CN116821644A - Flight data identification method - Google Patents
Flight data identification method Download PDFInfo
- Publication number
- CN116821644A CN116821644A CN202310291958.XA CN202310291958A CN116821644A CN 116821644 A CN116821644 A CN 116821644A CN 202310291958 A CN202310291958 A CN 202310291958A CN 116821644 A CN116821644 A CN 116821644A
- Authority
- CN
- China
- Prior art keywords
- flight data
- flight
- network
- detected
- wind shear
- 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 33
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 239000010410 layer Substances 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 239000011229 interlayer Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a flight data identification method, and belongs to the technical field of flight data identification. The method comprises the steps of preprocessing an acquired original flight data set to obtain a standard flight data set; selecting flight parameters capable of distinguishing normal flight from flight under the influence of wind shear, and constructing a to-be-detected flight data set; extracting features of the flight data set to be detected to obtain the feature set of the flight data to be detected; and establishing a wind shear flight data identification model based on the depth confidence network, and carrying out data identification according to wind shear flight characteristics. The invention provides a wind shear flight data identification method based on data feature extraction by using a deep confidence network, which can quickly identify flight data when flying under the influence of wind shear, and provides convenience for analyzing the capability of pilots to wind shear; meanwhile, the method solves the problem of low manual identification precision, and improves the efficiency and accuracy of wind shear flight data identification.
Description
Technical Field
The invention relates to the technical field of flight data identification, in particular to a flight data identification method under the influence of wind shear.
Background
Wind shear is a common atmospheric phenomenon, mainly caused by factors such as frontal surface, reverse temperature layer, lightning, complex terrain, ground friction effect and the like, wherein the influence of micro undershoot airflow is the greatest. Wind shear, which typically occurs during the take-off and landing phases of flight, is one of the important sources of danger today that affects the flight safety during the take-off and landing phases of an aircraft. When the aircraft encounters wind shear, the aircraft's attitude is difficult to control, leaving less space and time for the pilot.
The international civil aviation organization believes that vertical wind shears above 0.1m/s pose a threat to jet transport aircraft. Thus, in order for the pilot to be able to effectively influence wind shear during real flight, the airline company may schedule wind shear to change out of the flight subjects during pilot ground simulator lessons. The pilot's ground simulator course typically lasts four hours, each simulator course containing multiple flight subjects. After the course is finished, the airlines analyze the flight technology capability of the pilot by combining the flight data obtained in the course. But the flight data obtained after the course is finished is presented in a complete data file, and the flight data of the subject stage of wind shear cannot be directly obtained.
After the course of the existing simulator is finished, the flight data of the pilot when the pilot encounters wind shear are usually identified in a manual mode, and the method needs more manual effort and has lower identification efficiency.
Disclosure of Invention
Aiming at the problems in the field, the invention provides a flight data identification method, which solves the technical problems that the time and the labor are consumed and the identification efficiency is lower when the pilot controls the flight data to suffer wind shear through manual identification after the current simulator course is finished.
In order to solve the technical problems, the invention discloses a flight data identification method, which comprises the following specific steps:
obtaining a standard flight data set;
selecting a standard flight data set, distinguishing flight parameters of the flight under the influence of normal flight and wind shear, and summarizing all flight data under the selected parameters to form a to-be-detected flight data set;
extracting a time domain characteristic value of the to-be-detected flight data set, extracting a wavelet singular entropy characteristic value of the to-be-detected flight data set by a wavelet singular entropy method, and constructing the to-be-detected flight data characteristic set containing wind shear flight characteristics;
and (3) constructing an identification model based on a deep confidence network algorithm, and identifying the to-be-detected flight data feature set after feature extraction, so as to realize the distinction between the flight data in normal flight and the flight data in flight under the influence of wind shear.
Preferably, the selection of the flight parameters that distinguish between normal flight and flight affected by wind shear includes time, altitude, true airspeed, pitch angle, roll angle, pitch angle rate, and roll angle rate.
Preferably, the wind shear flight characteristic extraction of the to-be-detected flight data set includes:
performing time window division on the flight data set to be detected;
respectively obtaining the characteristic values of the mean, the variance and the root mean square of the flight data set to be detected by using a time domain characteristic extraction technology; the time domain feature extraction technology comprises the steps of calculating the feature values of the mean value, the variance and the root mean square of the flight data to be detected;
and extracting a k-order wavelet singular entropy characteristic value of the flight data to be detected by using a wavelet singular entropy method.
Preferably, the step of calculating the wavelet singular entropy method includes:
performing wavelet transformation on flight data, obtaining a wavelet coefficient array A according to an inner product formula, decomposing a matrix A with any order of k into the sum of k single-rank subarrays according to singular values by adopting the wavelet coefficient array A:
A＝UΛV T
in U, V T Are all orthogonal matrices; upper diagonal element lambda in matrix lambda i Singular eigenvalues of the a-array;
the wavelet coefficient array A is a diagonal array obtained after SVD decomposition, and the singular value of the coefficient array A after wavelet transformation is considered to measure a wavelet singular entropy characteristic value according to the information entropy principle;
wherein WSE (k) is a wavelet singular entropy eigenvalue.
Preferably, the recognition model includes training several layers of the boltzmann machine-constrained RBM and a back propagation network employing a BP neural network as a deep belief network tuning stage.
Preferably, the step of training the several layers of boltzmann-limiting machines RBM comprises:
the network energy formula defining the limited boltzmann machine is:
wherein n represents the number of visible nodes in the network; m represents the number of hidden nodes in the network; v i Representing a given input signal in the network; h is a j Hidden feature vector representing network output correspondence；b i Representing the transfer amount of the underlying visible node; c j Representing hidden node offsets of the hidden layer; w (w) ij Representing a weight matrix for communicating the hidden node with the visible node;
the probability of each display layer and hidden layer is calculated from the network energy formula of the limited boltzmann machine:
where E (v, h) is the network energy of the limited Boltzmann machine, Z is the sum of the display and hidden vector pairs, and P (v, h) is the probability of the display and hidden layers;
the probability distribution calculation formula of the display layer is as follows:
the probability distribution calculation formula of the hidden layer is obtained through interlayer relation calculation:
wherein σ (x) is a sigmoid function;
preferably, the back propagation network adopting the BP neural network as the deep belief network fine tuning stage implements the back propagation optimization network global by the top layer through the back propagation network constructed by the probability distribution formula of the hidden layer, so as to fine tune the network model to obtain the optimal parameters of the deep belief network, complete the training of the network, and the constructed back propagation network calculation formula is as follows:
randomly selecting part of to-be-detected flight data feature sets as training sets of the model, and the rest part of to-be-detected flight data feature sets as test sets of the model; and using the test set to verify the flight data identification model under the influence of wind shear based on the deep belief network.
Compared with the prior art, the invention has the following beneficial effects:
the method comprises the steps of preprocessing an acquired original flight data set to obtain a standard flight data set; selecting flight parameters capable of distinguishing normal flight from flight under the influence of wind shear, and constructing a to-be-detected flight data set; extracting features of the flight data set to be detected to obtain the feature set of the flight data to be detected; and establishing a wind shear flight data identification model based on the depth confidence network, and carrying out data identification according to wind shear flight characteristics. The invention provides a wind shear flight data identification method based on data feature extraction by using a deep confidence network, which can quickly identify flight data when flying under the influence of wind shear, and provides convenience for analyzing the capability of pilots to wind shear; meanwhile, the method solves the problem of low manual identification precision, and effectively improves the efficiency and accuracy of wind shear flight data identification.
Drawings
FIG. 1 is a flow chart of a method of identifying flight data according to the present invention;
FIG. 2 is a flow chart of feature extraction of a to-be-detected flight dataset of the present invention;
FIG. 3 is a flow chart of wavelet singular entropy method feature extraction of the present invention;
FIG. 4 is a topology diagram of a deep belief network for implementing data recognition in accordance with 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 fig. 1 to 4 in the embodiments of the present invention. It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
As shown in fig. 1, the invention provides a flight data identification method, which comprises the following steps:
s1: after the course of the simulator is finished, acquiring an original flight data set when the pilot controls the simulator to fly;
when a simulator course is carried out, 174 real-time flight parameters generated by a pilot operating an aircraft are stored in a quick storage recorder of the simulator in a time sequence form, and after the simulator course is finished, the flight data under all the flight parameters are derived to form an original flight data set;
s2: preprocessing an original flight data set, and removing illegal values, null values and abnormal values from a standard flight data set;
because the unprocessed original flight data set has illegal values, null values and abnormal values and is difficult to be used for identifying the flight data under the influence of wind shear, the original flight data set is obtained and then standardized, and the original flight data set is converted into a standard flight data set which does not have the illegal values, the null values and the abnormal values and is arranged in a time sequence form;
s3: selecting flight parameters capable of distinguishing normal flight from flight under the influence of wind shear, and summarizing all flight data under the selected parameters to form a to-be-detected flight data set;
when the flight of the aircraft is affected by wind shear, the flight attitude and state of the aircraft are suddenly changed, at the moment, part of flight parameters in the flight data set can reflect the sudden change of the attitude and state of the aircraft, and a new data set is constructed by utilizing the flight parameters to form a to-be-detected flight data set;
specifically, in step S3, parameters capable of distinguishing between normal flight and flight under the influence of wind shear, such as time, altitude, vacuum speed, vertical speed, pitch angle, roll angle, pitch angle rate, roll angle rate, and the like, are selected;
s4: performing wind shear flight characteristic extraction on the to-be-detected flight data set obtained in the step S3, and performing normalization processing on the extracted characteristic data to obtain the to-be-detected flight data characteristic set;
specifically, as shown in fig. 2, the feature extraction of the to-be-detected flight data set in step S4 should include the following steps:
establishing a time window, taking 1s as a unit, and dividing the time window of the flight data set to be detected;
respectively obtaining the characteristic values of the mean value, the variance and the root mean square of the flight data to be detected by using a time domain characteristic extraction technology;
wherein, the average value can be calculated by the formula (1):
wherein M is a mean characteristic value; x is x i Is a flight data value; p (P) xi Is x i Probability of occurrence.
The variance can be calculated using equation (2):
wherein V is a variance characteristic value; x is x i Is a flight data value; p (P) xi Is x i Probability of occurrence.
The root mean square value can be calculated by the formula (3).
Wherein, RMS is root mean square characteristic value; x is x i Is a flight data value.
Extracting k-order wavelet singular entropy of the flight data to be detected by using a wavelet singular entropy method;
as shown in fig. 3, the calculation of the wavelet singular entropy method is to obtain a wavelet coefficient array a through an inner product formula after the flight data is subjected to wavelet transformation, and decompose the matrix a with any order of k rank into the sum of k single rank subarrays according to singular values by adopting a formula (4).
A＝UΛV T (4)
In U, V T Are all orthogonal matrices; the diagonal element λ on Λ in equation (5) i Is the singular eigenvalue of the a-array.
The wavelet coefficient array A is subjected to SVD decomposition to obtain a diagonal array, singular values of the wavelet coefficient array A after wavelet transformation are considered, and the singular entropy characteristic values of the wavelet are measured according to the information entropy principle.
Wherein WSE is a wavelet singular entropy eigenvalue.
And respectively obtaining the mean value, variance and root mean square characteristic value of the flight data to be detected and extracting the k-order wavelet singular entropy characteristic value of the flight data to be detected by using a wavelet singular entropy method by using a time domain characteristic extraction technology to obtain the characteristic data of the flight data to be detected.
Carrying out normalization processing on the obtained characteristic data by using a formula (8), concentrating the characteristic data between [0,1], and integrating the normalized characteristic data to form a to-be-detected flight data characteristic set comprising time domain and wavelet singular entropy characteristics;
s5: identifying the feature set of the flight data to be detected, and identifying the flight data in normal flight and the flight data in flight under the influence of wind shear;
specifically, the data identification is realized by adopting a deep belief network algorithm, which comprises the following steps:
as shown in fig. 4, an identification model of the topology as shown is constructed. The deep belief network is built in two steps:
firstly, limiting Boltzmann machines RBM for training a plurality of layers;
secondly, the overall situation of the network is optimized through the training of the back propagation network of the top layer in a supervision mode, and a network model is finely tuned to obtain the optimal parameters of the deep belief network;
the network energy of the limited boltzmann machine is defined by equation (8):
wherein n represents the number of visible nodes in the network; m represents the number of hidden nodes in the network; v i Representing a given input signal in the network; h is a j Representing the hidden feature vector corresponding to the network output; b i Representing the transfer amount of the underlying visible node; c j Representing hidden node offsets of the hidden layer; w (w) ij And a weight matrix for communicating the hidden node and the visible node is represented.
The probability of each possible display layer and hidden layer is given according to the network energy formula of the limited boltzmann machine of equation (8):
where E (v, h) is the network energy of the limited Boltzmann machine, Z is the sum of the display and hidden vector pairs, and P (v, h) is the probability of the display and hidden layers;
the probability distribution of the display layer is calculated with the formula (11):
and obtaining the distribution of the hidden layers through interlayer relation calculation:
where σ (x) is a sigmoid function.
And (3) adopting the BP neural network as a back propagation network in a deep confidence network fine tuning stage, and realizing the back propagation optimization network global by the top layer through the back propagation network constructed by the formula (13), thereby fine tuning a network model to obtain the optimal parameters of the deep confidence network, and finally completing the training of the network.
Randomly selecting part of to-be-detected flight data feature sets as training sets of the model, and the rest part of to-be-detected flight data feature sets as test sets of the model;
inputting the obtained training set into a flight data identification model under the influence of wind shear, taking characteristic data in the training set as input of the model, taking normal flight data (y= +1) and wind shear flight data (y= -1) as output of the model, and realizing training of the model;
and using the test set to verify the flight data identification model under the influence of wind shear based on the deep belief network.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
In addition, unless otherwise indicated, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. All documents mentioned in this specification are incorporated by reference for the purpose of disclosing and describing the methodologies associated with the documents. In case of conflict with any incorporated document, the present specification will control.
Claims (7)
1. The method for identifying the flight data is characterized by comprising the following specific steps of:
obtaining a standard flight data set;
selecting a standard flight data set, distinguishing flight parameters of the flight under the influence of normal flight and wind shear, and summarizing all flight data under the selected parameters to form a to-be-detected flight data set;
extracting a time domain characteristic value of the to-be-detected flight data set, extracting a wavelet singular entropy characteristic value of the to-be-detected flight data set by a wavelet singular entropy method, and constructing the to-be-detected flight data characteristic set containing wind shear flight characteristics;
and (3) constructing an identification model based on a deep confidence network algorithm, and identifying the to-be-detected flight data feature set after feature extraction, so as to realize the distinction between the flight data in normal flight and the flight data in flight under the influence of wind shear.
2. The method of claim 1, wherein the selection of the flight parameters that distinguish between normal flight and flight affected by wind shear includes time, altitude, vacuum rate, pitch angle, roll angle, pitch angle rate, and roll angle rate.
3. The method of claim 1, wherein the wind shear flight feature extraction of the to-be-detected flight data set comprises:
performing time window division on the flight data set to be detected;
respectively obtaining the characteristic values of the mean, the variance and the root mean square of the flight data set to be detected by using a time domain characteristic extraction technology; the time domain feature extraction technology comprises the steps of calculating the feature values of the mean value, the variance and the root mean square of the flight data to be detected;
and extracting a k-order wavelet singular entropy characteristic value of the flight data to be detected by using a wavelet singular entropy method.
4. The method for identifying flight data according to claim 1, wherein the step of calculating the wavelet singular entropy method comprises:
performing wavelet transformation on flight data, obtaining a wavelet coefficient array A according to an inner product formula, decomposing a matrix A with any order of k into the sum of k single-rank subarrays according to singular values by adopting the wavelet coefficient array A:
A＝UΛV T
in U, V T Are all orthogonal matrices; upper diagonal element lambda in matrix lambda i Singular eigenvalues of the a-array;
the wavelet coefficient array A is a diagonal array obtained after SVD decomposition, and the singular value of the coefficient array A after wavelet transformation is considered to measure a wavelet singular entropy characteristic value according to the information entropy principle;
wherein WSE (k) is a wavelet singular entropy eigenvalue.
5. A method of identifying flight data according to claim 1, wherein the identification model comprises training several layers of boltzmann-restricted RBM and back propagation networks employing BP neural networks as deep belief network fine tuning stages.
6. The method of claim 5, wherein the training the plurality of layers of boltzmann machine-constrained RBMs comprises:
the network energy formula defining the limited boltzmann machine is:
wherein n represents the number of visible nodes in the network; m represents the number of hidden nodes in the network; v i Representing a given input signal in the network; h is a j Representing the hidden feature vector corresponding to the network output; b i Representing the transfer amount of the underlying visible node; c j Representing hidden node offsets of the hidden layer; w (w) ij Representing a weight matrix for communicating the hidden node with the visible node;
the probability of each display layer and hidden layer is calculated from the network energy formula of the limited boltzmann machine:
where E (v, h) is the network energy of the limited Boltzmann machine, Z is the sum of the display and hidden vector pairs, and P (v, h) is the probability of the display and hidden layers;
the probability distribution calculation formula of the display layer is as follows:
the probability distribution calculation formula of the hidden layer is obtained through interlayer relation calculation:
where σ (x) is a sigmoid function.
7. The method for identifying flight data according to claim 6, wherein the back propagation network using BP neural network as the fine tuning stage of the deep belief network implements the global back propagation optimization network by the probability distribution formula of the hidden layer, so as to fine tune the network model to obtain the optimal parameters of the deep belief network, complete the training of the network, and the calculation formula of the back propagation network constructed by the probability distribution calculation formula of the hidden layer is as follows:
randomly selecting part of to-be-detected flight data feature sets as training sets of the model, and the rest part of to-be-detected flight data feature sets as test sets of the model; and using the test set to verify the flight data identification model under the influence of wind shear based on the deep belief network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310291958.XA CN116821644A (en) | 2023-03-23 | 2023-03-23 | Flight data identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310291958.XA CN116821644A (en) | 2023-03-23 | 2023-03-23 | Flight data identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116821644A true CN116821644A (en) | 2023-09-29 |
Family
ID=88122929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310291958.XA Pending CN116821644A (en) | 2023-03-23 | 2023-03-23 | Flight data identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116821644A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103474066A (en) * | 2013-10-11 | 2013-12-25 | 福州大学 | Ecological voice recognition method based on multiband signal reconstruction |
| US20150019070A1 (en) * | 2012-02-29 | 2015-01-15 | Sagem Defense Securite | Method of analysing flight data |
| CN107392226A (en) * | 2017-06-13 | 2017-11-24 | 上海交通大学 | The modeling method of pilot's working condition identification model |
| CN111107082A (en) * | 2019-12-18 | 2020-05-05 | 哈尔滨理工大学 | Immune intrusion detection method based on deep belief network |
| CN113095381A (en) * | 2021-03-29 | 2021-07-09 | 西安交通大学 | Underwater sound target identification method and system based on improved DBN |
-
2023
- 2023-03-23 CN CN202310291958.XA patent/CN116821644A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150019070A1 (en) * | 2012-02-29 | 2015-01-15 | Sagem Defense Securite | Method of analysing flight data |
| CN103474066A (en) * | 2013-10-11 | 2013-12-25 | 福州大学 | Ecological voice recognition method based on multiband signal reconstruction |
| CN107392226A (en) * | 2017-06-13 | 2017-11-24 | 上海交通大学 | The modeling method of pilot's working condition identification model |
| CN111107082A (en) * | 2019-12-18 | 2020-05-05 | 哈尔滨理工大学 | Immune intrusion detection method based on deep belief network |
| CN113095381A (en) * | 2021-03-29 | 2021-07-09 | 西安交通大学 | Underwater sound target identification method and system based on improved DBN |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111292562B (en) | Aviation flow prediction method | |
| CN106197424B (en) | The unmanned plane during flying state identification method of telemetry driving | |
| Fu et al. | Information processing of remotely sensed agricultural data | |
| CN108107911B (en) | Solar airplane autonomous optimization flight path planning method | |
| CN103440505B (en) | The Classification of hyperspectral remote sensing image method of space neighborhood information weighting | |
| CN107045638A (en) | A kind of flight safety affair analytical method based on context-aware model | |
| CN108100301B (en) | Test flight data processing method for objective test of helicopter simulator | |
| CN111626366B (en) | Operation characteristic-based area sector scene similarity identification method | |
| CN110533095A (en) | A kind of schedule flight risk behavior recognition methods based on improvement random forest | |
| CN113362604B (en) | Controller workload assessment method based on sector dynamic traffic characteristics | |
| CN112966773A (en) | Unmanned aerial vehicle flight condition mode identification method and system | |
| CN112966555A (en) | Remote sensing image airplane identification method based on deep learning and component prior | |
| Behere et al. | Aircraft landing and takeoff operations clustering for efficient environmental impact assessment | |
| US7206674B1 (en) | Information display system for atypical flight phase | |
| Qian et al. | An improved aircraft hard landing prediction model based on panel data clustering | |
| CN116821644A (en) | Flight data identification method | |
| Wu et al. | Flight situation recognition under different weather conditions | |
| Fala et al. | Study on Machine Learning Methods for General Aviation Flight Phase Identification | |
| CN110427956B (en) | LiDAR point cloud data single tree extraction method based on spectral clustering algorithm | |
| CN111461427A (en) | Method and system for generating tropical cyclone strength forecast information | |
| Koprinkova-Hristova et al. | Clustering of spectral images using Echo state networks | |
| CN111445063B (en) | Method and device for selecting take-off and landing points based on flight line | |
| CN116304966A (en) | Track association method based on multi-source data fusion | |
| CN114692786A (en) | Civil aircraft fault diagnosis method based on multi-source data fusion | |
| Klaproth et al. | Investigation of Mission Performance Sensitivities for Unmanned Aerial Vehicles Based on Parametric Similarity Assessment of Mission Requirements |
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 |