CN111570331B - Unqualified product removing device and method under variable-speed assembly line environment - Google Patents
Unqualified product removing device and method under variable-speed assembly line environment Download PDFInfo
- Publication number
- CN111570331B CN111570331B CN202010363250.7A CN202010363250A CN111570331B CN 111570331 B CN111570331 B CN 111570331B CN 202010363250 A CN202010363250 A CN 202010363250A CN 111570331 B CN111570331 B CN 111570331B
- Authority
- CN
- China
- Prior art keywords
- product
- photoelectric switch
- personal computer
- industrial personal
- production line
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004519 manufacturing process Methods 0.000 claims abstract description 57
- 238000001514 detection method Methods 0.000 claims abstract description 31
- 230000001133 acceleration Effects 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 21
- 230000008030 elimination Effects 0.000 claims description 57
- 238000003379 elimination reaction Methods 0.000 claims description 57
- 238000013135 deep learning Methods 0.000 claims description 7
- 102100032202 Cornulin Human genes 0.000 claims description 6
- 101000920981 Homo sapiens Cornulin Proteins 0.000 claims description 6
- 150000001875 compounds Chemical class 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 230000002950 deficient Effects 0.000 claims 1
- 230000002452 interceptive effect Effects 0.000 abstract description 2
- 238000005507 spraying Methods 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 3
- 239000008267 milk Substances 0.000 description 3
- 210000004080 milk Anatomy 0.000 description 3
- 235000013336 milk Nutrition 0.000 description 3
- 230000001788 irregular Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a device and a method for rejecting unqualified products in a variable-speed assembly line environment, wherein the device comprises a plurality of photoelectric switches arranged on any one side of two sides of an assembly line; the information collector is arranged at the head end of the production line; the removing device is arranged at the tail end of the production line; the industrial personal computer determines the correctness of product information through a product detection algorithm according to the received image, if the product information is judged to be wrong, when the product passes through the last photoelectric switch, the industrial personal computer calculates the initial speed and the initial acceleration of the product at the moment according to the time point transmitted by each photoelectric switch, determines the product rejection time through a uniform acceleration motion calculation method according to the set length of a product rejection area, sends a rejection instruction to a rejection device, and the rejection device rejects the product operation according to the received rejection instruction. The device can realize that unqualified products can be quickly removed by dynamically tracking the positions of the products under the conditions of a uniform speed production line or a uniform speed change production line without interfering the production flow and setting removal stop.
Description
Technical Field
The invention relates to the technical field of product detection, in particular to a device and a method for removing unqualified products in a variable-speed assembly line environment.
Background
In industrial production, in order to improve production efficiency, the production, assembly, test and other links of products are all finished on an automatic production line; the assembly line product elimination is a process of carrying out rule verification on the detection result of the assembly line product and executing elimination operation on unqualified products. The existing common product removing methods include an electric signal output method, a mark removing method, a time delay removing method and the like.
The existing production line product elimination generally adopts two elimination schemes of an electric signal output method and a delay elimination method, has the characteristics of simple realization and accurate elimination, but has the following problems:
(1) the elimination scheme based on the electric signal output method is suitable for simple product detection, for example, in the milk pouring detection, the exclusive OR operation is carried out on the upper and lower photoelectric switch point positions to judge whether pouring exists; and if the sucker detection algorithm is defined by the image sensor in the milk bag sucker detection, whether the sucker is lost is judged. However, when the system is faced with the problem of complex product detection, such as the detection of the code spraying content of milk, the system cannot directly use an electric signal output method to complete the rejection of unqualified products.
(2) The scheme based on the delay elimination method is suitable for a constant-speed assembly line scene, and when the conditions of assembly line speed change and assembly line product displacement are met, the set fixed elimination delay cannot track the production state, so that delay errors occur, and the mistaken elimination operation is caused. The root cause of the problem is that the method depends on the regular operation of the production line, the product elimination is completed according to the same rule, and the motion tracking of each product cannot be carried out.
In view of the above, it is desirable to provide a device capable of quickly and accurately removing unqualified products in a scene with a complex detection task and a non-uniform motion of a product line.
Disclosure of Invention
In order to solve the technical problems, the invention adopts the technical scheme that the unqualified product removing device under the variable-speed assembly line environment comprises an information collector, a removing device and a plurality of photoelectric switches, wherein the information collector, the removing device and the photoelectric switches are respectively connected with an industrial personal computer;
the photoelectric switches are arranged on any one side of two sides of the production line at equal intervals and used for detecting products on the production line, determining time points and feeding back time point information to the industrial personal computer; the information collector (1) is arranged at the head end of the production line and used for shooting and collecting product information on a product and feeding back a collected picture to the industrial personal computer; the removing device is arranged at the tail end of the production line and used for removing corresponding products according to a removing instruction sent by the industrial personal computer;
the product removing device comprises a plurality of photoelectric switches, a product removing device and a product tracking device, wherein the photoelectric switches are arranged on the product removing device, the product tracking device is arranged in the product removing device, and the photoelectric switches are arranged on the product tracking device;
the industrial personal computer determines the correctness of product information through a product detection algorithm according to the received image, determines an unqualified product, calculates the initial speed and the initial acceleration of the product at the moment according to the time point transmitted by each photoelectric switch when the unqualified product passes through the last photoelectric switch, determines the product elimination time through a uniform acceleration motion calculation method according to the set length of a product elimination area, sends an elimination instruction to an elimination device when the elimination time is reached, and the elimination device finishes the elimination operation of the unqualified product according to the received elimination instruction.
In the scheme, the arrangement distance of each product on the production line is larger than the arrangement distance between the photoelectric switches.
In the scheme, the distance between the photoelectric switches is 2-3 cm;
the distance between the last photoelectric switch and the removing device is 3-6 cm;
the distance of the products on the production line is set to be 3-5 cm.
In the scheme, the photoelectric switch comprises an acquisition trigger arranged on one side of a front-end assembly line of a plurality of photoelectric switches;
the acquisition trigger is in communication connection with the information collector and is used for triggering the information collector to collect product information when a detection product passes by.
In the scheme, 3 photoelectric switches, namely a first photoelectric switch, a second photoelectric switch and a third photoelectric switch, are arranged on one side of the assembly line at equal intervals, and the acquisition trigger is further arranged on one side of the assembly line at the front end of the first photoelectric switch; the product passes through 3 photoelectric switches in sequenceThe first photoelectric switch, the second photoelectric switch and the third photoelectric switch respectively change the time pointt C 、t B 、t A The signal is fed back to the industrial personal computer, and meanwhile, when the product passes through the last photoelectric switch, the industrial personal computer calculates the initial speed and the initial acceleration of the product operation at the moment and determines the removal time of the product A through a uniform acceleration motion calculation method, and the calculation is as follows:
the initial velocity of product a at the moment of leaving the product tracking area is as follows:
in the formula (I), the compound is shown in the specification,
the distances from the acquisition trigger to the first photoelectric switch, the second photoelectric switch and the third photoelectric switch are respectively;
the initial acceleration at the moment the product leaves the product tracking area is as follows:
the formula of the uniform linear motion is as follows:
in the formula (I), the compound is shown in the specification,
taking the value of zero,sthe distance between the last photoelectric switch on the production line and the rejecting device is calculated;
then converting the above equation into a time delay for cullingtThe equation set of (1) calculates the next class equation and takes the positive root as the elimination delaytSpecifically, the following formula:
in the above scheme, the acquisition trigger is a photoelectric switch sensor.
The invention also provides a method for removing unqualified products in a variable-speed assembly line environment, which comprises the following steps:
the industrial personal computer receives the acquired product information image and each monitored time point of the movement of the product on the production line; the industrial personal computer determines the correctness of the product information in the image according to a product detection algorithm, and if the product information is determined to be an unqualified product, the initial speed and the initial acceleration of the corresponding product at the moment are calculated according to the obtained time points; the industrial personal computer determines the product elimination time through a uniform acceleration motion calculation method according to the set length of the product elimination area, when the elimination time is reached, the industrial personal computer sends an elimination instruction to an elimination device, the elimination device completes the elimination operation of unqualified products according to the received elimination instruction, wherein,
the product information image is collected and fed back to the industrial personal computer through an information collector arranged at the head end of the production line; each time point of the product moving on the production line is monitored and obtained by a plurality of photoelectric switches which are arranged on any one side of two sides of the production line at equal intervals; the length of the product rejecting area is the distance between the last photoelectric switch and the rejecting device, and when the product passes through the last photoelectric switch, the product enters the product rejecting area.
In the method, the product detection algorithm set by the industrial personal computer is to confirm that the product is unqualified through an image recognition algorithm based on deep learning and a preset character matching rule, wherein character positioning and feature extraction in the image are realized through an East text detector and a trained CRNN model to obtain a character string of product information, the character string is subjected to character matching with a preset standard character string, and if the character string is not matched with the preset standard character string, the product is determined to be an unqualified product.
In the method, the industrial personal computer compares an image recognition result with a preset standard character string through a regular matching rule, if one character string is not matched, an unqualified product is determined to be removed, and if the character string is identified to be a qualified product, the photoelectric switch finishes tracking the corresponding product.
The industrial personal computer receives the product information images acquired by the information acquisition device and determines each time point when the product passes through the plurality of photoelectric switches, the product detection algorithm determines the correctness of the product information, if the product is judged to be an unqualified product, the industrial personal computer determines and calculates the initial speed and the initial acceleration of the product reaching the initial moment of a product elimination area according to each received time point, and determines the product elimination time through a uniform acceleration motion calculation method according to the known length of the elimination area to put forward the unqualified product; the device can realize the uncontrollable problem of irregular displacement of the product relative to the production line by dynamically tracking the product position under the condition of a uniform velocity production line or a uniform speed change production line without interfering the production flow and setting rejection stop, thereby rapidly rejecting unqualified products.
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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic view of the apparatus according to the present invention;
FIG. 2 is a schematic view of the working process of the apparatus according to the present invention;
FIG. 3 is a schematic structural diagram of an embodiment of the present invention;
FIG. 4 is a flow chart of a method provided by the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all, embodiments of the present 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.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", and the like, indicate orientations and positional relationships based on those shown in the drawings, and are used only for convenience of description and simplicity of description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise. Furthermore, the terms "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
As shown in fig. 1, the invention provides a rejected product removing device in a variable-speed assembly line environment, which comprises an information collector 1, a removing device 2, a plurality of photoelectric switches 3 and a collecting trigger 4, wherein the information collector 1, the removing device 2, the photoelectric switches 3 and the collecting trigger are respectively connected with an industrial personal computer. In this embodiment, 3 photoelectric switches 3 can be set, and according to the speed of the production line and the determination of the identification time, each product needs to be identified and verified when leaving the tracking area.
The acquisition trigger 4 and the photoelectric switches 3 are arranged on any one of two sides of the assembly line along the flow direction of the assembly line, and the acquisition trigger 4 is in communication connection with the information collector 1 and is used for triggering the information collector 1 to collect product information when a detected product passes through;
the photoelectric switches 3 are arranged on any one side of two sides of the production line at equal intervals, are used for detecting products on the production line and determining time points, feed back time point information to the industrial personal computer, and are arranged on the same side to facilitate the arrangement of a connection line with the industrial personal computer; the information collector 1 is arranged at the head end of the production line and used for shooting and collecting product information on products and feeding collected pictures back to the industrial personal computer; the removing device 2 is arranged at the tail end of the production line and used for removing corresponding products according to a removing instruction sent by the industrial personal computer; the area covered by the photoelectric switches 3 is a product tracking area, the area between the last photoelectric switch 3 and the rejecting device 2 is a product rejecting area, and when a product passes through the last photoelectric switch 3, the product leaves the product tracking area and enters the product rejecting area.
The industrial personal computer determines the correctness of product information through a product detection algorithm according to the received image, if the product information is judged to be wrong, when the product passes through the last photoelectric switch 3, the industrial personal computer calculates the initial speed and the initial acceleration of the product at the moment according to the time point transmitted by each photoelectric switch 3, determines the product rejection time through a uniform acceleration motion calculation method according to the set length of a product rejection area, sends a rejection instruction to the rejection device 2 when the proposed time is up, and the rejection device 2 finishes the rejection operation of unqualified products according to the received rejection instruction. According to the embodiment, the industrial personal computer monitors the elimination time and sends the elimination instruction to the elimination device 2 to eliminate unqualified products, so that the hardware requirement of the elimination device can be reduced, and the electric signal is supported to be driven quickly.
In this embodiment, the collection trigger 4 and the plurality of photoelectric switches 3 can be arranged on the assembly line guardrail, and the collection trigger 4 can be arranged on the same assembly line guardrail with the plurality of photoelectric switches 3, and can also be arranged on the guardrails on two sides of the assembly line respectively with the plurality of photoelectric switches 3.
In the embodiment, the industrial personal computer receives the product information images acquired by the information acquisition device and determines each time point when the product passes through the plurality of photoelectric switches, the product detection algorithm determines the correctness of the product information, if the product is judged to be an unqualified product, the industrial personal computer determines and calculates the initial speed and the initial acceleration of the product reaching the initial moment of a product elimination area according to each received time point, and determines the product elimination time through a uniform acceleration motion calculation method according to the known elimination area length to extract the unqualified product.
In this embodiment, the information collector 1 may be an industrial camera, specifically, a seafarewe MV-CA013-20GM type industrial camera, collects a 1280 × 1024 single-channel picture, and the position of the information collector 1 may be set according to the position of the product information to be identified, which is not limited by the present apparatus; the information collector 1 is not arranged in front of the collecting trigger 4; the output end of the acquisition trigger 4 is electrically connected with the input end of the information acquisition device 1.
In this embodiment, the acquisition trigger 4 is a photoelectric switch sensor.
In this embodiment, preferably, the arrangement distance between the products on the production line is greater than the arrangement distance between the photoelectric switches 3; the arrangement is that the photoelectric switches are arranged on the same track, so that the collision volume needs to be considered, the production line speed is high, the product distance on the production line can fluctuate, a distance needs to be reserved to complete identification and verification, the product distance is larger than the photoelectric switch distance, and the phenomenon that tracking dislocation causes wrong rejection is avoided.
In this embodiment, preferably, the product detection algorithm set by the industrial personal computer is to confirm that the product is not qualified through an image recognition algorithm based on deep learning and a preset character matching rule, wherein character positioning and feature extraction in the image are realized through an East text detector and a trained CRNN model, a character string of product information is obtained, the character string is subjected to character matching with a preset standard character string, and if the character string is not matched with the preset standard character string, the product is determined to be a non-qualified product, specifically:
the East text detector acquires each code spraying area in an input image as a target area, the target area is mapped once to be deformed into a standard character picture, a trained CRNN model identifies the content of the deformed character picture, code spraying is acquired as a final identification result and is fed back to the industrial personal computer, the industrial personal computer compares the image identification result with a preset standard character string through a regular matching rule, if one character string is not matched, an unqualified product is determined to be removed, and if the character string is identified to be a qualified product, the photoelectric switch 3 finishes tracking the corresponding product. Specifically, the invention patent CN108921163A discloses a package code-spraying detection method based on deep learning, which includes constructing a combined system based on a deep learning image segmentation network and a deep learning image classification network, and realizing the positioning and identification of each character on the package code-spraying, including three steps of character region extraction, single-line character segmentation and single character identification:
1) extracting a character area:
1a) segmenting an input image by using a semantic segmentation network, outputting a black-white binary image, wherein white pixel points are foreground, namely the areas of the white pixel points are character areas;
1b) extracting a rotating rectangle from the white pixel point region to obtain a rectangular character region, and correcting the character region according to the inclination angle of the rotating rectangle;
2) single-line character segmentation:
2a) packaging and spraying codes into two lines, namely a character area is two lines of characters, folding and splitting the corrected character area obtained in the step 1b) to obtain a single line of characters, performing secondary classification on each line of pixels of the single line of characters by using a classification network based on deep learning, and dividing the single line of characters into a foreground and a background, wherein the foreground is the characters;
2b) segmenting the single-line character according to the classification result and the prior knowledge in the step 2a) to obtain a single character;
3) single character recognition:
3a) and carrying out image classification on the obtained single character based on the convolutional neural network, and identifying to obtain a detection result.
In this embodiment, the CRNN model is trained through the acquired historical images of the product, and the training is implemented by a conventional method, which is not described herein again.
In the embodiment, the image is identified by the East text detector and the trained CRNN model, and the method has the advantages of small model, high training speed, no need of character segmentation and horizontal scaling operation, and capability of identifying sequences with any length by scaling to a fixed length in the vertical direction.
In this embodiment, the product information may include information such as a production address, a date, a production line, and a time point.
In this embodiment, the industrial computer makes the rejecting device 2 reject the product by sending a pulse signal to the rejecting device 2 as a rejecting instruction.
In the preferred embodiment, the distance between the plurality of photoelectric switches 3 is 2-3cm, and the distance between the last photoelectric switch 3 and the rejecting device 2 is 3-6 cm; the time for judging whether the product information is qualified is 70-120 ms through the product detection algorithm, and the calculation of the rejection time when the product enters a product rejection area can be completed in a very short time, so the distance between the photoelectric switches 3 and the distance between the last photoelectric switch 3 and the rejection device 2 are only required to meet the two calculation times, the distance between the products on the production line is set to be 3-5cm, and the distance between the acquisition trigger 4 and the first photoelectric switch 3 is set to be 3-6 cm; therefore, unqualified products can be eliminated in a short time and on the shortest production line, and time and equipment cost are saved.
In this embodiment, the distance between the photoelectric switches is obtained by the products through triggering test and sending signals to the industrial personal computer for calculation, and the distance between trigger points of the products is measured and used as the distance between the photoelectric switches.
In this embodiment, other detection algorithms can be used to determine whether the product is qualified, and the response waiting time for the high-delay detection algorithm is only increased by lengthening the distance of each photoelectric switch 3.
In this embodiment, the removing device 2 is provided with a nozzle and removes unqualified products through air flow, specifically, the industrial personal computer obtains the removing time of corresponding products according to calculation, and sends removing instructions to the removing device 2 at the corresponding removing time, and the removing device 2 receives the instructions and outputs enabling electric signals, and opens the air valve to remove the unqualified products. The removing device 2 is realized by a solenoid valve of Delwey 3V-210-08-DC 24V.
The apparatus is illustrated by the following specific examples.
As shown in fig. 3, in this embodiment, 4 photoelectric switches D-a are respectively and sequentially arranged on a guardrail of a production line, where the photoelectric switch D is an acquisition trigger 4, and is connected with an information acquisition device 1 for triggering the information acquisition device 1, the photoelectric switches C-a are arranged at equal intervals, a production line area covered by the photoelectric switches C-a is a product tracking area, an area between the photoelectric switches a and a removing device 2 is a product removing area, and a process of removing a product a by the device is discussed below.
When a product A reaches a photoelectric switch D through a production line, an information collector 1 starts to collect and shoot the product to obtain an image containing product information and transmits the image to an industrial personal computer for image recognition to judge whether the product information is qualified or not, if the product A is recognized and confirmed to be an unqualified product, when the product A passes through a photoelectric switch C-A, time points are respectively sett C 、t B 、t A The product A is fed back to the industrial personal computer, and meanwhile, when the product A passes through the photoelectric switch A, the product A enters a product removing area, the industrial personal computer calculates the initial speed and the initial acceleration of the operation of the product A at the moment and determines the removing time of the product A through a uniform acceleration motion calculation method, and the calculation is as follows:
the initial velocity of product a at the moment of leaving the product tracking area is as follows:
in the formula (I), the compound is shown in the specification,
the distances from the trigger 4 to the photoelectric switch A, the photoelectric switch B and the photoelectric switch C are collected respectively;
the speed of the product A at the moment when the product A passes through the photoelectric switch A,
the speed of the product A at the moment when the product A passes through the photoelectric switch B.
The initial acceleration at the moment product a leaves the product tracking area is given by:
the formula of the uniform linear motion is as follows:
in the formula (I), the compound is shown in the specification,
taking the value of zero,sthe distance between the last photoelectric switch on the production line and the removing device.
Then converting the above equation into a time delay for cullingtThe equation set of (1) calculates the next class equation and takes the positive root as the elimination delaytSpecifically, the following formula:
in this embodiment, 3 photoelectric switch C-a have been set up and have been used for tracking the motion trail and the time point of product, the interval between specific 3 photoelectric switch is 3cm, photoelectric switch D can set up the interval between it and photoelectric switch C than the apparatus as gathering the trigger, in order to guarantee whole assembly line occupation space, reduce device cost, can accomplish nonconforming product rejection operation in short time high efficiency, the interval between photoelectric switch D and the photoelectric switch C can be set up to 2cm, the interval between photoelectric switch a and the rejection device 2 sets up to 3cm, the product interval sets up to 4cm on the assembly line.
The device has the advantages that:
(1) the device has no interference to the production flow, does not need to set rejection stop, and does not need to build a constant-speed environment.
(2) The detection and calculation method in the device can theoretically be any detection algorithm capable of returning effective signals, and the response waiting time for the high-delay detection algorithm can be prolonged by lengthening the distance of the tracking area.
(3) The device can be adapted to the non-uniform velocity assembly line process, and supports the uniform acceleration motion tracking of products on the assembly line to realize the elimination of unqualified products.
(4) The device completes the control of the product instead of the assembly line, and solves the uncontrollable problem of the product relative to the irregular displacement of the assembly line by dynamically tracking the position of the product.
As shown in fig. 4, the present invention further provides a method for removing rejected products in a variable speed assembly line environment, comprising the steps of:
and S1, the industrial personal computer receives the acquired product information image and each monitored time point of the movement of the product on the production line.
And S2, the industrial personal computer determines whether the product information in the image is correct or incorrect according to the product detection algorithm, and if the product information is determined to be an unqualified product, the initial speed and the initial acceleration of the corresponding product at the moment are calculated according to the obtained time points.
And S3, determining the product elimination time by the industrial personal computer through a uniform acceleration motion calculation method according to the set length of the product elimination area, sending an elimination instruction to the elimination device by the industrial personal computer when the elimination time is reached, and finishing the unqualified product elimination operation by the elimination device according to the received elimination instruction.
In the embodiment, a product information image is collected and fed back to an industrial personal computer through an information collector arranged at the head end of a production line; each time point of the product moving on the production line is monitored and obtained by a plurality of photoelectric switches which are arranged on any one side of two sides of the production line at equal intervals; the length of the product rejecting area is the distance between the last photoelectric switch and the rejecting device, and when the product passes through the last photoelectric switch, the product enters the product rejecting area.
It should be noted that, in the method, the specific process of determining the product rejection time by the even acceleration motion calculation method according to the set length of the product rejection region by using the product detection algorithm for determining whether the product information in the image is correct or incorrect and calculating the initial velocity and the initial acceleration of the corresponding product at this time by using the industrial control computer, may refer to the corresponding contents in the above-mentioned apparatus, and the method is not described in detail again.
The present invention is not limited to the above-mentioned preferred embodiments, and any structural changes made under the teaching of the present invention shall fall within the protection scope of the present invention, which has the same or similar technical solutions as the present invention.
Claims (8)
1. A rejected product removing device in a variable-speed assembly line environment is characterized by comprising an information collector (1), a removing device (2) and a plurality of photoelectric switches (3), wherein the information collector, the removing device and the plurality of photoelectric switches are respectively connected with an industrial personal computer;
the photoelectric switches (3) are arranged on any one side of two sides of the assembly line at equal intervals and are used for detecting products on the assembly line, determining time points and feeding back time point information to the industrial personal computer; the information collector (1) is arranged at the head end of the production line and used for shooting and collecting product information on a product and feeding back a collected picture to the industrial personal computer; the removing device (2) is arranged at the tail end of the production line and used for removing corresponding products according to a removing instruction sent by the industrial personal computer;
the area covered by the photoelectric switches (3) is a product tracking area, and the area between the last photoelectric switch (3) and the rejecting device (2) is a product rejecting area;
the industrial personal computer determines the correctness of product information through a product detection algorithm according to the received image and determines an unqualified product, when the unqualified product passes through the last photoelectric switch (3), the industrial personal computer calculates the initial speed and the initial acceleration of the product at the moment according to the time point transmitted by each photoelectric switch (3), determines the product rejection time through a uniform acceleration motion calculation method according to the set length of a product rejection area, sends a rejection instruction to the rejection device when the rejection time is reached, and the rejection device finishes the rejection operation of the unqualified product according to the received rejection instruction;
the photoelectric switches (3) are arranged on one side of the assembly line at equal intervals and are respectively a first photoelectric switch (3), a second photoelectric switch (3) and a third photoelectric switch (3), and an acquisition trigger (4) is arranged on one side of the assembly line at the front ends of the photoelectric switches (3); the product passes through 3 in proper order when photoelectric switch (3), first photoelectric switch (3), second photoelectric switch (3) and third photoelectric switch (3) are respectively with the time pointt C 、t B 、t A Feeding back to an industrial personal computer, and simultaneously when a product passes through the last photoelectric switch (3), calculating the initial speed and the initial acceleration of the product operation at the moment by the industrial personal computer and determining the removal time of the product A by a uniform acceleration motion calculation method, wherein the calculation is as follows:
the initial velocity of product a at the moment of leaving the product tracking area is as follows:
the speed of the product A at the moment of passing through the second photoelectric switch (3) is as follows:
in the formula (I), the compound is shown in the specification,
the distances from the acquisition trigger (4) to the first photoelectric switch (3), the second photoelectric switch (3) and the third photoelectric switch (3) respectively,
is the speed of the product A at the moment when the product A passes through the third photoelectric switch (3),
the speed of the product A at the moment when the product A passes through the second photoelectric switch (3);
the initial acceleration at the moment the product leaves the product tracking area is as follows:
the formula of the uniform linear motion is as follows:
in the formula (I), the compound is shown in the specification,
taking the value of zero,sthe distance between the last photoelectric switch on the production line and the rejecting device is calculated;
then converting the above equation into a time delay for cullingtThe following equations are calculated, and taking the positive root is taken as the elimination delaytSpecifically, the following formula:
2. the reject removal device in a variable speed line environment according to claim 1, wherein the distance between the products on the line is larger than the distance between the photoelectric switches (3).
3. The reject removing device in the environment of the variable speed production line according to any one of claims 1 to 2, wherein a plurality of the photoelectric switches (3) are arranged at a spacing of 2 to 3 cm;
the distance between the last photoelectric switch (3) and the rejecting device (2) is 3-6 cm;
the distance of the products on the production line is set to be 3-5 cm.
4. The defective product removing device in the environment of the variable speed assembly line according to claim 1, wherein the collection trigger (4) is in communication connection with the information collector (1) and is used for triggering the information collector (1) to collect product information when a detected product passes through.
5. The reject removal device in the environment of a variable speed production line according to claim 4, wherein the acquisition trigger (4) is a photoelectric switch sensor.
6. A method for reject in a variable speed line environment using the reject removing device in a variable speed line environment according to any one of claims 1 to 5, comprising the steps of:
the industrial personal computer receives the acquired product information image and each monitored time point of the movement of the product on the production line; the industrial personal computer determines the correctness of the product information in the image according to a product detection algorithm, and if the product information is determined to be an unqualified product, the initial speed and the initial acceleration of the corresponding product at the moment are calculated according to the obtained time points; the industrial personal computer determines the product elimination time through a uniform acceleration motion calculation method according to the set length of the product elimination area, when the elimination time is reached, the industrial personal computer sends an elimination instruction to an elimination device, the elimination device completes the elimination operation of unqualified products according to the received elimination instruction, wherein,
the product information image is collected and fed back to the industrial personal computer through an information collector arranged at the head end of the production line; each time point of the product moving on the production line is monitored and obtained by a plurality of photoelectric switches which are arranged on any one side of two sides of the production line at equal intervals; the length of the product rejecting area is the distance between the last photoelectric switch and the rejecting device, and when the product passes through the last photoelectric switch, the product enters the product rejecting area.
7. The method for removing the unqualified products in the variable speed assembly line environment of claim 6, wherein a product detection algorithm set by the industrial personal computer is to confirm that the products are unqualified through an image recognition algorithm based on deep learning and a preset character matching rule, wherein a character string of product information is obtained by realizing character positioning and characteristic extraction in an image through an East text detector and a trained CRNN model, the character string is subjected to character matching with a preset standard character string, and if the character string is not matched, the products are determined to be unqualified products.
8. The method for rejecting the unqualified products in the variable speed assembly line environment according to claim 7, wherein the industrial personal computer compares an image recognition result with a preset standard character string through a regular matching rule, if one character string is not matched, the unqualified product is determined to be rejected, and if the character string is identified to be qualified, the photoelectric switch ends tracking the corresponding product.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010363250.7A CN111570331B (en) | 2020-04-30 | 2020-04-30 | Unqualified product removing device and method under variable-speed assembly line environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010363250.7A CN111570331B (en) | 2020-04-30 | 2020-04-30 | Unqualified product removing device and method under variable-speed assembly line environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111570331A CN111570331A (en) | 2020-08-25 |
| CN111570331B true CN111570331B (en) | 2022-04-12 |
Family
ID=72117089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010363250.7A Active CN111570331B (en) | 2020-04-30 | 2020-04-30 | Unqualified product removing device and method under variable-speed assembly line environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111570331B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112024426A (en) * | 2020-09-01 | 2020-12-04 | 北京智通云联科技有限公司 | Multi-station visual identification system |
| CN113343923A (en) * | 2021-07-01 | 2021-09-03 | 江苏舆图信息科技有限公司 | Real-time river drainage port drainage state identification method based on video images |
| CN113333303A (en) * | 2021-07-02 | 2021-09-03 | 江西绿萌科技控股有限公司 | Fruit sorting device and method |
| CN113671891A (en) * | 2021-08-03 | 2021-11-19 | 合肥友高物联网标识设备有限公司 | Online detection rejection control method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103521460A (en) * | 2012-07-03 | 2014-01-22 | 梅特勒-托利多仪器（上海）有限公司 | High-speed and accurate automatic sorting method |
| CN104096700A (en) * | 2013-04-03 | 2014-10-15 | 上海超玛机电科技有限公司 | Elimination method for bottle washing machine |
| CN104326301A (en) * | 2014-08-28 | 2015-02-04 | 北京凌云光技术有限责任公司 | Defective tag automatic removing device and system using automatic removing device |
| CN105260734A (en) * | 2015-10-10 | 2016-01-20 | 燕山大学 | Commercial oil surface laser code recognition method with self modeling function |
| CN109174693A (en) * | 2018-10-23 | 2019-01-11 | 上海骄成机电设备有限公司 | A kind of synchronous method of linear sweep graph as acquisition system and device for eliminating |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9147326B2 (en) * | 2008-01-18 | 2015-09-29 | Sensors Incorporated | Encoder based speed compensated reject system and method |
| CN105149231B (en) * | 2015-09-15 | 2017-12-12 | 上海邮政科学研究院 | A kind of three-stage piece supplying table control method supporting for halved belt sorter |
-
2020
- 2020-04-30 CN CN202010363250.7A patent/CN111570331B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103521460A (en) * | 2012-07-03 | 2014-01-22 | 梅特勒-托利多仪器（上海）有限公司 | High-speed and accurate automatic sorting method |
| CN104096700A (en) * | 2013-04-03 | 2014-10-15 | 上海超玛机电科技有限公司 | Elimination method for bottle washing machine |
| CN104326301A (en) * | 2014-08-28 | 2015-02-04 | 北京凌云光技术有限责任公司 | Defective tag automatic removing device and system using automatic removing device |
| CN105260734A (en) * | 2015-10-10 | 2016-01-20 | 燕山大学 | Commercial oil surface laser code recognition method with self modeling function |
| CN109174693A (en) * | 2018-10-23 | 2019-01-11 | 上海骄成机电设备有限公司 | A kind of synchronous method of linear sweep graph as acquisition system and device for eliminating |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111570331A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111570331B (en) | Unqualified product removing device and method under variable-speed assembly line environment | |
| CN110852219B (en) | Multi-pedestrian cross-camera online tracking system | |
| CN104573637B (en) | License plate recognition method based on multiple cameras | |
| US10005107B2 (en) | Workpiece sorting system and method | |
| CN110570454B (en) | Method and device for detecting foreign matter invasion | |
| US10007836B2 (en) | Bird detection device, bird detection system, bird detection method, and program extracting a difference between the corrected images | |
| CN108388879A (en) | Mesh object detection method, device and storage medium | |
| EP0548893A2 (en) | Character segmentation using an associative memory for optical character recognition | |
| CN106874902B (en) | License plate information identification method and device | |
| CN109176513B (en) | A kind of method for inspecting and cruising inspection system of intelligent inspection robot | |
| EP3702957B1 (en) | Target detection method and apparatus, and computer device | |
| CN104463124A (en) | Milk box spray-printed character recognition method | |
| CN111767798B (en) | Intelligent broadcasting guide method and system for indoor networking video monitoring | |
| CN109948725B (en) | Neural network target detection device based on address-event expression | |
| CN111709935A (en) | Real-time coal gangue positioning and identifying method for ground moving belt | |
| CN107609489A (en) | Calligraphy writing path evaluation device, method and electronic equipment | |
| CN106372613A (en) | Test paper statistical method and apparatus | |
| CN104794480A (en) | Method for eliminating milk boxes with defective printed characters | |
| CN113688795A (en) | Method and device for converting table in image into electronic table | |
| CN102436578A (en) | Formation method for dog face characteristic detector as well as dog face detection method and device | |
| CN116630376A (en) | Unmanned aerial vehicle multi-target tracking method based on ByteTrack | |
| CN106407906B (en) | Face face recognition method | |
| CN112733680B (en) | Model training method, extraction method, device and terminal equipment for generating high-quality face image based on monitoring video stream | |
| CN117576597A (en) | Visual identification method and system based on unmanned aerial vehicle driving | |
| JPH07234943A (en) | Method and device for position recognition |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |