CN108649112B - LED product yield optimization method - Google Patents
LED product yield optimization method Download PDFInfo
- Publication number
- CN108649112B CN108649112B CN201810283561.5A CN201810283561A CN108649112B CN 108649112 B CN108649112 B CN 108649112B CN 201810283561 A CN201810283561 A CN 201810283561A CN 108649112 B CN108649112 B CN 108649112B
- Authority
- CN
- China
- Prior art keywords
- product
- led
- yield
- recommendation model
- data
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000005457 optimization Methods 0.000 title claims description 9
- 239000000463 material Substances 0.000 claims abstract description 130
- 239000002994 raw material Substances 0.000 claims abstract description 77
- 238000004806 packaging method and process Methods 0.000 claims description 20
- 239000000843 powder Substances 0.000 abstract description 22
- 238000011161 development Methods 0.000 abstract description 15
- 238000003672 processing method Methods 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 description 13
- 239000003086 colorant Substances 0.000 description 12
- 108010043121 Green Fluorescent Proteins Proteins 0.000 description 7
- 239000000203 mixture Substances 0.000 description 7
- 238000012858 packaging process Methods 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 6
- 229920002472 Starch Polymers 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000003292 glue Substances 0.000 description 4
- 235000019698 starch Nutrition 0.000 description 4
- 239000008107 starch Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L33/00—Semiconductor devices having potential barriers specially adapted for light emission; Processes or apparatus specially adapted for the manufacture or treatment thereof or of parts thereof; Details thereof
- H01L33/48—Semiconductor devices having potential barriers specially adapted for light emission; Processes or apparatus specially adapted for the manufacture or treatment thereof or of parts thereof; Details thereof characterised by the semiconductor body packages
- H01L33/50—Wavelength conversion elements
- H01L33/501—Wavelength conversion elements characterised by the materials, e.g. binder
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L33/00—Semiconductor devices having potential barriers specially adapted for light emission; Processes or apparatus specially adapted for the manufacture or treatment thereof or of parts thereof; Details thereof
- H01L33/48—Semiconductor devices having potential barriers specially adapted for light emission; Processes or apparatus specially adapted for the manufacture or treatment thereof or of parts thereof; Details thereof characterised by the semiconductor body packages
- H01L33/50—Wavelength conversion elements
- H01L33/501—Wavelength conversion elements characterised by the materials, e.g. binder
- H01L33/502—Wavelength conversion materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/20—Packaging, e.g. boxes or containers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/18—Manufacturability analysis or optimisation for manufacturability
Landscapes
- Engineering & Computer Science (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Computer Hardware Design (AREA)
- Manufacturing & Machinery (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Led Device Packages (AREA)
Abstract
The invention relates to a method for optimizing the yield of an LED product, which comprises the following steps: acquiring a first product preset demand; selecting an original material according to a material recommendation model and the preset requirement of the first product; the material recommendation model is used for representing the corresponding relation between the material and the first product parameter; and obtaining an LED product according to the original material. According to the material processing method provided by the embodiment, the most appropriate raw materials can be quickly and effectively found through the material recommendation model, the prediction of the color development condition of the LED white light under different fluorescent powder ratios is realized through the material ratio recommendation model, the influence of artificial experience is eliminated, the loss is reduced, and the timeliness is improved.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence, and particularly relates to a method for optimizing the yield of an LED product.
Background
As a light source product which develops fastest in recent years, LEDs are bound to replace most of traditional lighting in the near future, and become mainstream products in the lighting market. The white light LED has the advantages of energy conservation, environmental protection, small volume, long light emitting time and the like, is widely applied in a plurality of fields such as automobile illumination, indoor illumination and the like, and is the most promising next generation solid light source. This brings a wide market space for white light LED packaging factories, and also puts higher demands on the quality level of white light LED packages.
At present, a white light LED packaging process needs to go through multiple links of research, development and design, raw material selection, solid welding and assembly, fluorescent powder proportioning, dispensing and packaging, light splitting inspection, braid packaging and the like, wherein the raw material selection and the fluorescent powder proportioning can have important influence on the luminous performance and the production yield of a product, the existing raw material selection and the existing fluorescent powder proportioning are generally determined by research personnel according to own experience and with a small amount of trial production experimental data, and the judgment of passing and production putting can be carried out only when an acceptable standard is reached.
The existing white light LED packaging process can basically meet the production requirements of most of the current enterprises, but certain problems still exist, such as selection of raw materials, determination of a formula, setting of process technological parameters and the like, which are greatly influenced by the experience of research and development personnel and are difficult to effectively ensure the accuracy and optimality of results, and on the other hand, the determination of the packaging process needs to pass the test of repeated experiments, so that the cost loss is high, and the timeliness is poor.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an LED product yield optimization method. The technical problem to be solved by the invention is realized by the following technical scheme:
an LED product yield optimization method comprises the following steps:
acquiring a first product preset demand;
selecting an original material according to a material recommendation model and the preset requirement of the first product; the material recommendation model is used for representing the corresponding relation between the material and the first product parameter;
and obtaining an LED product according to the original material.
In one embodiment of the present invention, the first product parameter includes one or more of color temperature, wavelength, yield parameter.
In one embodiment of the invention, establishing the material recommendation model comprises:
collecting parameter data of a plurality of groups of materials;
acquiring the first product parameter data corresponding to each group of materials;
and matching the plurality of groups of material parameter data with the corresponding plurality of groups of first product parameter data to obtain the material recommendation model.
In an embodiment of the present invention, the obtaining the first product parameter data corresponding to each group of materials includes:
establishing a material yield relation curve of different types of products; wherein the different types of products are produced from each of the sets of materials;
and acquiring the first product parameter corresponding to each group of materials according to the material yield relation curve.
In one embodiment of the present invention, the material yield relationship curve is a curve of the different types of products and corresponding yields.
The invention also provides another LED product yield optimization method, which comprises the following steps:
acquiring a preset requirement of a second product;
obtaining the proportion of the original material according to a proportion recommendation model and the preset requirement of the second product; the proportion recommendation model is used for representing the corresponding relation between the material proportion and the second product parameter;
and obtaining the LED product according to the proportion of the raw materials.
In one embodiment of the invention, the second product pre-set requirements comprise the raw material and first product parameters;
wherein the first product parameter comprises one or more of color temperature, wavelength, yield parameter.
In an embodiment of the present invention, the establishing the ratio recommendation model includes:
collecting multiple groups of material proportioning data;
acquiring the second product parameter data corresponding to each group of material proportions;
and matching the plurality of groups of material proportioning data with the plurality of groups of second product parameter data to obtain the proportioning recommendation model.
In an embodiment of the present invention, the obtaining the second product parameter data corresponding to each group of material proportions includes:
establishing a ratio yield relation curve of different types of packaging mode products; wherein the different packaging mode products are produced by proportioning each group of materials;
and acquiring the second product parameter through the ratio yield relation curve.
In an embodiment of the present invention, after obtaining the LED product according to the mixture ratio of the raw materials, the method further includes:
collecting product parameter data of the LED product;
comparing the LED product parameter data with the second product parameter data;
and if the LED product yield is higher than the yield corresponding to the second product parameter, taking the LED product parameter as the second product parameter.
Compared with the prior art, the invention has the beneficial effects that:
1) the most appropriate raw materials can be quickly and effectively found through the material recommendation model, the influence of artificial experience is eliminated, and the accuracy and the optimality of results are ensured;
2) through the material ratio recommendation model, the color development condition of the LED white light is predicted by calculation under different fluorescent powder ratios, the process of repeated tests is reduced, the loss is reduced, and the timeliness is improved.
Drawings
Fig. 1 is a schematic diagram of a process of optimizing an LED product yield by a material recommendation model according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an optimization flow of an LED product yield optimization method through a ratio recommendation model according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a material recommendation model establishing method for optimizing the yield of LED products according to an embodiment of the present invention;
fig. 4 is a schematic flow chart of a matching recommendation model establishing method for optimizing the yield of an LED product according to an embodiment of the present invention;
fig. 5 is a schematic flow chart of a method for optimizing yield of LED products according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to specific examples, but the embodiments of the present invention are not limited thereto.
Example one
Referring to fig. 1 and fig. 3, fig. 1 is a schematic diagram illustrating a process of optimizing a yield of an LED product according to an embodiment of the present invention by using a material recommendation model; fig. 3 is a schematic flow chart of a material recommendation model establishment process of the LED product yield optimization method according to the embodiment of the present invention. The yield is said to be the pass rate, and is obtained by dividing the number of shipped finished products by the total number of shipped products. The RGB color scheme is a color standard in the industry, and various colors are obtained by changing three color channels of red (R), green (G) and blue (B) and superimposing the three color channels on each other, wherein RGB represents colors of the three channels of red, green and blue, and when their lights are superimposed on each other, the colors are mixed, and the mixed luminance is higher. In the superposition condition of three lights of red, green and blue, the central brightest superposition area of three colors is white, and the brighter superposition area is. The existing white light LED packaging process is mainly realized by mixing yellow and green fluorescent powder to form a mixture which is stressed and then displays yellow according to the RGB color development principle and then packaging the mixture with a blue chip. In the process, the control of the final white light color development can be realized by controlling the selection of the light source material.
As shown in fig. 1, a method for optimizing yield of LED products includes obtaining a first product preset requirement; selecting an original material according to a material recommendation model and the preset requirement of the first product; the material recommendation model is used for representing the corresponding relation between the material and the first product parameter; and obtaining an LED product according to the original material.
Preferably, before a new white light LED product is produced, parameter requirements such as white color temperature, wavelength, etc. of the new white light LED product to be produced are generally determined, and the first product preset requirement includes parameters such as white color temperature, wavelength, etc. of the new white light LED product to be produced.
Preferably, the material recommendation model is called, and parameters and constraints of the product to be produced are input, that is, the preset requirements and constraints of the first product are input into the material recommendation model, and the model outputs the original material of the product to be produced. The product parameter corresponding to the original material in the material recommendation model, namely the first product parameter, is a product parameter of a product with the highest yield in the same type of products produced by the material, and the first product parameter data and the material data corresponding to the first product parameter data are historical data and are obtained through big data processing.
Preferably, as shown in fig. 4, establishing the material recommendation model includes the following steps:
step 1, acquiring historical material data, and preprocessing historical formula data;
when a white light LED light source product is produced, the required raw materials comprise red fluorescent powder, green fluorescent powder, A/B glue, anti-deposition starch and other raw materials, wherein the raw materials have different specifications and models, for example, the fluorescent powder comprises the fluorescent powder with different specifications produced by different manufacturers. The combination of the raw materials with different specifications and models can produce different white light LED light source products, and one group of raw materials which can produce the white light LED light source products is called a group of raw materials, wherein the historical materials comprise a plurality of groups of raw materials. Different types of white LED products can be produced from a set of raw materials, wherein the product parameters of these different types of white LED products are also different.
Preferably, the obtaining of the historical material data includes obtaining a plurality of sets of raw material data, that is, obtaining a plurality of sets of material parameter data, obtaining product parameter data of different products produced by each set of raw material, and storing the data, wherein the raw material data includes data such as specification, model, name, and the like, and the product parameter data includes data such as color development, wavelength, service life, and the like of the product. And preprocessing historical formula data, namely extracting characteristic attributes from the data of the raw material combination and the product parameter data, wherein the characteristic attributes of the raw materials comprise specification models, and the characteristic attributes of the product parameters comprise color temperature and wavelength.
Step 2, analyzing data to obtain product parameters corresponding to the raw materials;
integrating product parameter data of different products produced by the same group of raw materials, analyzing the proportion of the same color-developing product in the total product number, analyzing the proportion of the product number of each wavelength band in the total product number, analyzing data such as yield and the like, finding out a product which is good in making the group of raw materials through the data such as color development, wavelength, yield and the like, and taking the product parameter of the product which is good in making the group of raw materials as a first product parameter corresponding to the group of raw materials, namely establishing a material yield relation curve of different products; and acquiring the first product parameter corresponding to each group of materials according to the material yield relation curve. The material yield rate relation curve is a curve of the different types of products and corresponding yield rates. And extracting characteristic attributes of the raw material and the product parameters, and storing.
Step 3, establishing a material recommendation model;
and (3) repeating the step (2), analyzing and finding out products produced by multiple groups of raw materials, finding out product parameters of each group of raw materials which are good for manufacturing the products, correspondingly matching each group of raw materials with the product parameters of the products which are good for manufacturing the raw materials, establishing a matching relation, and establishing a material recommendation model. Wherein, each group of raw materials corresponds to a group of product parameters, and can also be a plurality of groups of product parameters arranged according to the preferred sequence.
The material processing method provided by the embodiment can quickly and effectively find the most appropriate raw material through the material recommendation model, eliminates the influence of artificial experience, and ensures the accuracy and optimality of the result.
Example two
Referring to fig. 2 and fig. 4, fig. 2 is a schematic diagram of a process of optimizing a yield rate of an LED product according to an embodiment of the present invention through a ratio recommendation model; fig. 4 is a schematic flow chart of a matching recommendation model establishing method for optimizing the yield of LED products according to an embodiment of the present invention. The RGB color scheme is a color standard in the industry, and various colors are obtained by changing three color channels of red (R), green (G) and blue (B) and superimposing the three color channels on each other, wherein RGB represents colors of the three channels of red, green and blue, and when their lights are superimposed on each other, the colors are mixed, and the mixed luminance is higher. In the superposition condition of three lights of red, green and blue, the central brightest superposition area of three colors is white, and the brighter superposition area is. The existing white light LED packaging process is mainly realized by mixing yellow and green fluorescent powder to form a mixture which is stressed and then displays yellow according to the RGB color development principle and then packaging the mixture with a blue bottom plate. In the process, the control of the final white light color development can be realized by controlling the proportioning of the light source materials.
As shown in fig. 2, a method for optimizing yield of LED products includes: acquiring a preset requirement of a second product; obtaining the proportion of the original material according to a proportion recommendation model and the preset requirement of the second product; the proportion recommending model is used for representing the corresponding relation between the material proportion and the second product parameter, and obtaining the LED product according to the proportion of the original material.
Preferably, before a new white light LED product is produced, the requirements of the new white light LED product to be produced on parameters such as color temperature and wavelength of white light are generally determined, and a raw material for manufacturing the product is selected, where the second current product parameter includes parameters such as color temperature and wavelength of white light LED product to be produced and material parameters of the raw material.
Preferably, as shown in fig. 4, the establishing of the ratio recommendation model includes the following steps:
step 1, obtaining historical proportioning data and preprocessing the historical proportioning data;
historical proportioning data of raw materials for manufacturing a white light LED light source product is obtained, wherein the raw materials comprise red fluorescent powder, green fluorescent powder, A/B glue, anti-settling starch and the like. The different proportion of the raw materials in production can determine the product parameters for producing white light LED products. The historical proportioning data refers to that in the reproduction process, a group of raw material proportioning of the white light LED light source product which can be produced by a fixed proportioning is called as a group of material proportioning data, namely the proportioning data of the raw materials, the historical proportioning data is obtained and includes the data of a plurality of groups of proportioning, and then the proportioning data is stored.
Step 2, obtaining product parameters corresponding to the raw material ratio;
the method comprises the steps that products are produced in different packaging modes through a group of material proportions to obtain different products, product parameters of a group of white light LED light source products produced in different packaging modes through the material proportions are obtained, factors causing differences are analyzed through records of different packaging yields, color temperatures, wavelengths and the like, the relation between the material proportions and the product parameters is analyzed according to the factors, the product parameter with the highest yield is found to be a second product parameter, and namely a relationship curve of the matching yields of the products in different packaging modes is established; wherein, different packaging mode products are produced by each group of material proportion; and acquiring the second product parameter through the ratio yield relation curve. And similarly, obtaining a plurality of groups of second product parameters corresponding to the representation material ratio.
Step 3, establishing a ratio recommendation model;
and establishing a mapping relation between the multiple groups of characterization material proportioning data and the corresponding second product parameter data, and establishing a proportioning recommendation model, wherein each group of material proportioning corresponds to one group of product parameters.
Preferably, after the optimal material ratio is obtained through the material ratio recommendation model, the actual usage amount of each material is respectively calculated, and the white light LED light source product is obtained by producing according to the actual usage amount of each material.
Preferably, after the white light LED light source product is obtained, the product parameters of the white light LED light source product are collected and compared with the corresponding second product parameters, and if the yield of the white light LED light source product is higher than the yield corresponding to the second product parameters, the product parameters of the white light LED light source product are used as the second product parameters.
According to the material processing method provided by the embodiment, the prediction of the color development condition of the LED white light under different fluorescent powder ratios is realized through the material ratio recommendation model, the repeated test process is reduced, the loss is reduced, and the timeliness is improved.
EXAMPLE III
Referring to fig. 3, fig. 4 and fig. 5, fig. 3 is a schematic flow chart illustrating a material recommendation model establishing method for optimizing the yield of an LED product according to an embodiment of the present invention; fig. 4 is a schematic flow chart of a matching recommendation model establishing method for optimizing the yield of an LED product according to an embodiment of the present invention; fig. 5 is a schematic flow chart of a method for optimizing yield of LED products according to an embodiment of the present invention. The RGB color scheme is a color standard in the industry, and various colors are obtained by changing three color channels of red (R), green (G) and blue (B) and superimposing the three color channels on each other, wherein RGB represents colors of the three channels of red, green and blue, and when their lights are superimposed on each other, the colors are mixed, and the mixed luminance is higher. In the superposition condition of three lights of red, green and blue, the central brightest superposition area of three colors is white, and the brighter superposition area is. The existing white light LED packaging process is mainly realized by mixing yellow and green fluorescent powder to form a mixture which is stressed and then displays yellow according to the RGB color development principle and then packaging the mixture with a blue bottom plate. In the process, the control of the final white light color development can be realized by controlling the selection of the light source materials and the proportion of the materials.
As shown in fig. 5, a method for optimizing yield of LED products includes: acquiring a first product preset demand; selecting an original material according to a material recommendation model and the preset requirement of the first product; the material recommendation model is used for representing the corresponding relation between the material and the first product parameter; acquiring a preset requirement of a second product; obtaining the proportion of the original material according to a proportion recommendation model and the preset requirement of the second product; the ratio recommendation model is used for representing the corresponding relation between the material ratio and the second product parameter. And acquiring the actual consumption of the current material according to the current material proportion to obtain the LED product.
Preferably, before the new white LED product is produced, the requirements of the new white LED product to be produced on parameters such as white color temperature, wavelength, etc. are generally determined, that is, the preset requirement of the first product includes the parameters such as white color temperature, wavelength, etc. of the new white LED product to be produced, and the second current product parameter includes the parameters such as white color temperature, wavelength, etc. and the original material parameters of the new white LED product to be produced.
Preferably, the material recommendation model is called, and parameters and constraints of the product to be produced are input, that is, the preset requirements and constraints of the first product are input into the material recommendation model, and the model outputs the raw material combination of the product to be produced. The first product parameter data and the corresponding material data are historical data and are obtained through big data processing.
Preferably, as shown in fig. 3, establishing the material recommendation model includes the following steps:
step 1, obtaining historical material data and preprocessing historical formula data
When a white light LED light source product is produced, the required raw materials comprise red fluorescent powder, green fluorescent powder, A/B glue, anti-deposition starch and other raw materials, wherein the raw materials have different specifications and models, for example, the fluorescent powder comprises the fluorescent powder with different specifications produced by different manufacturers. The combination of the raw materials with different specifications and models can produce different white light LED light source products, and one group of raw materials which can produce the white light LED light source products is called a group of raw materials, wherein the historical materials comprise a plurality of groups of raw materials. Different types of white LED products can be produced from a set of raw materials, wherein the product parameters of these different types of white LED products are also different.
Preferably, the obtaining of the historical material data includes obtaining a plurality of sets of raw material data, that is, obtaining a plurality of sets of material parameter data, obtaining product parameter data of different products produced by each set of raw material, and storing the data, wherein the raw material data includes data such as specification, model, name, and the like, and the product parameter data includes data such as color development, wavelength, service life, and the like of the product. And preprocessing historical formula data, namely extracting characteristic attributes from the data of the raw material combination and the product parameter data, wherein the characteristic attributes of the raw materials comprise specification models, and the characteristic attributes of the product parameters comprise color temperature and wavelength.
Step 2, analyzing the data to obtain product parameters corresponding to the raw materials
Integrating product parameter data of different products produced by the same group of raw materials, analyzing the proportion of the same color-developing product in the total product number, analyzing the proportion of the product number of each wavelength band in the total product number, analyzing data such as yield and the like, finding out a product which is good in making the group of raw materials through the data such as color development, wavelength, yield and the like, and taking the product parameter of the product which is good in making the group of raw materials as a first product parameter corresponding to the group of raw materials, namely establishing a material yield relation curve of different products; and acquiring the first product parameter corresponding to each group of materials according to the material yield relation curve. The material yield rate relation curve is a curve of the different types of products and corresponding yield rates. And extracting characteristic attributes of the raw material and the product parameters, and storing.
Step 3, establishing a material recommendation model
And (3) repeating the step (2), analyzing and finding out products produced by multiple groups of raw materials, finding out product parameters of each group of raw materials which are good for manufacturing the products, correspondingly matching each group of raw materials with the product parameters of the products which are good for manufacturing the raw materials, establishing a matching relation, and establishing a material recommendation model. Wherein, each group of raw materials corresponds to a group of product parameters, and can also be a plurality of groups of product parameters arranged according to the preferred sequence.
Preferably, as shown in fig. 4, the establishing of the ratio recommendation model includes the following steps:
step 1, obtaining historical matching data and preprocessing the historical matching data
Historical proportioning data of raw materials for manufacturing a white light LED light source product is obtained, wherein the raw materials comprise red fluorescent powder, green fluorescent powder, A/B glue, anti-settling starch and the like. The different proportion of the raw materials in production can determine the product parameters for producing white light LED products. The historical proportioning data refers to that in the reproduction process, a group of raw material proportioning of the white light LED light source product which can be produced by a fixed proportioning is called as a group of material proportioning data, namely the proportioning data of the raw materials, and the obtaining of the historical proportioning data comprises obtaining of a plurality of groups of proportioning data. The proportioning data is then stored.
Step 2, obtaining product parameters corresponding to raw material ratio
The method comprises the steps that products are produced in different packaging modes through a group of material proportions to obtain different products, product parameters of a group of white light LED light source products produced in different packaging modes through the material proportions are obtained, factors causing differences are analyzed through records of different packaging yields, color temperatures, wavelengths and the like, the relation between the material proportions and the product parameters is analyzed according to the factors, the product parameter with the highest yield is found to be a second product parameter, and namely a relationship curve of the matching yields of the products in different packaging modes is established; wherein, different packaging mode products are produced by each group of material proportion; and acquiring the second product parameter through the ratio yield relation curve. And similarly, obtaining a plurality of groups of second product parameters corresponding to the representation material ratio.
Step 3, establishing a ratio recommendation model
And establishing a mapping relation between the multiple groups of characterization material proportioning data and the corresponding second product parameter data, and establishing a proportioning recommendation model, wherein each group of material proportioning corresponds to one group of product parameters.
Preferably, after the optimal material ratio is obtained through the material ratio recommendation model, the actual usage amount of each material is respectively calculated, and the white light LED light source product is obtained by producing according to the actual usage amount of each material.
Preferably, after the white light LED light source product is obtained, the product parameters of the white light LED light source product are collected and compared with the corresponding second product parameters, and if the yield of the white light LED light source product is higher than the yield corresponding to the second product parameters, the product parameters of the white light LED light source product are used as the second product parameters.
According to the material processing method provided by the embodiment, the most appropriate raw materials can be quickly and effectively found through the material recommendation model, the prediction of the color development condition of the LED white light under different fluorescent powder ratios is realized through the material ratio recommendation model, the influence of artificial experience is eliminated, the accuracy and optimality of the result are ensured, the process of repeated tests is reduced, the loss is reduced, and the timeliness is improved.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (3)
1. An LED product yield optimization method is characterized by comprising the following steps:
acquiring a preset requirement of a second product;
obtaining the proportion of the original material according to a proportion recommendation model and the preset requirement of the second product; the proportion recommendation model is used for representing the corresponding relation between the material proportion and the second product parameter;
obtaining an LED product according to the proportion of the raw materials;
the establishment of the ratio recommendation model comprises the following steps:
collecting multiple groups of material proportioning data;
acquiring the second product parameter data corresponding to each group of material proportions;
matching the plurality of groups of material proportioning data with a plurality of groups of second product parameter data to obtain the proportioning recommendation model;
the obtaining of the second product parameter data corresponding to each group of material proportions comprises:
establishing a ratio yield relation curve of different types of packaging mode products; wherein the different packaging mode products are produced by proportioning each group of materials;
and acquiring the second product parameter through the ratio yield relation curve.
2. The method of claim 1, wherein the second product pre-set requirement comprises the raw material and a first product parameter;
wherein the first product parameter comprises one or more of color temperature, wavelength, yield parameter.
3. The method of claim 1, wherein the step of obtaining the LED product according to the raw material ratio further comprises:
collecting product parameter data of the LED product;
comparing the LED product parameter data with the second product parameter data;
and if the LED product yield is higher than the yield corresponding to the second product parameter, taking the LED product parameter as the second product parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810283561.5A CN108649112B (en) | 2018-04-02 | 2018-04-02 | LED product yield optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810283561.5A CN108649112B (en) | 2018-04-02 | 2018-04-02 | LED product yield optimization method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108649112A CN108649112A (en) | 2018-10-12 |
| CN108649112B true CN108649112B (en) | 2020-06-12 |
Family
ID=63745273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810283561.5A Expired - Fee Related CN108649112B (en) | 2018-04-02 | 2018-04-02 | LED product yield optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108649112B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112382714B (en) * | 2020-11-13 | 2022-09-13 | 福建鸿博光电科技有限公司 | LED spectrum synthesis method and terminal |
| CN113780727A (en) * | 2021-08-03 | 2021-12-10 | 深圳市智华信息技术有限公司 | LED formula data recommendation method, system and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101436627B (en) * | 2007-11-16 | 2011-09-14 | 广州市鸿利光电股份有限公司 | Device for on-line autocontrol of light color when coating high-power LED fluorescent powder |
| CN101677117B (en) * | 2008-09-19 | 2012-03-21 | 展晶科技(深圳)有限公司 | Method for configuring high color rendering light emitting diode and system |
| CN102136528B (en) * | 2010-12-24 | 2015-12-02 | 晶能光电（江西）有限公司 | The method of phosphor powder layer is prepared on LED crystal particle surface |
| CN102163678B (en) * | 2010-12-24 | 2016-03-02 | 晶能光电（江西）有限公司 | To the data processing method of LED applying fluorescent material, device and manufacture method |
-
2018
- 2018-04-02 CN CN201810283561.5A patent/CN108649112B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN108649112A (en) | 2018-10-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI479196B (en) | The method for mixing light of led array | |
| CN106162981A (en) | Light mixing method based on three-primary color LED | |
| CN101310236A (en) | An led assembly with a communication protocol for led light engines | |
| CN108649112B (en) | LED product yield optimization method | |
| CN102196633B (en) | Colour correction method for coloured light lamp | |
| US11388794B2 (en) | Method and illumination system for simulating CIE standard illuminant with multi-channel LED | |
| CN105848354B (en) | A kind of shading process being used in intelligent illuminating system and system | |
| CN104167174B (en) | A kind of method and device of LED display white balance adjusting | |
| CN112203383B (en) | Multi-spectral LED dimming method | |
| CN104538391A (en) | White light led module | |
| CN111185407A (en) | LED Bin dividing method and application product thereof | |
| CN100501953C (en) | Luminous diode color matching method | |
| CN106304527A (en) | A kind of Lighting Control Assembly and illumination control method | |
| CN103337495A (en) | Color temperature adjustable white-light LED | |
| CN102005161A (en) | Method for manufacturing light-emitting diode (LED) display screen | |
| CN103629603A (en) | High-brightness and wide-color-gamut direct type backlight module and liquid crystal display applying module | |
| CN113033777A (en) | Vehicle-mounted atmosphere lamp chromaticity calibration method based on neural network calibration model | |
| CN110072316B (en) | Spectral feedback control method, controller and system of multi-channel LED light source | |
| CN209295003U (en) | A kind of glory lamps and lanterns of outdoor utility | |
| CN202633301U (en) | LED lighting device | |
| CN111710771A (en) | Rubber powder ratio recommendation method for LED product | |
| CN102269390B (en) | Design method of LED (light emitting diode) backlight module | |
| CN106255282A (en) | A kind of Lighting Control Assembly and illumination control method | |
| CN111509094B (en) | Three-color LED light source chip type selection method, system, medium and electronic equipment | |
| CN106332383A (en) | Intelligent lighting device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200612 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |