CN114219116A - Capacity prediction method for terminal area affected by convection weather - Google Patents

Capacity prediction method for terminal area affected by convection weather Download PDF

Info

Publication number
CN114219116A
CN114219116A CN202111029482.XA CN202111029482A CN114219116A CN 114219116 A CN114219116 A CN 114219116A CN 202111029482 A CN202111029482 A CN 202111029482A CN 114219116 A CN114219116 A CN 114219116A
Authority
CN
China
Prior art keywords
weather
waf
terminal area
capacity
influence
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
Application number
CN202111029482.XA
Other languages
Chinese (zh)
Inventor
彭瑛
王鹏
郭聪聪
赵征
尹嘉男
江斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN202111029482.XA priority Critical patent/CN114219116A/en
Publication of CN114219116A publication Critical patent/CN114219116A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Economics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Medical Informatics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Development Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Game Theory and Decision Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention belongs to the technical field of airport terminal area capacity prediction, and particularly relates to a capacity prediction method for a terminal area affected by convection weather, which comprises the following steps: constructing convection weather characteristics influencing a terminal area; constructing a clustering model based on the convective weather influence scene according to the characteristics; obtaining classification scenes with different degrees of influence of convection weather on the terminal area according to the clustering model; simulating and evaluating a corresponding capacity value according to the classified scene and performing characteristic reconstruction on the convection weather; constructing a machine learning prediction model according to the estimated capacity value and the reconstruction characteristics; and performing comparative analysis according to the prediction result of the machine learning prediction model, so that the capacity prediction of the corresponding convection weather scene can be output by inputting a convection weather prediction product, and a corresponding capacity decision basis is provided for the control work.

Description

Capacity prediction method for terminal area affected by convection weather
Technical Field
The invention belongs to the technical field of airport terminal area capacity prediction, and particularly relates to a capacity prediction method for a terminal area affected by convection weather.
Background
The main production indexes of the civil aviation industry in 2019 continue to maintain stable and rapid growth. The national civil aviation industry development statistics bulletin shows that the weather causes are the main causes causing flight departure and landing to be abnormal, and account for 47.46% of the total number of abnormal flights, which shows that the weather becomes the most main factor causing flight delay, and the convective weather in the weather category is the highest factor. After the occurrence of the convection weather, the severity of the capacity reduction varies due to different durations, different range influences and different occurrence times. Therefore, how to quickly identify the influence on the convection weather of the terminal area is very important for predicting whether the corresponding take-off and landing capacity can be realized.
The prediction of the airspace capacity refers to predicting the dynamic change of the airspace traffic capacity under the influence of certain reasons, wherein the reasons are often related to certain weather conditions, the failed air management equipment, the workload of a controller and the like. At present, the coordination between seven large control areas in China is not perfect enough, so that the specific implementation of a flow management strategy has relative hysteresis, and the dynamic change of airspace capacity caused by weather has time-varying property, so that the imbalance of air traffic capacity and flow is aggravated by the two problems. Under different weather conditions, the airspace capacity is rapidly and accurately predicted, a reasonable airspace and traffic management method is favorably formed in advance, the airspace resource utilization rate is favorably improved, and the flight delay condition caused by sudden change of the capacity is reduced as much as possible. At present, the research of China mainly focuses on the construction of the influence indexes of the convection weather on the airway weather, the prediction of flight flow conflict and the flight adjustment and take-off and landing sequencing, and the complexity of the capacity evaluation and prediction results in relatively less research on the capacity prediction of a terminal area, so that how to realize the conversion between the influence of the convection weather on the terminal area and a control rule and how to use a clustering scene to predict the airspace capacity of the terminal area in real time provides more timely and efficient technical support for the formulation of an airport flow management strategy is urgent to solve at present.
Therefore, it is necessary to design a new capacity prediction method for a convection weather influence terminal area based on the above technical problems.
Disclosure of Invention
The invention aims to provide a capacity prediction method for a terminal area affected by convection weather.
In order to solve the above technical problem, the present invention provides a method for predicting a capacity of a terminal area affected by convection weather, including:
constructing convection weather characteristics influencing a terminal area;
constructing a clustering model based on the convective weather influence scene according to the characteristics;
obtaining classification scenes with different degrees of influence of convection weather on the terminal area according to the clustering model;
simulating and evaluating a corresponding capacity value according to the classified scene and performing characteristic reconstruction on the convection weather;
constructing a machine learning prediction model according to the estimated capacity value and the reconstruction characteristics; and
and performing comparative analysis according to the prediction result of the machine learning prediction model.
Further, the method for predicting the capacity of the terminal area affected by the convection weather comprises the following steps:
constructing features through attributes possessed by convective weather;
constructing characteristics through the influence of convection weather on main off-site points;
constructing features through the influence of convection weather on the main approach corridor;
the features are constructed by the effect of convective weather on the airspace near the runway.
Further, the method for constructing the characteristics through the attributes of the convective weather comprises the following steps:
performing binarization processing on the WAF, capturing the WAF contour edge and performing convex hull processing on the WAF contour edge to form the WAF which accords with the actual operation condition, and reserving the WAF convex hull which is in the terminal area and has intersection with the terminal area;
solving a minimum external matrix of the irregular polygon WAF subjected to convex hull processing, and calculating the central coordinate of the minimum external matrix to be used as the central coordinate (X, Y) of the WAF convex hull;
the perimeter and the area of the WAF convex hull reflect the severity of the convection weather, C is the perimeter of the WAF convex hull, S is the area of the convex hull, and the perimeter-area ratio is characterized in that
Figure RE-GDA0003499305890000031
The method for constructing the characteristics through the influence of the convective weather on the main off-site points comprises the following steps:
the WAF convex hull set is WAF ═ P1,P2,...,PnDetermining whether the WAF covers the main off-site point D ═ D of the terminal areaiI belongs to the number of main field-leaving points contained in the terminal area }, namely i
Figure RE-GDA0003499305890000032
When x is 1, DiWhen e is equal to D, DwxlTo be DiLength of the line covered by the left side of the WAF convex hull, dwxrTo be DiLength of the line covered for the right side of the WAF convex hull, dilIs a reaction of with DiAdjacent left termination field boundary length, dirIs a reaction of with DiThe boundary length of the adjacent right terminal area is calculated, and the WAF edge off-field point D is calculatediAdjacent boundary coverage specific gravity of
Figure RE-GDA0003499305890000033
Determining the flow control condition of each field departure point under the influence of the WAF;
when weather coverage D has been determinediFrom DiClearance time interval beta between two aircraft leaving the field, i.e. DiProportion q of point flow control to covering terminal area boundary with WAFDiExpressed by a piecewise function, a positive value is WAF and is covered at DiLeft side of the dotted off-field direction, with a negative WAF covering DiThe point is to the right of the field direction.
Further, the method for constructing features through influence of convection weather on the main approach corridor comprises the following steps:
terminal area main entrance corridor A ═ Ak|k＝1,2,...,10}，SwxIs the area of airspace covered by convective weather, SGeneral assemblyThe proportion of the airspace covered by dangerous weather is the total area of the airspace, namely the weather danger index of the kth approach corridor
Figure RE-GDA0003499305890000034
Each entrance corridor polygon comprises a source, a sink, a top and a bottom, Mincutj is the minimum cut of the kth entrance corridor polygon under the influence of the jth WAF convex hull, Mincutk0Is the smallest cut of the k-th entrance corridor polygon in good weather, eiAnd ebRespectively, the top and bottom edges of the approach corridor polygon, the available flow capacity ratio of the kth approach corridor polygon under the influence of the jth WAF convex hull is:
Figure RE-GDA0003499305890000041
the method for constructing the characteristics through the influence of the convective weather on the airspace near the runway comprises the following steps:
dividing the area near the runway into several parts, (cX, cY) is the coordinate on the WAF center, (x)0,y0) The coordinates on the graph of the runway center are, the Euclidean distance between the WAF center and the runway center is
Figure RE-GDA0003499305890000042
Further, the method for constructing the clustering model based on the convective weather influence scene according to the characteristics comprises the following steps:
selecting the characteristics cX and cY related to the position and the distance d between the weather center and the runwayRWYAnd obtaining the optimal clustering number with the four characteristics of the weather hazard index WSI, evaluating the clustering result to determine a clustering cluster K, and establishing a clustering model by adopting a K-means clustering algorithmMolding;
traversing the clustering value n and the parameter gamma of the Gaussian kernel function, comparing the size relationship of Calinski-Harbasz Score, finding the value of the corresponding category when the Calinski-Harbasz Score is maximum or remarkably large, wherein gamma is the optimal Gaussian kernel parameter and n is the optimal clustering number, standardizing the convective weather convex hull sample set P according to the characteristic columns, and mapping characteristic data of each column to [0, 1%]Features of weather convex hull samples over intervals, i.e. after normalisation
Figure RE-GDA0003499305890000043
Establishing a clustering model by adopting a spectral clustering algorithm;
and selecting the optimal clustering category number of the Gaussian mixture model by using a penalty item AIC and a BIC criterion of the model complexity, determining the clustering category number according to the variation trend of the AIC and BIC values under different clustering category numbers, and establishing the clustering model by using a Gaussian mixture clustering algorithm.
Further, the method for obtaining the classification scenes with different degrees of influence of the convection weather on the terminal area according to the clustering model comprises the following steps:
and establishing a clustering model according to a Gaussian mixture clustering algorithm to obtain an actual control scene which accords with the terminal area.
Further, the method for simulating and evaluating the corresponding capacity value according to the classified scene and reconstructing the characteristics of the convection weather comprises the following steps:
carrying out capacity evaluation through a computer simulation model to obtain capacity values of different classification scenes;
constructing a simulation model of an airport scene and a terminal area sector structure, acquiring a daily actual total lifting and landing frame sample set of a terminal area from the daily actual total lifting and landing frame sample set of the terminal area, sequencing the daily actual total lifting and landing frame samples of the day from small to large, determining the date corresponding to a preset percentage quantile sample as a typical day, and generating a flight plan for three days in total by combining with the flight plans of two days before and after the typical day to serve as the input of the simulation model;
monitoring the data recording step length according to a preset simulation process, monitoring the average flow of three days in a flight plan, observing the average entering and leaving delay, and observing the real-time average flow of the average delay in a preset time, wherein the flow value at the moment is the terminal area capacity value under the influence of the current convection weather, namely the capacity evaluation value;
and (4) reconstructing the characteristics under the influence of convection weather, wherein the category of the Gaussian cluster is that the set is P ═ { P ═ P1,p2,…,pmAnd f, the number of times of updating the WAF picture information in the preset time is t ═ 1,2, …,10}, and the category of the jth convective weather convex hull of the ith WAF picture is cijmThe number of each class contained therein is n1,n2,…,nmThen c isi＝[ni1,ni2,…,nim]；
Performing weather characteristic reconstruction according to the number q of weather convex hulls contained in each WAF picture and the membership class P to form weather characteristic class matrix characteristic reconstruction taking hours as units
Figure RE-GDA0003499305890000051
I.e. the reconstructed features.
Further, the method for constructing the machine learning prediction model according to the evaluation capacity value and the reconstruction characteristics comprises the following steps:
using the reconstruction characteristics as an input layer of a neural network, using the capacity evaluation value as an output layer, and performing empirical formula
Figure RE-GDA0003499305890000052
Presetting the number of layers and the number of nodes of a hidden layer, and establishing a BP neural network model according to an activation function and an optimizer to predict the capacity of a terminal area under the influence of convection weather;
dividing a data set of the reconstruction characteristics into training set data and test set data, and establishing a linear regression model according to a linear regression formula to predict the capacity of the terminal area under the influence of convection weather;
according to the objective function
Figure RE-GDA0003499305890000061
Constraint conditions
Figure RE-GDA0003499305890000062
Selecting a Gaussian kernel function by the kernel function, and establishing a support vector machine regression model to predict the capacity of the terminal area under the influence of convection weather;
wherein w is a coefficient matrix of x; f (x)i)w′xi+ b, will | yi-f(xi)|-ξ(*)Epsilon is less than or equal to two inequality constraints in the objective function; xiiAnd
Figure RE-GDA0003499305890000063
indicates that the sample points x other than the "divided bands" are to beiThe cost required to pull back in both bands.
Further, the method for performing comparative analysis according to the prediction result of the machine learning prediction model comprises the following steps:
and comparing and analyzing the prediction accuracies of the three prediction models according to the overall conditions of goodness of fit R2, mean absolute error MAE and mean square error MSE of the performance measurement indexes of the training set and the test set and the trend of the predicted value deviating from the simulation evaluation capacity value so as to determine the capacity prediction model of the convection weather influence terminal area.
The method has the advantages that the convection weather characteristics affecting the terminal area are constructed; constructing a clustering model based on the convective weather influence scene according to the characteristics; obtaining classification scenes with different degrees of influence of convection weather on the terminal area according to the clustering model; simulating and evaluating a corresponding capacity value according to the classified scene and performing characteristic reconstruction on the convection weather; constructing a machine learning prediction model according to the estimated capacity value and the reconstruction characteristics; and performing comparative analysis according to the prediction result of the machine learning prediction model, so that the capacity prediction of the corresponding convection weather scene can be output by inputting a convection weather prediction product, and a corresponding capacity decision basis is provided for the control work.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method of capacity prediction for a convective weather affecting terminal area in accordance with the present invention;
FIG. 2 is a binary map of WAF convex encapsulation;
FIG. 3 is a schematic diagram of the center coordinates of a WAF;
FIG. 4 is a diagram illustrating WAF overlay density along adjacent boundaries of off-field points;
FIG. 5 is a schematic view of the division of airspace near the runway;
FIG. 6 is a diagram illustrating a classification scenario in which the influence of convective weather on a terminal area is different;
FIG. 7 is a schematic view of a Guangzhou white cloud airport terminal area model;
FIG. 8 is a schematic diagram of a Guangzhou terminal area simulation real-time traffic distribution;
FIG. 9 is a convective weather convex wrapper map;
FIG. 10 is a diagram illustrating a first prediction result;
FIG. 11 is a diagram illustrating a second prediction result;
FIG. 12 is a graph showing a third prediction result;
FIG. 13 is a graph illustrating a fourth prediction result;
fig. 14 is a schematic diagram of a capacity prediction method for a convective weather effect terminal area.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Fig. 1 is a flow chart of a method for predicting the capacity of a convective weather affecting terminal area according to the present invention.
As shown in fig. 1 and fig. 14, this embodiment 1 provides a capacity prediction method for a convective weather affecting terminal area, including: constructing convection weather characteristics influencing a terminal area; constructing a clustering model based on the convective weather influence scene according to the characteristics; obtaining classification scenes with different degrees of influence of convection weather on the terminal area according to the clustering model; simulating and evaluating a corresponding capacity value according to the classified scene and performing characteristic reconstruction on the convection weather; constructing a machine learning prediction model according to the estimated capacity value and the reconstruction characteristics; and performing comparative analysis according to the prediction result of the machine learning prediction model, so that the capacity prediction of the corresponding convection weather scene can be output by inputting a convection weather prediction product (such as a WAF picture), and a corresponding capacity decision basis is provided for the control work.
In this embodiment, the method for predicting the capacity of the terminal area affected by the convection weather includes: constructing features through attributes possessed by convective weather; constructing characteristics through the influence of convection weather on main off-site points; constructing features through the influence of convection weather on the main approach corridor; the features are constructed by the effect of convective weather on the airspace near the runway.
FIG. 2 is a binary map of WAF convex encapsulation;
FIG. 3 is a schematic diagram of the center coordinates of a WAF;
FIG. 4 is a diagram illustrating WAF overlay density along adjacent boundaries of off-field points;
fig. 5 is a schematic view of the division of airspace near the runway.
As shown in fig. 2, 3, 4 and 5, in the present embodiment, the passing pair isThe method for constructing the characteristics of the attributes of the streaming weather comprises the following steps: performing binarization processing on WAF (Weather Avoidance area, Weather Avoidance Field), displaying a WAF area of a red part as white in a binarization picture, displaying other areas without Weather influence as black, grabbing a WAF outline edge and performing convex hull processing on the WAF outline edge to form WAF meeting actual operation conditions, deleting Weather with a Weather center outside 125km of the terminal area and Weather without intersection with the terminal area, and only keeping WAF convex hulls which are in the terminal area and have intersection with the terminal area; solving a minimum external matrix of the irregular polygon WAF subjected to convex hull processing, and calculating the central coordinate of the minimum external matrix to be used as the central coordinate (X, Y) of the WAF convex hull; the two indexes of the perimeter and the area of the WAF convex hull reflect the severity of the convection weather to a great extent, but the convection weather with relatively fragmented edges does not necessarily cover a large area, C is the perimeter of the WAF convex hull, S is the area of the convex hull, and the perimeter-area ratio is characterized in that
Figure RE-GDA0003499305890000091
The method for constructing the characteristics through the influence of the convective weather on the main off-site points comprises the following steps:
the WAF convex hull set is WAF ═ P1,P2,...,PnDetermining whether the WAF covers the main off-site point D ═ D of the terminal areaiI belongs to the number of main field-leaving points contained in the terminal area }, namely i
Figure RE-GDA0003499305890000092
When x is 1, DiWhen e is equal to D, DwxlTo be DiLength of the line covered by the left side of the WAF convex hull, dwxrTo be DiLength of the line covered for the right side of the WAF convex hull, dilIs a reaction of with DiAdjacent left termination field boundary length, dirIs a reaction of with DiThe boundary length of the adjacent right terminal area is calculated, and the WAF edge off-field point D is calculatediAdjacent boundary coverage specific gravity of
Figure RE-GDA0003499305890000093
And according to regulationsEmpirically determining the flow control condition of each field departure point under the influence of the WAF;
when weather coverage D has been determinediFrom DiClearance time interval beta between two aircraft leaving the field, i.e. DiProportion q of point flow control to covering terminal area boundary with WAFDiExpressed by a piecewise function, a positive value is WAF and is covered at DiLeft side of the dotted off-field direction, with a negative WAF covering DiPoint-to-field direction right;
when weather coverage D has been determined1From D1Clearance time interval beta between two aircraft leaving the field, i.e. D1The proportion of point flow control to the boundary of the WAF coverage terminal area is expressed by a piecewise function
Figure RE-GDA0003499305890000101
Positive values are WAF overlaid at D1Left side of the dotted off-field direction, with a negative WAF covering D1The point is away from the right side of the field direction, and the critical value of beta is determined by a control expert;
when weather coverage D has been determined2From D2Clearance time interval beta between two aircraft leaving the field, i.e. D2The proportion of point flow control to the boundary of the WAF coverage terminal area is expressed by a piecewise function
Figure RE-GDA0003499305890000102
Positive values are WAF overlaid at D2Left side of the dotted off-field direction, with a negative WAF covering D2The point is away from the right side of the field direction, and the critical value of beta is determined by a control expert;
when weather coverage D has been determined3From D3Clearance time interval beta between two aircraft leaving the field, i.e. D3The proportion of point flow control to the boundary of the WAF coverage terminal area is expressed by a piecewise function
Figure RE-GDA0003499305890000103
Positive values are WAF overlaid at D3Left side of the dotted off-field direction, with a negative WAF covering D3The point is away from the right side of the field direction, and the critical value of beta is determined by a control expert;
when having already finishedDetermining weather coverage D4From D4Clearance time interval beta between two aircraft leaving the field, i.e. D4The proportion of point flow control to the boundary of the WAF coverage terminal area is expressed by a piecewise function
Figure RE-GDA0003499305890000104
Positive values are WAF overlaid at D4Left side of the dotted off-field direction, with a negative WAF covering D4The point to the right of the field direction, the critical value of β is determined by the regulatory expert.
In this embodiment, the method for constructing features through the influence of convection weather on the main approach corridor comprises the following steps: terminal area main entrance corridor A ═ Ak|k＝1,2,...,10}，SwxIs the area of airspace covered by convective weather, SGeneral assemblyThe total area of the airspace, the proportion of the airspace covered by dangerous Weather, i.e., the Weather hazard Index (WSI) of the kth approach corridor
Figure RE-GDA0003499305890000111
Researching the residual traffic Capacity of the airspace covered by the weather by utilizing the maximum Flow minimum cut theory, namely the Available Flow Capacity Ratio (AFCR), wherein each entrance corridor polygon comprises a source, a sink, a top and a bottom, and MincutjMincut, the minimum cut of the k-th entrance corridor polygon under the influence of the j-th WAF convex hullk0Is the smallest cut of the k-th entrance corridor polygon in good weather, eiAnd ebRespectively, the top and bottom edges of the approach corridor polygon, the available flow capacity ratio of the kth approach corridor polygon under the influence of the jth WAF convex hull is:
Figure RE-GDA0003499305890000112
the method for constructing the characteristics through the influence of the convective weather on the airspace near the runway comprises the following steps: dividing the area around the runway into several parts (e.g. 8 parts), (cX, cY) being the on-map coordinates of the WAF center, (x)0,y0) As the centre of a runwayThe Euclidean distance between the WAF center and the runway center is
Figure RE-GDA0003499305890000113
In this embodiment, the method for constructing a clustering model based on a convective weather influence scene according to features includes: selecting the characteristics cX and cY related to the position and the distance d between the weather center and the runwayRWYPerforming a K-means inflection point method on the four characteristics of the weather hazard index WSI to calculate the optimal clustering number, evaluating a clustering result to determine that a clustering cluster K is 6, and establishing a clustering model by adopting a K-means clustering algorithm; traversing a clustering value n and a parameter gamma of a Gaussian kernel function, comparing the size relationship of Calinski-Harbasz Score, finding out a value of a corresponding category when the Calinski-Harbasz Score is maximum or remarkably large, wherein gamma is 0.01 as an optimal Gaussian kernel parameter, n is 3 as an optimal clustering number, and normalizing the convection weather convex hull sample set P according to characteristic columns to map characteristic data of each column to [0,1]Features of weather convex hull samples over intervals, i.e. after normalisation
Figure RE-GDA0003499305890000121
Establishing a clustering model by adopting a spectral clustering algorithm; selecting the optimal clustering category number of the Gaussian mixture model by using a penalty item AIC and a BIC criterion of the model complexity, determining the clustering category number according to the variation trend of the AIC and BIC values under different clustering category numbers, and establishing the clustering model by using a Gaussian mixture clustering algorithm; the Calinski-Harabaz Score is an internal evaluation method which can help to determine the number of clustering categories more quickly during the clustering analysis of mass data: the evaluation on the clustering effect of the algorithm can be realized through a single quantization score without using data which is similar to labels and realizes a monitoring function;
the formula for Calinski-Harabaz Score is:
Figure RE-GDA0003499305890000122
wherein k represents the number of clustering classes, N represents the number of whole samples, SSB is the inter-class variance, and SSW is the intra-class variance;
SSB＝tr(Bk)
Figure RE-GDA0003499305890000123
trace only considers the elements on the diagonal of the matrix, i.e. the euclidean distance from all sample points in class q to the class;
SSW＝tr(Wk)
Figure RE-GDA0003499305890000124
wherein c isqIs a particle of class q, cEIs the center point of all sample data, nqThe total number of class q sample data points, Calinski-Harbasz Score measures the difference between the classification and ideal classification (largest inter-class variance, smallest intra-class variance), and the normalization factor (N-k)/(k-1) decreases with the increase of class number k, so that the method tends to obtain results with fewer classes; at this time, another locally optimal k needs to be found according to the requirement, even if the locally optimal k is not the highest score, the value can be accepted as long as the corresponding score is significantly high, and as with the gradient, the global optimal can not be found in some cases, but the locally optimal result is still acceptable.
Fig. 6 is a diagram illustrating a classification scenario in which the influence of the convective weather on the terminal area is different.
As shown in fig. 6, in this embodiment, the method for obtaining classification scenes with different degrees of influence on the terminal area by the convective weather according to the clustering model includes: and (3) according to the clustering effect index profile coefficient scores of different clustering methods, the accurate matching degree of the main scene reflecting the weather influence terminal area and the control experience is comprehensively considered, the Gaussian mixed clustering is clearer to divide data relative to other two types, and finally, a Gaussian mixed clustering algorithm is determined to be selected to establish a clustering model to obtain the actual control scene conforming to the terminal area.
FIG. 7 is a schematic view of a Guangzhou white cloud airport terminal area model;
FIG. 8 is a schematic diagram of a Guangzhou terminal area simulation real-time traffic distribution;
fig. 9 is a convective weather convex wrapper map.
As shown in fig. 7 and 8, in this embodiment, the method for evaluating the corresponding capacity value according to the classification scene simulation and performing feature reconstruction on the convection weather includes: carrying out capacity evaluation through a computer simulation model to obtain capacity values of different classification scenes; communicating with a controller through NAIP data of an airport, setting rules according to an airport runway operation mode, main ascending and descending route distribution and main departure and departure points, constructing a simulation model of an airport scene and a terminal area sector structure based on AirTOp software, acquiring a daily actual total ascending and descending rack sample set of a day d from a daily actual total ascending and descending rack sample set of a terminal area, sequencing the daily actual total ascending and descending rack samples of the day d from small to large, determining a date corresponding to a preset percentage quantile (95% quantile) sample as a typical day, and generating a flight plan of three days in total by combining with flight plans of two days before and after the typical day to serve as input of the simulation model; the method comprises the steps that through different experience flow control measures corresponding to different areas near a main off-site point, a main entrance corridor and a runway of a weather coverage terminal area, the influence of convection weather of each radar reflectivity WAF product diagram on the terminal area is converted into a specific control strategy, when the weather coverage terminal area is at a specific position, simulation operation parameter setting of weather influence is carried out in a mode of adjusting control operation time intervals or distance intervals of the on-site point of the terminal area, under the influence of the convection weather, different scenes where the convection weather influences the terminal area can be extracted, and further capacity under different scenes is evaluated based on an AirTOp simulation platform; according to the preset simulation process monitoring data recording step length (the simulation process monitoring data recording step length is set to be 1 hour), the main monitoring content is the average flow of three days in the flight plan, the average approach and departure delay is observed, the flight plan is gradually increased and decreased to a certain extent, and the average approach and departure is guaranteedThe delay time is not higher than 8 minutes, the real-time average flow of the average delay in the preset time (8 minutes) is observed, and the flow value at the moment is the terminal area capacity value under the influence of the current convection weather, namely the capacity evaluation value; as shown in fig. 9, for feature reconstruction under the influence of convective weather, the class of gaussian clustering is set as P ═ { P ═ P1,p2,…,pmAnd f, updating the WAF picture information within a preset time (1 hour) for a number of times t ═ 1,2, …,10, where the category to which the jth convection weather convex hull of the ith WAF picture belongs is cijmThe number of each class contained therein is n1,n2,…,nmThen c isi＝[ni1,ni2,…,nim](ii) a Performing weather characteristic reconstruction according to the number q of weather convex hulls contained in each WAF picture and a membership class (class of Gaussian cluster) P to form weather characteristic class matrix characteristic reconstruction taking hours as a unit
Figure RE-GDA0003499305890000141
I.e. the reconstructed features.
In this embodiment, the method for constructing the machine learning prediction model according to the estimated capacity value and the reconstructed features includes: taking the reconstruction characteristics as an input layer of the neural network, wherein the number of nodes of the input layer is set to be 20; taking the capacity evaluation value as an output layer, setting the output layer to be 1, and setting the number of output nodes to be 1; according to empirical formula
Figure RE-GDA0003499305890000142
Presetting the number of layers and the number of nodes of a hidden layer to be 10, using a Leaky ReLU function as an activation function, and establishing a BP neural network model for predicting the capacity of a terminal area under the influence of convection weather by using an optimizer Adam; dividing a data set with reconstructed characteristics into training set data and test set data, setting 80% of the data set with the reconstructed characteristics as the training set data, setting 20% of the data set with the reconstructed characteristics as the test set data, and establishing a linear regression model according to a linear regression formula to predict the capacity of the terminal area under the influence of convection weather; according to the objective function
Figure RE-GDA0003499305890000151
Constraint conditions
Figure RE-GDA0003499305890000152
Selecting a Gaussian kernel function by the kernel function, and establishing a Support Vector Machine (SVM) regression model to predict the capacity of the terminal area under the influence of convection weather; wherein w is a coefficient matrix of x; f (x)i)＝w′xi+ b, will
|yi-f(xi)|-ξ(*)Epsilon is less than or equal to two inequality constraints in the objective function; xiiAnd
Figure RE-GDA0003499305890000153
indicates that the sample points x other than the "divided bands" are to beiThe cost required to pull back in both bands.
FIG. 10 is a diagram illustrating a first prediction result;
FIG. 11 is a diagram illustrating a second prediction result;
FIG. 12 is a graph showing a third prediction result;
fig. 13 is a diagram illustrating a fourth prediction result.
As shown in fig. 10, 11, 12, and 13, in this embodiment, the method for performing comparative analysis according to the prediction result of the machine learning prediction model includes: and comparing and analyzing the prediction accuracies of the three prediction models according to the overall conditions of goodness of fit R2, mean absolute error MAE and mean square error MSE of the performance measurement indexes of the training set and the test set and the trend of the predicted value deviating from the simulation evaluation capacity value so as to determine the capacity prediction model of the convection weather influence terminal area.
In summary, the present invention constructs the convection weather characteristics affecting the terminal area; constructing a clustering model based on the convective weather influence scene according to the characteristics; obtaining classification scenes with different degrees of influence of convection weather on the terminal area according to the clustering model; simulating and evaluating a corresponding capacity value according to the classified scene and performing characteristic reconstruction on the convection weather; constructing a machine learning prediction model according to the estimated capacity value and the reconstruction characteristics; and performing comparative analysis according to the prediction result of the machine learning prediction model, so that the capacity prediction of the corresponding convection weather scene can be output by inputting a convection weather prediction product, and a corresponding capacity decision basis is provided for the control work.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.

Claims (9)

1. A capacity prediction method for a terminal area affected by convection weather is characterized by comprising the following steps:
constructing convection weather characteristics influencing a terminal area;
constructing a clustering model based on the convective weather influence scene according to the characteristics;
obtaining classification scenes with different degrees of influence of convection weather on the terminal area according to the clustering model;
simulating and evaluating a corresponding capacity value according to the classified scene and performing characteristic reconstruction on the convection weather;
constructing a machine learning prediction model according to the estimated capacity value and the reconstruction characteristics; and
and performing comparative analysis according to the prediction result of the machine learning prediction model.
2. The method for predicting the capacity of a convective weather affecting terminal area of claim 1,
the method for predicting the capacity of the convection weather influence terminal area comprises the following steps:
constructing features through attributes possessed by convective weather;
constructing characteristics through the influence of convection weather on main off-site points;
constructing features through the influence of convection weather on the main approach corridor;
the features are constructed by the effect of convective weather on the airspace near the runway.
3. The method for predicting the capacity of a convective weather affecting terminal area of claim 2,
the method for constructing the characteristics through the attributes of the convective weather comprises the following steps:
performing binarization processing on the WAF, capturing the WAF contour edge and performing convex hull processing on the WAF contour edge to form the WAF which accords with the actual operation condition, and reserving the WAF convex hull which is in the terminal area and has intersection with the terminal area;
solving a minimum external matrix of the irregular polygon WAF subjected to convex hull processing, and calculating the central coordinate of the minimum external matrix to be used as the central coordinate (X, Y) of the WAF convex hull;
the perimeter and the area of the WAF convex hull reflect the severity of the convection weather, C is the perimeter of the WAF convex hull, S is the area of the convex hull, and the perimeter-area ratio is characterized in that
Figure RE-FDA0003499305880000011
The method for constructing the characteristics through the influence of the convective weather on the main off-site points comprises the following steps:
the WAF convex hull set is WAF ═ P1,P2,...,PnDetermining whether the WAF covers the main off-site point D ═ D of the terminal areaiI belongs to the number of main field-leaving points contained in the terminal area }, namely i
Figure RE-FDA0003499305880000021
When x is 1, DiWhen e is equal to D, DwxlTo be DiLength of the line covered by the left side of the WAF convex hull, dwxrTo be DiLength of the line covered for the right side of the WAF convex hull, dilIs a reaction of with DiAdjacent left termination field boundary length, dirIs a reaction of with DiThe boundary length of the adjacent right terminal area is calculated, and the WAF edge off-field point D is calculatediAdjacent boundary coverage specific gravity of
Figure RE-FDA0003499305880000022
Determining the flow control condition of each field departure point under the influence of the WAF;
when weather coverage D has been determinediFrom DiClearance time interval beta between two aircraft leaving the field, i.e. DiProportion of point flow control to covering terminal area boundary with WAF
Figure RE-FDA0003499305880000025
Expressed by a piecewise function, a positive value is WAF and is covered at DiLeft side of the dotted off-field direction, with a negative WAF covering DiThe point is to the right of the field direction.
4. The method for predicting the capacity of a convective weather affecting terminal area of claim 3,
the method for constructing the characteristics through the influence of convection weather on the main approach corridor comprises the following steps:
terminal area main entrance corridor A ═ Ak|k＝1,2,...,10}，SwxIs the area of airspace covered by convective weather, SGeneral assemblyThe proportion of the airspace covered by dangerous weather is the total area of the airspace, namely the weather danger index of the kth approach corridor
Figure RE-FDA0003499305880000023
Each entrance corridor polygon comprises a source, a sink, a top and a bottom, Mincutj is the minimum cut of the kth entrance corridor polygon under the influence of the jth WAF convex hull, Mincutk0Is the smallest cut of the k-th entrance corridor polygon in good weather, eiAnd ebRespectively, the top and bottom edges of the approach corridor polygon, the available flow capacity ratio of the kth approach corridor polygon under the influence of the jth WAF convex hull is:
Figure RE-FDA0003499305880000024
the method for constructing the characteristics through the influence of the convective weather on the airspace near the runway comprises the following steps:
dividing the area near the runway into several parts, (cX, cY) is the coordinate on the WAF center, (x)0,y0) The coordinates on the graph of the runway center are, the Euclidean distance between the WAF center and the runway center is
Figure RE-FDA0003499305880000031
5. The method for predicting the capacity of a convective weather affecting terminal area of claim 4,
the method for constructing the clustering model based on the convective weather influence scene according to the characteristics comprises the following steps:
selecting the characteristics cX and cY related to the position and the distance d between the weather center and the runwayRWYAcquiring the optimal clustering number with the four characteristics of the weather hazard index WSI, evaluating a clustering result to determine a clustering cluster K, and establishing a clustering model by adopting a K-means clustering algorithm;
traversing the clustering value n and the parameter gamma of the Gaussian kernel function, comparing the size relationship of Calinski-Harbasz Score, finding the value of the corresponding category when the Calinski-Harbasz Score is maximum or remarkably large, wherein gamma is the optimal Gaussian kernel parameter and n is the optimal clustering number, standardizing the convective weather convex hull sample set P according to the characteristic columns, and mapping characteristic data of each column to [0, 1%]Features of weather convex hull samples over intervals, i.e. after normalisation
Figure RE-FDA0003499305880000032
Establishing a clustering model by adopting a spectral clustering algorithm;
and selecting the optimal clustering category number of the Gaussian mixture model by using a penalty item AIC and a BIC criterion of the model complexity, determining the clustering category number according to the variation trend of the AIC and BIC values under different clustering category numbers, and establishing the clustering model by using a Gaussian mixture clustering algorithm.
6. The method for predicting the capacity of a convective weather affecting terminal zone of claim 5,
the method for acquiring the classification scenes with different influence degrees of the convection weather on the terminal area according to the clustering model comprises the following steps:
and establishing a clustering model according to a Gaussian mixture clustering algorithm to obtain an actual control scene which accords with the terminal area.
7. The method for predicting the capacity of a convective weather affecting terminal area of claim 6,
the method for simulating and evaluating the corresponding capacity value according to the classified scene and reconstructing the characteristics of the convection weather comprises the following steps:
carrying out capacity evaluation through a computer simulation model to obtain capacity values of different classification scenes;
constructing a simulation model of an airport scene and a terminal area sector structure, acquiring a daily actual total lifting and landing frame sample set of a terminal area from the daily actual total lifting and landing frame sample set of the terminal area, sequencing the daily actual total lifting and landing frame samples of the day from small to large, determining the date corresponding to a preset percentage quantile sample as a typical day, and generating a flight plan for three days in total by combining with the flight plans of two days before and after the typical day to serve as the input of the simulation model;
monitoring the data recording step length according to a preset simulation process, monitoring the average flow of three days in a flight plan, observing the average entering and leaving delay, and observing the real-time average flow of the average delay in a preset time, wherein the flow value at the moment is the terminal area capacity value under the influence of the current convection weather, namely the capacity evaluation value;
and (4) reconstructing the characteristics under the influence of convection weather, wherein the category of the Gaussian cluster is that the set is P ═ { P ═ P1,p2,…,pmAnd f, the number of times of updating the WAF picture information in the preset time is t ═ 1,2, …,10}, and the category of the jth convective weather convex hull of the ith WAF picture is cijmThe number of each class contained therein is n1,n2,…,nmThen c isi＝[ni1,ni2,…,nim]；
Performing weather characteristic reconstruction according to the number q of weather convex hulls contained in each WAF picture and the Gaussian membership class P to form weather characteristic class matrix characteristic reconstruction taking hours as unit
Figure RE-FDA0003499305880000041
I.e. the reconstructed features.
8. The method for predicting the capacity of a convective weather affecting terminal zone of claim 7,
the method for constructing the machine learning prediction model according to the evaluation capacity value and the reconstruction characteristics comprises the following steps:
using the reconstruction characteristics as an input layer of a neural network, using the capacity evaluation value as an output layer, and performing empirical formula
Figure RE-FDA0003499305880000042
Presetting the number of layers and the number of nodes of a hidden layer, and establishing a BP neural network model according to an activation function and an optimizer to predict the capacity of a terminal area under the influence of convection weather;
dividing a data set of the reconstruction characteristics into training set data and test set data, and establishing a linear regression model according to a linear regression formula to predict the capacity of the terminal area under the influence of convection weather;
according to the objective function
Figure RE-FDA0003499305880000051
Constraint conditions
Figure RE-FDA0003499305880000052
Selecting a Gaussian kernel function by the kernel function, and establishing a support vector machine regression model to predict the capacity of the terminal area under the influence of convection weather;
wherein w is a coefficient matrix of x; f (x)i)＝w'xi+ b, will | yi-f(xi)|-ξ(*)Epsilon is less than or equal to two inequality constraints in the objective function; xiiAnd
Figure RE-FDA0003499305880000053
indicates that the sample points x other than the "divided bands" are to beiThe cost required to pull back in both bands.
9. The method for predicting the capacity of a convective weather affecting terminal area of claim 8,
the method for performing comparative analysis according to the prediction result of the machine learning prediction model comprises the following steps:
and comparing and analyzing the prediction accuracies of the three prediction models according to the overall conditions of goodness of fit R2, mean absolute error MAE and mean square error MSE of the performance measurement indexes of the training set and the test set and the trend of the predicted value deviating from the simulation evaluation capacity value so as to determine the capacity prediction model of the convection weather influence terminal area.
CN202111029482.XA 2021-09-02 2021-09-02 Capacity prediction method for terminal area affected by convection weather Pending CN114219116A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111029482.XA CN114219116A (en) 2021-09-02 2021-09-02 Capacity prediction method for terminal area affected by convection weather

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111029482.XA CN114219116A (en) 2021-09-02 2021-09-02 Capacity prediction method for terminal area affected by convection weather

Publications (1)

Publication Number Publication Date
CN114219116A true CN114219116A (en) 2022-03-22

Family

ID=80695946

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111029482.XA Pending CN114219116A (en) 2021-09-02 2021-09-02 Capacity prediction method for terminal area affected by convection weather

Country Status (1)

Country Link
CN (1) CN114219116A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115100907A (en) * 2022-06-17 2022-09-23 南京航空航天大学 Terminal area airspace flight flow prediction method for meteorological scene classification
CN117153000A (en) * 2023-11-01 2023-12-01 天宇航空数据科技(合肥)有限责任公司 Method and system for analyzing influence of approach and departure routes based on three-dimensional radar data

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115100907A (en) * 2022-06-17 2022-09-23 南京航空航天大学 Terminal area airspace flight flow prediction method for meteorological scene classification
CN117153000A (en) * 2023-11-01 2023-12-01 天宇航空数据科技(合肥)有限责任公司 Method and system for analyzing influence of approach and departure routes based on three-dimensional radar data
CN117153000B (en) * 2023-11-01 2024-02-02 天宇航空数据科技(合肥)有限责任公司 Method and system for analyzing influence of approach and departure routes based on three-dimensional radar data

Similar Documents

Publication Publication Date Title
EP3822905A1 (en) Method and device for predicting thermal load of electrical system
CN110503245B (en) Prediction method for large-area delay risk of airport flight
WO2021082393A1 (en) Airport surface variable slide-out time prediction method based on big data deep learning
CN114219116A (en) Capacity prediction method for terminal area affected by convection weather
CN108805337B (en) Aviation operation control risk management and control method and system
Choi et al. Artificial neural network models for airport capacity prediction
CN112180471B (en) Weather forecasting method, device, equipment and storage medium
CN112132005A (en) Face detection method based on cluster analysis and model compression
CN116186548B (en) Power load prediction model training method and power load prediction method
Subramanian et al. Deep-learning based time series forecasting of go-around incidents in the national airspace system
Sridhar Applications of machine learning techniques to aviation operations: Promises and challenges
CN112257914A (en) Aviation safety cause and effect prediction method based on random forest
CN113128769A (en) Intelligent flight delay prediction method based on deep learning
CN113723533B (en) Mode identification method of convection weather influence terminal area and Gaussian mixture clustering model
US20230386199A1 (en) Automated hazard recognition using multiparameter analysis of aerial imagery
Sridhar et al. Lessons Learned in the Application of Machine Learning Techniques to Air Traffic Management
CN115130380A (en) Strategic flight schedule delay distribution prediction method based on machine learning
CN110555552B (en) Terminal area take-off and landing capacity prediction method based on weather risk index
CN114118508A (en) OD market aviation passenger flow prediction method based on space-time convolution network
Tin et al. Incoming Work‐In‐Progress Prediction in Semiconductor Fabrication Foundry Using Long Short‐Term Memory
CN113723532B (en) Convection weather effect terminal area mode identification system
Tarasonok et al. Models for forecasting flight delays
Kuhn et al. Characterizing and classifying historical days based on weather and air traffic
CN115222150B (en) Flight delay prediction method and system based on Stacking
Corrado A Data-Driven Methodology to Analyze Air Traffic Management System Operations within the Terminal Airspace

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