CN111860987A - Mixed fluorescent material emission spectrum prediction method and device - Google Patents
Mixed fluorescent material emission spectrum prediction method and device Download PDFInfo
- Publication number
- CN111860987A CN111860987A CN202010649378.XA CN202010649378A CN111860987A CN 111860987 A CN111860987 A CN 111860987A CN 202010649378 A CN202010649378 A CN 202010649378A CN 111860987 A CN111860987 A CN 111860987A
- Authority
- CN
- China
- Prior art keywords
- emission spectrum
- proportion
- fluorescent material
- mixed
- fluorescent
- 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.)
- Pending
Links
- 239000000463 material Substances 0.000 title claims abstract description 171
- 238000000295 emission spectrum Methods 0.000 title claims abstract description 170
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013528 artificial neural network Methods 0.000 claims abstract description 69
- 238000000862 absorption spectrum Methods 0.000 claims abstract description 22
- 235000013405 beer Nutrition 0.000 claims abstract description 21
- 238000010521 absorption reaction Methods 0.000 claims description 34
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 4
- 239000000843 powder Substances 0.000 abstract description 31
- 238000012360 testing method Methods 0.000 abstract description 10
- 230000006870 function Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 108010043121 Green Fluorescent Proteins Proteins 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000741 silica gel Substances 0.000 description 1
- 229910002027 silica gel Inorganic materials 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The invention provides a mixed fluorescent material emission spectrum prediction method and a device, wherein the method comprises the following steps: respectively obtaining absorption spectra, emission spectra and quantum efficiencies of N fluorescent materials, wherein N is an integer greater than or equal to 2; obtaining the proportion of each fluorescent material after the N fluorescent materials are mixed; calculating the emission spectrum proportionality coefficient of the N fluorescent materials after being mixed according to any proportion; establishing a neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient; and acquiring an emission spectrum proportionality coefficient through the neural network prediction model, and realizing the prediction of the emission spectrum of the mixed N fluorescent materials according to the emission spectrum proportionality coefficient acquired through the neural network prediction model and the emission spectrum of the fluorescent material corresponding to the emission spectrum proportionality coefficient. The mixed fluorescent powder material emission spectrum is predicted by combining the corrected beer lambert model and the artificial neural network, and the complicated experimental test is replaced, so that the labor and time cost is saved.
Description
Technical Field
The invention relates to the technical field of semiconductors, in particular to a mixed fluorescent material emission spectrum prediction method and a mixed fluorescent material emission spectrum prediction device.
Background
At present, the most commonly used white Light LED (Light-Emitting Diode) generally is a blue Light chip with a surface coated with a yellow phosphor and a silica gel composite material, and this method has the advantages of simple process and good reliability, but the white Light LED combined by the blue Light excited yellow phosphor lacks a red Light part, and has poor color rendering performance. In order to solve the above problems, a technical solution is proposed to improve the color rendering index of white LED illumination by mixing multi-color phosphor, and the emission spectrum of the phosphor is one of the important indexes for characterizing the performance. At present, emission spectra of a plurality of mixed fluorescent materials are tested by instruments, which consumes labor and time, and particularly, when the proportion of each mixed fluorescent powder is adjusted, the mixed fluorescent materials need to be repeatedly tested. Therefore, the method has certain guiding significance for researching the design of the high-quality white light LED light source by predicting the emission spectrum of the mixture of the multiple fluorescent powders.
Disclosure of Invention
The invention aims to solve the technical problems and provides a mixed fluorescent material emission spectrum prediction method, which can predict the mixed fluorescent powder material emission spectrum by combining a corrected beer lambert model and an artificial neural network, replaces complicated experimental tests, and saves labor and time cost. .
The technical scheme adopted by the invention is as follows:
a mixed fluorescent material emission spectrum prediction method comprises the following steps: respectively obtaining absorption spectra, emission spectra and quantum efficiencies of N fluorescent materials, wherein N is an integer greater than or equal to 2; obtaining the proportion of each fluorescent material after the N fluorescent materials are mixed; calculating the emission spectrum proportionality coefficient of the N fluorescent materials after being mixed according to any proportion; establishing a neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient; and acquiring an emission spectrum proportionality coefficient through the neural network prediction model, and realizing the prediction of the emission spectrum of the mixed N fluorescent materials according to the emission spectrum proportionality coefficient acquired through the neural network prediction model and the emission spectrum of the fluorescent material corresponding to the emission spectrum proportionality coefficient.
According to an embodiment of the present invention, the calculating the emission spectrum proportionality coefficient of the N fluorescent materials after mixing according to any proportion includes: and calculating the emission spectrum proportionality coefficient of the N fluorescent materials mixed according to any proportion based on the corrected beer Lambert model.
According to one embodiment of the invention, the calculation of the emission spectrum proportionality coefficients of the N fluorescent materials after being mixed according to any proportion based on the modified beer lambertian model comprises the following steps: calculating the absorption probability of mutual absorption among the fluorescent materials according to the respective absorption spectrum and emission spectrum of the N fluorescent materials; and calculating the emission spectrum proportion coefficient of the N fluorescent materials mixed according to any proportion according to the proportion of each fluorescent material, the quantum efficiency and the absorption probability of mutual absorption among the fluorescent materials.
According to one embodiment of the invention, the emission spectrum scaling factor is generated by the following formula:
wherein, KiRepresenting the emission spectral scaling factor, riAnd rjRepresents the proportion of the fluorescent material, qiAnd q isjWhich represents the quantum efficiency of the fluorescent material,ijindicating the probability that light emitted by the j-type phosphor is absorbed by the i-type phosphor,jiindicating the probability that light emitted by the i-type phosphor is absorbed by the j-type phosphor.
According to an embodiment of the present invention, the absorption probability of mutual absorption between each of the fluorescent materials is generated by the following formula:
wherein, bi(λ) represents an absorption spectrum of the i-type fluorescent material, emj(λ) represents a j-type fluorescent material emission spectrum.
According to an embodiment of the present invention, establishing a neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient includes: and establishing a neural network prediction model by taking the emission spectrum proportionality coefficient obtained by mixing the N fluorescent materials according to any proportion and the proportion of each fluorescent material as a data set of the neural network prediction model, wherein the proportion of each fluorescent material is taken as an input variable of the neural network prediction model, and the emission spectrum proportionality coefficient obtained by mixing the N fluorescent materials according to any proportion is taken as an output variable.
According to an embodiment of the present invention, the emission spectra after the N fluorescent materials are mixed are predicted by the following formula:
wherein emeq(λ) represents the predicted emission spectrum, k, of N phosphors after mixingi' represents an emission spectrum scale coefficient obtained by the neural network prediction model, and em (lambda) represents ki' emission spectrum of the corresponding fluorescent material.
In addition, a mixed fluorescent material emission spectrum prediction device is also provided, which comprises: the first acquisition module is used for respectively acquiring the absorption spectrum, the emission spectrum and the quantum efficiency of N fluorescent materials, wherein N is an integer greater than or equal to 2; the second acquisition module is used for acquiring the proportion of each fluorescent material after the N fluorescent materials are mixed; the calculation module is used for calculating the emission spectrum proportionality coefficient of the N fluorescent materials after being mixed according to any proportion; the establishing module is used for establishing a neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient; and the prediction module is used for acquiring the emission spectrum proportionality coefficient through the neural network prediction model and realizing the prediction of the emission spectrum of the mixed N fluorescent materials according to the emission spectrum proportionality coefficient acquired through the neural network prediction model and the emission spectrum of the fluorescent material corresponding to the emission spectrum proportionality coefficient.
The invention has the beneficial effects that:
the method provided by the invention has the advantages that the beer lambert model is corrected, the beer lambert model is popularized to a luminescent material system mixed by multiple kinds of fluorescent powder, the neural network training and learning are carried out according to the proportionality coefficient obtained by the beer lambert model and the proportion of each fluorescent powder, the predicted value of the proportionality coefficient is obtained by applying a neural network algorithm, then the emission spectra of the corresponding fluorescent powder are multiplied and summed to realize the prediction of the emission spectra after the multiple kinds of fluorescent powder are mixed, so that the redundant experimental test is replaced, the manpower and the time are saved, and the method has a certain guiding significance for researching the design of a high-quality white light LED light source.
Drawings
FIG. 1 is a flow chart of a hybrid fluorescent material emission spectrum prediction method flow according to an embodiment of the invention;
FIG. 2 is an absorption spectrum of each of three phosphors according to an embodiment of the present invention;
FIG. 3 is an emission spectrum of each of three phosphors according to one embodiment of the present invention;
FIG. 4 is a topological diagram of a BP neural network prediction model according to one embodiment of the present invention;
FIG. 5 is a graph of the percentage of error between neural network prediction and modified beer Lambert theory calculated scaling coefficients, in accordance with one embodiment of the present invention;
FIG. 6 shows three phosphors in a ratio of 7: 1: 2, comparing the emission spectrum of experiment and neural network prediction;
FIG. 7 shows three phosphors in a ratio of 5: 3: 2, comparing the emission spectrum of experiment and neural network prediction;
FIG. 8 shows three phosphors in a ratio of 2: 2: 6, comparing the emission spectrum of the experiment and the prediction of the neural network;
FIG. 9 shows three phosphors in a ratio of 2: 6: 2, comparing the emission spectrum of experiment and neural network prediction;
FIG. 10 shows three phosphors in a ratio of 3: 3: 4, comparing the emission spectrum of the experiment and the prediction of the neural network;
FIG. 11 is a block schematic diagram of a hybrid fluorescent material emission spectrum prediction device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the method for predicting an emission spectrum of a mixed fluorescent material according to an embodiment of the present invention may include the following steps:
and S1, respectively obtaining absorption spectra, emission spectra and quantum efficiencies of the N fluorescent materials, wherein N is an integer greater than or equal to 2.
Wherein, the fluorescent material can be fluorescent powder, and the corresponding absorption spectrum can be abi(λ) and i represents the absorption spectrum of the i-th fluorescent material, e.g., ab1(λ) represents an absorption spectrum of the first fluorescent material; the corresponding emission spectrum can be emi(λ) and i represents the emission spectrum of the i-th fluorescent material, e.g. em1(λ) represents an emission spectrum of the first fluorescent material; the corresponding quantum efficiency can be represented by qiI denotes the quantum efficiency of the i-th fluorescent material, e.g. q1Indicating the quantum efficiency of the first fluorescent material.
And S2, acquiring the proportion of each fluorescent material after the N fluorescent materials are mixed. It should be noted that the ratio of each mixed fluorescent material is recorded and stored when being mixed.
And S3, calculating the emission spectrum proportionality coefficient of the N fluorescent materials mixed according to any proportion.
In one embodiment of the present invention, calculating the emission spectrum proportionality coefficient of the N fluorescent materials mixed according to any proportion includes: and calculating the emission spectrum proportionality coefficient of the N fluorescent materials mixed according to any proportion based on the corrected beer Lambert model.
It should be noted that, the beer lambertian model is only for a single phosphor light emitting system, and the quantum efficiency of a single phosphor and the mutual absorption between multiple phosphors are considered, so the beer lambertian model needs to be corrected, for example, the absorption probability of the mutual absorption between the phosphors is calculated first, and as a possible implementation, the emission spectrum proportionality coefficients after mixing N phosphors according to any proportion are calculated based on the corrected beer lambertian model, including:
and S31, calculating the absorption probability of mutual absorption among the fluorescent materials according to the respective absorption spectrum and emission spectrum of the N fluorescent materials.
In particular, by giving the respective absorption spectra ab of the N phosphorsi(lambda) and emission spectrum emi(lambda) calculating the absorption probability of mutual absorption among the fluorescent powders. For example, the absorption probability of mutual absorption between the i-type phosphor and the j-type phosphor, wherein the i-type phosphor absorbs blue light, the i-type phosphor absorbs light emitted by the j-type phosphor, the j-type phosphor absorbs light emitted by the i-type phosphor, and the absorption probability of mutual absorption between phosphorsijIs the probability that the light emitted by the j-type phosphor is absorbed by the i-type phosphor, i.e. the i-type phosphor absorption spectrum ab i(lambda) and j-type fluorescent material emission spectrum emi(λ) is generated by the following formula (1):
wherein, bi(λ) represents an absorption spectrum of the i-type fluorescent material, emj(λ) represents a j-type fluorescent material emission spectrum.
And S32, calculating the emission spectrum proportionality coefficient of the N fluorescent materials mixed according to any proportion according to the proportion of each fluorescent material, the quantum efficiency and the absorption probability of mutual absorption among the fluorescent materials.
By the ratio r of the individual monochromatic phosphorsiQuantum efficiency qiAnd by introducing a mutual absorption probability between the fluorescent materialsijThen, the emission spectrum proportionality coefficient is generated by the following formula (2):
wherein, KiRepresenting the emission spectral scaling factor, riAnd rjRepresents the proportion of the fluorescent material, qiAnd q isjWhich represents the quantum efficiency of the fluorescent material,ijindicating the probability that light emitted by the j-type phosphor is absorbed by the i-type phosphor,jiindicating the probability that light emitted by the i-type phosphor is absorbed by the j-type phosphor.
It should be noted that the calculation manners of the above equations (1) and (2) can be implemented by programming software, for example, by Matlab programming.
And S4, establishing a neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient. The neural Network prediction model may be a Back-ProPagation (BP) neural Network prediction model.
According to one embodiment of the invention, the establishing of the neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient comprises the following steps: and establishing a neural network prediction model by taking the emission spectrum proportionality coefficient obtained by mixing the N fluorescent materials according to any proportion and the proportion of each fluorescent material as a data set of the neural network prediction model, wherein the proportion of each fluorescent material is taken as an input variable of the neural network prediction model, and the emission spectrum proportionality coefficient obtained by mixing the N fluorescent materials according to any proportion is taken as an output variable.
Specifically, an input layer, an output layer, a hidden layer and a weight threshold of the BP neural network prediction model are set:
an input layer: in the ratio r between the phosphorsiAs an input variable, assuming that the number of input layer nodes is m;
an output layer: the proportionality coefficient K calculated in the step 3iAs an output variable, assuming that the number of output layer nodes is n;
hidden layer: the number of hidden layer nodes is obtained by the following empirical formula (3):
wherein q is the number of hidden layer nodes, m is the number of input layer nodes, n is the number of output layer nodes, and a is an adjustment constant between 1 and 10;
weight and threshold: and after the weight and the threshold are preliminarily selected, correcting through an error back propagation principle.
The activation functions of the neurons in the hidden layer and the output layer of the BP neural network adopt tansig type hyperbolic tangent sigmoid transfer functions, and the expression is as follows:
it should be noted that, the normalization and de-normalization processes for the input and output samples of the training set and the test set can be implemented by the mapminimax function in the Matlab programming software.
In addition, after the iteration times, the training target and the learning rate are set, the emission spectrum proportionality coefficient k can be predictedi' the creation execution for the BP neural network can be implemented in Matlab.
And S5, acquiring the emission spectrum proportionality coefficient through the neural network prediction model, and realizing the prediction of the emission spectrum of the mixed N fluorescent materials according to the emission spectrum proportionality coefficient acquired through the neural network prediction model and the emission spectrum of the fluorescent material corresponding to the emission spectrum proportionality coefficient.
Specifically, the scale factor k is obtained by BP neural network predictioni' respectively multiplying the emission spectra of the corresponding phosphors and summing, i.e.The method can obtain the equivalent emission spectrum of a plurality of mixed fluorescent powders, and realize the prediction of the emission spectrum of the mixed fluorescent powders. As a possible implementation, the emission spectrum after the fluorescent material in N is mixed can be predicted by the following formula (4):
Wherein emeq(λ) represents the predicted emission spectrum, k, of N phosphors after mixingi' represents an emission spectrum scale coefficient obtained by a neural network prediction model, and em (lambda) represents ki' emission spectrum of the corresponding fluorescent material.
In order to describe the technical solution of the present invention in more detail, the following takes 3 kinds of fluorescent materials as an example, and describes how to realize the prediction of the mixed emission spectrum of the 3 kinds of fluorescent materials in detail.
3 types of fluorescent powder (fluorescent materials) are selected, namely yellow fluorescent powder YAG04, red fluorescent powder R6535 and green fluorescent powder G525 which are named as 1, 2 and 3. The absorption spectra (ab1, ab2, ab3) and emission spectra (em1, em2, em3) of the three monochromatic phosphors were measured separately, and as shown in fig. 2 and 3, the absorption probability was calculated by the formula using Matlab softwareij。
The proportionality coefficient KiThe formula (a) is expressed in a matrix form, wherein the quantum efficiency q of the three phosphors is1、q2、q3Respectively 0.75, 0.8 and 0.78, and 80 groups of proportionality coefficients K can be calculated according to the quantum efficiencies of the three fluorescent powders, the different proportions of 80 groups of the three fluorescent powders and the mutual absorption probability among 3 fluorescent powdersi. Coefficient of proportionality KiThe matrix expression of the formula is as follows:
the proportion r of 80 groups of fluorescent powder iAnd 80 sets of calculated proportionality coefficients KiAs a data set of the BP neural network, 75 groups are shared by a training set and 5 groups are shared by a test set. Selecting the ratio r of 3 kinds of fluorescent powder as input layer variableiTherefore, the number of nodes in the input layer is m — 3. The output layer variable is a proportionality coefficient ki' so, the output layer node n is 3, and the prediction result is optimal when the number of hidden layer nodes is 6 obtained by an empirical formula, so the number of hidden layer nodes is 6, and the topological graph of the BP neural network prediction model of the present embodiment is shown in fig. 4. The input variables for testing five sets of data are shown in table 1 below:
TABLE 1
| Numbering | r1 | r2 | r3 |
| 1 | 7 | 1 | 2 |
| 2 | 5 | 3 | 2 |
| 3 | 2 | 2 | 6 |
| 4 | 2 | 6 | 2 |
| 5 | 3 | 3 | 4 |
After the iteration times, the training targets and the learning rate are set, 5 groups of proportionality coefficients serving as a test set are predicted through a BP neural network algorithm, the error percentage between the predicted proportionality coefficients and the proportionality coefficients calculated based on the modified beer Lambert theory is analyzed, the maximum error percentage between the predicted proportionality coefficients and the proportionality coefficients is not more than 5%, the average error is not more than 2.1%, as shown in FIG. 5, wherein the error percentage formula is shown as the following formula:
wherein E isPFor error percentage, R is the scaling factor calculated by beer Lambert theory, and P is the scaling factor predicted by the neural network.
And (3) obtaining the proportional coefficient corresponding to each group of test sets through BP neural network prediction, respectively multiplying the proportional coefficients by the emission spectra of the corresponding fluorescent powder, and then summing the proportional coefficients to calculate the emission spectra of the mixed fluorescent powder.
In order to verify the accuracy of the method, the yellow fluorescent powder YAG, the red fluorescent powder R6535 and the green fluorescent powder G525 are measured according to the proportion given in the table 1 and are fully mixed, the emission spectrum of the mixed fluorescent powder is measured by equipment, the emission spectrum predicted by a BP neural network is compared with the emission spectrum tested by the equipment, and as can be seen from the graphs in FIGS. 6-10, the emission spectrum predicted by the method has better coincidence degree with the emission spectrum tested by the equipment. Therefore, the emission spectrum of the mixed fluorescent material can be well predicted by adopting the BP neural network.
In summary, the mixed fluorescent material emission spectrum prediction method provided by the invention is popularized to a multi-fluorescent powder mixed luminescent material system by correcting the beer lambert model, training and learning of the neural network are carried out according to the proportionality coefficient obtained by correcting the beer lambert model and the proportion of each fluorescent powder, the prediction value of the proportionality coefficient is obtained by applying the neural network algorithm, and then the emission spectra of the corresponding fluorescent powder are multiplied and summed to realize the prediction of the emission spectrum after mixing the multiple fluorescent powders, so that a complicated experimental test is replaced, the manpower and the time are saved, and a certain guiding significance is provided for researching the design of a high-quality white light LED light source.
FIG. 11 is a block schematic diagram of a hybrid fluorescent material emission spectrum prediction device according to an embodiment of the present invention.
As shown in fig. 11, the mixed fluorescent material emission spectrum prediction apparatus of the present invention may include: a first acquisition module 10, a second acquisition module 20, a calculation module 30, a creation module 40 and a prediction module 50.
The first obtaining module 10 is configured to obtain absorption spectra, emission spectra, and quantum efficiencies of N fluorescent materials, respectively, where N is an integer greater than or equal to 2. The second obtaining module 20 is configured to obtain a ratio of each of the N mixed fluorescent materials. The calculating module 30 is used for calculating the emission spectrum proportionality coefficient of the N fluorescent materials mixed according to any proportion. The establishing module 40 is used for establishing a neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient. The prediction module 50 is configured to obtain the emission spectrum proportionality coefficient through the neural network prediction model, and predict the emission spectrum after the N fluorescent materials are mixed according to the emission spectrum proportionality coefficient obtained through the neural network prediction model and the emission spectrum of the fluorescent material corresponding to the emission spectrum proportionality coefficient.
According to an embodiment of the present invention, the calculating module 30 calculates the emission spectrum proportionality coefficients of the N fluorescent materials mixed according to an arbitrary proportion, and is specifically configured to calculate the emission spectrum proportionality coefficients of the N fluorescent materials mixed according to an arbitrary proportion based on the modified beer lambertian model.
According to an embodiment of the present invention, the calculation module 30 is further configured to calculate an absorption probability of mutual absorption between each of the N fluorescent materials according to the respective absorption spectrum and emission spectrum of the N fluorescent materials; and calculating the emission spectrum proportion coefficient of the N fluorescent materials mixed according to any proportion according to the proportion of each fluorescent material, the quantum efficiency and the absorption probability of mutual absorption among the fluorescent materials.
According to one embodiment of the invention, the emission spectrum scaling factor is generated by the following formula:
wherein, KiRepresenting the emission spectral scaling factor, riAnd rjRepresents the proportion of the fluorescent material, qiAnd q isjWhich represents the quantum efficiency of the fluorescent material,ijindicating the probability that light emitted by the j-type phosphor is absorbed by the i-type phosphor,jiindicating the probability that light emitted by the i-type phosphor is absorbed by the j-type phosphor.
According to one embodiment of the present invention, the absorption probability of mutual absorption between each fluorescent material is generated by the following formula:
wherein, bi(λ) represents an absorption spectrum of the i-type fluorescent material, emj(λ) represents a j-type fluorescent material emission spectrum.
According to an embodiment of the present invention, the establishing module 40 establishes the neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient, and is specifically configured to establish the neural network prediction model by taking the emission spectrum proportion coefficient obtained by mixing N kinds of fluorescent materials according to any proportion and the proportion of each fluorescent material as a data set of the neural network prediction model, where the proportion of each fluorescent material is used as an input variable of the neural network prediction model, and the emission spectrum proportion coefficient obtained by mixing N kinds of fluorescent materials according to any proportion is used as an output variable.
According to one embodiment of the present invention, the prediction module 50 predicts the emission spectra of the N mixed fluorescent materials by the following formula:
wherein emeq(λ) represents the predicted emission spectrum, k, of N phosphors after mixingi' represents an emission spectrum scale coefficient obtained by a neural network prediction model, and em (lambda) represents ki' emission spectrum of the corresponding fluorescent material.
It should be noted that details not disclosed in the mixed fluorescent material emission spectrum prediction apparatus of the embodiment of the present invention refer to details disclosed in the mixed fluorescent material emission spectrum prediction method of the embodiment of the present invention, and details are not repeated herein.
In summary, the present invention utilizes the correction beer lambert model to popularize the model into a luminescent material system with a plurality of mixed phosphors, trains and learns the neural network according to the proportionality coefficient obtained by the correction beer lambert model and the ratio of each phosphor, obtains the predicted value of the proportionality coefficient by applying the neural network algorithm, multiplies the emission spectra of the corresponding phosphors and sums up to predict the emission spectra after the plurality of phosphors are mixed, thereby replacing the complicated experimental tests, saving the manpower and time, and having a certain guiding significance for researching the design of the high-quality white light LED light source.
In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The meaning of "plurality" is two or more unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (8)
1. A mixed fluorescent material emission spectrum prediction method is characterized by comprising the following steps:
respectively obtaining absorption spectra, emission spectra and quantum efficiencies of N fluorescent materials, wherein N is an integer greater than or equal to 2;
obtaining the proportion of each fluorescent material after the N fluorescent materials are mixed;
calculating the emission spectrum proportionality coefficient of the N fluorescent materials after being mixed according to any proportion;
establishing a neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient;
and acquiring an emission spectrum proportionality coefficient through the neural network prediction model, and realizing the prediction of the emission spectrum of the mixed N fluorescent materials according to the emission spectrum proportionality coefficient acquired through the neural network prediction model and the emission spectrum of the fluorescent material corresponding to the emission spectrum proportionality coefficient.
2. The method for predicting the emission spectrum of the mixed fluorescent material according to claim 1, wherein the calculating the emission spectrum proportionality coefficient of the N kinds of fluorescent materials after being mixed according to any proportion comprises:
and calculating the emission spectrum proportionality coefficient of the N fluorescent materials mixed according to any proportion based on the corrected beer Lambert model.
3. The method for predicting the emission spectrum of the mixed fluorescent material according to claim 2, wherein calculating the emission spectrum proportionality coefficients of the N fluorescent materials mixed according to any proportion based on the modified beer lambertian model comprises:
calculating the absorption probability of mutual absorption among the fluorescent materials according to the respective absorption spectrum and emission spectrum of the N fluorescent materials;
and calculating the emission spectrum proportion coefficient of the N fluorescent materials mixed according to any proportion according to the proportion of each fluorescent material, the quantum efficiency and the absorption probability of mutual absorption among the fluorescent materials.
4. The method of claim 3, wherein the emission spectrum scaling factor is generated by the following formula:
wherein, K iRepresenting the emission spectral scaling factor, riAnd rjRepresents the proportion of the fluorescent material, qiAnd q isjWhich represents the quantum efficiency of the fluorescent material,ijindicating the probability that light emitted by the j-type phosphor is absorbed by the i-type phosphor,jiindicating the probability that light emitted by the i-type phosphor is absorbed by the j-type phosphor.
5. The method for predicting an emission spectrum of a mixed fluorescent material according to claim 4, wherein the absorption probability of mutual absorption between each fluorescent material is generated by the following formula:
wherein, bi(λ) represents an absorption spectrum of the i-type fluorescent material, emj(λ) represents a j-type fluorescent material emission spectrum.
6. The method for predicting the emission spectrum of the mixed fluorescent material according to claim 1, wherein the step of establishing a neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient comprises the following steps:
and establishing a neural network prediction model by taking the emission spectrum proportionality coefficient obtained by mixing the N fluorescent materials according to any proportion and the proportion of each fluorescent material as a data set of the neural network prediction model, wherein the proportion of each fluorescent material is taken as an input variable of the neural network prediction model, and the emission spectrum proportionality coefficient obtained by mixing the N fluorescent materials according to any proportion is taken as an output variable.
7. The method for predicting the emission spectrum of the mixed fluorescent material according to claim 1, wherein the emission spectrum of the N fluorescent materials after mixing is predicted by the following formula:
wherein emeq(λ) represents the predicted emission spectrum, k, of N phosphors after mixingi' represents an emission spectrum scale coefficient obtained by the neural network prediction model, and em (lambda) represents ki' emission spectrum of the corresponding fluorescent material.
8. A mixed fluorescent material emission spectrum prediction device, comprising:
the first acquisition module is used for respectively acquiring the absorption spectrum, the emission spectrum and the quantum efficiency of N fluorescent materials, wherein N is an integer greater than or equal to 2;
the second acquisition module is used for acquiring the proportion of each fluorescent material after the N fluorescent materials are mixed;
the calculation module is used for calculating the emission spectrum proportionality coefficient of the N fluorescent materials after being mixed according to any proportion;
the establishing module is used for establishing a neural network prediction model according to the proportion of each fluorescent material and the emission spectrum proportion coefficient;
and the prediction module is used for acquiring the emission spectrum proportionality coefficient through the neural network prediction model and realizing the prediction of the emission spectrum of the mixed N fluorescent materials according to the emission spectrum proportionality coefficient acquired through the neural network prediction model and the emission spectrum of the fluorescent material corresponding to the emission spectrum proportionality coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010649378.XA CN111860987A (en) | 2020-07-08 | 2020-07-08 | Mixed fluorescent material emission spectrum prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010649378.XA CN111860987A (en) | 2020-07-08 | 2020-07-08 | Mixed fluorescent material emission spectrum prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111860987A true CN111860987A (en) | 2020-10-30 |
Family
ID=73152386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010649378.XA Pending CN111860987A (en) | 2020-07-08 | 2020-07-08 | Mixed fluorescent material emission spectrum prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860987A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112816687A (en) * | 2020-12-31 | 2021-05-18 | 华南农业大学 | Broad-spectrum immunosensor for image matching by using machine learning |
Citations (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4725316A (en) * | 1985-04-09 | 1988-02-16 | Eldon Enterprises Ltd. | Color compositions and method |
| JPH0238484A (en) * | 1988-07-27 | 1990-02-07 | Toshiba Corp | Inorganic light-emitting substance |
| US5424959A (en) * | 1993-07-19 | 1995-06-13 | Texaco Inc. | Interpretation of fluorescence fingerprints of crude oils and other hydrocarbon mixtures using neural networks |
| WO1997023776A1 (en) * | 1995-12-21 | 1997-07-03 | Philips Electronics N.V. | X-ray fluorescence analysis utilizing a neural network for determining composition ratios |
| JPH09284581A (en) * | 1996-04-15 | 1997-10-31 | Toyo Ink Mfg Co Ltd | Color simulation device |
| US5864834A (en) * | 1994-05-20 | 1999-01-26 | Tokyo Ink Manufacturing Co., Ltd. | Method and apparatus for estimating a special reflectance distribution or a spectral transmittance distribution using illuminant-independent characteristic parameters |
| JPH11341297A (en) * | 1998-05-29 | 1999-12-10 | Toyo Ink Mfg Co Ltd | Device and method for toning |
| JP2000308097A (en) * | 1999-04-19 | 2000-11-02 | Toyo Ink Mfg Co Ltd | Method and device for predicting displaying color of crt |
| JP2001045307A (en) * | 1999-07-26 | 2001-02-16 | Toyo Ink Mfg Co Ltd | Color estimating method |
| DE69627366D1 (en) * | 1996-03-11 | 2003-05-15 | Shell Int Research | METHOD FOR PREDICTING A PHYSICAL PROPERTY OF A RESIDUAL HYDROCARBON MATERIAL |
| JP2003169224A (en) * | 2001-12-03 | 2003-06-13 | Toppan Printing Co Ltd | Method for calculating color gamut of color material, method for discriminating color reproduction, method for calculating color material blending ratio, apparatus for calculating color gamut of color material, apparatus for discriminating color reproduction, and apparatus for calculating color material blending ratio |
| US20060091790A1 (en) * | 2004-10-28 | 2006-05-04 | Dowa Mining Co., Ltd. | Phosphor mixture and light emitting device |
| CN1885071A (en) * | 2005-06-23 | 2006-12-27 | 住友化学株式会社 | Method for producing optical film |
| JP2008163061A (en) * | 2006-12-27 | 2008-07-17 | Kyushu Institute Of Technology | Phosphor material and lamp |
| US20090326383A1 (en) * | 2008-06-18 | 2009-12-31 | Michael Barnes | Systems and methods for hyperspectral imaging |
| US20100304421A1 (en) * | 2007-10-04 | 2010-12-02 | Cranfield University | Optical monitoring method |
| US20110101848A1 (en) * | 2009-10-30 | 2011-05-05 | Institut National D'optique | Fluorescence-based light emitting device |
| US20120043478A1 (en) * | 2010-08-18 | 2012-02-23 | Canon Kabushiki Kaisha | Fluorescent Estimating Apparatus, Fluorescent Estimating Method, and Fluorescent Measuring Apparatus |
| CN102507516A (en) * | 2011-09-28 | 2012-06-20 | 江南大学 | Method for detecting food pigment by combination of fluorescence spectroscopy and artificial neural network |
| US20130264937A1 (en) * | 2010-10-15 | 2013-10-10 | Mitsubishi Chemical Corporation | White light-emitting device and illumination device |
| TW201412935A (en) * | 2012-07-02 | 2014-04-01 | Nanosys Inc | Highly luminescent nanostructures and methods of producing same |
| CN103911153A (en) * | 2014-03-25 | 2014-07-09 | 复旦大学 | Up-conversion emission fluorescent powder precursor and preparation method thereof |
| JP2014175322A (en) * | 2013-03-05 | 2014-09-22 | Mitsubishi Chemicals Corp | Light-emitting device, luminaire having the same, image display device, fluorescent material composition, and wavelength conversion member arranged by shaping fluorescent material composition |
| DE102014105994A1 (en) * | 2013-04-29 | 2014-10-30 | Technische Universität Dresden | Method for detecting signal patterns in spectroscopically generated data sets |
| CN104409608A (en) * | 2014-11-12 | 2015-03-11 | 上海亚明照明有限公司 | High-voltage white-light LED with high mesopic luminous efficiency and acquisition method thereof |
| US20150102261A1 (en) * | 2012-05-22 | 2015-04-16 | Ube Material Industries, Ltd. | Phosphor mixture having optimized color rendering properties and emission intensity of emitted light in visible region |
| US20150184813A1 (en) * | 2013-12-31 | 2015-07-02 | Xicato, Inc. | Efficient led-based illumination modules with high color rendering index |
| JP2015225070A (en) * | 2014-05-25 | 2015-12-14 | 泰三 毛利 | Prediction of spectrum or chromaticity of mixed color material and determination of mixture of color material having desired spectrum or chromaticity |
| US20160116410A1 (en) * | 2014-10-24 | 2016-04-28 | The Board Of Trustees Of The Leland Stanford Junior University | Apparatus and method for joint reflectance and fluorescence spectra estimation |
| US20170373700A1 (en) * | 2014-12-22 | 2017-12-28 | Massachusetts Institute Of Technology | Analog to digital computations in biological systems |
| CN109086827A (en) * | 2018-08-10 | 2018-12-25 | 北京百度网讯科技有限公司 | Method and apparatus for detecting monocrystaline silicon solar cell defect |
| CN110222870A (en) * | 2019-05-05 | 2019-09-10 | 中国农业大学 | Assimilate the Regional Fall Wheat yield estimation method of satellite fluorescence data and crop growth model |
| CN110414729A (en) * | 2019-07-19 | 2019-11-05 | 西北农林科技大学 | The potential maximum photosynthetic capacity prediction technique of plant based on characteristic wavelength |
| US20190340306A1 (en) * | 2017-04-27 | 2019-11-07 | Ecosense Lighting Inc. | Methods and systems for an automated design, fulfillment, deployment and operation platform for lighting installations |
| CN110426380A (en) * | 2019-09-29 | 2019-11-08 | 常州星宇车灯股份有限公司 | A kind of test device of the laser excitation remote fluorescence material of transmission-type controllable temperature |
| CN110487403A (en) * | 2019-09-02 | 2019-11-22 | 常州市武进区半导体照明应用技术研究院 | A kind of prediction technique of LED light spectral power distributions |
| CN110543656A (en) * | 2019-07-12 | 2019-12-06 | 华南理工大学 | LED fluorescent powder glue coating thickness prediction method based on deep learning |
| WO2019237203A1 (en) * | 2018-06-12 | 2019-12-19 | Paige Growth Technologies Inc. | Devices, systems and methods of identifying plants, plant material and plant state |
| US20200166909A1 (en) * | 2018-11-20 | 2020-05-28 | Relativity Space, Inc. | Real-time adaptive control of manufacturing processes using machine learning |
| EP3675476A1 (en) * | 2018-12-25 | 2020-07-01 | SCREEN Holdings Co., Ltd. | Color prediction model construction method and color prediction model construction program |
-
2020
- 2020-07-08 CN CN202010649378.XA patent/CN111860987A/en active Pending
Patent Citations (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4725316A (en) * | 1985-04-09 | 1988-02-16 | Eldon Enterprises Ltd. | Color compositions and method |
| JPH0238484A (en) * | 1988-07-27 | 1990-02-07 | Toshiba Corp | Inorganic light-emitting substance |
| US5424959A (en) * | 1993-07-19 | 1995-06-13 | Texaco Inc. | Interpretation of fluorescence fingerprints of crude oils and other hydrocarbon mixtures using neural networks |
| US5864834A (en) * | 1994-05-20 | 1999-01-26 | Tokyo Ink Manufacturing Co., Ltd. | Method and apparatus for estimating a special reflectance distribution or a spectral transmittance distribution using illuminant-independent characteristic parameters |
| WO1997023776A1 (en) * | 1995-12-21 | 1997-07-03 | Philips Electronics N.V. | X-ray fluorescence analysis utilizing a neural network for determining composition ratios |
| DE69627366D1 (en) * | 1996-03-11 | 2003-05-15 | Shell Int Research | METHOD FOR PREDICTING A PHYSICAL PROPERTY OF A RESIDUAL HYDROCARBON MATERIAL |
| JPH09284581A (en) * | 1996-04-15 | 1997-10-31 | Toyo Ink Mfg Co Ltd | Color simulation device |
| JPH11341297A (en) * | 1998-05-29 | 1999-12-10 | Toyo Ink Mfg Co Ltd | Device and method for toning |
| JP2000308097A (en) * | 1999-04-19 | 2000-11-02 | Toyo Ink Mfg Co Ltd | Method and device for predicting displaying color of crt |
| JP2001045307A (en) * | 1999-07-26 | 2001-02-16 | Toyo Ink Mfg Co Ltd | Color estimating method |
| JP2003169224A (en) * | 2001-12-03 | 2003-06-13 | Toppan Printing Co Ltd | Method for calculating color gamut of color material, method for discriminating color reproduction, method for calculating color material blending ratio, apparatus for calculating color gamut of color material, apparatus for discriminating color reproduction, and apparatus for calculating color material blending ratio |
| US20060091790A1 (en) * | 2004-10-28 | 2006-05-04 | Dowa Mining Co., Ltd. | Phosphor mixture and light emitting device |
| CN1885071A (en) * | 2005-06-23 | 2006-12-27 | 住友化学株式会社 | Method for producing optical film |
| JP2008163061A (en) * | 2006-12-27 | 2008-07-17 | Kyushu Institute Of Technology | Phosphor material and lamp |
| US20100304421A1 (en) * | 2007-10-04 | 2010-12-02 | Cranfield University | Optical monitoring method |
| US20090326383A1 (en) * | 2008-06-18 | 2009-12-31 | Michael Barnes | Systems and methods for hyperspectral imaging |
| US20110101848A1 (en) * | 2009-10-30 | 2011-05-05 | Institut National D'optique | Fluorescence-based light emitting device |
| US20120043478A1 (en) * | 2010-08-18 | 2012-02-23 | Canon Kabushiki Kaisha | Fluorescent Estimating Apparatus, Fluorescent Estimating Method, and Fluorescent Measuring Apparatus |
| US20130264937A1 (en) * | 2010-10-15 | 2013-10-10 | Mitsubishi Chemical Corporation | White light-emitting device and illumination device |
| CN102507516A (en) * | 2011-09-28 | 2012-06-20 | 江南大学 | Method for detecting food pigment by combination of fluorescence spectroscopy and artificial neural network |
| US20150102261A1 (en) * | 2012-05-22 | 2015-04-16 | Ube Material Industries, Ltd. | Phosphor mixture having optimized color rendering properties and emission intensity of emitted light in visible region |
| TW201412935A (en) * | 2012-07-02 | 2014-04-01 | Nanosys Inc | Highly luminescent nanostructures and methods of producing same |
| JP2014175322A (en) * | 2013-03-05 | 2014-09-22 | Mitsubishi Chemicals Corp | Light-emitting device, luminaire having the same, image display device, fluorescent material composition, and wavelength conversion member arranged by shaping fluorescent material composition |
| DE102014105994A1 (en) * | 2013-04-29 | 2014-10-30 | Technische Universität Dresden | Method for detecting signal patterns in spectroscopically generated data sets |
| US20150184813A1 (en) * | 2013-12-31 | 2015-07-02 | Xicato, Inc. | Efficient led-based illumination modules with high color rendering index |
| CN103911153A (en) * | 2014-03-25 | 2014-07-09 | 复旦大学 | Up-conversion emission fluorescent powder precursor and preparation method thereof |
| JP2015225070A (en) * | 2014-05-25 | 2015-12-14 | 泰三 毛利 | Prediction of spectrum or chromaticity of mixed color material and determination of mixture of color material having desired spectrum or chromaticity |
| US20160116410A1 (en) * | 2014-10-24 | 2016-04-28 | The Board Of Trustees Of The Leland Stanford Junior University | Apparatus and method for joint reflectance and fluorescence spectra estimation |
| CN104409608A (en) * | 2014-11-12 | 2015-03-11 | 上海亚明照明有限公司 | High-voltage white-light LED with high mesopic luminous efficiency and acquisition method thereof |
| US20170373700A1 (en) * | 2014-12-22 | 2017-12-28 | Massachusetts Institute Of Technology | Analog to digital computations in biological systems |
| US20190340306A1 (en) * | 2017-04-27 | 2019-11-07 | Ecosense Lighting Inc. | Methods and systems for an automated design, fulfillment, deployment and operation platform for lighting installations |
| WO2019237203A1 (en) * | 2018-06-12 | 2019-12-19 | Paige Growth Technologies Inc. | Devices, systems and methods of identifying plants, plant material and plant state |
| CN109086827A (en) * | 2018-08-10 | 2018-12-25 | 北京百度网讯科技有限公司 | Method and apparatus for detecting monocrystaline silicon solar cell defect |
| US20200166909A1 (en) * | 2018-11-20 | 2020-05-28 | Relativity Space, Inc. | Real-time adaptive control of manufacturing processes using machine learning |
| EP3675476A1 (en) * | 2018-12-25 | 2020-07-01 | SCREEN Holdings Co., Ltd. | Color prediction model construction method and color prediction model construction program |
| CN110222870A (en) * | 2019-05-05 | 2019-09-10 | 中国农业大学 | Assimilate the Regional Fall Wheat yield estimation method of satellite fluorescence data and crop growth model |
| CN110543656A (en) * | 2019-07-12 | 2019-12-06 | 华南理工大学 | LED fluorescent powder glue coating thickness prediction method based on deep learning |
| CN110414729A (en) * | 2019-07-19 | 2019-11-05 | 西北农林科技大学 | The potential maximum photosynthetic capacity prediction technique of plant based on characteristic wavelength |
| CN110487403A (en) * | 2019-09-02 | 2019-11-22 | 常州市武进区半导体照明应用技术研究院 | A kind of prediction technique of LED light spectral power distributions |
| CN110426380A (en) * | 2019-09-29 | 2019-11-08 | 常州星宇车灯股份有限公司 | A kind of test device of the laser excitation remote fluorescence material of transmission-type controllable temperature |
Non-Patent Citations (6)
| Title |
|---|
| CADMUS C.A.YUAN: "The extended Beer–Lambert theory for ray tracing modeling of LED chip-scaled packaging application with multiple luminescence materials", 《OPTICAL MATERIALS》, pages 193 - 198 * |
| 徐艳芳;张国生;李路海;丁莹琨;: "白光LED用YAG黄色荧光粉实用中发射光谱的测量方法", 光谱学与光谱分析, no. 07 * |
| 樊嘉杰等: "基于Lambert-Beer 理论与人工神经网络的 混合荧光粉发射光谱预测", 《稀有金属材料与工程》, vol. 50, no. 7 * |
| 罗亮亮;樊嘉杰;经周;钱诚;樊学军;张国旗;: "LED白光芯片的光色一致性及光谱优化设计方法研究", 照明工程学报, no. 01 * |
| 许建文;陈国庆;吴亚敏;马超群;辜姣;: "两种荧光粉混合涂覆的白光LED的光谱方程的建立", 光谱学与光谱分析, no. 03 * |
| 陈英涛;吴炜;石一兴;何艳;王正勇;: "岩屑荧光图像的混合石油组分研究", 四川大学学报(自然科学版), no. 03, 28 May 2012 (2012-05-28) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112816687A (en) * | 2020-12-31 | 2021-05-18 | 华南农业大学 | Broad-spectrum immunosensor for image matching by using machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104199536B (en) | A kind of FPGA dynamic power consumption evaluation methods based on BP neural network | |
| CN110059377A (en) | A kind of fuel battery service life prediction technique based on depth convolutional neural networks | |
| Menche et al. | Asymptotic properties of degree-correlated scale-free networks | |
| CN113780436B (en) | Complex network key node identification method based on comprehensive degree | |
| Fan et al. | Machine-learning assisted prediction of spectral power distribution for full-spectrum white light-emitting diode | |
| CN111814401B (en) | LED life prediction method of BP neural network based on genetic algorithm | |
| CN105326475B (en) | A kind of Bioluminescence tomography reconstruction method differentiated based on multiple light courcess | |
| Panda | Quanos: adversarial noise sensitivity driven hybrid quantization of neural networks | |
| CN111612142B (en) | BP neural network-based high-power LED life prediction method | |
| CN111860987A (en) | Mixed fluorescent material emission spectrum prediction method and device | |
| CN108009730A (en) | A kind of photovoltaic power station system health status analysis method | |
| CN111163487B (en) | Communication waveform comprehensive transmission performance evaluation method and system | |
| CN112380768A (en) | BP neural network-based LED chip life prediction method | |
| CN114114039A (en) | Method and device for evaluating consistency of single battery cells of battery system | |
| Yeh et al. | A new universal generating function method for solving the single $(d,\tau) $-quick-path problem in multistate flow networks | |
| CN101206727B (en) | Data processing apparatus, data processing method | |
| CN104244502A (en) | Method and device for determining arrangement of illuminance transducer and illumination control system | |
| Guo et al. | Bit-width adaptive accelerator design for convolution neural network | |
| CN106650060A (en) | Prediction method of internal resistance attenuation coefficient for photovoltaic cells | |
| CN111191340A (en) | Reliability test method for shipborne satellite communication system | |
| CN116187383A (en) | Method for determining 3D NoC optimal test plan based on improved whale optimization algorithm | |
| CN116502939A (en) | Load adjustment evaluation method, device, equipment and medium | |
| CN113691312B (en) | Method and system for designing multi-path light source spectrum | |
| CN115270636A (en) | Deep learning-based marine fuel oil trace element analysis method | |
| CN112989689A (en) | Method for simulating RGB atmosphere light color |
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 |