A method for constructing a scatter-shaped dangerous weather rerouting path based on multi-objective decision

Abstract

The application discloses a kind of based on the construction method of dangerous meteorological rerouting path of scattered spot, comprising: step 1: the airspace grid map including airspace boundary and the constraint of scattered spot dangerous meteorology is built;Step 2: the starting point and end point of rerouting path are set, and the feasible path that can avoid all scattered spot dangerous meteorological obstacle grid is searched and generated between starting point and end point, and form rerouting path set;Step 3: the feasible path in rerouting path set is carried out path smoothing optimization;Step: 4: to each feasible path in rerouting path set, evaluation index matrix is constructed;Step 5: using projection tracking method constructs index weight model, and the objective weight of each evaluation index is solved;Step 6: according to the value and weight of evaluation index, the score of each feasible path in rerouting path set is calculated, and the highest score feasible path is selected as optimal rerouting path, and the construction of rerouting path under scattered spot dangerous meteorology is completed.

Description

Technical Field

[0001] This invention relates to the field of air traffic management, and in particular to a method for constructing scattered hazardous weather diversion routes based on multi-objective decision-making. Background Technology

[0002] With the continuous growth of civil aviation traffic, aircraft flight safety has become a core development goal in the field of air traffic management. During the cruise and approach phases, aircraft often encounter scattered hazardous weather such as thunderstorms, severe convection, and turbulence areas. These weather phenomena are characterized by their scattered spatial distribution, irregular shape, small impact range, and high density, posing a serious threat to flight safety and requiring aircraft to divert or detour in a timely manner.

[0003] Existing rerouting route planning methods have significant shortcomings: the traditional A* algorithm can only generate a shortest path between the rerouting start and end points, and cannot provide multiple differentiated feasible paths, making it difficult to meet the multi-option selection requirements of air traffic control decisions and flight operations; at the same time, common route construction methods only take the shortest flight distance as the optimization objective, ignoring key indicators that affect flight safety and smoothness, such as safety distance, turning angle, and number of inflection points, and cannot take into account the safety, economy, and flight stability of the rerouting process.

[0004] Therefore, for scattered hazardous weather scenarios, there is an urgent need for an intelligent rerouting path construction method that can generate multiple feasible rerouting paths in batches and is based on objective multi-objective decision-making, so as to improve the safety and reliability of aircraft rerouting. Summary of the Invention

[0005] Purpose of the invention: The technical problem to be solved by the present invention is to provide a method for constructing scattered hazardous weather rerouting paths based on multi-objective decision-making, which addresses the shortcomings of the existing technology.

[0006] To address the aforementioned technical problems, this invention discloses a method for constructing scattered hazardous weather rerouting paths based on multi-objective decision-making, comprising the following steps:

[0007] Step 1: For the target flight airspace, perform uniform raster modeling, mark the areas where scattered hazardous weather is located as obstacle grids, and construct an airspace raster map that includes airspace boundaries and scattered hazardous weather constraints. ;

[0008] Step 2: Set the starting point of the rerouting route and the end point The system searches for and generates multiple feasible paths between the origin and destination that can avoid all scattered hazardous weather obstacle grids, forming a set of alternative routes. ;

[0009] Step 3: Analyze the set of reroutes Path smoothing optimization is performed on feasible paths in the data;

[0010] Step 4: Analyze the set of reroutes Each feasible path in Four core evaluation indicators were extracted: detour distance, average turning angle, number of inflection points, and minimum safe distance. These indicators were then standardized to construct an evaluation indicator matrix. ;

[0011] Step 5: Construct an index weight model using the projection pursuit method and solve it using a genetic algorithm to obtain the objective weights of each evaluation index;

[0012] Step 6: Calculate the score of each feasible path in the rerouting path set according to the value and weight of the evaluation index, select the feasible path with the highest score as the optimal rerouting path, and complete the construction of rerouting paths under scattered hazardous weather conditions.

[0013] In step 1, the airspace grid map construction process is as follows: the target flight airspace is divided into uniform grids, and each grid is identified by a unique index ( , ) identifier, in which Indicates the horizontal index of the raster. Represents the vertical index of the grid; collects the location range of scattered hazardous weather, marks the grids covered by it as no-fly obstacle grids, and marks the remaining grids as passable grids, constructing a complete airspace environment map, denoted as . .

[0014] In step 2, the set of reroutes The construction process is as follows:

[0015] Step 2-1: For the starting point of the rerouting route where a feasible path needs to be searched. and the end point The A* algorithm is used to search for the shortest path from the starting point to the ending point that avoids all no-fly zones. and add it to the modified route set. In the middle, set the number of feasible paths to be searched. ;

[0016] Step 2-2, adjust the set of reroutes. Sort by distance in ascending order and retrieve the last feasible path. ;

[0017] Steps 2-3: Extract feasible paths inflection point set , Feasible path The A turning point Initially 1, , Feasible path The total number of inflection points;

[0018] Steps 2-4, targeting the inflection point Feasible paths Split into pre-sub-path and subsequent subpaths At the turning point and the end point Reuse the A* algorithm to search for new subsequent subpaths. The search process must meet the following conditions:

[0019] 1) Sub-path With the previous sub-path remove In addition, there should be no repeated inflection points;

[0020] 2) Sub-path All no-fly zones must be avoided;

[0021] 3) Turning angle at each inflection point on the path ;

[0022] 4) Flight distance between inflection points ;

[0023] 5) The additional distance after the rerouting shall not exceed 50% of the original distance;

[0024] 6) New Subpath With the original sub-path Path repetition The formula for calculating path repetition is as follows:

[0025]

[0026] in, It is the new sub-path Airspace environment map The set of grid cells passed through, It is the original sub-path Airspace environment map The set of grid cells that have been passed through.

[0027] Steps 2-5 involve retrieving new sub-paths. With the previous sub-path splicing together to form a new feasible path Add to the rerouting path set If set The number of paths has reached If the value is found, the path search is exited and the construction process ends; otherwise... If yes, then proceed to step 2-2; otherwise, let... Proceed to steps 2-4.

[0028] In step 3, the path smoothing optimization process is as follows:

[0029] Step 3-1, extract feasible paths inflection point set , Feasible path The A turning point Initially 1, ; The initial value is 2. ; Feasible path The total number of inflection points;

[0030] Step 3-2, connect the inflection points and If it does not intersect with the no-fly zone grid, then it is a feasible path. Change from arrive If directly connected, proceed to step 3-3; if it intersects with the no-fly zone grid, proceed to step 3-4.

[0031] Step 3-3, if End path smoothing optimization; otherwise, let Proceed to step 3-2;

[0032] Steps 3-4, if End path smoothing optimization; otherwise, let , Proceed to step 3-2.

[0033] In step 4, the process of constructing the evaluation index matrix is ​​as follows:

[0034] Step 4-1, Calculate feasible paths New detour routes Feasible path The difference between the total length and the original route length;

[0035] Calculate feasible paths average turning angle Feasible path The average turning angle of all inflection points;

[0036] Calculate feasible paths inflection point number Feasible path The number of inflection points;

[0037] Calculate feasible paths Minimum safe distance Feasible path Minimum distance from all no-fly zones;

[0038] Step 4-2: Standardize all indicators. The standardization formula is as follows:

[0039]

[0040] In the above formula, For the first Feasible path The The original value of each indicator; For the first Feasible path The The standardized value of the indicator; for The maximum value, for The minimum value, , For the set of reroutes The total number of feasible paths in the path.

[0041] Standardized index values Add to the evaluation index matrix In the evaluation index matrix Build complete.

[0042] In step 5, the process of constructing the index weight model using the projection pursuit method and solving it using a genetic algorithm is as follows:

[0043] Step 5-1, Initialize the projection direction vector ,in For the first The initial weights of each evaluation indicator must meet the following conditions:

[0044]

[0045]

[0046] Step 5-2, calculate the first... Feasible path projection value The calculation formula is as follows:

[0047]

[0048] in, For the first Feasible path The The standardized value of the indicator.

[0049] Step 5-3: Calculate the mean of the projected index. and standard deviation The calculation formula is as follows:

[0050]

[0051]

[0052] in, For the set of reroutes The total number of feasible paths in the path.

[0053] Step 5-4: Calculate the local density of the projected values. The calculation formula is as follows:

[0054]

[0055] Step 5-5: Construct a comprehensive projection tracking index The calculation formula is as follows:

[0056]

[0057] Steps 5-6: Solve using a genetic algorithm. The maximum value is used to obtain the optimal projection direction vector. ,in For the first Objective weights of evaluation indicators.

[0058] In step 6, the process of selecting the optimal rerouting route is as follows:

[0059] Step 6-1, calculate the first... Feasible path Overall rating The calculation formula is as follows:

[0060]

[0061] Step 6-2, set the rerouting routes All feasible paths in the list are ranked according to their comprehensive score. Arrange the routes in descending order of high to low score, select the feasible route with the highest score as the optimal rerouting route, and complete the construction of rerouting routes under scattered hazardous weather conditions.

[0062] Beneficial effects:

[0063] This invention enables batch generation of rerouting routes and multi-objective decision-making for scattered hazardous weather conditions. While ensuring flight safety, it improves flight smoothness through route smoothing optimization. It achieves a balance between safety, economy, and stability through comprehensive multi-index evaluation, objectively determining weights using projection pursuit and genetic algorithms to avoid bias from manual assignment. Route repeatability constraints ensure route diversity, providing multiple options for air traffic control decision-making. This invention enhances the reliability and scientific rigor of aircraft detours under scattered hazardous weather conditions. Attached Figure Description

[0064] Figure 1 This is a flowchart of the present invention.

[0065] Figure 2 This is an example of an airspace raster map for an embodiment of the present invention.

[0066] Figure 3 This is the feasible path 1 constructed in the embodiment of the present invention.

[0067] Figure 4 This is feasible path 2 constructed in the embodiment of the present invention.

[0068] Figure 5 This is the feasible path 3 constructed in the embodiment of the present invention.

[0069] Figure 6 This is feasible path 4 constructed in the embodiment of the present invention.

[0070] Figure 7 This is feasible path 5 constructed in the embodiment of the present invention. Detailed Implementation

[0071] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings.

[0072] A method for constructing scattered hazardous weather rerouting paths based on multi-objective decision-making is as follows: Figure 1 As shown, it includes the following steps:

[0073] Step 1: For the target flight airspace, perform uniform raster modeling, mark the areas where scattered hazardous weather is located as obstacle grids, and construct an airspace raster map that includes airspace boundaries and scattered hazardous weather constraints. ;

[0074] In this embodiment, specifically:

[0075] A real airway route from waypoint DPX to waypoint SASAN was selected. The original distance from waypoint DPX to waypoint SASAN is 369.18km. The grid cells are set to be 20km in both length and width. Six scattered hazardous weather conditions were set. The grid cells covered by these conditions were marked as no-fly zones, and the remaining grid cells were marked as passable grid cells, thus constructing a complete airspace environment map. ,like Figure 2 As shown, since it is necessary to avoid dangerous weather zones, the rerouting route needs to be regenerated.

[0076] Step 2: Set the starting point of the rerouting route and the end point The system searches for and generates multiple feasible paths between the origin and destination that can avoid all scattered hazardous weather obstacle grids, forming a set of alternative routes. ;

[0077] In this embodiment, specifically:

[0078] Set waypoint DPX as the starting point for the rerouting. Its raster index is (1,12); set the waypoint SASAN as the destination of the rerouting. Its raster index is (10,1). Let the number of feasible paths to be searched be... The value is 5, at the starting point. and the end point Search for feasible paths between them and construct a set of modified routes. .

[0079] Step 3: Analyze the set of reroutes Path smoothing optimization is performed on feasible paths in the data;

[0080] In this embodiment, specifically:

[0081] Smoothed rerouting path set As shown in Table 1 and Figures 3 to 7 As shown:

[0082] Table 1. Set of Changed Routes

[0083] Path name raster index set Feasible path 1 (1,12)、(5,11)、(8,6)、(10,1) Feasible path 2 (1,12)、(4,11)、(6,9)、(8,6)、(10,1) Feasible path 3 (1,12)、(2,9)、(6,3)、(10,1) Feasible path 4 (1,12)、(2,9)、(5,5)、(7,3)、(10,1) Feasible path 5 (1,12)、(3,7)、(7,2)、(10,1)

[0084] Step 4: Analyze the set of reroutes Each feasible path in Four core evaluation indicators were extracted: detour distance, average turning angle, number of inflection points, and minimum safe distance, corresponding to the four evaluation dimensions of economy, flight stability, path simplicity, and safety, respectively. These indicators overcome the shortcomings of existing methods that only consider distance as a single objective and neglect safety and flight stability. They can also be combined with multi-objective decision-making methods to comprehensively weigh safety, economy, and stability for each feasible path. The indicators are then standardized to construct an evaluation indicator matrix. ;

[0085] In this embodiment, specifically:

[0086] The calculation results are shown in Table 2. The indicators were then standardized to construct an evaluation indicator matrix. .

[0087] Table 2 Calculation Results of Indicators

[0088] Path name New detour route (km) Average turning angle (°) Inflection point number Minimum safe distance (km) Feasible path 1 22.53 27.08 2 3.01 Feasible path 2 15.38 16.59 3 0 Feasible path 3 12.66 22.50 2 3.42 Feasible path 4 7.67 12.62 3 0 Feasible path 5 14.76 24.88 2 1.89

[0089] Step 5: Construct an index weight model using the projection pursuit method and solve it using a genetic algorithm to obtain the objective weights of each evaluation index;

[0090] In this embodiment, specifically:

[0091] The objective weights of the four indicators are as follows: , , , .

[0092] Step 6: Calculate the score of each feasible path in the rerouting path set according to the value and weight of the evaluation index, select the feasible path with the highest score as the optimal rerouting path, and complete the construction of rerouting paths under scattered hazardous weather conditions.

[0093] In this embodiment, specifically:

[0094] The calculation results are shown in Table 3. Among them, feasible path 3 has the highest comprehensive score, so feasible path 3 is selected as the optimal rerouting path from waypoint DPX to waypoint SASAN, thus completing the construction of rerouting paths under scattered hazardous weather conditions.

[0095] Table 3 Overall Scoring Results

[0096] Path name Overall score Feasible path 1 0.9802 Feasible path 2 0.4376 Feasible path 3 1.4346 Feasible path 4 0.7824 Feasible path 5 0.9708

[0097] In step 1, the airspace grid map construction process is as follows: the target flight airspace is divided into uniform grids, and each grid is identified by a unique index ( , ) identifier, in which Indicates the horizontal index of the raster. Represents the vertical index of the grid; collects the location range of scattered hazardous weather, marks the grids covered by it as no-fly obstacle grids, and marks the remaining grids as passable grids, constructing a complete airspace environment map, denoted as . .

[0098] In step 2, to address the shortcomings of traditional rerouting methods that only search for the shortest path, this method re-applies the A* algorithm at the inflection point to search for new subsequent sub-paths, generating multiple feasible paths with distinct structures. Compared to directly re-searching for the global shortest path, this approach, without repeatedly searching for the already determined preceding sub-path, generates multiple feasible paths that differ from the original path by considering constraints such as turning angle, segment distance, maximum detour ratio, and path redundancy, thus forming a rerouting path set. Set of reroutes The construction process is as follows:

[0099] Step 2-1: For the starting point of the rerouting route where a feasible path needs to be searched. and the end point The A* algorithm is used to search for the shortest path from the starting point to the ending point that avoids all no-fly zones. and add it to the modified route set. In the middle, set the number of feasible paths to be searched. , The value is generally between 3 and 8, as in this embodiment. The value is 5;

[0100] Step 2-2, adjust the set of reroutes. Sort by distance in ascending order and retrieve the last feasible path. This route has the longest flight distance in the set;

[0101] Steps 2-3: Extract feasible paths inflection point set , Feasible path The A turning point Initially 1, , Feasible path The total number of inflection points; the criteria for determining inflection points are as follows:

[0102]

[0103] Among them, feasible paths Three adjacent coordinate points , , , and coordinate point of coordinates and Coordinates, when When the value is not 0, then Add the inflection point to the inflection point set. inside.

[0104] Steps 2-4, targeting the inflection point Feasible paths Split into pre-sub-path and subsequent subpaths At the turning point and the end point Reuse the A* algorithm to search for new subsequent subpaths. By setting constraints on feasible paths Based on this, new feasible paths are constructed, and the search process must meet the following conditions:

[0105] 1) Sub-path With the previous sub-path remove In addition, there cannot be any repeated inflection points. The judgment conditions are as follows:

[0106]

[0107] in, It is the subsequent subpath The set of inflection points It is the previous sub-path The set of inflection points, the intersection of the two can only have A turning point;

[0108] 2) Sub-path All no-fly zones must be avoided;

[0109] 3) Turning angle at each inflection point on the path The formula for calculating the turning angle is as follows:

[0110]

[0111] in, and inflection point of coordinates and coordinate, inflection point The turning angle should meet the following requirements. ;

[0112] 4) Flight distance between inflection points ;

[0113] 5) The additional distance after the rerouting shall not exceed 50% of the original distance;

[0114] 6) New Subpath With the original sub-path Path repetition The formula for calculating path repetition is as follows:

[0115]

[0116] in, It is the new sub-path Airspace environment map The set of grid cells passed through, It is the original sub-path Airspace environment map The set of grid cells that have been passed through.

[0117] Steps 2-5: Extract the subsequent sub-paths from the search results. With the previous sub-path splicing together to form a new feasible path Add to the rerouting path set If set The number of paths has reached If the value is found, the path search is exited and the construction process ends; otherwise... If yes, then proceed to step 2-2; otherwise, let... Proceed to steps 2-4.

[0118] In step 3, the path smoothing optimization process is as follows:

[0119] Step 3-1, extract feasible paths inflection point set , Feasible path The A turning point Initially 1, ; The initial value is 2. ; Feasible path The total number of inflection points;

[0120] Step 3-2, connect the inflection points and If it does not intersect with the no-fly zone grid, then it is a feasible path. Change from arrive If directly connected, proceed to step 3-3; if it intersects with the no-fly zone grid, proceed to step 3-4.

[0121] Step 3-3, if End path smoothing optimization; otherwise, let Proceed to step 3-2;

[0122] Steps 3-4, if End path smoothing optimization; otherwise, let , Proceed to step 3-2.

[0123] In step 4, the process of constructing the evaluation index matrix is ​​as follows:

[0124] Step 4-1, Calculate feasible paths New detour routes Feasible path The difference between the total length and the original route length;

[0125] Calculate feasible paths average turning angle Feasible path The average turning angle of all inflection points;

[0126] Calculate feasible paths inflection point number Feasible path The number of inflection points;

[0127] Calculate feasible paths Minimum safe distance Feasible path Minimum distance from all no-fly zones;

[0128] Step 4-2: Standardize all indicators. The standardization formula is as follows:

[0129]

[0130] In the above formula, For the first Feasible path The The original value of each indicator; For the first Feasible path The The standardized value of the indicator; for The maximum value, for The minimum value, , For the set of reroutes The total number of feasible paths in the path.

[0131] Standardized index values Add to the evaluation index matrix In the evaluation index matrix Construction complete.

[0132] In step 5, the process of constructing the index weight model using the projection pursuit method and solving it using a genetic algorithm is as follows:

[0133] Step 5-1, randomly initialize the projection direction vector ,in For the first The initial weights of each evaluation indicator must meet the following conditions:

[0134]

[0135]

[0136] Step 5-2, calculate the first... Feasible path projection value The calculation formula is as follows:

[0137]

[0138] in, For the first Feasible path The The standardized value of the indicator.

[0139] Step 5-3: Calculate the mean of the projected index. and standard deviation The calculation formula is as follows:

[0140]

[0141]

[0142] in, For the set of reroutes The total number of feasible paths in the path.

[0143] Step 5-4: Calculate the local density of the projected values. The calculation formula is as follows:

[0144]

[0145] Step 5-5: Construct a comprehensive projection tracking index The calculation formula is as follows:

[0146]

[0147] Steps 5-6: Solve using a genetic algorithm. The maximum value is used to obtain the optimal projection direction vector. ,in For the first Objective weights of evaluation indicators.

[0148] In step 6, the process of selecting the optimal rerouting route is as follows:

[0149] Step 6-1, calculate the first... Feasible path Overall rating The calculation formula is as follows:

[0150]

[0151] Step 6-2, set the rerouting routes All feasible paths in the list are ranked according to their comprehensive score. Arrange the routes in descending order of high to low score, select the feasible route with the highest score as the optimal rerouting route, and complete the construction of rerouting routes under scattered hazardous weather conditions.

[0152] This invention provides a method for constructing scattered hazardous weather rerouting paths based on multi-objective decision-making. Many methods and approaches exist for implementing this technical solution; the above description is merely a preferred embodiment of the invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this invention, and these improvements and modifications should also be considered within the scope of protection of this invention. All components not explicitly stated in this embodiment can be implemented using existing technologies.

Claims

1. A method for constructing scattered hazardous weather detour routes based on multi-objective decision-making, characterized in that, Includes the following steps: Step 1: For the target flight airspace, construct an airspace raster map that includes airspace boundaries and scattered hazardous weather constraints. ; Step 2: Set the starting point of the rerouting route and the end point The system searches for and generates feasible paths between the origin and destination that avoid all scattered hazardous weather obstacle grids, forming a set of alternative routes. ; Step 3: Analyze the set of reroutes Path smoothing optimization is performed on feasible paths in the data; Step 4: Analyze the set of reroutes Each feasible path in Construct an evaluation index matrix ; Step 5: Construct an index weight model using the projection pursuit method and solve it using a genetic algorithm to obtain the objective weights of each evaluation index; Step 6: Calculate the score of each feasible path in the rerouting path set according to the value and weight of the evaluation index, select the feasible path with the highest score as the optimal rerouting path, and complete the construction of rerouting paths under scattered hazardous weather conditions.

2. The method for constructing scattered hazardous weather diversion routes based on multi-objective decision-making according to claim 1, characterized in that, In step 1, the airspace grid map construction process is as follows: the target flight airspace is divided into uniform grids, each grid being uniquely indexed. , ] identifier, in which Indicates the horizontal index of the raster. Represents the vertical index of the grid; collects the location range of scattered hazardous weather, marks the grids covered by it as no-fly obstacle grids, and marks the remaining grids as passable grids, constructing a complete airspace environment map, denoted as . .

3. The method for constructing scattered hazardous weather diversion routes based on multi-objective decision-making according to claim 2, characterized in that, In step 2, the set of reroutes The construction process is as follows: Step 2-1: Use the A* algorithm to search for the shortest path from the starting point to the ending point that avoids all no-fly grids. and add it to the modified route set. In the middle, set the number of feasible paths to be searched. ; Step 2-2, adjust the set of reroutes. Sort by distance in ascending order and retrieve the last feasible path. ; Steps 2-3: Extract feasible paths inflection point set , Feasible path The A turning point Initially 1, , Feasible path The total number of inflection points; Steps 2-4, targeting the inflection point Feasible paths Split into pre-sub-path and subsequent subpaths At the turning point and the end point Reuse the A* algorithm to search for new subsequent subpaths. ; Steps 2-5 involve retrieving the new sub-paths. With the previous sub-path splicing together to form a new feasible path Add to the rerouting path set If set The number of paths has reached If the value is found, the path search is exited and the construction process ends; otherwise... If yes, then proceed to step 2-2; otherwise, let... Proceed to steps 2-4.

4. The method for constructing scattered hazardous weather diversion routes based on multi-objective decision-making according to claim 3, characterized in that, The search process described in steps 2-4 must meet the following conditions: 1) Sub-path With the previous sub-path remove In addition, there should be no repeated inflection points; 2) Sub-path All no-fly zones must be avoided; 3) The turning angle at each inflection point on the path is less than the angle threshold; 4) The distance between inflection points is greater than the distance threshold; 5) The additional distance after the rerouting shall not exceed n% of the original distance; 6) New Subpath With the original sub-path The path repetition is less than the repetition threshold.

5. The method for constructing scattered hazardous weather diversion routes based on multi-objective decision-making according to claim 4, characterized in that, The formula for calculating the path repetition is as follows: in, It is the new sub-path Airspace environment map The set of grid cells passed through, It is the original sub-path Airspace environment map The set of grid cells that have been passed through.

6. The method for constructing scattered hazardous weather diversion routes based on multi-objective decision-making according to claim 4, characterized in that, In step 4, the evaluation index matrix includes: additional detour route: the difference between the total length of the feasible path and the original route length; average turning angle: the average turning angle of all inflection points of the feasible path; number of inflection points: the number of inflection points of the feasible path; minimum safe distance: the minimum distance between the feasible path and all no-fly zones.

7. The method for constructing scattered hazardous weather diversion routes based on multi-objective decision-making according to claim 6, characterized in that, The construction of the evaluation index matrix specifically includes: Step 4-1, Calculate feasible paths New detour routes Average turning angle Feasible path The average turning angle of all inflection points, the number of inflection points and minimum safe distance ; Step 4-2: Standardize all indicators and convert the standardized indicator values... Add to the evaluation index matrix In the evaluation index matrix Construction complete.

8. The method for constructing scattered hazardous weather diversion routes based on multi-objective decision-making according to claim 7, characterized in that, In step 5, the process of constructing the index weight model using the projection pursuit method and solving it using a genetic algorithm is as follows: Step 5-1, Initialize the projection direction vector ,in For the first The weight of each evaluation indicator, where m is the number of evaluation indicators; Step 5-2, calculate the first... Feasible path projection value : in, For the first Feasible path The The standardized value of the indicator. Step 5-3: Calculate the mean of the projected index. and standard deviation ; Step 5-4: Calculate the local density of the projected values. The calculation formula is as follows: Step 5-5: Construct a comprehensive projection tracking index The calculation formula is as follows: Steps 5-6: Solve using a genetic algorithm. The maximum value is used to obtain the optimal projection direction vector. ,in For the first Objective weights of evaluation indicators.

9. A method for constructing scattered hazardous weather diversion routes based on multi-objective decision-making according to claim 8, characterized in that, Step 6 specifically involves: calculating the... Feasible path Overall rating The feasible path with the highest score is selected as the optimal rerouting path, thus completing the construction of rerouting paths under scattered hazardous weather conditions.

10. A method for constructing scattered hazardous weather diversion routes based on multi-objective decision-making according to claim 9, characterized in that, The first Feasible path Overall rating The calculation formula is as follows: 。

Images