CN109086501A - A kind of flutter prediction technique - Google Patents
A kind of flutter prediction technique Download PDFInfo
- Publication number
- CN109086501A CN109086501A CN201810800648.5A CN201810800648A CN109086501A CN 109086501 A CN109086501 A CN 109086501A CN 201810800648 A CN201810800648 A CN 201810800648A CN 109086501 A CN109086501 A CN 109086501A
- Authority
- CN
- China
- Prior art keywords
- flutter
- neural network
- prediction technique
- output
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013528 artificial neural network Methods 0.000 claims abstract description 37
- 238000012360 testing method Methods 0.000 claims abstract description 23
- 230000006835 compression Effects 0.000 claims description 5
- 238000007906 compression Methods 0.000 claims description 5
- 210000004218 nerve net Anatomy 0.000 claims 1
- 238000012952 Resampling Methods 0.000 description 4
- 238000013016 damping Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M9/00—Aerodynamic testing; Arrangements in or on wind tunnels
- G01M9/06—Measuring arrangements specially adapted for aerodynamic testing
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Fluid Mechanics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Geometry (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Aerodynamic Tests, Hydrodynamic Tests, Wind Tunnels, And Water Tanks (AREA)
Abstract
The present invention relates to aeroelasticity fields, in particular to a kind of flutter prediction technique, include following steps: according to predetermined flutter frequency, the parameter of expression speed corresponding to the data point and data point of predetermined quantity is chosen at flutter critical state, as characteristic；Neural network structure is established, the number of nodes of artificial neural network is determined according to characteristic；It will complete to actually occur a part in the measured data of flutter when wind tunnel test and be trained as the training sample of neural network structure, obtained desired output；Sample is verified using another part of measured data as neural network structure, is verified；If verifying is qualified, the building of neural network structure is completed；Otherwise, increase new measured data, and repeat step 3 and step 4, until verifying is qualified.Flutter prediction technique based on nerual network technique of the invention, can make full use of pre-stage test data, to improve forecasting accuracy and timeliness.
Description
Technical field
The present invention relates to aeroelasticity field, in particular to a kind of flutter prediction technique.
Background technique
Flutter is a kind of self-excited vibration, belongs to aeroelasticity dynamic stability problem, relates generally to aerospace, building, machine
The fields such as tool.Constant amplitude will occur when such as meeting or exceeding Flutter Boundaries speed during aerospace field, aircraft flight
Or diverging vibration, it is most of to cause the catastrophic effects to disintegrate within several seconds even shorter time, in order to guarantee personnel and
Aircraft security, it is necessary to carry out related work, if scale model carries out wind tunnel test, flutter is taken a flight test.
When flutter wind tunnel test and flutter are taken a flight test, the risk of destruction is similarly faced, for security consideration, is faced in Asia
It is optimal that boundary's state energy Accurate Prediction, which goes out Flutter Boundaries,.Current prediction technique is mainly include the following types: first is that speed-resistance
Buddhist nun's method, this method is more traditional, mainly identifies the intrinsic frequency and damping of subcritical state, and it is outer to fit curve progress
It pushes away, when damping is zero, corresponding speed is the Flutter Boundaries of prediction, the disadvantage is that it is high to test data quality requirement, and due to
Damping is the nonlinear function of speed, and extrapolation is likely to cause large error；Second is that flutter margin method, the disadvantage is that accuracy relies on
In the accuracy of Modal Parameter Identification, and need to determine it is which two rank mode couples in advance；Third is that Robust Flutter Margin Method, it will
Flutter theoretical calculation is combined with test data, the disadvantage is that result is too conservative.
Summary of the invention
The object of the present invention is to provide a kind of flutter prediction techniques, to solve existing for existing flutter prediction technique at least
One problem.
The technical scheme is that
A kind of flutter prediction technique, includes the following steps:
Step 1:, according to predetermined flutter frequency, predetermined quantity is chosen at flutter critical state in flutter measured data
Data point and the data point corresponding to expression speed parameter, as characteristic；
Step 2: establishing neural network structure, the number of nodes of artificial neural network is determined according to the characteristic；
Step 3: a part in the measured data of flutter will have been completed to actually occur as the mind when wind tunnel test
Training sample through network structure, is trained, and obtains desired output；
Step 4: sample is verified using another part of measured data described in step 3 as the neural network structure, into
Row verifying；If verifying is qualified, the building of the neural network structure is completed；If verifying is unqualified, increase new actual measurement
Data, and step 3 and step 4 are repeated, until verifying is qualified.
Optionally, the predetermined quantity of the data point is at least 100.
Optionally, in the step 2, the input number of nodes in the neural network is the predetermined quantity of the data point,
Output node number is 2, and hidden layer is at least 2 layers.
Optionally, the step 3 includes:
The characteristic and desired output of step 3.1, given neural network；
Wherein, desired output is the output data in measured data described in step 3；
Step 3.2, the hidden layer and output layer for calculating the neural network；
The deviation of step 3.3, the reality output for calculating the neural network and desired output；
Step 3.4, according to the deviation of the reality output and desired output, the weight of the neural network is adjusted
It is whole, until reality output restrains.
Optionally, the reality output is the parameter and frequency of the corresponding expression speed of Flutter Boundaries.
Optionally, in said step 1, the parameter of the expression speed includes equivalent airspeed (EAS), ram compression and wind speed.
Invention effect:
Flutter prediction technique of the invention, can make full use of pre-stage test data, thus improve forecasting accuracy and and
Shi Xing；And with the increase of test data, by continuing training and verifying, the predictive ability of neural network can also be mentioned gradually
Height, artificial operation of promptly cut-offfing when so as to substitute flutter wind tunnel test.
Detailed description of the invention
Fig. 1 is the flow chart of flutter prediction technique of the present invention.
Specific embodiment
To keep the purposes, technical schemes and advantages of the invention implemented clearer, below in conjunction in the embodiment of the present invention
Attached drawing, technical solution in the embodiment of the present invention is further described in more detail.In the accompanying drawings, identical from beginning to end or class
As label indicate same or similar element or element with the same or similar functions.Described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.The embodiments described below with reference to the accompanying drawings are exemplary, it is intended to use
It is of the invention in explaining, and be not considered as limiting the invention.Based on the embodiments of the present invention, ordinary skill people
Member's every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.Under
Face is described in detail the embodiment of the present invention in conjunction with attached drawing.
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", "front", "rear",
The orientation or positional relationship of the instructions such as "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is based on attached drawing institute
The orientation or positional relationship shown, is merely for convenience of description of the present invention and simplification of the description, rather than the dress of indication or suggestion meaning
It sets or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as protecting the present invention
The limitation of range.
1 pair of flutter prediction technique of the present invention is described in further details with reference to the accompanying drawing.
Flutter prediction technique of the invention mainly solving the technical problems that: 1) characteristic is determined according to test data；
2) neural network structure is established to solve forecasting problem.
Solving above-mentioned technical problem is mainly to be realized by the following: will be with reference to previous when 1) determining characteristic
The test data of test, picking and the mostly concerned use of Flutter Boundaries, and in view of training, verifying and later period use can be real
Existing property；2) mainly framework selects when designing neural network, determines number of nodes.
The present invention provides a kind of flutter prediction techniques, include the following steps:
Step 1:, according to predetermined flutter frequency f, predetermined number is chosen at flutter critical state in flutter measured data
The parameter of expression speed corresponding to the data point of amount and the data point, as characteristic.Wherein, data point is predetermined
Quantity is at least 100；The parameter for expressing speed includes equivalent airspeed (EAS), ram compression and wind speed.
Wherein, characteristic derives from previous flutter wind tunnel test data, with low-speed wind tunnel speed signal (or transonic speed wind
Hole ram compression signal) corresponding acceleration transducer, strain testing vibration data, the corresponding wind speed of Flutter Boundaries (or ram compression)
And frequency.
The sample frequency tested when test is generally all higher, and time domain data is very more, needs to carry out data to simplify
Resampling, resampling is according to actual measurement or the flutter frequency f calculated, and there are four principles, first is that when carrying out the initial data of resampling
Between length 40 periods (quantity is only for example, and is not polarized)；Second is that the equivalent in the time span in 40 periods
Air speed keeps increasing；Third is that initial data time span is closer apart from flutter critical point；Fourth is that resampling in the time span, obtains
To 280 data points (quantity is only for example, and is not polarized).These data points and its corresponding equivalent airspeed (EAS) are direct
It is used as input, uses x respectively1, x2..., x280And v1, v2..., v280It indicates.
The corresponding equivalent airspeed (EAS) of Flutter Boundaries and frequency are used as output, are indicated with v and f.
Step 2: establishing neural network structure, the number of nodes of artificial neural network is determined according to the characteristic.Its
In, the input number of nodes in neural network is the predetermined quantity of the data point, and output node number is 2, and hidden layer is at least 2
Layer (every layer includes 24 nodes or other quantity).In the present embodiment, input number of nodes is 280, and output node number is 2
A, hidden layer is 2 layers, and every layer includes 20 nodes (above-mentioned quantity is only for example, and is not polarized).
Step 3: by the measured data for having completed to actually occur flutter when wind tunnel test, (this data is not necessarily step
Data in rapid one, the data in step 1 can be the data that flutter does not occur) in a part as the neural network
The training sample of structure, is trained, and obtains desired output.
Specifically, step 3 includes:
The characteristic and desired output of step 3.1, given neural network；
Wherein, desired output is the output data in measured data described in step 3；
Step 3.2, the hidden layer and output layer for calculating the neural network；
The deviation of step 3.3, the reality output for calculating the neural network and desired output；
Step 3.4, according to the deviation of the reality output and desired output, the weight of the neural network is adjusted
It is whole, until reality output restrains.Wherein, reality output is the parameter and frequency of the corresponding expression speed of Flutter Boundaries.
Step 4: sample is verified using another part of measured data described in step 3 as the neural network structure, into
Row verifying；If verifying is qualified, the building of the neural network structure is completed；If verifying is unqualified, increase new actual measurement
Data, and step 3 and step 4 are repeated, until verifying is qualified.
Flutter prediction technique based on nerual network technique of the invention, can make full use of pre-stage test data, thus
Improve forecasting accuracy and timeliness；And with the increase of test data, by continuing training and verifying, neural network it is pre-
Survey ability can also step up, artificial operation of promptly cut-offfing when so as to substitute flutter wind tunnel test.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by those familiar with the art, all answers
It is included within the scope of the present invention.Therefore, protection scope of the present invention should be with the scope of protection of the claims
It is quasi-.
Claims (6)
1. a kind of flutter prediction technique, which comprises the steps of:
Step 1:, according to predetermined flutter frequency, the number of predetermined quantity is chosen at flutter critical state in flutter measured data
The parameter of expression speed corresponding to strong point and the data point, as characteristic；
Step 2: establishing neural network structure, the number of nodes of artificial neural network is determined according to the characteristic；
Step 3: a part in the measured data of flutter will have been completed to actually occur as the nerve net when wind tunnel test
The training sample of network structure, is trained, and obtains desired output；
Step 4: verifying sample for another part of measured data described in step 3 as the neural network structure, tested
Card；If verifying is qualified, the building of the neural network structure is completed；If verifying is unqualified, increase new measured data,
And step 3 and step 4 are repeated, until verifying is qualified.
2. flutter prediction technique according to claim 1, which is characterized in that in the step 1, the data point it is pre-
Fixed number amount is at least 100.
3. flutter prediction technique according to claim 1, which is characterized in that in the step 2, in the neural network
Input number of nodes be the data point predetermined quantity, output node number be 2, hidden layer is at least 2 layers.
4. flutter prediction technique according to claim 1, which is characterized in that the step 3 includes:
The characteristic and desired output of step 3.1, given neural network；
Wherein, desired output is the output data in measured data described in step 3；
Step 3.2, the hidden layer and output layer for calculating the neural network；
The deviation of step 3.3, the reality output for calculating the neural network and desired output；
Step 3.4, according to the deviation of the reality output and desired output, the weight of the neural network is adjusted, directly
It is restrained to reality output.
5. flutter prediction technique according to claim 4, which is characterized in that the reality output is that Flutter Boundaries are corresponding
Express the parameter and frequency of speed.
6. flutter prediction technique according to claim 5, which is characterized in that in said step 1, the expression speed
Parameter include equivalent airspeed (EAS), ram compression and wind speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810800648.5A CN109086501A (en) | 2018-07-20 | 2018-07-20 | A kind of flutter prediction technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810800648.5A CN109086501A (en) | 2018-07-20 | 2018-07-20 | A kind of flutter prediction technique |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109086501A true CN109086501A (en) | 2018-12-25 |
Family
ID=64838219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810800648.5A Pending CN109086501A (en) | 2018-07-20 | 2018-07-20 | A kind of flutter prediction technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086501A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110657939A (en) * | 2019-08-30 | 2020-01-07 | 中国空气动力研究与发展中心高速空气动力研究所 | Flutter critical prediction method and device |
| CN111898327A (en) * | 2020-06-30 | 2020-11-06 | 西北工业大学 | Flutter signal abnormal data expansion method for aeroelastic system |
| CN114491405A (en) * | 2022-04-02 | 2022-05-13 | 中国空气动力研究与发展中心高速空气动力研究所 | Flutter stability parameter acquisition method and device |
| CN115017963A (en) * | 2022-08-08 | 2022-09-06 | 中国空气动力研究与发展中心高速空气动力研究所 | Flutter boundary prediction method and device, electronic equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2098704A2 (en) * | 2008-03-05 | 2009-09-09 | United Technologies Corporation | Variable area fan nozzle fan flutter management system |
| CN103310060A (en) * | 2013-06-19 | 2013-09-18 | 西北工业大学 | Transonic limit cycle flutter analysis method |
| CN103530511A (en) * | 2013-10-10 | 2014-01-22 | 南京航空航天大学 | Flutter boundary prediction method in wind tunnel flutter test under turbulence excitation condition |
| CN103886373A (en) * | 2014-04-18 | 2014-06-25 | 天津理工大学 | High-speed cold-rolling mill third octave flutter prediction method based on BP neural network |
| CN104182560A (en) * | 2014-01-08 | 2014-12-03 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Aircraft flutter prediction and analysis method and device |
| CN104443427A (en) * | 2014-10-15 | 2015-03-25 | 西北工业大学 | Aircraft flutter prediction system and method |
| CN104786101A (en) * | 2015-04-29 | 2015-07-22 | 常州信息职业技术学院 | Monitoring method for vertical milling cutting vibration |
| CN104881585A (en) * | 2015-03-24 | 2015-09-02 | 南京航空航天大学 | Flutter boundary prediction method of two-degree-of-freedom wing |
| CN107860548A (en) * | 2017-09-12 | 2018-03-30 | 南京航空航天大学 | A kind of online flutter boundary prediction method of approximation |
| CN108182328A (en) * | 2018-01-05 | 2018-06-19 | 北京航空航天大学 | A kind of big angle of attack Nonlinear Aerodynamic reduced-order model suitable for stall flutter |
-
2018
- 2018-07-20 CN CN201810800648.5A patent/CN109086501A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2098704A2 (en) * | 2008-03-05 | 2009-09-09 | United Technologies Corporation | Variable area fan nozzle fan flutter management system |
| CN103310060A (en) * | 2013-06-19 | 2013-09-18 | 西北工业大学 | Transonic limit cycle flutter analysis method |
| CN103530511A (en) * | 2013-10-10 | 2014-01-22 | 南京航空航天大学 | Flutter boundary prediction method in wind tunnel flutter test under turbulence excitation condition |
| CN104182560A (en) * | 2014-01-08 | 2014-12-03 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Aircraft flutter prediction and analysis method and device |
| CN103886373A (en) * | 2014-04-18 | 2014-06-25 | 天津理工大学 | High-speed cold-rolling mill third octave flutter prediction method based on BP neural network |
| CN104443427A (en) * | 2014-10-15 | 2015-03-25 | 西北工业大学 | Aircraft flutter prediction system and method |
| CN104881585A (en) * | 2015-03-24 | 2015-09-02 | 南京航空航天大学 | Flutter boundary prediction method of two-degree-of-freedom wing |
| CN104786101A (en) * | 2015-04-29 | 2015-07-22 | 常州信息职业技术学院 | Monitoring method for vertical milling cutting vibration |
| CN107860548A (en) * | 2017-09-12 | 2018-03-30 | 南京航空航天大学 | A kind of online flutter boundary prediction method of approximation |
| CN108182328A (en) * | 2018-01-05 | 2018-06-19 | 北京航空航天大学 | A kind of big angle of attack Nonlinear Aerodynamic reduced-order model suitable for stall flutter |
Non-Patent Citations (7)
| Title |
|---|
| E. KULJANIC等: "Development of an intelligent multisensor chatter detection system in milling", 《MECHANICAL SYSTEMS & SIGNAL PROCESSING》 * |
| 刘昕: "基于神经网络的机翼气动参数预测仿真研究", 《计算机仿真》 * |
| 孙虎几: "《基于神经网络的优化设计及应用》", 31 March 2009, 国防工业出版社 * |
| 李扬等: "紊流激励条件下基于随机减量法的颤振边界预测研究", 《工程力学》 * |
| 王勋等: "《人工智能原理及应用》", 31 December 2005, 南海出版公司 * |
| 蒋亚琼等: "钢箱梁悬索桥颤振导数和颤振临界风速预测", 《阴山学刊》 * |
| 郑华: "基于神经网络的系统稳定性判定方法及其在FBP中的应用", 《中国优秀硕士学位论文全文数据库（电子期刊）信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110657939A (en) * | 2019-08-30 | 2020-01-07 | 中国空气动力研究与发展中心高速空气动力研究所 | Flutter critical prediction method and device |
| CN111898327A (en) * | 2020-06-30 | 2020-11-06 | 西北工业大学 | Flutter signal abnormal data expansion method for aeroelastic system |
| CN114491405A (en) * | 2022-04-02 | 2022-05-13 | 中国空气动力研究与发展中心高速空气动力研究所 | Flutter stability parameter acquisition method and device |
| CN115017963A (en) * | 2022-08-08 | 2022-09-06 | 中国空气动力研究与发展中心高速空气动力研究所 | Flutter boundary prediction method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086501A (en) | A kind of flutter prediction technique | |
| CN109063290A (en) | A kind of flutter prediction technique based on nerual network technique | |
| CN109145464A (en) | Merge the Structural Damage Identification of multiple target ant lion optimization and the sparse regularization of mark | |
| CN109885854A (en) | The real-time forecasting system of Flutter Boundaries and prediction technique based on arma modeling | |
| CN104200005A (en) | Bridge damage identification method based on neural network | |
| KR101965879B1 (en) | Ann-based sustainable strain sensing model system, structural health assessment system and method | |
| CN106156501B (en) | A kind of bridge local damage quantization method based on deflection line | |
| CN104200265A (en) | Improved bridge damage identification method based on neural network | |
| CN102034021A (en) | Integral and local information fusing method of structure health diagnosis | |
| CN108038315B (en) | A kind of Random dynamic loads recognition methods based on spectrum stochastic finite meta-model | |
| CN108491578A (en) | A kind of Random dynamic loads recognition methods based on perturbative matrix | |
| CN110017929B (en) | Ship-bridge collision load and damage synchronous identification method based on substructure sensitivity analysis | |
| CN107727338A (en) | A kind of bridge damnification diagnostic method based on Vehicle-Bridge Coupling System | |
| CN105183933B (en) | A kind of Structural Damage Identification based on artificial bee colony algorithm | |
| CN107423487B (en) | A kind of recognition methods of Random dynamic loads spatial distribution and statistical nature | |
| CN105844055B (en) | It is fissioned-is polymerize the damage monitoring method of probabilistic model based on guided wave dynamic contract-enhanced | |
| CN107357980A (en) | A kind of damnification recognition method of axial functionally gradient beam | |
| CN109299539A (en) | A method of utilizing curvilinear corner index evaluation cantilever beam rigidity weak link | |
| CN110472363B (en) | Surrounding rock deformation grade prediction method and system suitable for high-speed railway tunnel | |
| CN107356523B (en) | Feedback force modification method is tested in real-time hybrid analog-digital simulation based on the estimation of discrete tangent rigidity | |
| CN101793621B (en) | Progressive health monitoring method for cable system based on cable force monitoring during support settlement | |
| CN107341297A (en) | A kind of distribution Random dynamic loads recognition methods based on KL expansion | |
| CN109558621A (en) | A kind of Structural Damage Identification and system | |
| CN103913512B (en) | The damage reason location system of suspension cable periodic detection | |
| CN104807661B (en) | A kind of high-rise and tall and slender structure Dynamic testing evaluation on bearing capacity method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181225 |