CN105169979B - A kind of automotive paints mixing color method - Google Patents
A kind of automotive paints mixing color method Download PDFInfo
- Publication number
- CN105169979B CN105169979B CN201510570143.0A CN201510570143A CN105169979B CN 105169979 B CN105169979 B CN 105169979B CN 201510570143 A CN201510570143 A CN 201510570143A CN 105169979 B CN105169979 B CN 105169979B
- Authority
- CN
- China
- Prior art keywords
- color
- paint
- sample
- pso
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Application Of Or Painting With Fluid Materials (AREA)
- Paints Or Removers (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The present invention relates to a kind of automotive paints mixing color method, including step：S1：The surface image of touch-up paint vehicle is treated in collection, and obtains surface color information according to the identification of the surface image of collection；S2：Corresponding coarse adjustment color formula is generated according to surface color information, and the paint color masterbatch for obtaining designated ratio is formulated based on the toning, mixes and required paint is obtained by compensation of instead bursting.Compared with prior art, the present invention realizes the automatic Modulation for treating touch-up paint surface of vehicle color of paint, overcomes the drawbacks of manually modulating the inefficiency by virtue of experience allocated and lack experience, and greatly reduce the injury that paint volatilization is caused to human body.
Description
Technical field
The present invention relates to automobile touch-up paint field, more particularly, to a kind of automotive paints mixing color method.
Background technology
In recent years, auto industry was developed rapidly, and automobile spreading speed is very fast, particularly family-sized car.But as automobile is produced
That measures drastically increases, and the use of car surface paint is also continuously increased.On the one hand, car manufactures produced after automobile, it is necessary to
Its surface is handled using the paint of particular color, on the other hand, as automobile is continuously increased, traffic accident is also rapid therewith
Rise, the clashing and breaking of car surface are can hardly be avoided, and a large amount of Auto repair shops need to use the paint of particular color to handle it.But
Current programme is, each production firm or its 4S shop are merely able to obtain the color of needs according to color formulas proportion adjustment, to adjust
Mix colours and had determined each component ratio in advance, and each repair shop is then largely using messenger painter for having certain experiences technology
Color needed for work is prepared.
Above way has wretched insufficiency.4S shops according to formula rate modulate come color often with actual car table face
There is deviation in color, because automobile is using process, surface color is subjected to exposing to the weather, and color of dispatching from the factory has certain deviation, and
Repair shop is using the method manually prepared, completely by virtue of experience debugging by hand.On the one hand manual modulation paint meeting month after month throughout the year
Human body is damaged, on the other hand, paint supplier is numerous, each manufacturer's paint characteristic is inconsistent, and species is various.Therefore,
Painter is difficult to accurately hold allotment ratio by rule of thumb, there is technical problem, and process for preparation is slower, less efficient.
The content of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide a kind of automotive paints color
Concocting method.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of automotive paints mixing color method, including step：
S1：The surface image of touch-up paint vehicle is treated in collection, and obtains surface color information according to the identification of the surface image of collection；
S2：Corresponding coarse adjustment color formula is generated according to surface color information, and specified ratio is obtained based on the coarse adjustment color formula
The paint color masterbatch of example, mixes and obtains required paint by feedback compensation.
The step S2 specifically includes step：
S21：Coarse adjustment：Based on coarse adjustment color formula, the paint color masterbatch of designated ratio is obtained, is mixed and stirred for；
S22：Feedback：Sampling obtains paint sample, and judgement sample color and surface color in the paint obtained from stirring
Between aberration whether be less than threshold value, if it has, then allotment terminates, if it has not, then performing step S23；
S23：Fine setting：According to the aberration generation compensation formula between color sample and surface color, and matched somebody with somebody based on the compensation
Side obtains the paint color masterbatch of designated ratio, is mixed and stirred for.
The step S22 specifically includes step：
S221：By the paint application being stirred in obtaining paint sample on the sampling plate of automobile case same material；
S222：The light that paint sample is sent under the irradiation of base light source is caught by color sensor, according to the light of seizure
Learn color sample；
S223：Whether the aberration between judgement sample color and surface color is less than threshold value, if it has, then allotment terminates,
If it has not, then performing step S23.
After being painted needed for being obtained in the step S2, modulation daily record is uploaded into host computer and preserved.
Surface color information is obtained according to the identification of the surface image of collection using SVM classifier in the step S 1, it is described
SVM classifier kernel function is RBF kernel functions.
The optimization process of the SVMs parameter of the SVM classifier uses the mangcorn based on heredity with simulated annealing
Swarm optimization is carried out, and specifically includes step：
S11：Set GA population scale, crossing-over rate and aberration rate, the minimum fitness threshold value of maximum evolutionary generation and GA；
S12：GA initial population is generated, wherein, each GA chromosome represents one group of PSO accelerator coefficient；
S13：Calculate GA individual fitness；
S14：The select probability of each individual is calculated by obtained individual fitness, implements selection, intersect and make a variation, generation
GA populations of new generation；
S15：Judge whether at least one sets up following condition：
A. evolutionary generation reaches maximum evolutionary generation,
B. individual fitness reaches the minimum fitness threshold values of GA,
If it has not, then return to step S13, if it has, then performing step S16；
S16：Optimal value is exported, for the optimal solution of the Hybrid Particle Swarm.
The step S13 specifically includes step：
S131：Set PSO population scales, maximum iteration, PSO minimum fitness threshold values, each of which PSO particles
Represent the Optimal Parameters of one group of SVM classifier；
S132：Accelerator coefficient, inertia weight coefficient are initialized, particle initial velocity and position is calculated, and initialize simulation
Annealing algorithm initial value；
S133：Particle rapidity and position are updated, and calculates adaptation value difference Δ E before and after renewal；
S134：Judge to adapt to whether value difference is more than 0, if it has, then step S136 is performed, if it is not, then performing step S135；
S135：Judge whether exp (Δ E/T) ＞ rand (0,1) set up, if it has, then step S136 is performed, if it has not,
Then perform step S137；
S136：Receive to update result, and perform step S138；
S137：Refusal updates result, rollback particle rapidity and position, and performs step S138；
S138：Adaptive weighting coefficient is calculated, and according to adaptive value more new individual extreme value and global extremum；
S139：Judge whether at least one sets up following condition：
C. iterations reaches maximum iteration,
D. the minimum fitness threshold values of PSO are reached,
If it has not, then return to step S133；It is GA's by the PSO optimal values found if it has, then obtaining optimal value
Individual adaptation degree.
Compared with prior art, the present invention has advantages below：
1) automatic Modulation for treating touch-up paint surface of vehicle color of paint is realized, overcomes what artificial modulation was by virtue of experience modulated
Inefficiency and the drawbacks of lack experience, and greatly reduce the injury that paint volatilization is caused to human body.
2) device can be modulated according to the actual conditions of car table color, not adjusted by existing scheme of colour merely
Make the color come more accurate, reliable, reduce and the phenomenon done over again occur because paint color mixing is inaccurate, save a large amount of manpowers, thing
Power.
3) paint color mixing this in particular cases, using the complementary side of image procossing and sensor feedback compensation tache
Formula, can either ensure the degree of accuracy of modulator approach, and the spending of hardware system resource can be reduced again, improve modulation efficiency.
Brief description of the drawings
Fig. 1 is key step schematic flow sheet of the invention；
Fig. 2 is schematic flow sheet of the invention；
Fig. 3 controls flow graph for the method for the present invention；
Wherein 1, mechanism, 2, microprocessor are allocated.
Embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, give detailed embodiment and specific operating process, but protection scope of the present invention is not limited to
Following embodiments.
A kind of automotive paints mixing color method, as depicted in figs. 1 and 2, including step：
S1：The surface image of touch-up paint vehicle is treated in collection, and obtains surface color information according to the identification of the surface image of collection,
Specifically include step：
Surface color information, SVM classifier are obtained according to the identification of the surface image of collection using SVM classifier in step S1
Kernel function is RBF kernel functions.
The optimization process of the SVMs parameter of SVM classifier uses the hybrid particle swarm based on heredity with simulated annealing
Algorithm is carried out, and specifically includes step：
S11：GA (genetic algorithm) population scale, crossing-over rate and aberration rate is set, maximum evolutionary generation and GA minimum is suitable
Response threshold value；
S12：GA initial population is generated, wherein, each GA chromosome represents one group of PSO (particle cluster algorithm) and accelerates system
Number；
S13：GA individual fitness is calculated, step is specifically included：
S131：Set PSO population scales, maximum iteration, PSO minimum fitness threshold values, each of which PSO particles
The Optimal Parameters of one group of SVM classifier are represented, Optimal Parameters refer specifically to RBF kernel functional parameters and penalty factor；
S132：Accelerator coefficient, inertia weight coefficient are initialized, particle initial velocity and position is calculated, and initialize simulation
Annealing algorithm initial value；
S133：Particle rapidity and position are updated, and calculates adaptation value difference Δ E before and after renewal；
S134：Judge to adapt to whether value difference is more than 0, if it has, then step S136 is performed, if it is not, then performing step S135；
S135：Judge whether exp (Δ E/T) ＞ rand (0,1) set up, if it has, then step S136 is performed, if it has not,
Then perform step S137；
S136：Receive to update result, and perform step S138；
S137：Refusal updates result, rollback particle rapidity and position, and performs step S138；
S138：Adaptive weighting coefficient is calculated, and according to adaptive value more new individual extreme value and global extremum；
S139：Judge whether at least one sets up following condition：
C. iterations reaches maximum iteration,
D. the minimum fitness threshold values of PSO are reached,
If it has not, then return to step S133；It is GA's by the PSO optimal values found if it has, then obtaining optimal value
Individual adaptation degree.
S14：The select probability of each individual is calculated by obtained individual fitness, implements selection, intersect and make a variation, generation
GA populations of new generation；
S15：Judge whether at least one sets up following condition：
A. evolutionary generation reaches maximum evolutionary generation,
B. individual fitness reaches the minimum fitness threshold values of GA,
If it has not, then return to step S13, if it has, then performing step S16；
S16：Optimal value is exported, for the optimal solution of the Hybrid Particle Swarm.
S2：Corresponding coarse adjustment color formula is generated according to surface color information, and specified ratio is obtained based on the coarse adjustment color formula
The paint color masterbatch of example, mixes and obtains required paint by feedback compensation, specifically include step：
S21：Coarse adjustment：Based on coarse adjustment color formula, the paint color masterbatch of designated ratio is obtained, is mixed and stirred for；
S22：Feedback：Sampling obtains paint sample, and judgement sample color and surface color in the paint obtained from stirring
Between aberration whether be less than threshold value, if it has, then allotment terminate, if it has not, then perform step S23, specifically include step：
S221：By the paint application being stirred in obtaining paint sample on the sampling plate of automobile case same material；
S222：The light that paint sample is sent under the irradiation of base light source is caught by color sensor, according to the light of seizure
Learn color sample；
S223：Whether the aberration between judgement sample color and surface color is less than threshold value, if it has, then allotment terminates,
If it has not, then performing step S23.
S23：Fine setting：According to the aberration generation compensation formula between color sample and surface color, and matched somebody with somebody based on the compensation
Side obtains the paint color masterbatch of designated ratio, is mixed and stirred for；
S24：Judge whether the modulation result adds programs storehouse, if it is, step S25 is carried out, if it has not, then holding
Row step S26；
S25：Programs are obtained after the coarse adjustment color formula and compensation formula fusion, programs storehouse are added, and perform step
Rapid S26；
S26：Host computer, generation allotment daily record are reported, and uploads host computer and is preserved.
As shown in figure 3, the embodiment of this method is as follows：
During this method is implemented, microprocessor 2 can control the co-ordination of ingredient sector 1, and spice mechanism 1 is wrapped
Include the link mechanisms such as coarse adjustment, fine setting, sampling in methods described.Automobile table color of paint information is collected by camera to hand over
Handled by microprocessor 2, it is outside that the gatherer process eliminates or greatly reduced intensity of illumination, car table spot etc. by the way of certain
The factor that environment may be impacted to modulated process.Microprocessor is by the generation of the processes such as image preprocessing, SVM pattern-recognitions
Programs, spice mechanism charging carries out coarse modulated, after the completion of coarse adjustment, exchanges sample preparation product and carries out sampling judgement, dry to eliminate
Factor is disturbed, sample is sprayed on sampling plate plate, base light source is beaten on sampling plate, is made up of biosensor analysis color, rather than
Directly base light source is radiated on sample solution.If analysis result, which is shown, lacks certain composition, the composition obtained according to analysis
Ratio is fed by allotment mechanism 1 and modulated again, and process circulation is carried out, until modulation result is correct or reaches allowable error model
Enclose, then allotment is completed, and this programs is added into scheme base as needed, report host computer, generation allotment daily record.Whole
In modulated process, microprocessor is responsible for the co-ordination of control allotment mechanism and each peripheral cell, such as feeds, and stirring, touch screen shows
Show, the work such as communication.It should be noted that microprocessor strictly controls the combination behavior of variant chemical characteristic paint simultaneously,
It is preferred that the mechanism such as programs.
Claims (5)
1. a kind of automotive paints mixing color method, it is characterised in that including step：
S1：The surface image of touch-up paint vehicle is treated in collection, and obtains surface color information according to the identification of the surface image of collection,
S2：Corresponding coarse adjustment color formula is generated according to surface color information, and designated ratio is obtained based on the coarse adjustment color formula
Color masterbatch is painted, mixes and required paint is obtained by feedback compensation；
Surface color information, the SVM points are obtained according to the identification of the surface image of collection using SVM classifier in the step S1
Class device kernel function is RBF kernel functions；
The optimization process of the SVMs parameter of the SVM classifier uses the hybrid particle swarm based on heredity with simulated annealing
Algorithm is carried out, and specifically includes step：
S11：Setting GA population scale, crossing-over rate and aberration rate, the minimum fitness threshold value of maximum evolutionary generation and GA,
S12：GA initial population is generated, wherein, each GA chromosome represents one group of PSO accelerator coefficient；
S13：GA individual fitness is calculated,
S14：The select probability of each individual is calculated by obtained individual fitness, implements selection, intersect and make a variation, generation new one
For GA populations,
S15：Judge whether at least one sets up following condition：
A. evolutionary generation reaches maximum evolutionary generation,
B. individual fitness reaches the minimum fitness threshold values of GA,
If it has not, then return to step S13, if it has, then step S16 is performed,
S16：Optimal value is exported, for the optimal solution of the Hybrid Particle Swarm.
2. a kind of automotive paints mixing color method according to claim 1, it is characterised in that the step S2 is specifically wrapped
Include step：
S21：Coarse adjustment：Based on coarse adjustment color formula, the paint color masterbatch of designated ratio is obtained, is mixed and stirred for；
S22：Feedback：Sample and obtained between paint sample, and judgement sample color and surface color in the paint obtained from stirring
Aberration whether be less than threshold value, if it has, then allotment terminates, if it has not, then performing step S23；
S23：Fine setting：According to the aberration generation compensation formula between color sample and surface color, and obtained based on compensation formula
The paint color masterbatch of fetching certainty ratio, is mixed and stirred for.
3. a kind of automotive paints mixing color method according to claim 2, it is characterised in that the step S22 is specific
Including step：
S221：By the paint application being stirred in obtaining paint sample on the sampling plate of automobile case same material；
S222：The light that paint sample is sent under the irradiation of base light source is caught by color sensor, learned according to the light of seizure
Color sample；
S223：Whether the aberration between judgement sample color and surface color is less than threshold value, if it has, then allotment terminates, if
It is no, then perform step S23.
4. a kind of automotive paints mixing color method according to claim 1, it is characterised in that obtained in the step S2
After required paint, modulation daily record is uploaded into host computer and preserved.
5. a kind of automotive paints mixing color method according to claim 1, it is characterised in that the step S13 is specific
Including step：
S131：PSO population scales, maximum iteration are set, PSO minimum fitness threshold values, each of which PSO particles are represented
The Optimal Parameters of one group of SVM classifier；
S132：Accelerator coefficient, inertia weight coefficient are initialized, particle initial velocity and position is calculated, and initialize simulated annealing
Algorithm initial value；
S133：Particle rapidity and position are updated, and calculates adaptation value difference Δ E before and after renewal；
S134：Judge to adapt to whether value difference is more than 0, if it has, then step S136 is performed, if it is not, then performing step S135；
S135：Judge whether exp (Δ E/T) ＞ rand (0,1) set up, if it has, then step S136 is performed, if it has not, then holding
Row step S137；
S136：Receive to update result, and perform step S138；
S137：Refusal updates result, rollback particle rapidity and position, and performs step S138；
S138：Adaptive weighting coefficient is calculated, and according to adaptive value more new individual extreme value and global extremum；
S139：Judge whether at least one sets up following condition：
C. iterations reaches maximum iteration,
D. the minimum fitness threshold values of PSO are reached,
If it has not, then return to step S133；It is GA individual by the PSO optimal values found if it has, then obtaining optimal value
Fitness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510570143.0A CN105169979B (en) | 2015-09-09 | 2015-09-09 | A kind of automotive paints mixing color method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510570143.0A CN105169979B (en) | 2015-09-09 | 2015-09-09 | A kind of automotive paints mixing color method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105169979A CN105169979A (en) | 2015-12-23 |
| CN105169979B true CN105169979B (en) | 2017-10-27 |
Family
ID=54892693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510570143.0A Active CN105169979B (en) | 2015-09-09 | 2015-09-09 | A kind of automotive paints mixing color method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105169979B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107796502A (en) * | 2016-08-31 | 2018-03-13 | 车急修汽车科技有限公司 | A kind of car paint allotment and the quick process for repairing car paint |
| CN106994437B (en) * | 2017-05-19 | 2020-08-04 | 安徽鹰龙工业设计有限公司 | Automobile paint repair method and equipment based on image recognition technology |
| US10871888B2 (en) * | 2018-04-26 | 2020-12-22 | Ppg Industries Ohio, Inc. | Systems, methods, and interfaces for rapid coating generation |
| US11874220B2 (en) | 2018-04-26 | 2024-01-16 | Ppg Industries Ohio, Inc. | Formulation systems and methods employing target coating data results |
| CN108891140A (en) * | 2018-06-27 | 2018-11-27 | 东莞市美芯龙物联网科技有限公司 | A kind of concocting method of non-crude oil ink |
| CN109772186A (en) * | 2019-01-23 | 2019-05-21 | 杭州以诺行汽车科技股份有限公司 | A kind of paint method and system for automotive lacquer |
| CN111598960A (en) * | 2019-02-20 | 2020-08-28 | 上海德忱汽车服务有限公司 | Intelligent paint mixing instrument for automobile paint |
| CN117369546A (en) * | 2023-11-14 | 2024-01-09 | 广东交通职业技术学院 | Wall paint color collection and matching system, method and intelligent paint brush |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| LU87453A1 (en) * | 1989-02-14 | 1990-09-19 | Wurth Paul Sa | PROCESS FOR THE PNEUMATIC INJECTION OF QUANTITIES OF POWDERED MATERIALS INTO A VARIABLE PRESSURE ENCLOSURE |
| CN101588209B (en) * | 2008-05-23 | 2011-11-30 | 中兴通讯股份有限公司 | Self-adaptive chromatic dispersion compensation method |
| CN102223184B (en) * | 2011-06-27 | 2017-10-10 | 中兴通讯股份有限公司 | Dispersion compensation method and device |
| CN103817030A (en) * | 2012-11-16 | 2014-05-28 | 袁丽莉 | Portable color mixing and spraying device with color matching function |
| CN104785397A (en) * | 2015-04-01 | 2015-07-22 | 电子科技大学 | Full-automatic color measurement color blending paint spraying system |
-
2015
- 2015-09-09 CN CN201510570143.0A patent/CN105169979B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105169979A (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105169979B (en) | A kind of automotive paints mixing color method | |
| CN110135341A (en) | Weed identification method, apparatus and terminal device | |
| CN105233716B (en) | A kind of automotive paints mixing color system | |
| CN105676649A (en) | Control method for sewage treatment process based on self-organizing neural network | |
| US20190375036A1 (en) | Soldering system, control device, control method, and program | |
| CN101893884B (en) | Soft measurement method of quality index data in rubber mixing process of internal mixer | |
| CN110363355B (en) | Cloud-edge collaborative forecasting system and method for alumina production index | |
| CN1655904A (en) | Luminescence sensing system for welding | |
| CN114971433B (en) | Quality control method, device, equipment and storage medium based on industrial internet | |
| JP2017508952A (en) | Method and system for determining a color recipe | |
| CN115171097B (en) | Processing control method and system based on three-dimensional point cloud and related equipment | |
| US20030237058A1 (en) | Method and system for the automatic design of experiments | |
| CN112182910A (en) | Method and device for controlling preparation effect of cross-linked material | |
| CN115824595A (en) | UV curing light source uniformity detection and adjustment system | |
| Barcelos et al. | Disco: Double likelihood-free inference stochastic control | |
| CN107547128A (en) | The method and device of optical module light power calibration | |
| CN107728481B (en) | Closed-loop modeling method and device based on model predictive control | |
| CN106161976A (en) | Auto iris control method and device for protection and monitor field | |
| CN103514596A (en) | Method and device for processing image | |
| CN107755127A (en) | A kind of intelligent spray painting regulation and control method with temperature analysis function | |
| CN114637206B (en) | Weight control method based on dual-cluster self-adaptive fuzzy neural network | |
| CN108805173A (en) | Solar battery sheet aberration method for separating | |
| CN205095663U (en) | Car paint colour allotment device | |
| CN109046901A (en) | A kind of automobile coating repairing method for planning track | |
| CN116653449A (en) | Method, device, equipment and storage medium for controlling power of curing light source |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |