CN109297533A - A kind of method of precise measurement skin surface temperature and humidity - Google Patents
A kind of method of precise measurement skin surface temperature and humidity Download PDFInfo
- Publication number
- CN109297533A CN109297533A CN201811099609.3A CN201811099609A CN109297533A CN 109297533 A CN109297533 A CN 109297533A CN 201811099609 A CN201811099609 A CN 201811099609A CN 109297533 A CN109297533 A CN 109297533A
- Authority
- CN
- China
- Prior art keywords
- group
- sub
- neural network
- individual
- humidity
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
-
- 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
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a kind of methods of precise measurement skin surface temperature and humidity, are related to skin auxiliary conditioning technology field.This method constructs mind evolutionary model according to BP neural network topological structure first, then by carrying out convergent and operation dissimilation to mind evolutionary, the condition of convergence is optimized, and the weight and threshold value that improvement mind evolutionary global optimizing obtains are passed into BP neural network, it establishes based on the BP neural network model for improving mind evolutionary, dynamic compensation is carried out to humidity sensor.It eliminates in dynamic temperature control, temperature improves the accuracy and reliability of skin surface temperature and humidity measurement to humidity sensor bring non-linear effects, so that temperature and humidity (perspiration situation) regulation of skin surface can effectively be implemented.
Description
Technical field
The present invention relates to skin auxiliary conditioning technology field more particularly to a kind of sides of precise measurement skin surface temperature and humidity
Method.
Background technique
It is said in Huangdi's Internal Classics: " inferring the internal morbid changes of the body from the external manifestations, to see and too late reason.Sweat passes through the performance of sweat, Ke Yiguan in table
Infuse body interior whether one " in " state.Body body surface has countless pores, and what is had is long neglected and in disrepair, some blockings,
Some, which has been opened greatly, to close, and monitored by whole body sweating, see which pore be it is good, which be it is bad, if entire body
The pore of body is in state that is balanced, harmonious, coordinating, and people should be healthy, this just cries " survey sweat and know health ".
Currently, can be using the temperature and humidity situation of Temperature Humidity Sensor measurement skin surface.
But since the scene that Temperature Humidity Sensor uses is more special, so in use, temperature sensor and
Humidity sensor is highly susceptible to the caused cross jamming situation in temperature dynamic changing process, so that humidity sensor is defeated
Present out certain non-linear, the consistency for causing the output signal of humidity sensor and actual humidity to measure situation is poor, from
And lead to that the temperature and humidity measurement accuracy of skin surface is high, poor reliability, and then can not effective skin surface
Temperature and humidity (perspiration situation) is controlled and is adjusted.
Summary of the invention
The purpose of the present invention is to provide a kind of methods of precise measurement skin surface temperature and humidity, to solve the prior art
Present in foregoing problems.
To achieve the goals above, The technical solution adopted by the invention is as follows:
A kind of method of precise measurement skin surface temperature and humidity, includes the following steps:
S1 constructs mind evolutionary model according to BP neural network topological structure;
S2 is optimal operation convergence, is improved by carrying out convergent and operation dissimilation to mind evolutionary model
Mind evolutionary model;
S3 carries out global optimizing to the improved mind evolutionary model, obtains weight and threshold value;
Obtained weight and threshold value are passed to BP neural network by S4, are established based on improvement mind evolutionary model
BP neural network model;
S5 carries out dynamic to humidity sensor using based on the BP neural network model for improving mind evolutionary model
Compensation.
Preferably, S1 includes the following steps:
S101 initializes group, and group generates: individual, one group of all individual compositions is randomly generated in solution space
Body calculates the score of each individual according to fitness function, selects M+T wherein optimal individual as winner, wherein M
+T≤N;
S102, sub-group generate: around M+T optimal winner, being generated with normal distributionIndividual, composition
M winning sub-groups and T interim sub-groups.
Preferably, S2 includes the following steps:
Sub-group operation similartaxis: S201 in each sub-group, calculates each individual using following fitness function
Corresponding fitness, the i.e. score of each individual:
F=ξ-1,
Wherein, f is individual score, and S is number of training, yiIt (n) is practical desired value,For neural network forecast output
Value;
Sub-group operation dissimilation: S202 by comparing respective score between sub-group, the low sub-group of score is carried out
It discards, and discharges wherein individual, replace former winning sub-group with the high sub-group of score, constantly explored newly in solution space
Point generates new sub-group.
Preferably, S3 is specifically, iterative operation, confirm the initial weight and threshold value of BP neural network: operation dissimilation terminates
Afterwards, the individual being released is supplemented by new interim sub-group again, repeats step S2, until fitness value be less than setting error or
Maximum number of iterations is had reached, the optimum individual of output is parsed, no longer improves or iteration terminates, then it is assumed that operation convergence, output
Optimum individual, initial weight and threshold value as BP neural network.
Preferably, S4 is specifically, BP neural network initializes: setting the network number of plies, each layer neuron number, wherein improving
The weight and threshold value total number that mind evolutionary needs to optimize are N=(m+1) * n+ (n+1) * t, and wherein m is input neuron
Number, n are hidden neuron number, and t is output layer neuron number.
Preferably, S5 is specifically, training BP neural network: weight and threshold value that optimization obtains are passed to BP nerve net
Network, selected part normalization sample are trained BP neural network.
The beneficial effects of the present invention are: the method for precise measurement skin surface temperature and humidity provided by the invention, first basis
BP neural network topological structure constructs mind evolutionary model, is then grasped by carrying out convergent and alienation to mind evolutionary
Make, the condition of convergence is optimized, and the weight and threshold value that improvement mind evolutionary global optimizing obtains are passed into BP mind
It through network, establishes based on the BP neural network model for improving mind evolutionary, dynamic compensation is carried out to humidity sensor.It eliminates
In dynamic temperature control, temperature improves skin surface temperature and humidity measurement to humidity sensor bring non-linear effects
Accuracy and reliability so that skin surface temperature and humidity (perspiration situation) regulation can effectively implement.
Detailed description of the invention
Fig. 1 is a kind of method flow schematic diagram of precise measurement skin surface temperature and humidity provided by the invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing, to the present invention into
Row is further described.It should be appreciated that the specific embodiments described herein are only used to explain the present invention, it is not used to
Limit the present invention.
Aiming at the problems existing in the prior art, the precision to improve system, it is ensured that system linear output, it is necessary to take
Certain measure carries out dynamic compensation to humidity sensor, to eliminate non-linear effects brought by temperature, that is, will be to humidity
Sensor carries out linear compensation, and the nonlinear compensation of sensor includes hardware approach and two kinds of software approach.
Wherein, hardware circuit humidity dynamic compensation method is complicated, and electronic device is easy to produce drift, so that measurement accuracy
It is affected.So in the present invention, using software compensation method.Wherein, software compensation method includes reversed Scaling function
Method, schedule method, Newton iteration method, BP neural network etc..Wherein, reversed Scaling function method is more common, but specific aim is not strong;Ox
Iterative method realizes gamma correction based on existing phasing meter or Scaling function, however this method compensation time it is long and
Operand is larger;Schedule method mainly uses piecewise-linear techniques to approach the static characteristic curve of sensor, works as segment identifier
Between it is smaller when, will affect compensation precision, when piecewise interval is larger, tabling look-up will be relatively time-consuming;Simple BP neural network convergence
Speed is slow, and is easily trapped into local extremum.
In the present invention, dynamic compensates anti-interference method and applies in control human skin surface's temperature and humidity technology, to realize
To dermopathic adjuvant treatment.Humidity sensor is realized using the BP neural network model optimized based on mind evolutionary
Dynamic compensates, using the mind evolutionary with extremely strong ability of searching optimum come Optimized BP Neural Network.
As shown in Figure 1, the embodiment of the invention provides a kind of method of precise measurement skin surface temperature and humidity, including it is as follows
Step:
S1 constructs mind evolutionary model according to BP neural network topological structure,
S2 is optimal operation convergence, is improved by carrying out convergent and operation dissimilation to mind evolutionary model
Mind evolutionary model;
S3 carries out global optimizing to the improved mind evolutionary model, obtains weight and threshold value;
Obtained weight and threshold value are passed to BP neural network by S4, are established based on improvement mind evolutionary model
BP neural network model;
S5 carries out dynamic to humidity sensor using based on the BP neural network model for improving mind evolutionary model
Compensation.
Wherein, S1 may include steps of:
S101 initializes group, and group generates: individual, one group of all individual compositions is randomly generated in solution space
Body calculates the score of each individual according to fitness function, selects M+T wherein optimal individual as winner, wherein M
+T≤N;
S102, sub-group generate: around M+T optimal winner, being generated with normal distributionIndividual, composition
M winning sub-groups and T interim sub-groups.
S2 may include steps of:
S201, sub-group operation similartaxis: each sub-group Personal is to carry out local competition as victor, this process is
Convergent process.If a sub-group no longer generates new victor, competition terminates.The score of the sub-group be exactly in sub-group most
The score of excellent individual, and score is posted on global advertisement plate, until all sub-groups are all mature, convergent process terminates.
In each sub-group, the corresponding fitness of each individual is calculated using following fitness function, i.e., each is individual
Score:
F=ξ-1,
Wherein, f is individual score, and S is number of training, yiIt (n) is practical desired value,For neural network forecast output
Value;The f the big, thinks that individual score is higher, and highest scoring person is winner, and individual serial number and obtains grading information record
On bulletin board.When no longer generating new winner, then it is assumed that the sub-group is mature, and the score of winner is defined
For the score of the sub-group;
Sub-group operation dissimilation: S202 to carry out global competition as victor between the sub-group after mature, is constantly visited
The solution space of Suo Xin, this process are operation dissimilation, by comparing respective score between sub-group, by the low sub-group of score into
Row is discarded, and discharges wherein individual, replaces former winning sub-group with the high sub-group of score, constantly explores in solution space new
Point, generate new sub-group.
S3 confirms the initial weight and threshold value of BP neural network specifically, iterative operation: after operation dissimilation, being released
The individual put is supplemented by new interim sub-group again, repeats step S2, until fitness value is less than setting error or has reached
Maximum number of iterations parses the optimum individual of output, no longer improves or iteration terminates, then it is assumed that operation convergence exports optimal
Body, initial weight and threshold value as BP neural network.
S4 specifically, BP neural network initialize: setting the network number of plies, each layer neuron number, wherein improve thinking into
Changing weight and the threshold value total number that algorithm needs to optimize is N=(m+1) * n+ (n+1) * t, and wherein m is input neuron number, n
For hidden neuron number, t is output layer neuron number.
S5 is specifically, training BP neural network: weight and threshold value that optimization obtains are passed to BP neural network, selection portion
Normalization sample is divided to be trained BP neural network.
It using method provided by the invention, realizes under conditions of dynamic temperature control, reduces and cause in temperature changing process
Temperature and humidity cross jamming, and then accurately measure skin surface temperature and humidity.Interferential loads and sensor compensation in the present invention
Method realizes the precise measurement of temperature and humidity, algorithm letter according to sensor self character and product structure and skin measurement scene
It is single that effectively after amendment and compensation, measurement accuracy error can be up to 0.2, and can guarantee stable equipment operation, reliable,
Reach pre- target and design requirement, achieves good clinical use effect.
By using above-mentioned technical proposal disclosed by the invention, following beneficial effect has been obtained: essence provided by the invention
The really method of measurement skin surface temperature and humidity, constructs mind evolutionary model according to BP neural network topological structure first, so
Afterwards by carrying out convergent and operation dissimilation to mind evolutionary, the condition of convergence is optimized, and mind-evolution will be improved and calculated
The weight and threshold value that method global optimizing obtains pass to BP neural network, establish based on the BP nerve net for improving mind evolutionary
Network model carries out dynamic compensation to humidity sensor.It eliminates in dynamic temperature control, temperature is to humidity sensor bring
Non-linear effects improve the accuracy and reliability of skin surface temperature and humidity measurement, so that the temperature and humidity of skin surface (is perspired
Situation) regulate and control can effectively implement.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
Depending on protection scope of the present invention.
Claims (6)
1. a kind of method of precise measurement skin surface temperature and humidity, which comprises the steps of:
S1 constructs mind evolutionary model according to BP neural network topological structure;
S2 is optimal operation convergence, obtains improved think of by carrying out convergent and operation dissimilation to mind evolutionary model
Tie up evolution algorithm model;
S3 carries out global optimizing to the improved mind evolutionary model, obtains weight and threshold value;
Obtained weight and threshold value are passed to BP neural network by S4, are established based on the BP mind for improving mind evolutionary model
Through network model;
S5 carries out dynamic compensation to humidity sensor using based on the BP neural network model for improving mind evolutionary model.
2. the method for precise measurement skin surface temperature and humidity according to claim 1, which is characterized in that S1 includes following step
It is rapid:
S101 initializes group, and group generates: individual, one group of all individual compositions, root is randomly generated in solution space
The score that each individual is calculated according to fitness function selects M+T wherein optimal individual as winner, wherein M+T≤
N;
S102, sub-group generate: around M+T optimal winner, being generated with normal distributionIndividual, composition M excellent
Win sub-group and T interim sub-groups.
3. the method for precise measurement skin surface temperature and humidity according to claim 2, which is characterized in that S2 includes following step
It is rapid:
Sub-group operation similartaxis: S201 in each sub-group, it is corresponding to calculate each individual using following fitness function
Fitness, i.e., each individual score:
F=ξ-1,
Wherein, f is individual score, and S is number of training, yiIt (n) is practical desired value,For neural network forecast output valve;
Sub-group operation dissimilation: S202 by comparing respective score between sub-group, the low sub-group of score is carried out useless
Abandoning, and wherein individual is discharged, former winning sub-group is replaced with the high sub-group of score, is constantly explored newly in solution space
Point generates new sub-group.
4. the method for precise measurement skin surface temperature and humidity according to claim 3, which is characterized in that S3 is specifically, repeatedly
Generation operation, confirms the initial weight and threshold value of BP neural network: after operation dissimilation, the individual being released is faced by new again
When sub-group supplement, repeat step S2, until fitness value is less than setting error or has reached maximum number of iterations, parsing output
Optimum individual, no longer improve or iteration terminate, then it is assumed that operation convergence, export optimum individual, as BP neural network just
Beginning weight and threshold value.
5. the method for precise measurement skin surface temperature and humidity according to claim 4, which is characterized in that S4 is specifically, BP
Neural network initialization: setting the network number of plies, each layer neuron number, wherein improving the weight that mind evolutionary needs to optimize
It is N=(m+1) * n+ (n+1) * t with threshold value total number, wherein m is input neuron number, and n is hidden neuron number, and t is
Output layer neuron number.
6. the method for precise measurement skin surface temperature and humidity according to claim 5, which is characterized in that S5 is specifically, instruction
Practice BP neural network: weight and threshold value that optimization obtains being passed into BP neural network, selected part normalizes sample to BP mind
It is trained through network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811099609.3A CN109297533B (en) | 2018-09-20 | 2018-09-20 | Method for accurately measuring skin surface temperature and humidity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811099609.3A CN109297533B (en) | 2018-09-20 | 2018-09-20 | Method for accurately measuring skin surface temperature and humidity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109297533A true CN109297533A (en) | 2019-02-01 |
CN109297533B CN109297533B (en) | 2021-04-13 |
Family
ID=65163586
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811099609.3A Active CN109297533B (en) | 2018-09-20 | 2018-09-20 | Method for accurately measuring skin surface temperature and humidity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109297533B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110047015A (en) * | 2019-04-22 | 2019-07-23 | 水利部信息中心 | A kind of water total amount prediction technique merging KPCA and thinking Optimized BP Neural Network |
CN117686555A (en) * | 2024-02-04 | 2024-03-12 | 南京邮电大学 | LC humidity sensor drift compensation method based on machine learning |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1241128A (en) * | 1997-10-14 | 2000-01-12 | 庄臣消费者有限公司 | Skin refurfacing recovery system |
JP2003328837A (en) * | 2002-05-15 | 2003-11-19 | Caterpillar Inc | Engine control system using cascaded neural network |
CN102192894A (en) * | 2011-03-24 | 2011-09-21 | 周孟然 | Laser spectrum absorption detecting method of optical fiber sensing coalmine gas |
CN105510268A (en) * | 2015-12-07 | 2016-04-20 | 华中科技大学 | Optical fiber network gas sensing system based on photoelectric fusion |
CN106022549A (en) * | 2016-07-28 | 2016-10-12 | 兰州理工大学 | Short term load predication method based on neural network and thinking evolutionary search |
CN106769030A (en) * | 2016-11-10 | 2017-05-31 | 浙江工业大学 | A kind of bearing state tracking and Forecasting Methodology based on MEA BP neural network algorithms |
CN107967455A (en) * | 2017-11-24 | 2018-04-27 | 中南大学 | A kind of transparent learning method of intelligent human-body multidimensional physical feature big data and system |
-
2018
- 2018-09-20 CN CN201811099609.3A patent/CN109297533B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1241128A (en) * | 1997-10-14 | 2000-01-12 | 庄臣消费者有限公司 | Skin refurfacing recovery system |
JP2003328837A (en) * | 2002-05-15 | 2003-11-19 | Caterpillar Inc | Engine control system using cascaded neural network |
CN102192894A (en) * | 2011-03-24 | 2011-09-21 | 周孟然 | Laser spectrum absorption detecting method of optical fiber sensing coalmine gas |
CN105510268A (en) * | 2015-12-07 | 2016-04-20 | 华中科技大学 | Optical fiber network gas sensing system based on photoelectric fusion |
CN106022549A (en) * | 2016-07-28 | 2016-10-12 | 兰州理工大学 | Short term load predication method based on neural network and thinking evolutionary search |
CN106769030A (en) * | 2016-11-10 | 2017-05-31 | 浙江工业大学 | A kind of bearing state tracking and Forecasting Methodology based on MEA BP neural network algorithms |
CN107967455A (en) * | 2017-11-24 | 2018-04-27 | 中南大学 | A kind of transparent learning method of intelligent human-body multidimensional physical feature big data and system |
Non-Patent Citations (2)
Title |
---|
于明岩: "基于神经网络的电化学多气体传感器数据融合研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
杨威等: "基于光电调制式的多点多气体光纤传感网络", 《仪表技术与传感器》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110047015A (en) * | 2019-04-22 | 2019-07-23 | 水利部信息中心 | A kind of water total amount prediction technique merging KPCA and thinking Optimized BP Neural Network |
CN117686555A (en) * | 2024-02-04 | 2024-03-12 | 南京邮电大学 | LC humidity sensor drift compensation method based on machine learning |
CN117686555B (en) * | 2024-02-04 | 2024-05-14 | 南京邮电大学 | LC humidity sensor drift compensation method based on machine learning |
Also Published As
Publication number | Publication date |
---|---|
CN109297533B (en) | 2021-04-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Pryor et al. | Application of evidence-based recommendations for heat acclimation: individual and team sport perspectives | |
Edelmann‐nusser et al. | Modeling and prediction of competitive performance in swimming upon neural networks | |
Schuster et al. | Physical-preparation recommendations for elite rugby sevens performance | |
Gorzelic et al. | Model-based rational feedback controller design for closed-loop deep brain stimulation of Parkinson's disease | |
CN109297533A (en) | A kind of method of precise measurement skin surface temperature and humidity | |
Thompson et al. | The effects of changing pace on metabolism and stroke characteristics during high-speed breaststroke swimming | |
Ma et al. | Correlation analysis for the attack of bacillary dysentery and meteorological factors based on the Chinese medicine theory of Yunqi and the medical-meteorological forecast model | |
Donner | Linear regression analysis with repeated measurements | |
CN109731291A (en) | A kind of dynamic adjusting method and system of rehabilitation game | |
CN110400623A (en) | One kind carrying out health-preserving management system and its method based on interior can balance | |
Morton | The quantitative periodization of athletic training: a model study | |
Raya-González et al. | The effects of training based on Nordic hamstring and sprint exercises on measures of physical fitness and hamstring injury prevention in U19 male soccer players | |
Callison et al. | Grunting in tennis increases ball velocity but not oxygen cost | |
CN107392306A (en) | The training learning method and system of the neutral net of pattern specifications parameter inference pattern | |
CN106693129A (en) | Closed-loop capacity control method of breathing machine | |
Yang et al. | Smart health analysis on factors influencing physical health based on the self-organizing map network | |
Rossi et al. | Effect of physical fitness on the risk of stress fracture injury in Army basic training | |
KR20160042691A (en) | High altitude adaptation training method and system | |
CN105224786A (en) | A kind of method and smart machine regulating physical sign parameters | |
AYAT et al. | A comprehensive model using modified Zeeman model for generating ECG signals | |
Akbari Kamrani et al. | The effect of low and moderate intensity aerobic exercises on self-concept in older adults | |
CN117094695B (en) | Exercise training course planning and arranging method and system | |
Costa et al. | Longitudinal assessment of swimming performance in the 200-m freestyle event | |
Xiong | Research on the Construction of Athlete Training Load Evaluation Model | |
Sabry | Evaluation of the personal characteristics of disabled athletes in Sulaymaniyah province |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |