CN103344600B - Characteristic wavelength selecting method for near infrared spectrum in ant colony optimization algorithm - Google Patents
Characteristic wavelength selecting method for near infrared spectrum in ant colony optimization algorithm Download PDFInfo
- Publication number
- CN103344600B CN103344600B CN201310269615.XA CN201310269615A CN103344600B CN 103344600 B CN103344600 B CN 103344600B CN 201310269615 A CN201310269615 A CN 201310269615A CN 103344600 B CN103344600 B CN 103344600B
- Authority
- CN
- China
- Prior art keywords
- variable
- infrared spectrum
- near infrared
- optimization algorithm
- ant colony
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a characteristic wavelength selecting method for a near infrared spectrum in an ant colony optimization algorithm. The method comprises the following steps: creating a partial least squares analysis model by utilizing all wavelength points of the near infrared spectrum as initial selection equivalent variables of the ant colony optimization algorithm and utilizing the quality or characteristics of a test object as reference standard, re-weighing and calculating to update a pheromone vector according to the predicated mean square error of the model, searching and obtaining the optimal near infrared spectrum wavelength combination through using iterative computations, performing circular computation for a plurality of times, and automatically judging so as to obtain the optimal characteristic wavelength of the near infrared spectrum. The characteristic wavelength selecting method provided by the invention adopts the global search and positive feedback mechanisms of the ant colony optimization algorithm so as to effectively avoid the defects of subjective wavelength selection in the modeling process, so that the model has strong robustness and applicability.
Description
Technical field
The present invention relates to near-infrared spectral analysis technology field, particularly relate to a kind of characteristic wavelength of near-infrared spectrum system of selection of ant colony optimization algorithm.
Background technology
Near infrared spectrum district refers to the electromagnetic wave of wavelength within the scope of 780 ~ 2526nm by ASTM definition, is molecular vibration spectrum frequency multiplication and sum of fundamental frequencies absorption spectra, has abundant structure and composition information, can be used for the composition of carbon-hydrogen organic and the measurement of character.Compared with conventional analytical techniques, there is Non-Destructive Testing, analysis efficiency is high, cost is low, favorable reproducibility, sample measure and generally do not need pre-service, be suitable for the advantage such as Site Detection and on-line analysis.Along with the fast development of near-infrared spectral analysis technology, Chemical Measurement and near infrared spectroscopy instrument, near-infrared spectral analysis technology is used widely in the every field of the national economic development.
By the near infrared spectrometer of advanced person, researcher can a large amount of spectroscopic data of quick obtaining.But the frequency multiplication of material in this spectrum district and sum of fundamental frequencies absorption signal weak, bands of a spectrum are overlapping, resolve complicated; And the data gathered due to instrument are except the self information of sample, further comprises other irrelevant information and noise, as electric noise, sample background etc., these information are difficult to all eliminate in pre-service; Secondly the information of some SPECTRAL REGION sample is very weak, and between the composition of sample or character, degree of correlation is not high; In addition, there is co-linear relationship in the spectroscopic data inside of same sample, easily produces data redundancy.If these data are all participated in modeling, not only calculated amount is large, model is complicated, and precision is also affected.Therefore, spectral signature variable optimization method becomes the key link improving modeling quality.
Ant colony optimization algorithm is the new development of artificial intelligence or swarm intelligence, having that distribution calculates, the feature of information positive feedback and heuristic search, solves the combinatorial optimization problems such as travelling salesman, communication, network route and quantitative structure activity relationship preferably.ZL200810101081.9 discloses a kind of ant group optimization-differential evolution fusion method solving traveling salesman problem; ZL201010176931.9 discloses a kind of characteristics of image optimum choice method and system based on improving ant group algorithm, and the target signature being applied to cotton foreign fiber image is excellent; ZL200910050355.0 discloses the automanual extracting method of a kind of remote sensing image water system network based on intelligent ant colony algorithm.To be all ant colony optimization algorithm solve for the Combinatorial Optimization of discrete data or half discrete data for these.The near infrared spectrum of agricultural product or food is a large amount of continuous print data, during for predicting component or character, particularly during blending ingredients, is difficult to directly determine its characteristic of correspondence wavelength, and optimal combined algorithm need be adopted to find maximally related information in spectrum.
Summary of the invention
(1) technical matters that will solve
The object of this invention is to provide a kind of characteristic wavelength of near-infrared spectrum system of selection of ant colony optimization algorithm; avoid the subjectivity because of the modeling of full spectrum or artificial selection wavelength; be conducive to simplifying NIR Spectroscopy Analysis Model, improve robustness and the applicability of near infrared prediction model.
(2) technical scheme
For solving the problem, the invention provides a kind of characteristic wavelength of near-infrared spectrum system of selection of ant colony optimization algorithm, comprise the following steps: A: first pre-service is carried out near infrared spectrum, for stress release treatment impact, and all samples are randomly divided into calibration set and checking collection; B: each wavelength points of pretreated near infrared spectrum is as the variable to be selected of ant colony optimization algorithm, adopt Monte Carlo-wheel disc robin assignment in the pheromones weights of variable to be selected, the variable that pheromones weights are high is selected from variables set, until variable number reaches maximum variable number, set up partial least squares analysis model with selected variable, export root-mean-square error; C: when not reaching maximum iteration time, with the transforming function transformation function lastest imformation of minimum output root-mean-square error element vector, again carries out variables choice, sets up partial least square model together with the two stage selected variable in front and back; D: after reaching maximum iteration time, all by the variables collection selected through probability threshold value sorting, high probability variable is carried out modeling as the input of partial least square method, each variable synergy, exports optimum variable combination and the root-mean-square error of this circulation; E: after reaching maximum cycle, compares the modeling result of each circulation, selects optimum variable combination, i.e. the characteristic wavelength of the corresponding a certain component of near infrared spectrum or character.
Preferably, described ant colony optimization algorithm selects the concrete steps of characteristic variable as follows: the pheromones vector of (1) near-infrared spectrum wavelength point is τ
(n-1)time, choice variable group v
0; (2) when reaching maximum variable number, partial least square model is set up, with the root-mean-square error calculating target function F of model; (3), when not reaching maximum iteration time, objective function F and pheromones attenuation coefficient ρ carry out the vectorial τ of lastest imformation element
(n), again carry out Monte Carlo probability selection, and repeat step (1) and (2); (4) after reaching setting iterations, start loop computation, repeat step (1) ~ (3); (5) according to error minimum principle, the lowest mean square root error of the gained model of more each circulation, obtains near infrared spectrum optimal characteristics wavelength.
Preferably, described objective function is set to F=Q/ (1+RMSE
min), wherein,
y
ifor the measured value of sample components or character,
for predicted value, Significance factors Q is constant, for the convergence validity of adjustment aim function.
(3) beneficial effect
The present invention adopts the beneficial effect of technique scheme to be: the characteristic wavelength of ant colony optimization algorithm selects the mode adopting the search of Distributed Calculation, positive feedback mechanism and Greedy, there is the ability of very strong global search most optimum wavelengths combination, solve the modeling of full spectrum or the subjective low problem poor for applicability of model accuracy selecting wavelength modeling to cause; Adopt lowest mean square root error as objective function, and introduce constant Significance factors, can the speed of convergence of effective adjustment aim function, the renewal of appropriate adjustment information element; The analytical model that ant colony optimization algorithm selects characteristic wavelength of near-infrared spectrum to set up is simple, and counting yield is high, and strong robustness, the applicability of model are wide.
Accompanying drawing explanation
Fig. 1 is ant colony optimization algorithm process flow diagram;
Fig. 2 is the characteristic wavelength of near-infrared spectrum figure that ant colony optimization algorithm is selected.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples for illustration of the present invention, but are not used for limiting the scope of the invention.
The characteristic wavelength of near-infrared spectrum system of selection of a kind of ant colony optimization algorithm of the present invention comprises the steps: first to carry out pre-service near infrared spectrum, for stress release treatment impact, and according to the ratio of about 2:1, all samples is randomly divided into calibration set and checking collection; Each wavelength points of pretreated near infrared spectrum is as the variable to be selected of ant colony optimization algorithm; Adopt Monte Carlo-wheel disc robin assignment in the pheromones weights of variable to be selected, from variables set, select the variable that pheromones weights are high, until variable number reaches maximum variable number, set up partial least squares analysis model with selected variable, export root-mean-square error; When not reaching maximum iteration time, with the transforming function transformation function lastest imformation of minimum output root-mean-square error element vector, again carry out variables choice, set up partial least square model together with the two stage selected variable in front and back; After reaching maximum iteration time, all by the variables collection selected through probability threshold value sorting, high probability variable is carried out modeling as the input of partial least square method, each variable synergy, exports optimum variable combination and the root-mean-square error of this circulation; After reaching maximum cycle, the modeling result of each circulation is compared, select optimum variable combination, be i.e. the characteristic wavelength of the corresponding a certain component of near infrared spectrum or character.
First the present invention carries out pre-service near infrared spectrum.During near infrared spectra collection, the noise informations such as many high-frequency random noises, baseline wander, grain size and light scattering are had to sandwich, this will affect the correlationship between near infrared spectrum and soluble solid content, and directly affect the reliability and stability of institute's Modling model.For stress release treatment impact, normal adopt that standard normal variable conversion, S-G are level and smooth, homogenization, multiplicative scatter correction, minimum/one or both greatly in normalizing, first order derivative, second derivative etc. are used in conjunction and carry out pre-service near infrared spectrum.General Requirements total number of samples is greater than 60, according to the ratio of about 2:1, all samples is randomly divided into calibration set and checking collection.
Ant colony optimization algorithm is a kind of iterative algorithm, and algorithm realization flow process as shown in Figure 1.Each wavelength points of pretreated near infrared spectrum is as the variable to be selected of ant colony optimization algorithm, and each variable initial information element vector value is all set to 1, and namely each variable has identical by select probability; Starting algorithm program, adopt Monte Carlo-wheel disc robin assignment in the pheromones weights of variable to be selected, the variable that pheromones weights are high is selected from variables set, until variable number reaches maximum variable number, with the measured value of the soluble solid content of test sample book for normative reference, set up the partial least squares analysis model of calibration set sample with selected variable, export root-mean-square error; When not reaching maximum iteration time, with the transforming function transformation function lastest imformation of minimum output root-mean-square error element vector, again carry out variables choice, set up partial least square model together with the two stage selected variable in front and back; After reaching maximum iteration time, all by the variables collection selected through probability threshold value sorting, high probability variable is carried out modeling as the input of partial least square method, each variable synergy, exports optimum variable combination and the root-mean-square error of this circulation; After reaching maximum cycle, the modeling result of each circulation is compared, select optimum variable combination, be i.e. the characteristic wavelength of the corresponding a certain component of near infrared spectrum or character.
Ant colony optimization algorithm comprises laundering period and cooperation stage in the evolutionary process of seeking optimum solution.In the laundering period, each candidate solution constantly adjusts grouped by itself according to the information of accumulation; In the cooperation stage, by information interchange between candidate solution, can better separate with generation.The implementation procedure of ant colony optimization algorithm first need arrange correlation parameter:
(1) pheromones vector τ, initial information element vector value is all set to 1, namely each variable has identical by select probability, then Monte Carlo-wheel disc robin assignment is utilized, through n moment, after ant completes once circulation, on each variable, pheromones amount will make renewal, and selected variable information element is with τ
(n)=(1-ρ) τ
(n-1)+ ρ F changes, and not selected variable information element amount is because waving
(2) pheromones attenuation coefficient ρ directly affects the speed of algorithm convergence, and when ρ value is larger, volatilization is fast, and pheromones accumulation is few, therefore can not transmission of information between ant well; When ρ value is less, then volatilization seldom, and the information proportion before accumulated is comparatively large, and pheromones not easily upgrades, can not transmission of information all sidedly, and effect is also bad.
(3) objective function F, sets up a good objective function, can convergence speedup speed, carries
the predictive ability of type is better; And Significance factors Q is set, Q is constant, for the convergence validity of adjustment aim function.
(4) maximum variable number represents that the variable number of an ant group optimization iteration selection reaches setting value and just carries out offset minimum binary modeling.
(5) maximum iteration time represents the number of times that ant group optimization procedural information element vector upgrades.
(6) maximum cycle represents the number of times that ant colony optimization algorithm performs.
Ant colony optimization algorithm is adopted to select the concrete steps of characteristic variable as follows:
(1) the pheromones vector of near-infrared spectrum wavelength point is τ
(n-1)time, choice variable group v0;
(2) when reaching maximum variable number, partial least square model is set up, with the root-mean-square error calculating target function F of model;
(3), when not reaching maximum iteration time, objective function F and pheromones attenuation coefficient ρ carry out the vectorial τ of lastest imformation element
(n), again carry out Monte Carlo probability selection, and repeat step (1) and (2);
(4) after reaching setting iterations, start loop computation, repeat step (1) ~ (3);
(5) according to error minimum principle, the lowest mean square root error of the gained model of more each circulation, obtains near infrared spectrum optimal characteristics wavelength.
Using whole 5291 the wave number points of apple near infrared spectrum as alternative.The controling parameters of ant colony optimization algorithm is set as through test of many times checking: initial population size is 80, and maximum iteration time is 50 times, maximum cycle 20 times, and variables choice probability threshold value is 0.3, and Significance factors Q is 0.01.Pheromones attenuation coefficient ρ is taken as 0.65.Figure 2 shows that the wave number point selection probability that ant colony optimization algorithm once runs, the wave number point mainly wave number point such as 6275.2cm-1,5341.9cm-1,9538.2cm-1,4632.2cm-1 that selected probability is higher, may be interpreted as these wavelength points and soluble solid component degree of correlation is higher.Selected wave number point, all not in moisture absorption peak position, shows that the selection result of ant colony optimization algorithm has stronger antijamming capability.Ant colony optimization algorithm effectively can select characteristic wavelength of near-infrared spectrum, improves robustness and the applicability of model.
The above is only the preferred embodiment of the present invention; it should be pointed out that for those skilled in the art, under the prerequisite not departing from the technology of the present invention principle; can also make some improvement and replacement, these improve and replace and also should be considered as protection scope of the present invention.
Claims (1)
1. a characteristic wavelength of near-infrared spectrum system of selection for ant colony optimization algorithm, is characterized in that, comprise the following steps:
A: first carry out pre-service near infrared spectrum, for stress release treatment impact, and is randomly divided into calibration set and checking collection by all samples;
B: each wavelength points of pretreated near infrared spectrum is as the variable to be selected of ant colony optimization algorithm, adopt Monte Carlo-wheel disc robin assignment in the pheromones weights of variable to be selected, the variable that pheromones weights are high is selected from variables set, until variable number reaches maximum variable number, set up partial least squares analysis model with selected variable, export root-mean-square error;
C: when not reaching maximum iteration time, with the transforming function transformation function lastest imformation of minimum output root-mean-square error element vector, again carries out variables choice, sets up partial least square model together with the two stage selected variable in front and back;
D: after reaching maximum iteration time, all by the variables collection selected through probability threshold value sorting, high probability variable is carried out modeling as the input of partial least square method, each variable synergy, exports optimum variable combination and the root-mean-square error of this circulation;
E: after reaching maximum cycle, the modeling result of each circulation is compared, selects optimum variable combination, be i.e. the characteristic wavelength of the corresponding a certain component of near infrared spectrum or character, wherein, described ant colony optimization algorithm selects the concrete steps of characteristic variable as follows:
(1) the pheromones vector of near-infrared spectrum wavelength point is τ
(n-1)time, choice variable group v0;
(2) when reaching maximum variable number, partial least square model is set up, with the root-mean-square error calculating target function F of model;
(3), when not reaching maximum iteration time, objective function F and pheromones attenuation coefficient ρ carry out the vectorial τ of lastest imformation element
(n), again carry out Monte Carlo probability selection, and repeat step (1) and (2);
(4) after reaching setting iterations, start loop computation, repeat step (1) ~ (3);
(5) according to error minimum principle, the lowest mean square root error of the gained model of more each circulation, obtains near infrared spectrum optimal characteristics wavelength,
Wherein, described objective function is set to
F=Q/ (1+RMSE
min), wherein,
yi is the measured value of sample components or character,
for predicted value, Significance factors Q is constant, for the convergence validity of adjustment aim function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310269615.XA CN103344600B (en) | 2013-06-28 | 2013-06-28 | Characteristic wavelength selecting method for near infrared spectrum in ant colony optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310269615.XA CN103344600B (en) | 2013-06-28 | 2013-06-28 | Characteristic wavelength selecting method for near infrared spectrum in ant colony optimization algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103344600A CN103344600A (en) | 2013-10-09 |
| CN103344600B true CN103344600B (en) | 2015-06-03 |
Family
ID=49279414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310269615.XA Active CN103344600B (en) | 2013-06-28 | 2013-06-28 | Characteristic wavelength selecting method for near infrared spectrum in ant colony optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103344600B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927438B (en) * | 2014-04-11 | 2017-08-11 | 中国科学院重庆绿色智能技术研究院 | Near-infrared wavelength Variable Selection based on successive projection algorithm |
| CN106644983B (en) * | 2016-12-28 | 2019-12-31 | 浙江大学 | Spectral wavelength selection method based on PLS-VIP-ACO algorithm |
| CN107144548B (en) * | 2017-05-24 | 2019-10-29 | 长春理工大学 | Near infrared spectrum Variable Selection based on Monte Carlo variable combination of sets group |
| CN106950193B (en) * | 2017-05-24 | 2019-04-26 | 长春理工大学 | Based on the near infrared spectrum Variable Selection from weight variable combination cluster analysis |
| CN107219189A (en) * | 2017-07-10 | 2017-09-29 | 天津工业大学 | A kind of Wavelength selecting method for complex sample spectrum |
| CN109558845B (en) * | 2018-11-30 | 2022-10-11 | 合肥工业大学 | Intelligent fitting optimization method for magnetocardiogram signals based on ant colony algorithm |
| CN111795944B (en) * | 2020-06-30 | 2021-06-25 | 江南大学 | Near infrared spectrum wavelength screening method for improving team progress algorithm |
| CN111863147B (en) * | 2020-07-22 | 2024-06-14 | 云南电网有限责任公司电力科学研究院 | SF6And concentration detection method and device for decomposed component gas |
| CN113125377B (en) * | 2021-03-30 | 2024-02-23 | 武汉理工大学 | Method and device for detecting property of diesel based on near infrared spectrum |
| CN113267466B (en) * | 2021-04-02 | 2023-02-03 | 中国科学院合肥物质科学研究院 | Fruit sugar degree and acidity nondestructive testing method based on spectral wavelength optimization |
| CN114018864B (en) * | 2021-11-10 | 2022-09-16 | 黑龙江八一农垦大学 | Method for rapidly detecting content change of alcohol-soluble protein in corn kernels in grouting period |
| CN115656074B (en) * | 2022-12-28 | 2023-04-07 | 山东省科学院海洋仪器仪表研究所 | Adaptive selection and estimation method for sea water COD (chemical oxygen demand) spectral variable characteristics |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682209A (en) * | 2012-05-03 | 2012-09-19 | 桂林理工大学 | Variable selection method for modeling organic pollutant quantitative structure and activity relationship |
| CN102980972A (en) * | 2012-11-06 | 2013-03-20 | 南京工业大学 | Method for determining thermal risk of self-reactive chemical substance |
-
2013
- 2013-06-28 CN CN201310269615.XA patent/CN103344600B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682209A (en) * | 2012-05-03 | 2012-09-19 | 桂林理工大学 | Variable selection method for modeling organic pollutant quantitative structure and activity relationship |
| CN102980972A (en) * | 2012-11-06 | 2013-03-20 | 南京工业大学 | Method for determining thermal risk of self-reactive chemical substance |
Non-Patent Citations (4)
| Title |
|---|
| A new and efficient variable selection algorithm based on ant colony optimization. Applications to near infrared spectroscopy/partial least-squares analysis;Franco Allegrini 等;《Analytica Chimica Acta》;20110511(第699期);"ABSTRACT"、第18页右栏第2段、第19-21页"2.2. ACO algorithms"、第21页"3.3. Experimental OCTANE data"、Fig.1、Fig.6 * |
| Ant colony optimisation: a powerful tool for wavelength selection;Mojtaba Shamsipur 等;《JOURNAL OF CHEMOMETRICS》;20070129(第20期);146-157 * |
| 化学蚁群算法及其在光谱解析中的应用;丁亚平 等;《计算机与应用化学》;20020528;第19卷(第3期);326-328 * |
| 蚁群算法在近红外光谱定量分析中的应用研究;郭亮 等;《光谱学与光谱分析》;20090930;第27卷(第9期);1703-1705 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103344600A (en) | 2013-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103344600B (en) | Characteristic wavelength selecting method for near infrared spectrum in ant colony optimization algorithm | |
| CN103308463B (en) | Characteristic spectrum area selection method for near infrared spectrum | |
| CN106124449B (en) | A kind of soil near-infrared spectrum analysis prediction technique based on depth learning technology | |
| CN103235095B (en) | Water-injected meat detection method and device | |
| CN105630743B (en) | A kind of system of selection of spectrum wave number | |
| Ying et al. | Nondestructive measurement of internal quality in pear using genetic algorithms and FT-NIR spectroscopy | |
| CN104122210A (en) | Hyperspectral waveband extraction method based on optimum index factor-correlation coefficient method | |
| CN110569605B (en) | NSGA 2-ELM-based non-glutinous rice leaf nitrogen content inversion model method | |
| Liu et al. | A method combining ELM and PLSR (ELM-P) for estimating chlorophyll content in rice with feature bands extracted by an improved ant colony optimization algorithm | |
| CN111678599B (en) | Laser spectrum noise reduction method and device based on deep learning optimization S-G filtering | |
| CN104931453A (en) | Method for predicting water content of spread green leaves of green tea based on near infrared spectrum technology | |
| CN104778349B (en) | One kind is used for rice table soil nitrogen application Classified Protection | |
| CN102313712B (en) | Correction method of difference between near-infrared spectrums with different light-splitting modes based on fiber material | |
| CN105158200A (en) | Modeling method capable of improving accuracy of qualitative near-infrared spectroscopic analysis | |
| CN105784628A (en) | Method for detecting chemical composition of soil organic matter with mid-infrared spectra | |
| CN106018331B (en) | The method for estimating stability and pretreatment optimization method of multi-channel spectral system | |
| CN103278467A (en) | Rapid nondestructive high-accuracy method with for identifying abundance degree of nitrogen element in plant leaf | |
| CN110503156A (en) | A kind of multivariate calibration characteristic wavelength selection method based on least correlativing coefficient | |
| Mao et al. | Modeling research on wheat protein content measurement using near-infrared reflectance spectroscopy and optimized radial basis function neural network | |
| Liu et al. | Diagnosis of citrus greening using raman spectroscopy-based pattern recognition | |
| CN103743705A (en) | Rapid detection method for sorghum halepense and similar species | |
| Li et al. | Improvement of NIR prediction ability by dual model optimization in fusion of NSIA and SA methods | |
| Qi et al. | Rapid and non-destructive determination of soluble solid content of crown pear by visible/near-infrared spectroscopy with deep learning regression | |
| CN109100315B (en) | Wavelength selection method based on noise-signal ratio | |
| Jin et al. | Quantitative inversion model of protein and fat content in milk based on hyperspectral techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |