CN115780290A - Quick inspection method and equipment for injection molding product based on machine vision recognition - Google Patents
Quick inspection method and equipment for injection molding product based on machine vision recognition Download PDFInfo
- Publication number
- CN115780290A CN115780290A CN202211505334.5A CN202211505334A CN115780290A CN 115780290 A CN115780290 A CN 115780290A CN 202211505334 A CN202211505334 A CN 202211505334A CN 115780290 A CN115780290 A CN 115780290A
- Authority
- CN
- China
- Prior art keywords
- standard
- target
- shooting
- injection molding
- molding product
- 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.)
- Withdrawn
Links
- 238000001746 injection moulding Methods 0.000 title claims abstract description 154
- 238000007689 inspection Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000012899 standard injection Substances 0.000 claims abstract description 55
- 238000005516 engineering process Methods 0.000 claims abstract description 39
- 238000010835 comparative analysis Methods 0.000 claims abstract description 27
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000005477 standard model Effects 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 8
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 13
- 239000000243 solution Substances 0.000 description 11
- 239000007924 injection Substances 0.000 description 9
- 238000002347 injection Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 230000001360 synchronised effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Injection Moulding Of Plastics Or The Like (AREA)
Abstract
The embodiment of the invention relates to the technical field of injection molding product inspection, and particularly discloses a method and equipment for quickly inspecting an injection molding product based on machine vision identification. According to the embodiment of the invention, based on a binocular shooting technology, equidistant surrounding shooting is carried out on a standard injection molding product; determining standard feature points and constructing a standard three-dimensional model; performing equidistant surrounding shooting on a target injection molding product based on a binocular shooting technology; identifying target characteristic points and constructing a target three-dimensional model; and carrying out comparative analysis to judge whether the test is passed. The method has the advantages that the standard three-dimensional model can be built based on the standard characteristic points of the standard injection molding product, the target three-dimensional model is built based on the target characteristic points of the target injection molding product, the target three-dimensional model and the standard three-dimensional model are compared and analyzed, whether the target three-dimensional model passes the inspection or not is judged, so that the machine vision rapid inspection of the injection molding product is realized, all details of the injection molding product can be detected, the detection comprehensiveness is high, and the quality of the injection molding product can be comprehensively judged.
Description
Technical Field
The invention belongs to the technical field of injection molding product inspection, and particularly relates to a method and equipment for quickly inspecting an injection molding product based on machine vision identification.
Background
The injection molding product is a product which is formed by heating, plasticizing and melting plastic by an injection molding machine, injecting the plastic into a cavity of a forming mold for forming, cooling, solidifying and demolding the melt, and performing injection molding by the injection molding machine. The injection molding product is widely applied to all the fields of national economy such as transportation, packaging, post and telecommunications, communication, construction, household appliances, computers, aerospace, national defense tips and the like, and becomes indispensable production materials and consumption articles. The production of the injection molding product requires few molds, the required labor force is relatively low, the production efficiency of the injection molding product is high, and the waste of raw materials during injection molding is little.
The detection of the injection molding product is a process of detecting the quality of the injection molding product after the injection molding product is manufactured. The existing detection of injection molding products is generally that technical personnel carry out detection and judgment of qualified sizes in a mode of combining manual measurement through manual visual inspection, but the detection of all details of the injection molding products is difficult to realize in the process of manual detection due to the complex shapes of the injection molding products, so that the detection comprehensiveness is not high, and the quality of the injection molding products cannot be comprehensively judged.
Disclosure of Invention
The embodiment of the invention aims to provide a method and equipment for quickly inspecting an injection molding product based on machine vision identification, and aims to solve the problems in the background art.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:
a quick inspection method for injection molding products based on machine vision identification specifically comprises the following steps:
based on a binocular shooting technology, carrying out equidistant surrounding shooting on a standard injection molding product to obtain standard shooting data of the standard injection molding product;
analyzing the standard shooting data, determining standard characteristic points, and constructing a standard three-dimensional model;
performing equidistant surrounding shooting on a target injection molding product based on a binocular shooting technology to obtain target shooting data of the target injection molding product;
analyzing the target shooting data, identifying target characteristic points, and constructing a target three-dimensional model;
and comparing and analyzing the target three-dimensional model based on the standard three-dimensional model, and judging whether the target three-dimensional model passes the inspection according to a comparison and analysis result.
As a further limitation of the technical solution of the embodiment of the present invention, the performing equidistant surround shooting on a standard injection molded product based on a binocular shooting technology to obtain standard shooting data of the standard injection molded product specifically includes the following steps:
after clamping the standard injection molding product, generating a standard clamping signal;
generating a standard surrounding shooting signal according to the standard clamping signal;
driving the standard injection molding product to rotate intermittently according to the standard surrounding shooting signal;
and based on a binocular shooting technology, carrying out intermittent shooting on the standard injection molding product according to the standard surrounding shooting signal to obtain standard shooting data.
As a further limitation of the technical solution of the embodiment of the present invention, the analyzing the standard shooting data, determining the standard feature points, and constructing the standard three-dimensional model specifically includes the following steps:
analyzing the standard shooting data, and determining standard characteristic points marked in advance;
constructing a space coordinate system by taking the standard characteristic points as an origin;
and constructing a standard three-dimensional model in the space coordinate system according to the standard shooting data.
As a further limitation of the technical solution of the embodiment of the present invention, the performing equidistant surround shooting on the target injection molded product based on the binocular shooting technology to obtain the target shooting data of the target injection molded product specifically includes the following steps:
after clamping the target injection molding product, generating a target clamping signal;
generating a target surrounding shooting signal according to the target clamping signal;
driving the target injection molding product to rotate intermittently according to the target surrounding shooting signal;
and based on a binocular shooting technology, intermittently shooting the target injection molding product according to the target surrounding shooting signal to obtain target shooting data.
As a further limitation of the technical solution of the embodiment of the present invention, the analyzing the target shooting data, identifying the target feature points, and constructing the target three-dimensional model specifically includes the following steps:
analyzing the target shooting data, and identifying target characteristic points corresponding to the standard characteristic points;
constructing a space coordinate system by taking the target characteristic point as an origin;
and constructing a target three-dimensional model in the space coordinate system according to the target shooting data.
As a further limitation of the technical solution of the embodiment of the present invention, the comparing and analyzing the target three-dimensional model based on the standard three-dimensional model, and determining whether the inspection is passed or not according to the comparing and analyzing result specifically includes the following steps:
the target feature points and the standard feature points are overlapped, and the target three-dimensional model is compared and analyzed based on the standard three-dimensional model to generate a comparative analysis result;
judging whether the models are overlapped or not according to the comparative analysis result;
when the models are not coincident, calculating an offset distance;
comparing the offset distance with a preset qualified distance;
and when the offset distance is smaller than the qualified distance, judging that the inspection is passed.
An injection molding product rapid inspection equipment based on machine vision discernment, the equipment includes that the standard encircles shooting unit, standard model construction unit, target encircle shooting unit, target model construction unit and inspection pass judgement unit, wherein:
the standard surrounding shooting unit is used for carrying out equidistant surrounding shooting on a standard injection molding product based on a binocular shooting technology to obtain standard shooting data of the standard injection molding product;
the standard model building unit is used for analyzing the standard shooting data, determining standard characteristic points and building a standard three-dimensional model;
the target surrounding shooting unit is used for carrying out equidistant surrounding shooting on a target injection molding product based on a binocular shooting technology and acquiring target shooting data of the target injection molding product;
the target model building unit is used for analyzing the target shooting data, identifying target characteristic points and building a target three-dimensional model;
and the inspection passing judgment unit is used for carrying out comparative analysis on the target three-dimensional model based on the standard three-dimensional model and judging whether the inspection is passed or not according to a comparative analysis result.
As a further limitation of the technical solution of the embodiment of the present invention, the standard surround shooting unit specifically includes:
the first signal generation module is used for generating a standard clamping signal after clamping the standard injection molding product;
the second signal generation module is used for generating a standard surrounding shooting signal according to the standard clamping signal;
the intermittent rotation module is used for driving the standard injection molding product to rotate intermittently according to the standard surrounding shooting signal;
and the intermittent shooting module is used for carrying out intermittent shooting on the standard injection molding product according to the standard surrounding shooting signal based on a binocular shooting technology to obtain standard shooting data.
As a further limitation of the technical solution of the embodiment of the present invention, the standard model building unit specifically includes:
the characteristic point determining module is used for analyzing the standard shooting data and determining a standard characteristic point marked in advance;
the coordinate system construction module is used for constructing a space coordinate system by taking the standard characteristic points as an origin;
and the model building module is used for building a standard three-dimensional model in the space coordinate system according to the standard shooting data.
As a further limitation of the technical solution of the embodiment of the present invention, the checking pass judging unit specifically includes:
the comparison analysis module is used for superposing the target characteristic points and the standard characteristic points, performing comparison analysis on the target three-dimensional model based on the standard three-dimensional model and generating a comparison analysis result;
the coincidence judgment module is used for judging whether the models coincide or not according to the comparative analysis result;
the offset calculation module is used for calculating an offset distance when the models are not overlapped;
the distance comparison module is used for comparing the offset distance with a preset qualified distance;
and the passing inspection module is used for judging that the inspection is passed when the offset distance is smaller than the qualified distance.
Compared with the prior art, the invention has the beneficial effects that:
according to the embodiment of the invention, based on a binocular shooting technology, equidistant surrounding shooting is carried out on a standard injection molding product; determining standard feature points and constructing a standard three-dimensional model; performing equidistant surrounding shooting on a target injection molding product based on a binocular shooting technology; identifying target characteristic points and constructing a target three-dimensional model; and carrying out comparative analysis to judge whether the test is passed. The method has the advantages that the standard three-dimensional model can be built based on the standard characteristic points of the standard injection molding product, the target three-dimensional model is built based on the target characteristic points of the target injection molding product, the target three-dimensional model and the standard three-dimensional model are compared and analyzed, whether the target three-dimensional model passes the inspection or not is judged, accordingly, the machine vision rapid inspection of the injection molding product is realized, all details of the injection molding product can be detected, the detection comprehensiveness is high, and the quality of the injection molding product can be comprehensively judged.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 shows a flow chart of a method provided by an embodiment of the invention.
Fig. 2 shows a flowchart of a standard injection-molded article photographing method according to an embodiment of the present invention.
Fig. 3 shows a flow chart of building a standard three-dimensional model in the method provided by the embodiment of the invention.
FIG. 4 shows a flow chart of a target injection molded article shot in a method provided by an embodiment of the invention.
FIG. 5 is a flow chart illustrating the construction of a three-dimensional model of an object in the method according to the embodiment of the present invention.
Fig. 6 shows a flowchart for determining whether the test is passed in the method provided by the embodiment of the present invention.
Fig. 7 shows an application architecture diagram of the apparatus provided by the embodiment of the present invention.
Fig. 8 is a block diagram showing a structure of a standard surround photographing unit in the apparatus according to the embodiment of the present invention.
Fig. 9 shows a block diagram of a standard model building unit in the device according to the embodiment of the present invention.
Fig. 10 shows a block diagram of a check-pass judging unit in the apparatus according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It can be understood that, in the prior art, the detection of the injection molding product is usually performed by a technician in combination with a manual measurement mode through manual visual inspection, but due to the complicated shape of the injection molding product, the detection of all details of the injection molding product is difficult to realize in the manual detection process, so that the detection comprehensiveness is not high, and the quality of the injection molding product cannot be comprehensively judged.
In order to solve the problems, the embodiment of the invention carries out equidistant surrounding shooting on a standard injection molding product based on a binocular shooting technology; determining standard feature points and constructing a standard three-dimensional model; performing equidistant surrounding shooting on a target injection molding product based on a binocular shooting technology; identifying target characteristic points and constructing a target three-dimensional model; and carrying out comparative analysis to judge whether the test is passed. The method has the advantages that the standard three-dimensional model can be built based on the standard characteristic points of the standard injection molding product, the target three-dimensional model is built based on the target characteristic points of the target injection molding product, the target three-dimensional model and the standard three-dimensional model are compared and analyzed, whether the target three-dimensional model passes the inspection or not is judged, so that the machine vision rapid inspection of the injection molding product is realized, all details of the injection molding product can be detected, the detection comprehensiveness is high, and the quality of the injection molding product can be comprehensively judged.
Fig. 1 shows a flow chart of a method provided by an embodiment of the invention.
Specifically, the method for quickly inspecting the injection molding product based on machine vision identification specifically comprises the following steps:
and S101, performing equidistant surrounding shooting on a standard injection molding product based on a binocular shooting technology, and acquiring standard shooting data of the standard injection molding product.
In the embodiment of the invention, before the processing of the injection molding product, a standard injection molding product corresponding to the model of the injection molding product to be processed is obtained, the standard injection molding product is clamped at a shooting position to generate a standard clamping signal, a corresponding standard surrounding shooting signal is generated according to the standard clamping signal, the clamped standard injection molding product is driven to rotate intermittently according to the standard surrounding shooting signal, meanwhile, based on a binocular shooting technology, the clamped standard injection molding product is shot intermittently according to the standard surrounding shooting signal, and the intermittent shooting and the intermittent rotation are kept synchronous to obtain standard shooting data related to the standard injection molding product.
It can be understood that the binocular shooting technology is an important form of machine vision, and is a method for acquiring three-dimensional geometric information of an object from a plurality of images based on a parallax principle, two digital images of the object to be measured are generally acquired by two cameras from different angles at the same time, or two digital images of the object to be measured are acquired by a single camera from different angles at different times, the three-dimensional geometric information of the object is restored based on the parallax principle, and the three-dimensional contour and position of the object are reconstructed, so that the binocular shooting technology has a wide application prospect in the field of machine vision.
Specifically, fig. 2 shows a flowchart of standard injection-molded product shooting in the method provided by the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the performing equidistant surround shooting on a standard injection molded product based on a binocular shooting technology to obtain standard shooting data of the standard injection molded product specifically includes the following steps:
step S1011, after the standard injection molding product is clamped, a standard clamping signal is generated.
And step S1012, generating a standard surrounding shooting signal according to the standard clamping signal.
And S1013, driving the standard injection molding product to intermittently rotate according to the standard surrounding shooting signal.
And S1014, based on a binocular shooting technology, intermittently shooting the standard injection molding product according to the standard surrounding shooting signal to obtain standard shooting data.
Further, the injection molding product rapid inspection method based on machine vision recognition further comprises the following steps:
and S102, analyzing the standard shooting data, determining standard characteristic points, and constructing a standard three-dimensional model.
In the embodiment of the invention, standard shooting data are analyzed to determine standard characteristic points for marking standard injection-molded products in advance, a space coordinate system is constructed by taking the standard characteristic points as the original points, and a standard three-dimensional model of the standard injection-molded products is constructed by identifying the space size of the standard injection-molded products in the standard shooting data and carrying out substitution and visual display in the space coordinate system.
Specifically, fig. 3 shows a flowchart for constructing a standard three-dimensional model in the method provided by the embodiment of the invention.
In a preferred embodiment provided by the present invention, the analyzing the standard shooting data, determining standard feature points, and constructing a standard three-dimensional model specifically includes the following steps:
and step S1021, analyzing the standard shooting data and determining a standard feature point marked in advance.
And step S1022, constructing a space coordinate system by taking the standard feature points as an origin.
And S1023, constructing a standard three-dimensional model in the space coordinate system according to the standard shooting data.
Further, the injection molding product rapid inspection method based on machine vision recognition further comprises the following steps:
and S103, carrying out equidistant surrounding shooting on the target injection molding product based on a binocular shooting technology, and acquiring target shooting data of the target injection molding product.
In the embodiment of the invention, when the processing of the injection molding product is carried out, after the processing of a target injection molding product is finished, the target injection molding product is placed at a shooting position to be clamped, a target clamping signal is generated, a corresponding target surrounding shooting signal is generated according to the target clamping signal, the clamped target injection molding product is driven to rotate intermittently according to the target surrounding shooting signal, meanwhile, based on a binocular shooting technology, the clamped target injection molding product is shot intermittently according to the target surrounding shooting signal, and the intermittent shooting and the intermittent rotation are kept synchronous, so that target shooting data related to the target injection molding product are obtained.
Specifically, fig. 4 shows a flowchart of shooting a target injection molding product in the method provided by the embodiment of the invention.
In a preferred embodiment provided by the present invention, the performing equidistant surrounding shooting on a target injection molded product based on a binocular shooting technology, and acquiring target shooting data of the target injection molded product specifically includes the following steps:
and step S1031, after clamping the target injection molding product, generating a target clamping signal.
And step S1032, generating a target surrounding shooting signal according to the target clamping signal.
And step S1033, driving the target injection molding product to rotate intermittently according to the target surrounding shooting signal.
And S1034, based on a binocular shooting technology, intermittently shooting the target injection molding product according to the target surrounding shooting signal to obtain target shooting data.
Further, the injection molding product rapid inspection method based on machine vision recognition further comprises the following steps:
and step S104, analyzing the target shooting data, identifying target characteristic points and constructing a target three-dimensional model.
In the embodiment of the invention, the target shooting data is analyzed to identify the target characteristic points corresponding to the standard characteristic points in the target injection molding product, a space coordinate system is constructed by taking the target characteristic points as the original points, and the space size of the target injection molding product in the target shooting data is identified, so that substitution and visual display are carried out in the space coordinate system to construct the target three-dimensional model of the target injection molding product.
Specifically, fig. 5 shows a flowchart for constructing a target three-dimensional model in the method provided by the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the analyzing the target shooting data, identifying the target feature points, and constructing the target three-dimensional model specifically includes the following steps:
and step S1041, analyzing the target shooting data, and identifying target feature points corresponding to the standard feature points.
And step S1042, constructing a space coordinate system by taking the target feature point as an origin.
And S1043, constructing a target three-dimensional model in the space coordinate system according to the target shooting data.
Further, the injection molding product rapid inspection method based on machine vision recognition further comprises the following steps:
and S105, comparing and analyzing the target three-dimensional model based on the standard three-dimensional model, and judging whether the target three-dimensional model passes the inspection or not according to a comparison and analysis result.
In the embodiment of the invention, the target characteristic point and the standard characteristic point are coincided, so that the target three-dimensional model and the standard three-dimensional model are in the same space coordinate system, a comparative analysis result is generated by carrying out comparative analysis on the target three-dimensional model and the standard three-dimensional model, whether the target three-dimensional model and the standard three-dimensional model are coincided or not is judged according to the comparative analysis result, and if the target three-dimensional model and the standard three-dimensional model are coincided, the target three-dimensional model and the standard three-dimensional model are judged to be passed through the inspection; if the target three-dimensional model is not coincident with the standard three-dimensional model, marking the maximum offset position of the target three-dimensional model and the standard three-dimensional model, calculating an offset distance, comparing the offset distance with a preset qualified distance, and if the offset distance is smaller than the qualified distance, judging that the inspection is passed; and if the offset distance is not less than the qualified distance, judging that the inspection is not passed.
Specifically, fig. 6 shows a flowchart for determining whether the test is passed in the method provided in the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the comparing and analyzing the target three-dimensional model based on the standard three-dimensional model, and determining whether the target three-dimensional model passes the inspection according to a result of the comparing and analyzing specifically includes the following steps:
step S1051, the target characteristic points and the standard characteristic points are overlapped, and the target three-dimensional model is compared and analyzed based on the standard three-dimensional model to generate a comparative analysis result.
And step S1052, judging whether the models are overlapped or not according to the comparison and analysis result.
Step S1053, when the models do not overlap, calculates the offset distance.
Step S1054, comparing the offset distance with a preset qualified distance.
And step S1055, judging that the inspection is passed when the offset distance is smaller than the qualified distance.
Further, fig. 7 shows an application architecture diagram of the apparatus provided by the embodiment of the present invention.
Among others, in still another preferred embodiment provided by the present invention, an injection molded article rapid inspection apparatus based on machine vision recognition includes:
and the standard surrounding shooting unit 101 is used for carrying out equidistant surrounding shooting on the standard injection molding product based on a binocular shooting technology and acquiring standard shooting data of the standard injection molding product.
In the embodiment of the invention, before the processing of the injection molding product, a standard injection molding product corresponding to the model of the injection molding product to be processed is obtained, after the standard injection molding product is clamped at a shooting position, the standard surrounding shooting unit 101 generates a standard clamping signal, further, a corresponding standard surrounding shooting signal is generated according to the standard clamping signal, the clamped standard injection molding product is driven to rotate intermittently according to the standard surrounding shooting signal, meanwhile, based on a binocular shooting technology, the clamped standard injection molding product is shot intermittently according to the standard surrounding shooting signal, and the intermittent shooting and the intermittent rotation are kept synchronous, so that standard shooting data related to the standard injection molding product are obtained.
Specifically, fig. 8 shows a block diagram of a standard surround shooting unit 101 in the device according to the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the standard surround shooting unit 101 specifically includes:
the first signal generating module 1011 is configured to generate a standard clamping signal after clamping the standard injection molding product.
And a second signal generating module 1012, configured to generate a standard surround shooting signal according to the standard clamping signal.
And the intermittent rotation module 1013 is used for driving the standard injection molding product to rotate intermittently according to the standard surrounding shooting signal.
And the intermittent shooting module 1014 is used for performing intermittent shooting on the standard injection molding product according to the standard surrounding shooting signal based on a binocular shooting technology to obtain standard shooting data.
Further, the injection molding product rapid inspection equipment based on machine vision recognition still includes:
and the standard model building unit 102 is used for analyzing the standard shooting data, determining standard feature points and building a standard three-dimensional model.
In the embodiment of the present invention, the standard model building unit 102 analyzes the standard shooting data, determines a standard feature point that is used for marking a standard injection molding product in advance, constructs a spatial coordinate system with the standard feature point as an origin, and substitutes and visually displays the spatial size of the standard injection molding product in the standard shooting data in the spatial coordinate system to construct a standard three-dimensional model of the standard injection molding product.
Specifically, fig. 9 shows a block diagram of a structure of the standard model building unit 102 in the device according to the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the standard model building unit 102 specifically includes:
a feature point determining module 1021, configured to analyze the standard shooting data and determine a pre-marked standard feature point.
A coordinate system constructing module 1022, configured to construct a spatial coordinate system with the standard feature point as an origin.
And the model building module 1023 is used for building a standard three-dimensional model in the space coordinate system according to the standard shooting data.
Further, the injection molding product rapid inspection equipment based on machine vision recognition still includes:
and the target surrounding shooting unit 103 is used for carrying out equidistant surrounding shooting on the target injection molding product based on a binocular shooting technology and acquiring target shooting data of the target injection molding product.
In the embodiment of the invention, when the processing of the injection molding product is performed, after the processing of a target injection molding product is completed, the target injection molding product is placed at a shooting position for clamping, the target surrounding shooting unit 103 generates a target clamping signal, further generates a corresponding target surrounding shooting signal according to the target clamping signal, drives the clamped target injection molding product to intermittently rotate according to the target surrounding shooting signal, and simultaneously performs intermittent shooting on the clamped target injection molding product according to the target surrounding shooting signal based on a binocular shooting technology, and the intermittent shooting and the intermittent rotation are kept synchronous to obtain target shooting data related to the target injection molding product.
And the target model building unit 104 is configured to analyze the target shooting data, identify target feature points, and build a target three-dimensional model.
In the embodiment of the present invention, the target model building unit 104 identifies the target feature points corresponding to the standard feature points in the target injection molded product by analyzing the target shooting data, and builds the spatial coordinate system with the target feature points as the origin, and the target model building unit 104 substitutes and visually displays the spatial dimensions of the target injection molded product in the target shooting data in the spatial coordinate system to build the target three-dimensional model of the target injection molded product.
And the inspection pass judging unit 105 is used for performing comparative analysis on the target three-dimensional model based on the standard three-dimensional model and judging whether the inspection pass is performed or not according to a comparative analysis result.
In the embodiment of the present invention, the inspection pass determination unit 105 coincides the target feature point with the standard feature point, so that the target three-dimensional model and the standard three-dimensional model are in the same spatial coordinate system, and further performs comparative analysis on the target three-dimensional model and the standard three-dimensional model to generate a comparative analysis result, and determines whether the target three-dimensional model and the standard three-dimensional model coincide or not according to the comparative analysis result, and if the target three-dimensional model and the standard three-dimensional model coincide, it determines that the inspection pass; if the target three-dimensional model is not coincident with the standard three-dimensional model, marking the maximum offset position of the target three-dimensional model and the standard three-dimensional model, calculating an offset distance, comparing the offset distance with a preset qualified distance, and if the offset distance is smaller than the qualified distance, judging that the inspection is passed; and if the offset distance is not less than the qualified distance, judging that the inspection is not passed.
Specifically, fig. 10 shows a block diagram of the structure of the check passage determining unit 105 in the apparatus provided in the embodiment of the present invention.
In a preferred embodiment of the present invention, the inspection passing determining unit 105 specifically includes:
the comparative analysis module 1051 is configured to overlap the target feature points and the standard feature points, perform comparative analysis on the target three-dimensional model based on the standard three-dimensional model, and generate a comparative analysis result.
And an overlap determining module 1052, configured to determine whether the models overlap according to the comparison and analysis result.
An offset calculation module 1053, configured to calculate an offset distance when the models do not coincide.
A distance comparison module 1054 for comparing the offset distance with a predetermined qualified distance.
A pass verification module 1055 for determining a verification pass if the offset distance is less than the qualified distance.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a portion of sub-steps or stages of other steps.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a non-volatile computer readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct Rambus Dynamic RAM (DRDRAM), and Rambus Dynamic RAM (RDRAM), among others.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A quick inspection method for injection molding products based on machine vision recognition is characterized by comprising the following steps:
based on a binocular shooting technology, carrying out equidistant surrounding shooting on a standard injection molding product to obtain standard shooting data of the standard injection molding product;
analyzing the standard shooting data, determining standard characteristic points, and constructing a standard three-dimensional model;
performing equidistant surrounding shooting on a target injection molding product based on a binocular shooting technology to obtain target shooting data of the target injection molding product;
analyzing the target shooting data, identifying target characteristic points, and constructing a target three-dimensional model;
and comparing and analyzing the target three-dimensional model based on the standard three-dimensional model, and judging whether the target three-dimensional model passes the inspection according to a comparison and analysis result.
2. The machine-vision-recognition-based injection molding product rapid inspection method according to claim 1, wherein the binocular shooting-based technology is used for shooting a standard injection molding product in an equidistant surrounding manner, and the step of acquiring standard shooting data of the standard injection molding product specifically comprises the following steps:
after clamping the standard injection molding product, generating a standard clamping signal;
generating a standard surrounding shooting signal according to the standard clamping signal;
driving the standard injection molding product to rotate intermittently according to the standard surrounding shooting signal;
and based on a binocular shooting technology, carrying out intermittent shooting on the standard injection molding product according to the standard surrounding shooting signal to obtain standard shooting data.
3. The machine vision recognition-based injection molding product rapid inspection method according to claim 1, wherein the step of analyzing the standard shot data to determine standard feature points and constructing a standard three-dimensional model specifically comprises the steps of:
analyzing the standard shooting data, and determining a pre-marked standard feature point;
constructing a space coordinate system by taking the standard feature points as an origin;
and constructing a standard three-dimensional model in the space coordinate system according to the standard shooting data.
4. The machine-vision-recognition-based injection molding product rapid inspection method as claimed in claim 1, wherein the binocular shooting technology-based equidistant surround shooting of a target injection molding product and acquiring target shooting data of the target injection molding product specifically comprises the following steps:
after clamping the target injection molding product, generating a target clamping signal;
generating a target surrounding shooting signal according to the target clamping signal;
driving the target injection molding product to intermittently rotate according to the target surrounding shooting signal;
and based on a binocular shooting technology, intermittently shooting the target injection molding product according to the target surrounding shooting signal to obtain target shooting data.
5. The machine-vision-recognition-based injection molding product rapid inspection method according to claim 1, wherein the step of analyzing the target shot data, recognizing target feature points and constructing a target three-dimensional model specifically comprises the following steps:
analyzing the target shooting data, and identifying target characteristic points corresponding to the standard characteristic points;
constructing a space coordinate system by taking the target characteristic point as an origin;
and constructing a target three-dimensional model in the space coordinate system according to the target shooting data.
6. The machine vision recognition-based injection molding product rapid inspection method according to claim 1, wherein the step of performing comparative analysis on the target three-dimensional model based on the standard three-dimensional model and judging whether the inspection is passed or not according to the comparative analysis result specifically comprises the following steps:
the target feature points and the standard feature points are overlapped, and the target three-dimensional model is compared and analyzed based on the standard three-dimensional model to generate a comparative analysis result;
judging whether the models are overlapped or not according to the comparative analysis result;
when the models are not coincident, calculating an offset distance;
comparing the offset distance with a preset qualified distance;
and when the offset distance is smaller than the qualified distance, judging that the inspection is passed.
7. The utility model provides an injection molding quick check out test set based on machine vision discernment which characterized in that, equipment includes that the standard encircles shooting unit, standard model construction unit, target and encircles shooting unit, target model construction unit and inspection and pass the judgement unit, wherein:
the standard surrounding shooting unit is used for carrying out equidistant surrounding shooting on a standard injection molding product based on a binocular shooting technology to obtain standard shooting data of the standard injection molding product;
the standard model building unit is used for analyzing the standard shooting data, determining standard characteristic points and building a standard three-dimensional model;
the target surrounding shooting unit is used for carrying out equidistant surrounding shooting on a target injection molding product based on a binocular shooting technology to obtain target shooting data of the target injection molding product;
the target model building unit is used for analyzing the target shooting data, identifying target characteristic points and building a target three-dimensional model;
and the inspection passing judgment unit is used for carrying out comparative analysis on the target three-dimensional model based on the standard three-dimensional model and judging whether the inspection is passed or not according to a comparative analysis result.
8. The machine-vision-recognition-based injection molding product rapid inspection apparatus according to claim 7, wherein the standard surround shooting unit specifically comprises:
the first signal generation module is used for generating a standard clamping signal after clamping the standard injection molding product;
the second signal generation module is used for generating a standard surrounding shooting signal according to the standard clamping signal;
the intermittent rotation module is used for driving the standard injection molding product to rotate intermittently according to the standard surrounding shooting signal;
and the intermittent shooting module is used for performing intermittent shooting on the standard injection molding product according to the standard surrounding shooting signal based on a binocular shooting technology to obtain standard shooting data.
9. An injection molding article rapid inspection apparatus based on machine vision recognition as claimed in claim 7, wherein said standard model building unit specifically comprises:
the characteristic point determining module is used for analyzing the standard shooting data and determining a pre-marked standard characteristic point;
the coordinate system construction module is used for constructing a space coordinate system by taking the standard characteristic points as an origin;
and the model building module is used for building a standard three-dimensional model in the space coordinate system according to the standard shooting data.
10. The machine-vision-recognition-based injection molding product rapid inspection apparatus according to claim 7, wherein the inspection passing determination unit specifically comprises:
the comparison analysis module is used for superposing the target characteristic points and the standard characteristic points, and performing comparison analysis on the target three-dimensional model based on the standard three-dimensional model to generate a comparison analysis result;
the coincidence judgment module is used for judging whether the models coincide or not according to the comparative analysis result;
the offset calculation module is used for calculating an offset distance when the models are not overlapped;
the distance comparison module is used for comparing the offset distance with a preset qualified distance;
and the passing inspection module is used for judging that the inspection is passed when the offset distance is smaller than the qualified distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211505334.5A CN115780290A (en) | 2022-11-28 | 2022-11-28 | Quick inspection method and equipment for injection molding product based on machine vision recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211505334.5A CN115780290A (en) | 2022-11-28 | 2022-11-28 | Quick inspection method and equipment for injection molding product based on machine vision recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115780290A true CN115780290A (en) | 2023-03-14 |
Family
ID=85442556
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211505334.5A Withdrawn CN115780290A (en) | 2022-11-28 | 2022-11-28 | Quick inspection method and equipment for injection molding product based on machine vision recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115780290A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116342602A (en) * | 2023-05-30 | 2023-06-27 | 四川都得利管业有限公司 | Fine detection method and system for production quality of plastic pipe |
-
2022
- 2022-11-28 CN CN202211505334.5A patent/CN115780290A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116342602A (en) * | 2023-05-30 | 2023-06-27 | 四川都得利管业有限公司 | Fine detection method and system for production quality of plastic pipe |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115780290A (en) | Quick inspection method and equipment for injection molding product based on machine vision recognition | |
| JP6532845B2 (en) | Measuring device, measuring method, program | |
| NL2026165B1 (en) | Method for analyzing tensile failure performance of 3d printing sample | |
| CN103552224B (en) | Injection compression molding optical-grade transparent quality of item online test method | |
| Li et al. | Modeling and simulation of compression molding process for sheet molding compound (SMC) of chopped carbon fiber composites | |
| JP6779316B2 (en) | Molding condition estimation method for injection molding machine | |
| US9969109B2 (en) | Injection molding system | |
| Kazmer et al. | Feasibility analysis of an in-mold multivariate sensor | |
| US20220001586A1 (en) | Method and system for improving a physical production process | |
| CN111212280B (en) | Method and system for testing depth camera module, computer equipment and storage medium | |
| Zhang et al. | Automated vision-based inspection of mould and part quality in soft tooling injection moulding using imaging and deep learning | |
| Loftis et al. | Online quality monitoring of plastic parts using real-time data from an injection molding machine | |
| CN116223529A (en) | Intelligent detection method and system for production of film-pressed gloves | |
| JP2020140365A (en) | Product quality defect prediction system | |
| CN213166722U (en) | Mould warm-pressing monitoring device | |
| KR102558232B1 (en) | Space filling curve transformation method and system for deep learning analysis of manufacturing time series data | |
| CN104772879A (en) | Micro injection molding melt flow behavior visualized analysis detection system and method | |
| CN204701097U (en) | Micro injection molding melt flow behavior visual analyzing detection system | |
| KR102314599B1 (en) | quality inspection apparatus for gas injection molding products and method thereof | |
| CN114734601B (en) | Product flaw online detection method in injection molding process | |
| CN114219035A (en) | Multi-sensor data fusion method and device | |
| CN114829102A (en) | Learning model generation method, computer program, set value determination device, molding machine, and molding device system | |
| Mavi et al. | Identify defects in gears using digital image processing | |
| JP2017113981A (en) | Method and apparatus for supporting design of molding, computer software and storage medium | |
| JP7512626B2 (en) | Molded product judgment device, molded product judgment method, and molded product judgment program |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230314 |
|
| WW01 | Invention patent application withdrawn after publication |