A defect detection system for automotive plastic injection molded parts based on machine vision technology
Through machine vision technology, the surface and internal defects of automotive plastic injection molded parts are comprehensively detected, which solves the problem that existing systems cannot detect internal bubbles and require manual intervention, and achieves efficient and accurate defect detection, improving product quality and production efficiency.
Patent Information
- Application Number
- CN202410630365.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-21
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-05-21
AI Technical Summary
The existing automotive plastic injection molded parts defect detection system cannot fully detect product quality, ignore internal bubble problems, only focus on surface defects, and require manual intervention to lead to inaccurate detection and low production efficiency.
Using a detection system based on machine vision technology, the image acquisition, data acquisition and analysis modules are used to detect surface cracks, internal bubbles, through hole specifications and defects at the mold casting port cutting of the injection molded parts to achieve the overall and local defects of the injection molded parts. Analysis, reduce manual intervention.
It improves the stability and qualification of product quality, reduces the generation of defective products, saves human resources and time costs, and improves production efficiency.
Smart Images

Figure CN118549436B_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of automobile plastic injection molded part defect detection, in particular to an automobile plastic injection molded part defect detection system based on machine vision technology. Background Art
[0002] With the rapid development of the automobile manufacturing industry, the quality requirements for automobile plastic injection molded parts are getting higher and higher. As an important part of the automobile, the quality of automobile plastic injection molded parts directly affects the performance and safety of the automobile. Therefore, defect detection of automobile plastic injection molded parts is an important part of ensuring automobile quality, but the existing automobile plastic injection molded parts defect detection system cannot meet the growing needs.
[0003] The existing automotive plastic injection molding defect detection system has the following problems: First, the existing automotive plastic injection molding defect detection system may only focus on a single defect type, such as surface defects of automotive plastic injection molding parts, thereby ignoring other possible defects, such as internal bubbles in automotive plastic injection molding parts, etc., and cannot comprehensively detect product quality problems, resulting in unqualified products entering the market, which in turn creates safety hazards in subsequent use.
[0004] Second, the existing defect detection system for automobile plastic injection molded parts may be limited to analyzing the permeability of the through-hole and the specifications and dimensions of the through-hole, without considering the smoothness of the inner surface of the through-hole, which reduces the qualification of automobile plastic injection molded parts.
[0005] Third, the existing defect detection system for automobile plastic injection molding parts requires manual intervention for detection at the cutting point of the mold pouring gate of automobile plastic injection molding parts, which may lead to inaccurate detection results, increase labor costs and reduce production efficiency. Summary of the invention
[0006] In view of this, in order to solve the problems raised in the above background technology, a defect detection system for automobile plastic injection molded parts based on machine vision technology is proposed.
[0007] The purpose of the present invention can be achieved through the following technical solutions: A defect detection system for automotive plastic injection molded parts based on machine vision technology, comprising the following modules: an injection molded part image acquisition module: used to extract some samples from the injection molded parts to be inspected, record them as each injection molded part to be inspected, divide each injection molded part to be inspected into regions according to the component distribution area, obtain images of each region of each injection molded part to be inspected, and obtain the surface crack area and internal bubble volume of each region of each injection molded part to be inspected.
[0008] Injection molding data acquisition module: used to collect the brightness, saturation and hue corresponding to the surface color of each area of each injection molded part to be tested and the injection molding data of each injection molded part to be tested. The injection molding data includes injection molding temperature, injection molding pressure and injection molding speed.
[0009] Injection molded parts overall defect analysis module: used to analyze the crack defect, internal bubble defect, surface color defect and deformation of each injection molded part to be tested, and then obtain the overall defect of each injection molded part to be tested.
[0010] Injection molded parts through-hole analysis module: used to obtain the specifications of each through-hole of each injection molded part to be tested, the maximum height length of the protrusion on the inner surface of each through-hole and the total area of the inner surface occupied, as well as the light intensity and light area after the light passes through each through-hole, so as to obtain the conformity of each through-hole of each injection molded part to be tested.
[0011] Mold pouring gate analysis module: used to obtain images of the mold pouring gate of each injection molded part to be inspected, obtain the defect area of the mold pouring gate of each injection molded part to be inspected and the height difference at each inspection point, and comprehensively analyze to obtain the cutting qualification of each injection molded part to be inspected.
[0012] Injection molded parts local defect analysis module: used to analyze the conformity of each through hole of each injection molded part to be tested and the cutting conformity of each injection molded part to be tested, and obtain the local defect degree of each injection molded part to be tested.
[0013] Early warning module: used to analyze the overall defect degree of each injection molded part to be inspected and the local defect degree of each injection molded part to be inspected, and to issue an early warning.
[0014] Database: used to store the surface area, volume, brightness, saturation and hue of each area of standard automobile plastic injection molding parts, and the standard specifications, inner surface area and circular area of each through hole of standard automobile plastic injection molding parts.
[0015] In an alternative embodiment, the crack defect degree of each injection molded part to be inspected is analyzed as follows: an image of each region of each injection molded part to be inspected is acquired by image acquisition technology to obtain a grayscale image of each region of each injection molded part to be inspected, and then the surface crack area of each region of each injection molded part to be inspected is obtained, which is recorded as i represents the number of the i-th injection molded part to be inspected, i=1, 2, ..., j, a represents the number of the a-th area, a=1, 2, ..., b.
[0016] The surface area of each region of the standard automobile plastic injection molded part is extracted from the database and recorded as S a , compare the surface crack area of each region of each injection molded part to be tested with the surface area of each region of the standard automobile plastic injection molded part, and use the formula Get the crack defect degree δ of each injection molded part to be tested i , b represents the number of regions.
[0017] In an alternative embodiment, the internal bubble defect analysis of each injection molded part to be inspected is as follows: each injection molded part to be inspected is scanned by computer segment scanning technology to obtain a three-dimensional image of each area of each injection molded part to be inspected, and the total volume of internal bubbles in each area of each injection molded part to be inspected is obtained, which is recorded as
[0018] The volume of each area of the standard automobile plastic injection molded part is extracted from the database and recorded as V a , compare the total volume of internal bubbles in each area of each injection molded part to be tested with the volume of each area of each injection molded part to be tested, and use the formula Get the internal bubble defect α of each injection molded part to be tested i .
[0019] In an alternative embodiment, the surface color defect analysis of each injection molded part to be inspected is as follows: the brightness, saturation and hue corresponding to the surface color of each area of each injection molded part to be inspected are obtained by a color measuring instrument, and are recorded as D ia , Q ia and X ia , extract the brightness, saturation and hue corresponding to the surface color of standard automobile plastic injection molded parts from the database, record them as D0, Q0 and X0 respectively, and use the formula Get the surface color defect β of each injection molded part to be tested i .
[0020] In an alternative embodiment, the deformation degree of each injection molded part to be tested is analyzed as follows: the injection temperature, injection pressure and injection speed of each area of each injection molded part to be tested are respectively obtained by a temperature and humidity sensor, a pressure sensor and a speed sensor, and are respectively recorded as T ia d ia and v ia , through the formula Get the deformation degree χ of each injection molded part to be tested i , T, v and d represent the preset injection temperature, injection speed and injection pressure of the injection molded part to be tested, respectively, and e represents a natural constant.
[0021] In an alternative embodiment, the overall defect degree of each injection molded part to be inspected is obtained as follows: Get the overall defect degree ε of each injection molded part to be tested i .
[0022] In an alternative embodiment, the conformity analysis of each through hole of each injection molded part to be tested is as follows: scan each injection molded part to be tested, locate the position of each through hole of each injection molded part to be tested, obtain the specifications of each through hole of each injection molded part to be tested, extract the standard specifications of each through hole corresponding to the standard automobile plastic injection molded part from the database, compare the specifications of each through hole of each injection molded part to be tested with the standard specifications of each through hole corresponding to the standard automobile plastic injection molded part, and obtain the specification conformity φ of each through hole of each injection molded part to be tested im , m represents the number of the mth through hole, m=1,2,...,n.
[0023] The inner surface area of each through hole corresponding to the standard automobile plastic injection molded part is extracted from the database and recorded as Obtain the height of each protrusion on the inner surface of each through hole of each injection molded part to be tested and the area of the inner surface occupied, and select the highest height of the protrusion on the inner surface of each through hole of each injection molded part to be tested, and record it as Count the total raised area of the inner surface of each through hole of each injection molded part to be tested and record it as
[0024] By formula Obtain the smoothness conformity of each through hole of each injection molded part to be tested It represents the preset allowable protrusion height of the protrusion on the inner surface of the through hole of the injection molded part to be tested.
[0025] The light sensor is used to obtain the light intensity of each injection molded part after the light passes through each through hole, which is recorded as E im , obtain the light area of each injection molded part after the light passes through each through hole, and record it as The circular area of each through hole corresponding to the standard automobile plastic injection molded part is extracted from the database and recorded as By formula Obtain the transparency compliance γ of each through hole of each injection molded part to be tested im , E represents the standard light intensity after passing through each through hole.
[0026] By formula Obtain the conformity η of each through hole of each injection molded part to be tested im .
[0027] In an alternative embodiment, the cutting qualification analysis of each injection molded part to be inspected is as follows: the image contour of the mold pouring gate of each injection molded part to be inspected is obtained through the image of the mold pouring gate of each injection molded part to be inspected, each inspection point is arranged on the image contour of the mold pouring gate of each injection molded part to be inspected, and the image contour of the mold pouring gate of each injection molded part to be inspected is compared with the image contour of the mold pouring gate of a standard automobile plastic injection molded part to obtain the defect area of the mold pouring gate of each injection molded part to be inspected and the height difference between the mold pouring gate of the standard automobile plastic injection molded part at each inspection point, which are respectively recorded as and H io , o represents the number of the oth detection point, o=1,2,...,p, through the formula Get the cutting qualification κ of the mold gate of each injection molded part to be tested i , S 允许 It represents the reference defect area of the mold gate of the preset injection molded part to be inspected, H0 represents the deviation threshold of the height difference between the image contour detection point of the mold gate of the preset injection molded part to be inspected and the mold gate of the standard automobile plastic injection molded part, and p represents the number of detection points.
[0028] In an alternative embodiment, the local defect degree of each injection molded part to be inspected is obtained as follows: Get the local defect degree λ of each injection molded part to be tested i , n represents the number of through holes.
[0029] In an alternative embodiment, the overall defect degree of each injection molded part to be inspected and the local defect degree of each injection molded part to be inspected are analyzed as follows: the overall defect degree of each injection molded part to be inspected is compared with a preset overall reference defect degree of the injection molded part to be inspected. If the overall defect degree of an injection molded part to be inspected is greater than the preset overall reference defect degree of the injection molded part to be inspected, it indicates that the injection molded part to be inspected has defects. At this time, the crack defect degree of each injection molded part to be inspected, the internal bubble defect degree of each injection molded part to be inspected, the surface color defect degree of each injection molded part to be inspected, and the deformation degree of each injection molded part to be inspected are analyzed in turn, and the factors causing the defects of the injection molded parts to be inspected are output, and an early warning is issued at this time.
[0030] The local defect degree of each injection molded part to be inspected is compared with the preset local reference defect degree of the injection molded part to be inspected. If the local defect degree of a certain injection molded part to be inspected is greater than the preset local reference defect degree of the injection molded part to be inspected, it indicates that the injection molded part to be inspected has defects. At this time, the conformity of the through holes of each injection molded part to be inspected and the defect degree of the mold pouring gate of each injection molded part to be inspected are analyzed in turn, and the factors causing the defects of the injection molded parts to be inspected are output, and an early warning is issued at this time.
[0031] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. The present invention detects defects of automobile plastic injection molded parts through machine vision technology, and analyzes the overall defect degree of each injection molded part to be detected. It not only analyzes the surface defects of automobile plastic injection molded parts, but also analyzes the internal bubble defects of automobile plastic injection molded parts, thereby ensuring the stability and reliability of product quality, thereby improving customer satisfaction.
[0032] 2. The present invention analyzes the conformity of each through hole of each injection molded part to be tested, that is, analyzes the permeability of the through hole and the conformity of the through hole specifications, and analyzes the smoothness of the inner surface of the through hole, thereby improving the conformity of automobile plastic injection molded parts and avoiding the generation of a large number of defective products.
[0033] 3. The present invention analyzes the cutting eligibility of each injection molded part to be tested, and uses machine vision technology to analyze the cutting part of the mold pouring gate of the automobile plastic injection molded part, thereby avoiding manual intervention, saving human resources and time costs, and improving overall production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0035] Figure 1 It is a schematic diagram of the connection of various modules of the system of the present invention. DETAILED DESCRIPTION
[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0037] The present invention proposes a defect detection system for automobile plastic injection molded parts based on machine vision technology, comprising an injection molded part image acquisition module, an injection molding data acquisition module, an injection molded part overall defect analysis module, an injection molded part through-hole analysis module, a mold pouring gate analysis module, an injection molded part local defect analysis module, an early warning module and a database.
[0038] The above-mentioned injection molded part image acquisition module and injection molding data acquisition module are connected to the injection molded part overall defect analysis module, the injection molded part through hole analysis module and the mold pouring gate analysis module are connected to the injection molded part local defect analysis module, the injection molded part overall defect analysis module and the injection molded part local defect analysis module are connected to the early warning module, and the database is respectively connected to the injection molded part overall defect analysis module and the injection molded part through hole analysis module.
[0039] For the connection relationship between modules, see Figure 1 .
[0040] The injection molded parts image acquisition module is used to extract some samples from the injection molded parts to be inspected, record them as each injection molded part to be inspected, divide each injection molded part to be inspected into each area according to the component distribution area, obtain the image of each area of each injection molded part to be inspected, and obtain the surface crack area and internal bubble volume of each area of each injection molded part to be inspected.
[0041] It should be noted that the injection molded parts to be tested are automobile seat injection molded parts, and the components of the automobile seat injection molded parts include seat adjusters, seat brackets and seat adjustment buttons, etc.
[0042] The injection molding data acquisition module is used to collect the brightness, saturation and hue corresponding to the surface color of each area of each injection molded part to be inspected and the injection molding data of each injection molded part to be inspected, and the injection molding data includes injection molding temperature, injection molding pressure and injection molding speed.
[0043] The injection molded parts overall defect analysis module is used to analyze the crack defect degree of each injection molded part to be detected, the internal bubble defect degree of each injection molded part to be detected, the surface color defect degree of each injection molded part to be detected, and the deformation degree of each injection molded part to be detected, so as to obtain the overall defect degree of each injection molded part to be detected.
[0044] The crack defect analysis of each injection molded part to be inspected is as follows: the image of each area of each injection molded part to be inspected is obtained by image acquisition technology, and the grayscale image of each area of each injection molded part to be inspected is obtained, and then the surface crack area of each area of each injection molded part to be inspected is obtained, which is recorded as i represents the number of the i-th injection molded part to be inspected, i=1, 2, ..., j, a represents the number of the a-th area, a=1, 2, ..., b.
[0045] The surface area of each region of the standard automobile plastic injection molded part is extracted from the database and recorded as S a , compare the surface crack area of each region of each injection molded part to be tested with the surface area of each region of the standard automobile plastic injection molded part, and use the formula Get the crack defect degree δ of each injection molded part to be tested i , b represents the number of regions.
[0046] The internal bubble defect analysis of each injection molded part to be tested is as follows: each injection molded part to be tested is scanned by computer segment scanning technology to obtain a three-dimensional image of each area of each injection molded part to be tested, and the total volume of internal bubbles in each area of each injection molded part to be tested is obtained, which is recorded as
[0047] The volume of each area of the standard automobile plastic injection molded part is extracted from the database and recorded as V a , compare the total volume of internal bubbles in each area of each injection molded part to be tested with the volume of each area of each injection molded part to be tested, and use the formula Get the internal bubble defect α of each injection molded part to be tested i .
[0048] It should be noted that the total volume of internal bubbles in each area of each injection-molded part to be inspected is obtained by obtaining the volume of internal bubbles in each area of each injection-molded part to be inspected through a three-dimensional image of each area of each injection-molded part to be inspected, and accumulating them to obtain the total volume of internal bubbles in each area of each injection-molded part to be inspected.
[0049] The surface color defect analysis of each injection molded part to be tested is as follows: The brightness, saturation and hue corresponding to the surface color of each area of each injection molded part to be tested are obtained by a color measuring instrument and recorded as D ia , Q ia and X ia , extract the brightness, saturation and hue corresponding to the surface color of standard automobile plastic injection molded parts from the database, record them as D0, Q0 and X0 respectively, and use the formula Get the surface color defect β of each injection molded part to be tested i .
[0050] The deformation analysis of each injection molded part to be tested is as follows: The injection temperature, injection pressure and injection speed of each area of each injection molded part to be tested are obtained by temperature and humidity sensors, pressure sensors and speed sensors, and are recorded as T ia d ia and v ia , through the formula Get the deformation degree χ of each injection molded part to be tested i , T, v and d represent the preset injection temperature, injection speed and injection pressure of the injection molded part to be tested, respectively, and e represents a natural constant.
[0051] Furthermore, the overall defect degree of each injection molded part to be inspected is obtained as follows: Get the overall defect degree ε of each injection molded part to be tested i .
[0052] It should be noted that the present invention detects defects in automobile plastic injection molded parts through machine vision technology, and analyzes the overall defect degree of each injection molded part to be detected. It not only analyzes the surface defects of automobile plastic injection molded parts, but also analyzes the internal bubble defects of automobile plastic injection molded parts, thereby ensuring the stability and reliability of product quality and improving customer satisfaction.
[0053] The injection molded part through-hole analysis module is used to obtain the specifications of each through-hole of each injection molded part to be inspected, the maximum height length of the protrusion on the inner surface of each through-hole and the total area occupied by the inner surface, as well as the light intensity and light area after the light passes through each through-hole, so as to obtain the conformity of each through-hole of each injection molded part to be inspected.
[0054] The conformity analysis of each through hole of each injection molded part to be tested is as follows: scan each injection molded part to be tested, locate the position of each through hole of each injection molded part to be tested, obtain the specifications of each through hole of each injection molded part to be tested, extract the standard specifications of each through hole of the standard automobile plastic injection molded part from the database, compare the specifications of each through hole of each injection molded part to be tested with the standard specifications of each through hole of the standard automobile plastic injection molded part, and obtain the specification conformity φ of each through hole of each injection molded part to be tested im , m represents the number of the mth through hole, m=1,2,...,n.
[0055] It should be noted that the specification conformity of each through hole of each injection molded part to be tested is specifically analyzed as follows: the specifications of each through hole of each injection molded part to be tested are compared with the standard specifications of the corresponding through holes of the standard automobile plastic injection molded parts. If the specification of a through hole of a certain injection molded part to be tested is consistent with the standard specifications of the corresponding through hole of the standard automobile plastic injection molded part, the specification conformity of the through hole of the injection molded part to be tested is recorded as φ1; otherwise, the specification conformity of the through hole of the injection molded part to be tested is recorded as φ2, and φ im is φ1 or φ2.
[0056] Exemplarily, the value of φ1 is 1, and the value of φ2 is 0.
[0057] The inner surface area of each through hole corresponding to the standard automobile plastic injection molded part is extracted from the database and recorded as Obtain the height of each protrusion on the inner surface of each through hole of each injection molded part to be tested and the area of the inner surface occupied, and select the highest height of the protrusion on the inner surface of each through hole of each injection molded part to be tested, and record it as Count the total raised area of the inner surface of each through hole of each injection molded part to be tested and record it as
[0058] By formula Obtain the smoothness conformity of each through hole of each injection molded part to be tested It represents the preset allowable protrusion height of the protrusion on the inner surface of the through hole of the injection molded part to be tested.
[0059] The light sensor is used to obtain the light intensity of each injection molded part after the light passes through each through hole, which is recorded as E im , obtain the light area of each injection molded part after the light passes through each through hole, and record it as The circular area of each through hole corresponding to the standard automobile plastic injection molded part is extracted from the database and recorded as By formula Obtain the transparency compliance γ of each through hole of each injection molded part to be tested im , E represents the standard light intensity after passing through each through hole.
[0060] By formula Obtain the conformity η of each through hole of each injection molded part to be tested im .
[0061] It should be supplemented that the present invention improves the qualification of automotive plastic injection molded parts and avoids the production of a large number of defective products by analyzing the conformity of each through hole of each injection molded part to be inspected, that is, analyzing the permeability of the through hole and the conformity of the through hole specifications, and analyzing the smoothness of the inner surface of the through hole.
[0062] The mold pouring gate analysis module is used to obtain images of the mold pouring gates of each injection molded part to be tested, compare the images of the mold pouring gates of each injection molded part to be tested with images of the mold pouring gates of standard automobile plastic injection molded parts, obtain the defect area of the mold pouring gate of each injection molded part to be tested and the height difference at each testing point, and comprehensively analyze to obtain the cutting qualification of each injection molded part to be tested.
[0063] The cutting qualification analysis of each injection molded part to be inspected is as follows: the image contour of the mold pouring port of each injection molded part to be inspected is obtained through the image of the mold pouring port of each injection molded part to be inspected, each inspection point is arranged on the image contour of the mold pouring port of each injection molded part to be inspected, and the image contour of the mold pouring port of each injection molded part to be inspected is compared with the image contour of the mold pouring port of a standard automobile plastic injection molded part to obtain the defect area of the mold pouring port of each injection molded part to be inspected and the height difference between the mold pouring port of the standard automobile plastic injection molded part at each inspection point, which are recorded as and H io , o represents the number of the oth detection point, o=1,2,...,p, through the formula Get the cutting qualification κ of the mold gate of each injection molded part to be tested i , S 允许 It represents the reference defect area of the mold gate of the preset injection molded part to be inspected, H0 represents the deviation threshold of the height difference between the image contour detection point of the mold gate of the preset injection molded part to be inspected and the mold gate of the standard automobile plastic injection molded part, and p represents the number of detection points.
[0064] It should be noted that the present invention analyzes the cutting quality of each injection molded part to be tested and adopts machine vision technology to analyze the cutting part of the mold pouring gate of the automobile plastic injection molded part, thereby avoiding manual intervention, saving human resources and time costs, and improving overall production efficiency.
[0065] The injection molded part local defect analysis module is used to analyze the conformity of each through hole of each injection molded part to be inspected and the cutting conformity of each injection molded part to be inspected, so as to obtain the local defect degree of each injection molded part to be inspected.
[0066] The local defect degree of each injection molded part to be tested is obtained as follows: Get the local defect degree λ of each injection molded part to be tested i , n represents the number of through holes.
[0067] The early warning module is used to analyze the overall defect degree of each injection molded part to be inspected and the local defect degree of each injection molded part to be inspected, and to issue an early warning.
[0068] The overall defect degree of each injection molded part to be inspected and the local defect degree of each injection molded part to be inspected are analyzed as follows: the overall defect degree of each injection molded part to be inspected is compared with the preset overall reference defect degree of the injection molded part to be inspected. If the overall defect degree of an injection molded part to be inspected is greater than the preset overall reference defect degree of the injection molded part to be inspected, it indicates that the injection molded part to be inspected has defects. At this time, the crack defect degree of each injection molded part to be inspected, the internal bubble defect degree of each injection molded part to be inspected, the surface color defect degree of each injection molded part to be inspected, and the deformation degree of each injection molded part to be inspected are analyzed in turn, and the factors causing the defects of the injection molded parts to be inspected are output, and an early warning is issued at this time.
[0069] The local defect degree of each injection molded part to be inspected is compared with the preset local reference defect degree of the injection molded part to be inspected. If the local defect degree of a certain injection molded part to be inspected is greater than the preset local reference defect degree of the injection molded part to be inspected, it indicates that the injection molded part to be inspected has defects. At this time, the conformity of the through holes of each injection molded part to be inspected and the defect degree of the mold pouring gate of each injection molded part to be inspected are analyzed in turn, and the factors causing the defects of the injection molded parts to be inspected are output, and an early warning is issued at this time.
[0070] It should be noted that the output of defect-causing factors of the injection molded parts to be inspected specifically includes the following: comparing the crack defect degree of each injection molded part to be inspected with the preset crack reference defect degree of the injection molded parts to be inspected. If the crack defect degree of a certain injection molded part to be inspected is greater than the preset crack reference defect degree of the injection molded part to be inspected, then the crack defect of the injection molded part to be inspected is used as the defect-causing factor. Similarly, the internal bubble defect degree of each injection molded part to be inspected, the surface color defect degree of each injection molded part to be inspected, the deformation degree of each injection molded part to be inspected, the conformity of each through hole of each injection molded part to be inspected, and the cutting conformity of the mold pouring gate of each injection molded part to be inspected are analyzed, and all the causing factors of the injection molded parts to be inspected are counted.
[0071] The database is used to store the surface area, volume, brightness, saturation and hue of each region of a standard automobile plastic injection molded part, and the standard specifications, inner surface area and circular area of each through hole of a standard automobile plastic injection molded part.
[0072] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.
Claims
1. A defect detection system for automobile plastic injection molded parts based on machine vision technology, characterized in that: The system includes: Injection molded parts image acquisition module: used to extract some samples from the injection molded parts to be tested, record them as each injection molded part to be tested, divide each injection molded part to be tested into each area according to the component distribution area, obtain the image of each area of each injection molded part to be tested, and obtain the surface crack area and internal bubble volume of each area of each injection molded part to be tested; Injection molding data acquisition module: used to collect the brightness, saturation and hue corresponding to the surface color of each area of each injection molded part to be tested and the injection molding data of each injection molded part to be tested, the injection molding data includes injection molding temperature, injection molding pressure and injection molding speed; Injection molded parts overall defect analysis module: used to analyze the crack defect, internal bubble defect, surface color defect and deformation of each injection molded part to be tested, and then obtain the overall defect of each injection molded part to be tested; Injection molded part through-hole analysis module: used to obtain the specifications of each through-hole of each injection molded part to be tested, the maximum height length of the protrusion on the inner surface of each through-hole and the total area of the inner surface occupied, as well as the light intensity and light area after the light passes through each through-hole, and obtain the conformity of each through-hole of each injection molded part to be tested; Mold pouring gate analysis module: used to obtain images of the mold pouring gate of each injection molded part to be tested, obtain the defect area of the mold pouring gate of each injection molded part to be tested and the height difference at each test point, and comprehensively analyze to obtain the cutting qualification of each injection molded part to be tested; Injection molded parts local defect analysis module: used to analyze the conformity of each through hole of each injection molded part to be tested and the cutting conformity of each injection molded part to be tested, and obtain the local defect degree of each injection molded part to be tested; Early warning module: used to analyze the overall defect degree of each injection molded part to be inspected and the local defect degree of each injection molded part to be inspected, and issue an early warning; Database: used to store the surface area, volume, brightness, saturation and hue of each area of standard automobile plastic injection molded parts, and the standard specifications, inner surface area and circular area of each through hole of standard automobile plastic injection molded parts; The surface color defect analysis of each injection molded part to be tested is as follows: The color measuring instrument is used to obtain the brightness, saturation and hue of the surface color of each area of each injection molded part to be tested, and they are recorded as , and , extract the brightness, saturation and hue corresponding to the surface color of standard automobile plastic injection parts from the database and record them as , and , through the formula Get the surface color defect of each injection molded part to be tested , Indicates The number of the region, ; The deformation analysis of each injection molded part to be tested is as follows: The injection temperature, injection pressure and injection speed of each area of each injection molded part to be tested are obtained by temperature and humidity sensors, pressure sensors and speed sensors, respectively, and are recorded as , and , through the formula Get the deformation degree of each injection molded part to be tested , , and They represent respectively the preset injection temperature, injection speed and injection pressure of the injection molded part to be tested. Expressed as a natural constant; The conformity analysis of each through hole of each injection molded part to be tested is as follows: Scan each injection molded part to be tested, locate the position of each through hole of each injection molded part to be tested, obtain the specifications of each through hole of each injection molded part to be tested, extract the standard specifications of each through hole of standard automobile plastic injection molded parts from the database, compare the specifications of each through hole of each injection molded part to be tested with the standard specifications of each through hole of standard automobile plastic injection molded parts, and obtain the specification compliance of each through hole of each injection molded part to be tested , Indicates The number of the through holes, ; The inner surface area of each through hole corresponding to the standard automobile plastic injection molded part is extracted from the database and recorded as , obtain the height of each protrusion on the inner surface of each through hole of each injection molded part to be tested and the area of the inner surface occupied, screen out the highest height of the protrusion on the inner surface of each through hole of each injection molded part to be tested, and record it as , count the total raised area of the inner surface of each through hole of each injection molded part to be tested, and record it as ; By formula Obtain the smoothness conformity of each through hole of each injection molded part to be tested , It is represented by the preset allowable protrusion height of the inner surface protrusion of the through hole of the injection molded part to be tested; The light sensor is used to obtain the light intensity of each injection molded part after the light passes through each through hole, and it is recorded as , obtain the light area of each injection molded part after the light passes through each through hole, and record it as , extract the circular area of each through hole corresponding to the standard automobile plastic injection molded part from the database and record it as , through the formula Obtain the transparency compliance of each through hole of each injection molded part to be tested , It is expressed as the standard light intensity after passing through each through hole; By formula Obtain the conformity of each through hole of each injection molded part to be tested ; The cutting qualification analysis of each injection molded part to be tested is as follows: The image contour of the mold pouring port of each injection molded part to be inspected is obtained through the image of the mold pouring port of each injection molded part to be inspected, and each inspection point is arranged on the image contour of the mold pouring port of each injection molded part to be inspected. The image contour of the mold pouring port of each injection molded part to be inspected is compared with the image contour of the mold pouring port of a standard automobile plastic injection molded part to obtain the defect area of the mold pouring port of each injection molded part to be inspected and the height difference between the mold pouring port of the standard automobile plastic injection molded part and the mold pouring port at each inspection point are recorded as and , Indicates The number of the test point, , through the formula Get the cutting qualification of the mold pouring gate of each injection molded part to be tested , It is represented by the preset reference defect area of the mold gate of the injection molded part to be tested. It is represented by the deviation threshold of the height difference between the image contour detection point of the mold pouring gate of the injection molded part to be detected and the mold pouring gate of the standard automobile plastic injection molded part, It is expressed as the number of detection points; The local defect degree of each injection molded part to be inspected is obtained in the following manner: By formula Get the local defect degree of each injection molded part to be tested , Expressed as the number of through holes.
2. The automotive plastic injection molded parts defect detection system based on machine vision technology according to claim 1, characterized in that: The crack defect analysis of each injection molded part to be tested is as follows: The image of each area of each injection molded part to be inspected is obtained by image acquisition technology, and the grayscale image of each area of each injection molded part to be inspected is obtained, and then the surface crack area of each area of each injection molded part to be inspected is obtained, which is recorded as , Indicates The number of the injection molded part to be tested, , Indicates The number of the region, ; The surface area of each region of the standard automobile plastic injection molded part is extracted from the database and recorded as , compare the surface crack area of each region of each injection molded part to be tested with the surface area of each region of the standard automobile plastic injection molded part, and use the formula Get the crack defect degree of each injection molded part to be tested , Expressed as the number of regions.
3. The automotive plastic injection molded parts defect detection system based on machine vision technology according to claim 2 is characterized in that: The internal bubble defect analysis of each injection molded part to be tested is as follows: The three-dimensional images of each region of each injection molded part to be inspected are obtained by scanning each injection molded part by computer segment scanning technology, and the total volume of internal bubbles in each region of each injection molded part to be inspected is obtained and recorded as ; The volume of each area of the standard automobile plastic injection molded part is extracted from the database and recorded as , compare the total volume of internal bubbles in each area of each injection molded part to be tested with the volume of each area of each injection molded part to be tested, and use the formula Get the internal bubble defect degree of each injection molded part to be tested .
4. The automotive plastic injection molded parts defect detection system based on machine vision technology according to claim 3 is characterized by: The overall defect degree of each injection molded part to be inspected is obtained in the following manner: By formula Get the overall defect degree of each injection molded part to be tested .
5. The automotive plastic injection molded parts defect detection system based on machine vision technology according to claim 1, characterized in that: The overall defect degree of each injection molded part to be tested and the local defect degree of each injection molded part to be tested are analyzed as follows: The overall defect degree of each injection molded part to be tested is compared with the preset overall reference defect degree of the injection molded part to be tested. If the overall defect degree of a certain injection molded part to be tested is greater than the preset overall reference defect degree of the injection molded part to be tested, it indicates that the injection molded part to be tested has defects. At this time, the crack defect degree of each injection molded part to be tested, the internal bubble defect degree of each injection molded part to be tested, the surface color defect degree of each injection molded part to be tested, and the deformation degree of each injection molded part to be tested are analyzed in turn, and the factors causing the defects of the injection molded parts to be tested are output, and an early warning is issued at this time; The local defect degree of each injection molded part to be inspected is compared with the preset local reference defect degree of the injection molded part to be inspected. If the local defect degree of a certain injection molded part to be inspected is greater than the preset local reference defect degree of the injection molded part to be inspected, it indicates that the injection molded part to be inspected has defects. At this time, the conformity of the through holes of each injection molded part to be inspected and the defect degree of the mold pouring gate of each injection molded part to be inspected are analyzed in turn, and the factors causing the defects of the injection molded parts to be inspected are output, and an early warning is issued at this time.
Citation Information
Cited By
Automobile plastic injection molding part automatic detection system based on double-robot technology
CN119329018A
An automatic inspection system for automobile plastic injection molded parts based on dual robot technology
CN119329018B
