A method, device and equipment for route planning considering altitude

Abstract

The present invention discloses a route planning method, device and equipment considering altitude. First, a starting point, an end point, an aircraft performance model, an aircraft weight and a maximum flyable cruising altitude of a first aircraft are input, and a global route network diagram is clipped according to the starting point and the end point to obtain a first optional route edge set; the route distance is calculated using a Dijkstra algorithm, and the maximum flyable cruising altitude of a second aircraft is calculated by an aircraft maximum flyable cruising altitude prediction model, and compared with the maximum flyable cruising altitude of the first aircraft, the final aircraft maximum flyable cruising altitude is obtained, and the route edge with the lowest flyable altitude less than or equal to the final maximum flyable cruising altitude is retained to obtain a second optional route edge set; finally, an A* algorithm is used to perform horizontal path planning based on the second optional route edge set to determine the target route. The present invention can determine the flyable altitude range of an aircraft under different conditions based on the consideration of aircraft performance, and improve the reliability of route planning.

Description

Technical Field

[0001] The present invention relates to the field of aviation technology, and in particular to a method, device and equipment for route planning taking altitude into consideration. Background Art

[0002] When planning civil aviation routes, in order to ensure flight safety, it is necessary to take into account the optimization of both position and altitude. Therefore, the current civil aviation route planning methods generally adopt a phased planning strategy. First, in the horizontal optimization stage, the focus is on the consideration of location factors to determine the key waypoints that the aircraft needs to pass. Then, in the vertical optimization stage, the most suitable flight altitude is further selected for the determined horizontal path. Although this phased planning method helps to reduce the difficulty of calculation and improve planning efficiency, it also has certain limitations. Specifically, the horizontal optimization stage may cause vertical planning failure due to insufficient consideration of the aircraft performance range; at the same time, it is difficult to directly determine which altitude ranges correspond to the routes that can meet the aircraft performance in the horizontal optimization stage, resulting in a lack of choice during planning. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a route planning method, device and equipment taking altitude into consideration, which can determine the flyable altitude range of an aircraft under different conditions based on aircraft performance, thereby improving the reliability of route planning.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a route planning method considering altitude, including:

[0005] Enter the starting point, end point, aircraft performance model, aircraft weight and the maximum cruising altitude of the first aircraft;

[0006] Cutting the global route network graph according to the starting point and the end point to obtain a first optional route edge set;

[0007] Based on the first optional route edge set, using Dijkstra algorithm to calculate the unrestricted shortest path distance from the starting point to the end point;

[0008] Calculating the maximum cruising altitude of the second aircraft by using a pre-established aircraft maximum cruising altitude prediction model according to the aircraft performance model, the aircraft weight and the shortest path distance;

[0009] Selecting the smaller value between the maximum flyable cruising altitude of the first aircraft and the maximum flyable cruising altitude of the second aircraft as the maximum flyable cruising altitude of the aircraft; trimming the first optional route edge set, retaining all route edges whose minimum flyable altitude is less than or equal to the maximum flyable cruising altitude of the aircraft, and obtaining a second optional route edge set;

[0010] According to the starting point and the end point, based on the second optional route edge set, horizontal path planning is performed using the A* algorithm to determine the target route.

[0011] Optionally, the aircraft's maximum flyable cruising altitude prediction model is established by the following steps:

[0012] Obtain historical flight plan data and aircraft performance and model data for preprocessing;

[0013] Extracting a first feature field related to the maximum cruising altitude of the aircraft from the preprocessed data;

[0014] Performing data visualization analysis and data statistical analysis on the first characteristic field to obtain a data visualization result and a data statistical analysis result, and selecting a second characteristic field related to the maximum cruising altitude of the aircraft according to the data visualization result and the data statistical analysis result;

[0015] Selecting a machine learning model according to the data visualization results and the data statistical analysis results;

[0016] The selected machine learning model is trained using the training data set to obtain a prediction model for the aircraft's maximum cruising altitude.

[0017] Optionally, the first characteristic field includes aircraft weight, alternate airport, route distance, aircraft flight altitude, aircraft number and aircraft performance model.

[0018] Furthermore, the selecting of a second characteristic field related to the maximum cruising altitude of an aircraft according to the data visualization result and the data statistical analysis result specifically includes:

[0019] According to the data visualization result, the correlation between each first characteristic field and the maximum cruising altitude of the aircraft is analyzed, and the second characteristic field obtained according to the correlation includes at least the route distance and the aircraft weight;

[0020] The classification data of each first characteristic field is determined through the data statistical analysis result, and the second characteristic field obtained according to the classification data at least includes the aircraft performance model.

[0021] Optionally, the machine learning model includes a LightGBM model and a multivariate linear model.

[0022] Optionally, the performing horizontal path planning by using an A* algorithm based on the starting point and the end point and the second optional route edge set to determine the target route specifically includes:

[0023] Taking the starting point as the starting extended waypoint, searching for a waypoint starting from the starting point and meeting the restriction constraint in the second optional waypoint set;

[0024] Determine whether the flyable altitude ranges of the two route edges connected by the waypoint intersect;

[0025] If there is no intersection, it is not extended to the waypoint;

[0026] If there is an intersection, when the distance between the waypoint and the starting point is less than a specified threshold, the horizontal distance required to climb from the starting point to the minimum flyable altitude of the waypoint is calculated according to the climbing performance of the aircraft, and if the distance between the waypoint and the starting point is less than the horizontal distance, the route is not extended to the waypoint;

[0027] Otherwise, save the route edges connected to all expandable route points to obtain a third optional route edge set;

[0028] Selecting a wayside from the third optional wayside set that minimizes the sum of the weight from the wayside start point to the start point and the weight from the wayside start point to the end point, and extending the wayside with the end point of the selected wayside as the next extended waypoint;

[0029] Until the end point of the currently selected wayside is the end point, a number of extended waypoints from the starting point to the end point are determined, all waysides connected by the number of extended waypoints are obtained, and the target planned route is determined.

[0030] The embodiment of the present invention further provides a route planning device taking altitude into consideration, comprising:

[0031] An information input module is used to input a starting point, an end point, aircraft performance and model, aircraft weight, and a maximum cruising altitude of the first aircraft;

[0032] A first optional route edge set selection module is used to cut the global route-network graph according to the starting point and the end point to obtain a first optional route edge set;

[0033] A route distance calculation module, configured to calculate the unrestricted shortest path distance from the starting point to the end point using the Dijkstra algorithm based on the first optional route edge set;

[0034] An aircraft maximum cruising altitude calculation module, used to calculate the maximum cruising altitude of the second aircraft according to the aircraft performance model, the aircraft weight and the shortest path distance through a pre-established aircraft maximum cruising altitude prediction model;

[0035] A second optional route edge set selection module is used to select the smaller value between the first aircraft's maximum flyable cruising altitude and the second aircraft's maximum flyable cruising altitude as the aircraft's maximum flyable cruising altitude; trim the first optional route edge set, retain all route edges whose minimum flyable altitude is less than or equal to the aircraft's maximum flyable cruising altitude, and obtain a second optional route edge set;

[0036] The target route planning module is used to perform horizontal path planning based on the starting point and the end point and the second optional route edge set using the A* algorithm to determine the target route.

[0037] Optionally, the aircraft maximum cruising altitude calculation module further includes an aircraft maximum cruising altitude prediction model establishment unit, which is specifically used to:

[0038] Obtain historical flight plan data and aircraft performance and model data for preprocessing;

[0039] Extracting a first feature field related to the maximum cruising altitude of the aircraft from the preprocessed data;

[0040] Performing data visualization analysis and data statistical analysis on the first characteristic field to obtain a data visualization result and a data statistical analysis result, and selecting a second characteristic field related to the maximum cruising altitude of the aircraft according to the data visualization result and the data statistical analysis result;

[0041] Selecting a machine learning model according to the data visualization results and the data statistical analysis results;

[0042] The selected machine learning model is trained using the training data set to obtain a prediction model for the aircraft's maximum cruising altitude.

[0043] Furthermore, the target route planning module is specifically used for:

[0044] Taking the starting point as the starting extended waypoint, searching for a waypoint starting from the starting point and meeting the restriction constraint in the second optional waypoint set;

[0045] Determine whether the flyable altitude ranges of the two route edges connected by the waypoint intersect;

[0046] If there is no intersection, it is not extended to the waypoint;

[0047] If there is an intersection, when the distance between the waypoint and the starting point is less than a specified threshold, the horizontal distance required to climb from the starting point to the minimum flyable altitude of the waypoint is calculated according to the climbing performance of the aircraft, and if the distance between the waypoint and the starting point is less than the horizontal distance, the route is not extended to the waypoint;

[0048] Otherwise, save the route edges connected to all expandable route points to obtain a third optional route edge set;

[0049] Selecting a wayside from the third optional wayside set that minimizes the sum of the weight from the wayside start point to the start point and the weight from the wayside start point to the end point, and extending the wayside with the end point of the selected wayside as the next extended waypoint;

[0050] Until the end point of the currently selected wayside is the end point, a number of extended waypoints from the starting point to the end point are determined, all waysides connected by the number of extended waypoints are obtained, and the target planned route is determined.

[0051] An embodiment of the present invention further provides a route planning device that takes altitude into consideration, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the route planning method that takes altitude into consideration as described above is implemented.

[0052] Compared with the prior art, the embodiments of the present invention provide a method, device and equipment for route planning considering altitude. First, by inputting a starting point, an end point, an aircraft performance model, an aircraft weight and a maximum flyable cruising altitude of a first aircraft; the global route network diagram is clipped according to the starting point and the end point to obtain a first optional route edge set, and the shortest path distance from the starting point to the end point is calculated using the Dijkstra algorithm; secondly, according to the aircraft performance model, the aircraft weight and the shortest path distance, the maximum flyable cruising altitude of the second aircraft is calculated by a pre-established aircraft maximum flyable cruising altitude prediction model; then the smaller value of the maximum flyable cruising altitude of the first aircraft and the maximum flyable cruising altitude of the second aircraft is selected as the maximum flyable cruising altitude of the aircraft; then the first optional route edge set is clipped, and all route edges whose minimum flyable altitude is less than or equal to the maximum flyable cruising altitude of the aircraft are retained to obtain a second optional route edge set; finally, according to the starting point and the end point, the A* algorithm is used to perform horizontal path planning based on the second optional route edge set to determine the target route. The present invention calculates the maximum cruising altitude of an aircraft by taking into account a prediction model of aircraft performance, and can more accurately determine the range of the aircraft's flyable altitude under different conditions; further, it screens out all route edges that meet the requirements of the aircraft's maximum cruising altitude, and makes a reasonable judgment on the flyable altitude range of each optional route edge in the road network, providing a basis for subsequent route planning, ensuring that the planned route meets the performance requirements of the aircraft, and ensuring that the planning results are safe and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solution of the present invention, the drawings used in the implementation mode will be briefly introduced below. Obviously, the drawings described below are only some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 It is a flow chart of a preferred embodiment of a route planning method considering altitude provided by the present invention;

[0055] Figure 2 It is a structural block diagram of a preferred embodiment of a route planning device considering altitude provided by the present invention;

[0056] Figure 3 It is a structural block diagram of a preferred embodiment of a route planning device taking altitude into consideration provided by the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] See also Figure 1 , is a flow chart of a preferred embodiment of a route planning method considering altitude provided by the present invention, the method comprising steps S1 to S6:

[0059] S1. Input the starting point, end point, aircraft performance and model, aircraft weight, and the maximum cruising altitude of the first aircraft;

[0060] It should be noted that before planning the route, the user may enter a maximum cruising altitude value to limit the flight altitude of the entire route. Optionally, it is not necessary to enter it. If not, the maximum cruising altitude value is assumed to be a higher value, which is an altitude that the aircraft cannot reach under normal circumstances.

[0061] S2, cutting the global route network graph according to the starting point and the end point to obtain a first optional route edge set;

[0062] Specifically, it refers to extracting a part of the route network diagram related to the starting point and the end point from the global route network diagram. First, the global route network diagram data is obtained from a relevant database or an aviation information service provider, and then the ellipse restricted search area algorithm is used for clipping according to the starting point and the end point of the input route planning, and all the wayside and waypoint data within the ellipse are obtained to obtain the first optional wayside set.

[0063] It is worth noting that by clipping the global route network graph, the search space of route planning can be significantly reduced, thereby improving efficiency and accuracy.

[0064] S3. Based on the first optional route edge set, using Dijkstra algorithm to calculate the unrestricted shortest path distance from the starting point to the end point;

[0065] It should be noted that the Dijkstra algorithm is a greedy algorithm used to find the shortest path from a single source point to all other vertices in a weighted directed or undirected graph. First, the source point is set as the current node, all other nodes are marked as unvisited, and their distances from the source point are initialized to infinity, and the distance from the source point is set to 0; then the node with the smallest distance from the source point is selected from the unvisited nodes as the current node. If all nodes have been visited, the algorithm ends; otherwise, all edges starting from the current node are traversed; for each edge, the distance from the source point to the adjacent node through the edge is calculated; if the distance is less than the current distance of the adjacent node, the distance of the adjacent node is updated; repeat the steps until all nodes are visited. By using the Dijkstra algorithm, the present invention can efficiently calculate the unrestricted shortest path distance from the starting point to the end point, providing a basis for subsequent route planning.

[0066] S4, calculating the maximum cruising altitude of the second aircraft by using a pre-established aircraft maximum cruising altitude prediction model according to the aircraft performance model, the aircraft weight and the shortest path distance;

[0067] S5. Select the smaller value between the maximum flyable cruising altitude of the first aircraft and the maximum flyable cruising altitude of the second aircraft as the maximum flyable cruising altitude of the aircraft; trim the first optional route edge set, retain all route edges whose minimum flyable altitude is less than or equal to the maximum flyable cruising altitude of the aircraft, and obtain a second optional route edge set;

[0068] It is worth noting that the training data of the aircraft maximum cruising altitude prediction model uses historically calculated successful flight plan data, which all meet the aircraft performance limitations. Therefore, it can be considered that the second aircraft maximum cruising altitude calculated by the model also meets the flight performance limitations. The second optional route edge set further selected includes all route edges that meet the aircraft's maximum cruising altitude, that is, a reasonable judgment is made on the flyable altitude range of each optional route edge in the road network, which provides a basis for subsequent route planning, ensures that the planned route meets the aircraft's performance requirements, and ensures that the planning results are safe and reliable.

[0069] S6. According to the starting point and the end point, based on the second optional route edge set, use the A* algorithm to perform horizontal path planning to determine the target route.

[0070] It should be noted that the A* algorithm is a heuristic search algorithm used to find the shortest path from the starting point to the end point in a weighted graph. The A* algorithm combines the advantages of breadth-first search (BFS) and depth-first search (DFS). It uses a heuristic function to estimate the distance from the current node to the target node, and determines the next search direction based on the estimate.

[0071] As an optional embodiment, the step of performing horizontal path planning based on the starting point and the end point and based on the second optional route edge set using an A* algorithm to determine the target route specifically includes:

[0072] Taking the starting point as the starting extended waypoint, searching for a waypoint starting from the starting point and meeting the restriction constraint in the second optional waypoint set;

[0073] Determine whether the flyable altitude ranges of the two route edges connected by the waypoint intersect;

[0074] If there is no intersection, it is not extended to the waypoint;

[0075] If there is an intersection, when the distance between the waypoint and the starting point is less than a specified threshold, the horizontal distance required to climb from the starting point to the minimum flyable altitude of the waypoint is calculated according to the climbing performance of the aircraft, and if the distance between the waypoint and the starting point is less than the horizontal distance, the route is not extended to the waypoint;

[0076] Otherwise, save the route edges connected to all expandable route points to obtain a third optional route edge set;

[0077] Selecting a wayside from the third optional wayside set that minimizes the sum of the weight from the wayside start point to the start point and the weight from the wayside start point to the end point, and extending the wayside with the end point of the selected wayside as the next extended waypoint;

[0078] Until the end point of the currently selected wayside is the end point, a number of extended waypoints from the starting point to the end point are determined, all waysides connected by the number of extended waypoints are obtained, and the target planned route is determined.

[0079] It should be noted that the A* algorithm valuation function is:

[0080] f(n) = g(n) + h(n);

[0081] n represents any vertex;

[0082] f(n) is the minimum cost estimate from the starting point through n points to the target point;

[0083] g(n) represents the actual minimum cost from the starting point to any vertex n;

[0084] h(n) is a heuristic function that represents the minimum estimated cost of the path from point n to the target point.

[0085] In a specific embodiment of the present invention, the route edge with the smallest sum of the weight from the route edge starting point to the departure airport and the estimated weight from the route edge starting point to the landing airport is selected for expansion. The estimated weight from the route edge starting point to the landing airport is the unrestricted shortest weight from all route points to the landing airport calculated in advance using the Dijkstra algorithm, and the weight can be distance, time, fuel consumption, etc.

[0086] It is worth noting that the current route planning method generally adopts a phased strategy, the first is the horizontal optimization stage, but because the maximum flyable altitude and altitude switching ability of the aircraft are limited, if the flyable altitude layer of the route selected in the horizontal optimization stage is too high, or the height difference between two adjacent route sides is too large, it is easy to exceed the performance range of the aircraft, which will cause planning failure. At the same time, in terms of business, it is also impossible to always switch altitudes frequently, otherwise the passenger experience will be extremely poor. Therefore, in an embodiment of the present invention, by judging whether the flyable cruising altitude ranges of the two front and rear route sides connected by the waypoint have an intersection, if there is no intersection, it cannot be extended to this point, to ensure that the aircraft can smoothly transition between different route sides, and ensure the passenger experience without exceeding the performance range of the aircraft.

[0087] It is worth noting that in the embodiment of the present invention, not only the distance between the waypoint and the starting point is considered, but also the horizontal distance required for the aircraft to climb from the starting point to the waypoint. If the distance between the waypoint and the starting point is less than the horizontal distance, it means that the required horizontal distance to climb is insufficient, which can avoid extending the waypoint into the path when the aircraft's climbing ability is insufficient, thereby resulting in an infeasible path. The threshold of the climbing distance is not a fixed value, but is dynamically calculated based on the aircraft's climbing performance, which can better adapt to the climbing capabilities of different aircraft and ensure the accuracy of the judgment.

[0088] As an optional embodiment, the aircraft maximum cruising altitude prediction model is established through the following steps:

[0089] Obtain historical flight plan data and aircraft performance and model data for preprocessing;

[0090] Extracting a first feature field related to the maximum cruising altitude of the aircraft from the preprocessed data;

[0091] Performing data visualization analysis and data statistical analysis on the first characteristic field to obtain a data visualization result and a data statistical analysis result, and selecting a second characteristic field related to the maximum cruising altitude of the aircraft according to the data visualization result and the data statistical analysis result;

[0092] Selecting a machine learning model according to the data visualization results and the data statistical analysis results;

[0093] The selected machine learning model is trained using the training data set to obtain a prediction model for the aircraft's maximum cruising altitude.

[0094] Furthermore, the first characteristic field includes aircraft weight, alternate airport, route distance, aircraft flight altitude, aircraft number and aircraft performance model.

[0095] It is worth mentioning that selecting representative and relevant features from the original data can reduce redundancy and noise.

[0096] Furthermore, the selecting of a second characteristic field related to the maximum cruising altitude of an aircraft according to the data visualization result and the data statistical analysis result specifically includes:

[0097] According to the data visualization result, the correlation between each first characteristic field and the maximum cruising altitude of the aircraft is analyzed, and the second characteristic field obtained according to the correlation includes at least the route distance and the aircraft weight;

[0098] The classification data of each first characteristic field is determined through the data statistical analysis result, and the second characteristic field obtained according to the classification data at least includes the aircraft performance model.

[0099] It should be noted that through visualization, we can roughly see whether a certain field has an obvious relationship with the target value (the maximum cruising altitude of the aircraft). If the relationship is large, the feature can be used for model training.

[0100] However, although the correlation does not seem obvious in the visualization graph, it may be weakly correlated, but it can also be used as a target feature.

[0101] In specific implementation, the embodiment of the present invention mainly draws a scatter plot of aircraft performance model, aircraft weight, route distance and the aircraft's maximum cruising altitude, and it can be seen from the drawn scatter plots that there is an obvious correlation between the aircraft performance model, route distance and the aircraft's maximum cruising altitude.

[0102] At the same time, according to the data visualization results of the first feature field, further data analysis was performed to generate new application features. From the visualization diagram of the route distance, aircraft performance model and the maximum cruising altitude of the aircraft, it can be seen that the data can be clearly divided into two categories by model. By counting the model information corresponding to the maximum cruising altitude in two different feet, the model list corresponding to the two types of data is obtained. Therefore, an aircraft performance model type field is added as a new feature. In addition to statistical analysis, clustering algorithms such as KMeans can also be used to learn the key features that distinguish the two types of data.

[0103] As an optional embodiment, the machine learning model includes a LightGBM model and a multivariate linear model.

[0104] It should be noted that in addition to the above two models, other machine learning models, such as decision trees, random forests, etc., can also achieve prediction effects.

[0105] In a specific embodiment of the present invention, LightGBM (Light Gradient Boosting Machine) is used to train the prediction model. For example, the route distance, aircraft landing weight, and aircraft performance and model can be used as feature factors, and the maximum cruising altitude of the aircraft can be used as the prediction target.

[0106] However, considering the actual application scenarios, due to various restrictions and constraints, the final route distance is often not determined before route planning. If you want to more accurately determine the maximum flyable altitude of a waypoint, you need to frequently calculate the distance from the starting point and the end point during planning. This frequent model call will undoubtedly consume a certain amount of time. In order to improve computing efficiency, it is ideal to be able to convert the learning results of the model into a formula form, so that the results can be quickly obtained in large-scale calculations. According to the previous visualization analysis results, the relationship between distance and flight altitude roughly presents a piecewise linear characteristic. Therefore, a multivariate linear model can also be used, and parameter fitting learning can be performed for models of different performance types to meet the needs of actual applications.

[0107] The piecewise function formula is as follows:

[0108] ;

[0109] in is the target value, i.e. the maximum cruising altitude. is the parameter to be learned, and x is the influencing factor, such as route distance, aircraft weight, etc. When the route distance is less than k, a multivariate linear function is used to fit the relationship between the maximum flyable altitude and the influencing factors; when the route distance is greater than k, the maximum flyable cruising altitude will be fixed to a constant.

[0110] First, the maximum value of the maximum cruising altitude is obtained from the training data set, and an appropriate threshold is added to it (the threshold is generally a negative number, so that the predicted maximum cruising altitude is slightly less than the maximum cruising altitude, thereby ensuring that it meets the aircraft performance) to ensure the safety margin, thereby determining the maximum value of the piecewise function. This maximum value is the constant a in the above formula, and its corresponding minimum distance value is the inflection point k of the piecewise function.

[0111] For the data segment with a distance of 0 to k, we use a multivariate linear function for training. This is because within this distance range, the relationship between flight height and distance is approximately linear. Through the multivariate linear regression model, we can learn the impact of different factors on flight height within this range and fit the corresponding linear function accordingly.

[0112] Although the prediction effect of the multivariate linear regression model is slightly inferior to the above LightGBM model, its application is more flexible and can adapt to more different scenarios and needs. In practical applications, you can flexibly choose according to different application scenarios to achieve the best prediction effect.

[0113] It is worth mentioning that by building a prediction model, the range of flyable altitudes of an aircraft under different conditions can be determined by learning and analyzing historical flight plan data, thereby providing support for route side selection in route planning and improving the reliability of route planning.

[0114] In order to enable those skilled in the art to better understand the implementation process of the embodiments of the present invention, a more specific embodiment is described below:

[0115] The input conditions of the aircraft maximum cruising altitude prediction model are: planning starting point EGLL, planning end point EGCC, the maximum cruising altitude of the first aircraft of the flight maxAlt1=35000 feet, aircraft performance model B787-9, aircraft weight W=171833KG, and optimization goal: shortest distance.

[0116] 1) The global route network is trimmed according to the planned starting point and the planned end point to obtain the first optional route edge set, a total of 8992 route edge data;

[0117] 2) Based on the first optional route edge set, the Dijkstra algorithm is used to calculate the unrestricted shortest path distance D from EGLL to EGCC, which is 140.29 nautical miles;

[0118] 3) Substitute the aircraft weight W, the shortest path distance (route distance) D, and the aircraft performance model into the trained prediction model, and predict that the maximum cruising altitude of the second aircraft of the flight is maxAlt2=17474 feet. Then the maximum cruising altitude of the aircraft of the final flight is maxAlt=min{35000,17474}=17474 feet;

[0119] 4) Traverse the 8992 route edge data in the first optional route edge set. If the minimum cruising altitude of the route edge is greater than 17474, remove the edge. Otherwise, keep the edge. After reduction, the second optional route edge set is obtained, with 3275 route edges remaining.

[0120] 5) Based on the reduced set of route edges (the second optional set of route edges), the A* algorithm is used to perform horizontal path planning;

[0121] 6) Select EGLL as the starting extension point, find the route edge starting from EGLL, and traverse:

[0122] A. If the current route meets the various restrictions and constraints of the airline and the authority, proceed to the next step of judgment, otherwise determine the next route edge;

[0123] B. Get the minimum cruising altitude minAlt of the route edge. If minAlt==0 or the route distance d1 (the distance from the extension point to the route starting point EGLL, the route distance expressions below have the same meaning) is greater than 50 nautical miles (the specified threshold), put the route edge into the candidate set. Otherwise, proceed to the next step.

[0124] C. According to the aircraft climbing performance, calculate the horizontal distance d2 required to climb from the starting point EGLL to minAlt. If the route distance d1>=d2, put the route edge into the candidate set;

[0125] D. Select a route with the shortest route distance from the candidate set, take the end point of the route as the next extension point, and record the route information. The route id is 35725183, the end point of the route is ULTIB, the distance from EGLL to ULTIB is 28.68nm, and the cruising altitude range of the route is [0,99999];

[0126] 7) Select ULTIB as the starting extension point, find the route edge starting from ULTIB, and traverse:

[0127] A. Determine whether the altitude range of the airway edge and the previous airway edge 35725183 intersects. If so, proceed to the next step of determination. Otherwise, determine the next airway edge.

[0128] B. If the route from EGLL to the end point of the current route edge meets the various restrictions and constraints of the airline and the authority, proceed to the next step of judgment, otherwise judge the next route edge;

[0129] C. Get the minimum cruising altitude minAlt of the airway. If minAlt==0 or the distance d1 from EGLL to the end of the airway (airway distance + 28.68 nautical miles) is greater than 50 nautical miles, put the airway into the candidate set. Otherwise, proceed to the next step.

[0130] D. According to the aircraft climbing performance, calculate the horizontal distance d2 required to climb from the starting point EGLL to minAlt. If the route distance d1>=d2, put the route edge into the candidate set;

[0131] E. Select a route edge with the shortest route edge distance from the candidate set, and use the end point of the route edge as the next extension point. Record the route edge information, the route edge id is 35540214, the route edge end point is HEMEL, the distance from EGLL to HEMEL is 38.26 nautical miles, and the route can fly the cruising altitude range [12000,43000];

[0132] 8) Select HEMEL point as the starting extension point, find the route edge starting from HEMEL point, and traverse:

[0133] A. Determine whether the altitude range of the airway edge and the previous airway edge 35540214 intersects. If so, proceed to the next step of determination. Otherwise, determine the next airway edge.

[0134] B. If the route from EGLL to the end point of the current route edge meets the various restrictions and constraints of the airline and the authority, proceed to the next step of judgment, otherwise judge the next route edge;

[0135] C. Get the minimum takeoff altitude minAlt of the airway. If minAlt==0 or the distance d1 from EGLL to the end of the airway (airway distance + 38.26 nautical miles) is greater than 50 nautical miles, put the airway into the candidate set. Otherwise, proceed to the next step.

[0136] D. According to the aircraft climbing performance, calculate the horizontal distance d2 required to climb from the starting point EGLL to minAlt. If the route distance d1>=d2, put the route edge into the candidate set;

[0137] E. Select a route edge with the shortest distance from the candidate set, and use the end point of the route edge as the next extension point. Record the route edge information, the route edge id is 35534367, the route edge end point is BUZAD, the distance from EGLL to BUZAD is 51.27 nautical miles, and the route can fly the cruising altitude range [12000,43000];

[0138] 9) Select BUZAD as the starting extension point, find the route edge starting from BUZAD, and traverse:

[0139] A. Determine whether the altitude range of the airway edge and the previous airway edge 35534367 intersects. If so, proceed to the next step, otherwise determine the next airway edge;

[0140] B. If the route from EGLL to the end of the current route edge meets various restrictions and constraints of the airline and the authority, the route edge is placed in the candidate set (the distance from EGLL to the end of the route edge is definitely greater than 50 nautical miles, so the climb performance judgment is no longer performed), otherwise the next route edge is determined;

[0141] C. Select a route edge with the shortest distance from the candidate set, and use the end point of the route edge as the next extension point. Record the route edge information, the route edge id is 35534368, the route edge end point is OLNEY, the distance from EGLL to OLNEY is 59.66 nautical miles, and the route can fly in the altitude range of [12000,43000];

[0142] 10) The remaining steps are similar to the above steps and will not be repeated here. The final optimized path is: EGLL-ULTIB-HEMEL-BUZAD-OLNEY-WELIN-AKUPA-TIMPO-ELVOS-TNT-DAYNE-EGCC. The distance from EGLL to EGCC is 148.57 nautical miles.

[0143] Based on the above method embodiments, the present invention provides corresponding system embodiments.

[0144] See also Figure 2 , Figure 2 : is a structural block diagram of a preferred embodiment of a route planning device considering altitude provided by the present invention, wherein the route planning device considering altitude comprises:

[0145] The information input module 21 is used to input the starting point, the end point, the aircraft performance and model, the aircraft weight, and the maximum cruising altitude of the first aircraft;

[0146] A first optional route edge set selection module 22, configured to clip the global route-network graph according to the starting point and the end point to obtain a first optional route edge set;

[0147] A route distance calculation module 23, configured to calculate the unrestricted shortest path distance from the starting point to the end point using the Dijkstra algorithm based on the first optional route edge set;

[0148] An aircraft maximum cruising altitude calculation module 24 is used to calculate the maximum cruising altitude of the second aircraft according to the aircraft performance model, the aircraft weight and the shortest path distance through a pre-established aircraft maximum cruising altitude prediction model;

[0149] The second optional route edge set selection module 25 is used to select the smaller value between the first aircraft's maximum flyable cruising altitude and the second aircraft's maximum flyable cruising altitude as the aircraft's maximum flyable cruising altitude; trim the first optional route edge set, retain all route edges whose minimum flyable altitude is less than or equal to the aircraft's maximum flyable cruising altitude, and obtain a second optional route edge set;

[0150] The target route planning module 26 is used to perform horizontal path planning using the A* algorithm based on the starting point and the end point and the second optional route edge set to determine the target route.

[0151] As an optional embodiment, the aircraft maximum cruising altitude calculation module further includes an aircraft maximum cruising altitude prediction model establishment unit, which is specifically used to:

[0152] Obtain historical flight plan data and aircraft performance and model data for preprocessing;

[0153] Extracting a first feature field related to the maximum cruising altitude of the aircraft from the preprocessed data;

[0154] Performing data visualization analysis and data statistical analysis on the first characteristic field to obtain a data visualization result and a data statistical analysis result, and selecting a second characteristic field related to the maximum cruising altitude of the aircraft according to the data visualization result and the data statistical analysis result;

[0155] Selecting a machine learning model according to the data visualization results and the data statistical analysis results;

[0156] The selected machine learning model is trained using the training data set to obtain a prediction model for the aircraft's maximum cruising altitude.

[0157] As an optional embodiment, the target route planning module is specifically used for:

[0158] Taking the starting point as the starting extended waypoint, searching for a waypoint starting from the starting point and meeting the restriction constraint in the second optional waypoint set;

[0159] Determine whether the flyable altitude ranges of the two route edges connected by the waypoint intersect;

[0160] If there is no intersection, it is not extended to the waypoint;

[0161] If there is an intersection, when the distance between the waypoint and the starting point is less than a specified threshold, the horizontal distance required to climb from the starting point to the minimum flyable altitude of the waypoint is calculated according to the climbing performance of the aircraft, and if the distance between the waypoint and the starting point is less than the horizontal distance, the route is not extended to the waypoint;

[0162] Otherwise, save the route edges connected to all expandable route points to obtain a third optional route edge set;

[0163] Selecting a wayside from the third optional wayside set that minimizes the sum of the weight from the wayside start point to the start point and the weight from the wayside start point to the end point, and extending the wayside with the end point of the selected wayside as the next extended waypoint;

[0164] Until the end point of the currently selected wayside is the end point, a number of extended waypoints from the starting point to the end point are determined, all waysides connected by the number of extended waypoints are obtained, and the target planned route is determined.

[0165] It should be noted that a route planning device taking altitude into consideration provided in an embodiment of the present invention is used to execute all process steps of a route planning method taking altitude into consideration in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be described in detail.

[0166] The embodiment of the present invention also provides a route planning device taking altitude into consideration, such as Figure 3 , which is a structural block diagram of a preferred embodiment of a route planning device considering altitude provided by the present invention. The terminal device includes a processor 31, a memory 32, and a computer program stored in the memory 32 and configured to be executed by the processor 31. When the processor 31 executes the computer program, the route planning method considering altitude as described in any of the above embodiments is implemented.

[0167] In addition, an embodiment of the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the route planning method considering altitude as described in any of the above embodiments.

[0168] When the processor 31 executes the computer program, the steps in the above-mentioned route planning method embodiment considering altitude are implemented, for example: Figure 1 Alternatively, when the processor 31 executes the computer program, the functions of each module in the above-mentioned embodiment of the route planning device considering altitude are realized, for example Figure 2 The functions of the various modules of the route planning device taking altitude into consideration are shown.

[0169] Preferably, the computer program can be divided into one or more modules / units, which are stored in the memory 32 and executed by the processor 31 to implement the present invention. The one or more modules / units can be a series of computer program instruction segments that can implement specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0170] The processor 31 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor 31 may be any conventional processor. The processor 31 is the control center of the terminal device, and various parts of the terminal device are connected using various interfaces and lines.

[0171] The memory 32 mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory 32 can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card (Flash Card), etc., or the memory 32 can also be other volatile solid-state storage devices.

[0172] It should be noted that the above-mentioned route planning device considering altitude may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 3 The structural block diagram shown is only a structural example of the above-mentioned terminal device and does not constitute a structural limitation on the above-mentioned route planning device taking altitude into consideration. The above-mentioned route planning device taking altitude into consideration may include more or fewer components than shown in the figure, or a combination of certain components, or different components.

[0173] In summary, an embodiment of the present invention provides a method, device and equipment for route planning considering altitude. First, by inputting a starting point, an end point, an aircraft performance model, an aircraft weight and a maximum flyable cruising altitude of a first aircraft; the global route network diagram is clipped according to the starting point and the end point to obtain a first optional route edge set, and the shortest path distance from the starting point to the end point is calculated using the Dijkstra algorithm; secondly, according to the aircraft performance model, the aircraft weight and the shortest path distance, the maximum flyable cruising altitude of the second aircraft is calculated by a pre-established aircraft maximum flyable cruising altitude prediction model; then the smaller value of the maximum flyable cruising altitude of the first aircraft and the maximum flyable cruising altitude of the second aircraft is selected as the maximum flyable cruising altitude of the aircraft; then the first optional route edge set is clipped, and all route edges whose minimum flyable altitude is less than or equal to the maximum flyable cruising altitude of the aircraft are retained to obtain a second optional route edge set; finally, according to the starting point and the end point, the A* algorithm is used to perform horizontal path planning based on the second optional route edge set to determine the target route. The present invention calculates the maximum cruising altitude of an aircraft by taking into account a prediction model of aircraft performance, and can more accurately determine the range of the aircraft's flyable altitude under different conditions; further, it screens out all route edges that meet the requirements of the aircraft's maximum cruising altitude, and makes a reasonable judgment on the flyable altitude range of each optional route edge in the road network, providing a basis for subsequent route planning, ensuring that the planned route meets the performance requirements of the aircraft, and ensuring that the planning results are safe and reliable.

[0174] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A route planning method taking altitude into consideration, characterized in that: include: Enter the starting point, end point, aircraft performance model, aircraft weight and the maximum cruising altitude of the first aircraft; Cutting the global route network graph according to the starting point and the end point to obtain a first optional route edge set; Based on the first optional route edge set, using Dijkstra algorithm to calculate the unrestricted shortest path distance from the starting point to the end point; Calculating the maximum cruising altitude of the second aircraft by using a pre-established aircraft maximum cruising altitude prediction model according to the aircraft performance model, the aircraft weight and the shortest path distance; Selecting the smaller value between the maximum cruising altitude of the first aircraft and the maximum cruising altitude of the second aircraft as the maximum cruising altitude of the aircraft; The first optional route edge set is trimmed to retain all route edges whose minimum flyable altitude is less than or equal to the maximum flyable cruising altitude of the aircraft, thereby obtaining a second optional route edge set; According to the starting point and the end point, based on the second optional route edge set, horizontal path planning is performed using the A* algorithm to determine the target route; The step of performing horizontal path planning based on the starting point and the end point and the second optional route edge set using an A* algorithm to determine a target route specifically includes: Taking the starting point as the starting extended waypoint, searching for a waypoint starting from the starting point and meeting the restriction constraint in the second optional waypoint set; Determine whether the flyable altitude ranges of the two route edges connected by the waypoint intersect; If there is no intersection, it is not extended to the waypoint; If there is an intersection, when the distance between the waypoint and the starting point is less than a specified threshold, the horizontal distance required to climb from the starting point to the minimum flyable altitude of the waypoint is calculated according to the climbing performance of the aircraft, and if the distance between the waypoint and the starting point is less than the horizontal distance, the route is not extended to the waypoint; Otherwise, save the route edges connected to all expandable route points to obtain a third optional route edge set; Selecting a wayside from the third optional wayside set that minimizes the sum of the weight from the wayside start point to the start point and the weight from the wayside start point to the end point, and extending the wayside with the end point of the selected wayside as the next extended waypoint; Until the end point of the currently selected wayside is the end point, a number of extended waypoints from the starting point to the end point are determined, all waysides connected by the number of extended waypoints are obtained, and the target planned route is determined.

2. The route planning method considering altitude as claimed in claim 1, characterized in that: The maximum cruising altitude prediction model of the aircraft is established by the following steps: Obtain historical flight plan data and aircraft performance and model data for preprocessing; Extracting a first feature field related to the maximum cruising altitude of the aircraft from the preprocessed data; Performing data visualization analysis and data statistical analysis on the first characteristic field to obtain a data visualization result and a data statistical analysis result, and selecting a second characteristic field related to the maximum cruising altitude of the aircraft according to the data visualization result and the data statistical analysis result; Selecting a machine learning model according to the data visualization results and the data statistical analysis results; The selected machine learning model is trained using the training data set to obtain a prediction model for the aircraft's maximum cruising altitude.

3. The route planning method considering altitude as claimed in claim 2, characterized in that: The first characteristic field includes aircraft weight, alternate airport, route distance, aircraft flight altitude, aircraft number, and aircraft performance model.

4. The method for route planning taking altitude into consideration as claimed in claim 3, characterized in that: The selecting, according to the data visualization result and the data statistical analysis result, a second characteristic field related to the maximum cruising altitude of the aircraft specifically includes: According to the data visualization result, the correlation between each first characteristic field and the maximum cruising altitude of the aircraft is analyzed, and the second characteristic field obtained according to the correlation includes at least the route distance and the aircraft weight; The classification data of each first characteristic field is determined through the data statistical analysis result, and the second characteristic field obtained according to the classification data at least includes the aircraft performance model.

5. The route planning method considering altitude as claimed in claim 2, characterized in that: The machine learning models include LightGBM model and multivariate linear model.

6. A route planning device taking altitude into consideration, characterized in that: include: An information input module is used to input a starting point, an end point, aircraft performance and model, aircraft weight, and a maximum cruising altitude of the first aircraft; A first optional route edge set selection module is used to cut the global route-network graph according to the starting point and the end point to obtain a first optional route edge set; A route distance calculation module, configured to calculate the unrestricted shortest path distance from the starting point to the end point using the Dijkstra algorithm based on the first optional route edge set; An aircraft maximum cruising altitude calculation module, used to calculate the maximum cruising altitude of the second aircraft according to the aircraft performance model, the aircraft weight and the shortest path distance through a pre-established aircraft maximum cruising altitude prediction model; A second optional route edge set selection module is used to select the smaller value between the maximum flyable cruising altitude of the first aircraft and the maximum flyable cruising altitude of the second aircraft as the maximum flyable cruising altitude of the aircraft; The first optional route edge set is trimmed to retain all route edges whose minimum flyable altitude is less than or equal to the maximum flyable cruising altitude of the aircraft, thereby obtaining a second optional route edge set; A target route planning module, configured to perform horizontal path planning using an A* algorithm based on the starting point and the end point and the second optional route edge set to determine a target route; Wherein, the target route planning module is specifically used for: Taking the starting point as the starting extended waypoint, searching for a waypoint starting from the starting point and meeting the restriction constraint in the second optional waypoint set; Determine whether the flyable altitude ranges of the two route edges connected by the waypoint intersect; If there is no intersection, it is not extended to the waypoint; If there is an intersection, when the distance between the waypoint and the starting point is less than a specified threshold, the horizontal distance required to climb from the starting point to the minimum flyable altitude of the waypoint is calculated according to the climbing performance of the aircraft, and if the distance between the waypoint and the starting point is less than the horizontal distance, the route is not extended to the waypoint; Otherwise, save the route edges connected to all expandable route points to obtain a third optional route edge set; Selecting a wayside from the third optional wayside set that minimizes the sum of the weight from the wayside start point to the start point and the weight from the wayside start point to the end point, and extending the wayside with the end point of the selected wayside as the next extended waypoint; Until the end point of the currently selected wayside is the end point, a number of extended waypoints from the starting point to the end point are determined, all waysides connected by the number of extended waypoints are obtained, and the target planned route is determined.

7. The route planning device taking altitude into consideration as claimed in claim 6, characterized in that: The aircraft maximum cruising altitude calculation module also includes an aircraft maximum cruising altitude prediction model establishment unit, which is specifically used to: Obtain historical flight plan data and aircraft performance and model data for preprocessing; Extracting a first feature field related to the maximum cruising altitude of the aircraft from the preprocessed data; Performing data visualization analysis and data statistical analysis on the first characteristic field to obtain a data visualization result and a data statistical analysis result, and selecting a second characteristic field related to the maximum cruising altitude of the aircraft according to the data visualization result and the data statistical analysis result; Selecting a machine learning model according to the data visualization results and the data statistical analysis results; The selected machine learning model is trained using the training data set to obtain a prediction model for the aircraft's maximum cruising altitude.

8. A route planning device taking altitude into consideration, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for route planning taking altitude into consideration as claimed in any one of claims 1 to 5 is implemented.

Images