conveyor running position; the control unit 403 controls the operation of the belt conveyor according to the current state monitoring result of the belt conveyor. The running picture that this scheme was gathered through analysis camera equipment realizes the control and corresponding control to the state of belt feeder, compares in the sensor of installing at the belt feeder, and camera equipment more can resist adverse circumstances's interference, is difficult for breaking down with the sensor contrast, and consequently, this scheme has higher reliability for prior art.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, 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 process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
It should be noted that the terms "first", "second", and the like in the present invention are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
Those skilled in the art can make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A control method of a belt conveyor is characterized by comprising the following steps:
when the belt conveyor runs, acquiring a current running picture of the belt conveyor, which is obtained by real-time shooting of camera equipment;
analyzing the current operation picture of the belt conveyor by using a pre-trained state detection model to obtain the current state monitoring result of the belt conveyor; the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state, a load degree and a belt conveyor running position;
and controlling the belt conveyor to operate according to the current state monitoring result of the belt conveyor.
2. The control method according to claim 1, wherein the acquiring, when the belt conveyor is running, a current running picture of the belt conveyor, which is obtained by real-time shooting by a camera device, comprises:
and extracting a frame of image closest to the current moment from the running video of the belt conveyor shot by the camera equipment in real time to be used as the current running picture of the belt conveyor.
3. The control method according to claim 2, wherein the controlling the operation of the belt conveyor according to the current state monitoring result of the belt conveyor comprises:
generating a corresponding state word according to the current state monitoring result of the belt conveyor;
and controlling the belt conveyor to operate according to the state words.
4. The control method according to claim 1, wherein the state detection model comprises a deviation detection model, and the state monitoring result comprises a deviation degree of the belt conveyor;
wherein, the controlling the operation of the belt conveyor according to the current state monitoring result of the belt conveyor comprises:
if the deviation degree of the belt conveyor is not deviation, controlling the belt conveyor to continuously operate at the current power;
if the deviation degree of the belt conveyor is slight deviation or moderate deviation, controlling the belt conveyor to continuously operate at a first power, and outputting belt conveyor deviation prompt information; wherein the first power is lower than the current power of the belt conveyor;
and if the deviation degree of the belt conveyor is severe deviation, controlling the belt conveyor to stop running.
5. The control method according to claim 1, wherein the state detection model includes a load detection model, and the state monitoring result includes a load degree of the belt conveyor;
wherein, the controlling the operation of the belt conveyor according to the current state monitoring result of the belt conveyor comprises:
if the load degree of the belt conveyor is that the material quantity is normal, controlling the belt conveyor to continuously operate at the current power;
if the load degree of the belt conveyor is that the material quantity is too large, controlling the belt conveyor to continuously operate at a second power; wherein the second power is higher than the current power of the belt conveyor;
if the load degree of the belt conveyor is that the material quantity is too small, controlling the belt conveyor to continuously operate at a third power; and the third power is lower than the current power of the belt conveyor.
6. A control device of a belt conveyor is characterized by comprising:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring a current operation picture of the belt conveyor, which is obtained by real-time shooting of camera equipment when the belt conveyor operates;
the analysis unit is used for analyzing the current running picture of the belt conveyor by utilizing a pre-trained state detection model to obtain the current state monitoring result of the belt conveyor; the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state, a load degree and a belt conveyor running position;
and the control unit is used for controlling the operation of the belt conveyor according to the current state monitoring result of the belt conveyor.
7. The control device according to claim 6, wherein the acquiring unit, when the belt conveyor runs, is configured to, when acquiring a current running picture of the belt conveyor, which is obtained by real-time shooting by a camera device, specifically:
and extracting a frame of image closest to the current moment from the running video of the belt conveyor shot by the camera equipment in real time to be used as the current running picture of the belt conveyor.
8. The control device according to claim 7, wherein the control unit includes:
the generating unit is used for generating a corresponding state word according to the current state monitoring result of the belt conveyor;
and the sub-control unit is used for controlling the belt conveyor to operate according to the state words.
9. The control device according to claim 6, wherein the state detection model comprises a deviation detection model, and the state monitoring result comprises a deviation degree of the belt conveyor;
the control unit is used for controlling the operation of the belt conveyor according to the current state monitoring result of the belt conveyor, and is specifically used for:
if the deviation degree of the belt conveyor is not deviation, controlling the belt conveyor to continuously operate at the current power;
if the deviation degree of the belt conveyor is slight deviation or moderate deviation, controlling the belt conveyor to continuously operate at a first power, and outputting belt conveyor deviation prompt information; wherein the first power is lower than the current power of the belt conveyor;
and if the deviation degree of the belt conveyor is severe deviation, controlling the belt conveyor to stop running.
10. A control system for a belt conveyor, comprising:
the system comprises a camera device, a video identification server and a belt conveyor controller;
the camera device is used for shooting in real time to obtain a current operation picture of the belt conveyor when the belt conveyor operates;
the video recognition server is configured to:
acquiring a current running picture of the belt conveyor, which is obtained by real-time shooting of the camera equipment;
analyzing the current operation picture of the belt conveyor by using a pre-trained state detection model to obtain the current state monitoring result of the belt conveyor; the state monitoring result at least comprises any one or combination of a deviation degree, a slip state, a start-stop state, a load degree and a belt conveyor running position;
the belt feeder controller is used for:
and controlling the belt conveyor to operate according to the current state monitoring result of the belt conveyor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010837514.8A CN111935458A (en) | 2020-08-19 | 2020-08-19 | Control method, device and system of belt conveyor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010837514.8A CN111935458A (en) | 2020-08-19 | 2020-08-19 | Control method, device and system of belt conveyor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111935458A true CN111935458A (en) | 2020-11-13 |
Family
ID=73305371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010837514.8A Pending CN111935458A (en) | 2020-08-19 | 2020-08-19 | Control method, device and system of belt conveyor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111935458A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113998419A (en) * | 2021-11-09 | 2022-02-01 | 中铁工程服务有限公司 | Visual automatic deviation adjusting device of belt conveyor |
| CN114013923A (en) * | 2021-11-10 | 2022-02-08 | 中国联合网络通信集团有限公司 | Belt deviation rectifying method, device and system and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103848183A (en) * | 2012-10-17 | 2014-06-11 | 陕西杰创科技有限公司 | Well belt conveyor real-time monitoring system |
| CN205802574U (en) * | 2016-06-27 | 2016-12-14 | 攀钢集团攀枝花钢钒有限公司 | Prevent galvanizing unit strip steel from running the automatic reduction of speed control system of sideslip broken belt |
| CN207417784U (en) * | 2017-11-07 | 2018-05-29 | 江苏高盛华宇电力设备制造有限公司 | Full-automatic variable-frequency belt deviation rectifying adjusting device |
| CN109305534A (en) * | 2018-10-25 | 2019-02-05 | 安徽理工大学 | Coal wharf's belt conveyor self-adaptation control method based on computer vision |
| CN110490995A (en) * | 2019-08-26 | 2019-11-22 | 精英数智科技股份有限公司 | A kind of belt operating status method for monitoring abnormality, system, equipment and storage medium |
-
2020
- 2020-08-19 CN CN202010837514.8A patent/CN111935458A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103848183A (en) * | 2012-10-17 | 2014-06-11 | 陕西杰创科技有限公司 | Well belt conveyor real-time monitoring system |
| CN205802574U (en) * | 2016-06-27 | 2016-12-14 | 攀钢集团攀枝花钢钒有限公司 | Prevent galvanizing unit strip steel from running the automatic reduction of speed control system of sideslip broken belt |
| CN207417784U (en) * | 2017-11-07 | 2018-05-29 | 江苏高盛华宇电力设备制造有限公司 | Full-automatic variable-frequency belt deviation rectifying adjusting device |
| CN109305534A (en) * | 2018-10-25 | 2019-02-05 | 安徽理工大学 | Coal wharf's belt conveyor self-adaptation control method based on computer vision |
| CN110490995A (en) * | 2019-08-26 | 2019-11-22 | 精英数智科技股份有限公司 | A kind of belt operating status method for monitoring abnormality, system, equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113998419A (en) * | 2021-11-09 | 2022-02-01 | 中铁工程服务有限公司 | Visual automatic deviation adjusting device of belt conveyor |
| CN114013923A (en) * | 2021-11-10 | 2022-02-08 | 中国联合网络通信集团有限公司 | Belt deviation rectifying method, device and system and computer readable storage medium |
| CN114013923B (en) * | 2021-11-10 | 2023-05-16 | 中国联合网络通信集团有限公司 | Belt deviation correcting method, device and system and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110996060A (en) | Industrial automation intelligent linkage system and method | |
| CN211293956U (en) | AI-based identification and alarm system for abnormal agent on construction site | |
| CN111935458A (en) | Control method, device and system of belt conveyor | |
| CN110989594A (en) | Intelligent robot inspection system and method | |
| CN109179128A (en) | A kind of elevator monitoring apparatus, system and method | |
| CN109544870B (en) | Alarm judgment method for intelligent monitoring system and intelligent monitoring system | |
| CN208732382U (en) | Elevator signal acquisition device and system | |
| CN112919050A (en) | Conveyor belt monitoring method, device, equipment and computer readable storage medium | |
| CN111045889A (en) | Closed network equipment state monitoring system, method and device and readable storage medium | |
| CN112084087A (en) | Industrial equipment state monitoring and operation and maintenance management method and system | |
| CN110716803A (en) | Computer system, resource allocation method and image identification method thereof | |
| CN112966552B (en) | Routine inspection method and system based on intelligent identification | |
| CN112543376B (en) | Self-operation media operation and maintenance method, system, storage medium and device based on Internet of things | |
| CN110928305B (en) | Patrol method and system for patrol robot of railway passenger station | |
| KR102459503B1 (en) | Monitoring area abnormality monitoring system using dual sensor and method thereof | |
| CN116778836A (en) | Information monitoring method, system, device and storage medium of display system | |
| CN115083132B (en) | Research and judgment method for reducing false alarm rate of fire alarm | |
| JP2020065258A (en) | Monitoring device, monitoring method, monitoring program, and monitoring system | |
| CN115393340A (en) | AI vision product quality detection system based on 5G algorithm | |
| US11714721B2 (en) | Machine learning systems for ETL data streams | |
| CN115631459A (en) | Conveyor belt monitoring method and device based on artificial intelligence | |
| CN113852915A (en) | Subway station equipment control method and device, electronic equipment and storage medium | |
| CN107121970A (en) | It is electromechanical in a kind of building of use BIM technology to safeguard and supervising device | |
| US11132893B2 (en) | Multi-sensor edge computing system | |
| CN112383137A (en) | Transformer area monitoring system and method based on machine vision and thermal imaging technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201113 |