CN116659512A - A Helicopter Route Planning Method Based on Weather Forecast Information - Google Patents

Abstract

The invention discloses a helicopter route planning method based on weather forecast information, which comprises the following steps: a navigational space structure; modeling environment information, and carrying out feasibility analysis of a starting point, a task point and an ending point according to the environment information; under the condition of meeting feasibility, adopting a particle swarm algorithm to carry out route planning from a starting point to a task point and from the task point to an end point; carrying out fuel estimation according to the planned path result; calculating the maximum operation duration of the task area according to the fuel oil estimated result; and outputting the calculation result of the planning path, the residual oil consumption and the maximum operation duration of the task area. According to the planning method disclosed by the invention, weather forecast information is taken as one of safety indexes, an improved particle swarm optimization algorithm is adopted, parameters such as learning factors and the like are self-adaptive, and under the condition of given digital maps, aircraft parameters and flight tasks, automatic planning of the route of the helicopter is realized, planning time is saved, and the safety of the route is improved.

Description

A Helicopter Route Planning Method Based on Weather Forecast Information

technical field

The invention belongs to the field of computing intelligence, in particular to a helicopter route planning method based on weather forecast information.

Background technique

At present, people usually use helicopters to perform missions such as penetration, detection, and hoisting in low-altitude environments. Bad weather poses an extremely serious threat to the safety of aircraft flight. According to relevant data, one out of every seven aircraft or aircraft crashes is due to Caused by bad weather. Therefore, meteorological factors need to be taken into account in the route planning of helicopters.

Helicopter route planning refers to finding the optimal flight trajectory that satisfies its maneuverability and environmental information constraints under specific constraints. An optimal three-dimensional trajectory is planned at a certain height above the ground on the digital map.

At present, the particle swarm algorithm is used for the route planning of the helicopter. Particle swarm optimization algorithm is an optimization algorithm of swarm intelligence. Each particle in the algorithm represents a potential solution to the problem, and each particle corresponds to a fitness value determined by the fitness function. The speed of the particle determines the direction and distance of the particle's movement. The speed is dynamically adjusted according to the movement experience of itself and other particles, so as to realize the optimization of the individual in the solution space. The particle swarm optimization algorithm first initializes a group of particles in the solution space, and each particle represents a potential optimal solution of the extremum optimization problem. The particle is characterized by three indicators: position, speed and fitness value. The fitness value is determined by the fitness function Calculated, the quality of its value represents the quality of the particle. The particles move in the solution space, and update the individual position by tracking the individual extremum and group extremum. The individual extremum refers to the optimal position of fitness value searched by individual particles, and the group extremum refers to the optimal position of fitness searched by all particles in the population. Every time a particle updates its position, the fitness value is calculated, and the individual extremum and group extremum positions are updated by comparing the fitness value of the new particle with the fitness value of the individual extremum and the group extremum. Its core idea is to use the information sharing of individuals in the group to make the movement of the whole group evolve from disorder to order in the problem solving space, so as to obtain the optimal solution of the problem. However, the traditional particle swarm optimization algorithm has the problem of poor handling of discrete optimization problems and easy to fall into local optimum.

Contents of the invention

In order to solve the above technical problems, the present invention provides a helicopter route planning method based on weather forecast information, which takes weather forecast information into consideration as one of the safety indicators, adopts an improved particle swarm optimization algorithm, and adapts parameters such as learning factors to In the case of a given digital map, aircraft parameters, and flight missions, the automatic route planning of the helicopter is realized, which saves planning time and improves the safety of the route.

To achieve the above object, the technical scheme of the present invention is as follows:

A helicopter route planning method based on weather forecast information, comprising the following steps:

Step 1, constructing the navigation space according to the starting point, mission point and end point of the helicopter;

Step 2, modeling environmental information in the constructed navigation space, the environmental information including weather forecast information and geometric information;

Step 3, carry out the feasibility analysis of the start point, task point and end point according to the environmental information;

Step 4, under the condition of satisfying the feasibility, use the particle swarm optimization algorithm to plan the route from the starting point to the mission point and from the mission point to the end point;

Step 5, perform fuel estimation according to the result of the planned path;

Step 6, calculate the maximum operation time in the task area according to the fuel estimation result;

Step 7, output the calculation results of the planned path, remaining fuel consumption and maximum operating time in the task area.

In the above scheme, the method of step 1 is as follows: use the Mercator projection to convert the starting point, task point, and end point into latitude and longitude coordinates, combine the coordinate information of the starting point, task point, and end point to calculate the range of the area where it is located, and expand it A certain range is used as the navigation space range.

In the above scheme, the method of step 2 is as follows: use the grid method to discretize the weather forecast information in the navigation space; use geometric modeling to extract the geometric information of the no-navigation area and height obstacles in the navigation space.

In the above scheme, the method of step 3 is as follows: judge whether the weather forecast information of the start point, task point and end point meet the safety requirements, whether the three points are in the no-navigation area, whether they are too close to the height obstacle, and if they do not meet the planned If required, the reason for the decision is output.

In the above scheme, in step 4, the route planning methods from the starting point to the mission point and from the mission point to the end point are the same, including the following steps:

(1) Particle swarm initialization

Suppose the solution space of the particle swarm optimization algorithm is M=[m ₁ ,m ₂ ,...,m _N ], where m _i represents a planning path, i∈{1,2,..N.,, N represents the particle The number of swarm populations; each planned path is composed of several path nodes, and the information of each path node is represented by latitude and longitude information. Therefore, the initialization of particle swarm refers to the initialization of the latitude and longitude of the path nodes of each path;

(2) Determine the penalty setting method and fitness function

Set the fitness function S=CD, where C is the penalty for passing through no-navigation areas, thunderstorm areas, excessive wind speed areas, and high obstacles. The initial value is set to 1, and D is the Euclidean distance of the planned path. Mercator is used for calculation The projection converts the latitude and longitude coordinates into coordinates in the Cartesian coordinate system, and then calculates the Euclidean distance of the path;

(3) Iterative update

Update the velocity of the particles:

in, is the speed of the current particle i in the gth iteration; k is the shrinkage factor; w is the inertia factor, a non-negative number, used to adjust the search range of the solution space; /> is the speed of the current particle i in the g-1 iteration; P _i ^best and G ^best respectively represent the optimal value of the current particle i and the global optimal value; c ₁ and c ₂ represent the learning factors, which are used to adjust the learning maximum step Long, c ₁ ,c ₂ ∈(0,4]; r ₁ ,r ₂ ∈(0,1) represent random numbers, which are used to increase the randomness of the search;

The expression of shrinkage factor k is:

Among them, k ₀ is the set shrinkage factor coefficient, T _max is the maximum number of iterations, and t is the current number of iterations;

The expression of inertia factor w is:

Among them, w _min and w _max are the test parameters to be adjusted, which respectively represent the minimum and maximum values of the inertia factor, and the inertia factor w decreases with the number of iterations from w _max to w _min ;

The learning factor c ₁ decreases as the number of iterations increases, and c ₂ increases as the number of iterations increases. The parameter change formula is:

Among them, c _1start , c _1end , c _2start , and c _2start are parameters to be adjusted, respectively representing the initial value and final value of learning factor c ₁ and the initial value and final value of learning factor c ₂ ;

Update the particle's position:

in, is the position of the current particle i in the gth iteration, /> is the position of the current particle i in the g-1 iteration, and time represents the time factor, which is defined as:

Among them, _t0 is the parameter to be adjusted, which is a constant greater than 1, representing the initial step size of the time factor;

(4) Calculate the fitness value and update the local and global optimum:

According to the fitness function setting method of (2), calculate the particle fitness value, and then update the particle local and global optimal solution;

(5) Termination condition judgment:

If the set maximum number of iterations is reached or the particle does not update the global optimal solution for a certain number of times, the calculation will be terminated.

In the above-mentioned scheme, the method of particle swarm initialization is as follows: firstly, it is processed by non-completely random initialization method, that is, select the dimension with a large span in the direction of longitude and latitude, and divide it into equal parts, and use a random method in the other dimension Initialization, the random number conforms to the uniform distribution, and the random range is the corresponding dimension range of the navigation space; after that, if the non-complete initialization method planning fails, the completely random method is used for initialization, that is, the longitude and latitude are initialized in a uniformly distributed random method, and the random range is the range of navigation space.

In the above scheme, the method of step 5 is as follows: the navigation process is divided into three stages, the first stage is from the starting point to the mission point, the second stage is the mission area, and the third stage is from the mission point to the end point;

(1) The voyage of the first stage is

Among them, (x _nf ,y _nf ,z _nf ) represents the coordinates of the nfth path point including the starting point and task point in the Cartesian coordinate system, (x _nf+1 ,y _nf+1 ,z _nf+1 ) represents the coordinates of the nf+1th path point including the starting point and the task point under the Cartesian coordinate system, and NF represents that there are NF path nodes;

(2) The fuel consumption in the first stage is

FirstOil＝FirstDis/HighSpeed×HighOil,

Among them, HighSpeed and HighOil respectively represent the high-altitude flight speed and the fuel consumption per unit time during high-altitude flight;

(3) The fuel consumption calculation method of the third stage is the same as that of the first stage; if the sum of the fuel consumption of the first stage and the third stage exceeds the total amount of fuel carried by the helicopter, it means that the planning fails.

In the above scheme, the method of step 6 is as follows:

The total fuel consumption of the first, second and third stages of the voyage cannot exceed the total fuel quantity, expressed as:

t×LowOil+t×ratio×HighOil≤TotalOil-FirstOil-ThirdOil

Among them, t represents the low-altitude operation time in the mission area, LowOil represents the fuel consumption per unit time during low-altitude flight, ratio is the ratio of high-altitude flight time to low-altitude flight time, and TotalOil represents the total amount of fuel carried by the helicopter;

Then the maximum working time of the task area is t+t·ratio.

In the above solution, in step 7, if the planning fails, output the corresponding decision reason and return value.

Through the above-mentioned technical scheme, a kind of helicopter route planning method based on weather forecast information provided by the present invention has the following beneficial effects:

(1) The present invention improves the safety of route planning by modeling the navigation space structure and environmental information, and taking into account the constraints of no-navigation areas, height obstacles and weather forecast information.

(2) The present invention considers the fuel parameter information of the helicopter itself, and calculates the maximum operation time in the mission area according to the planned path, which can be used for reference.

(3) The present invention simultaneously sets shrinkage factor, inertia factor, learning factor, and time factor to make it self-adaptive, thereby improving the problem that the traditional particle swarm optimization algorithm is easy to fall into local optimum, and speeding up the convergence rate, making it more efficient Applicable to engineering practice.

(4) The present invention avoids the grid traversal check on the feasibility of the final planning path on the one hand by setting the fitness function; The calculation of the fitness function stops the grid traversal check of the path, which saves a lot of planning time.

(5) The gridded weather forecast information processing method of the present invention is also applicable to terrain information, so it can be adapted to a wider range of application scenarios with slight changes.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings that are required in the description of the embodiments or the prior art.

Fig. 1 is a schematic flow chart of a helicopter route planning method based on weather forecast information disclosed in an embodiment of the present invention.

Figure 2 is a two-dimensional rendering of the helicopter route planning matlab.

Figure 3 is a three-dimensional rendering of the helicopter route planning matlab.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention.

The invention provides a helicopter route planning method based on weather forecast information, comprising the following steps:

Step 1. Construct the navigation space according to the starting point, mission point and end point of the helicopter.

Specifically, the Mercator projection is used to transform the latitude and longitude coordinates of the start point, task point, and end point, and the range of the area is calculated by combining the coordinate information of the start point, task point, and end point, and expanding it to a certain extent as the navigation space range. In this embodiment, the range enclosed by the coordinates of the three points is enlarged by 0.4 times as the range of the navigation space.

Step 2: Carry out environmental information modeling in the constructed navigation space, and the environmental information includes weather forecast information and geometric information.

Specifically, the grid method is used to discretize the weather forecast information in the navigation space; the geometric modeling method is used to extract the geometric information of the no-navigation area and high obstacles in the navigation space. Import the grid wind speed and rainfall data within the range of navigation space, load the environmental information such as height obstacles and no-flying areas, import the helicopter parameter information, and import the helicopter flight height information, among which the helicopter parameter information includes the total fuel volume carried by the helicopter , Low-altitude flight speed, low-altitude flight fuel consumption, high-altitude flight speed, high-altitude flight fuel consumption.

Step 3. Carry out the feasibility analysis of the start point, task point and end point according to the environmental information.

Specifically, it is judged whether the weather forecast information of the start point, mission point and end point meet the safety requirements, whether the three points are in the no-flight zone, and whether they are too close to high obstacles. If they do not meet the planning requirements, output the reason for the decision.

Among them, the environmental forecast information mainly includes wind speed and rainfall information, and whether it meets the requirements is judged according to the wind speed and rainfall values.

The method of judging whether the three points are within the no-fly zone is as follows:

No-fly areas are divided into circular and arbitrary polygonal no-fly areas (including triangles, quadrilaterals, etc.). The method for judging that a point is within a circular no-fly area is: calculate the point to the center of the circle under the two-dimensional Cartesian coordinate system (latitude and longitude conversion) If the distance is less than the radius, it means it is within the circular no-flight zone.

The method of judging whether a point is within the polygonal no-go zone is as follows: suppose the vertices of the polygon are (x ₁ , y ₁ ), (x ₂ , y ₂ ), ..., (x _n , y _n ) and the point to be judged is (x ₀ , y ₀ ), define the maximum distance M _x and M _y of the horizontal and vertical coordinates from the point to be judged to the vertices of the polygon:

M _x ＝max{|x ₀ -x _i |,i＝1,2,...,n},

M _y ＝min{|y ₀ -y _i |,i＝1,2,...,n}.

Starting from (x ₀ , y ₀ ), draw a ray with the slope of M _y /2M _x . According to the selection conditions of M _x and M _y , this ray will not intersect any vertex of the polygon. Take additional points on the ray:

(x',y')=(x ₀ +2M _x ,y ₀ +M _y ).

It can be proved that the point (x',y') is outside the polygon area, then the detection point (x ₀ ,y ₀ ) can be converted into the calculation line segment (x ₀ ,y ₀ )-(x',y') whether it exists in the polygon The number of intersections with each edge of the polygon. If the number of intersection points is odd, the point (x ₀ , y ₀ ) is inside the polygon; if the number of intersection points is even, then the point (x ₀ , y ₀ ) is not inside the polygon.

Step 4, under the condition of satisfying the feasibility, use the particle swarm optimization algorithm to plan the route from the starting point to the mission point and from the mission point to the end point.

The route planning methods from the start point to the mission point and from the mission point to the end point are the same, including the following steps:

(1) Particle swarm initialization

Suppose the solution space of the particle swarm optimization algorithm is M=[m ₁ ,m ₂ ,...,m _N ], where m _i represents a planning path, i∈{1,2,..N.,, N represents the particle The number of swarm populations; each planned path is composed of several path nodes, and the information of each path node is represented by latitude and longitude information. Therefore, the initialization of particle swarm refers to the initialization of the latitude and longitude of the path nodes of each path.

The method of particle swarm initialization is as follows:

Firstly, use non-completely random initialization method for processing, that is: select the dimension with a large span in the longitude and latitude directions, and divide it into equal parts, and use random initialization on the other dimension. The random number conforms to the uniform distribution, and the random range is The corresponding dimension range of the navigation space; after that, if the non-complete initialization method planning fails, it will be initialized in a completely random manner, that is, the longitude and latitude are initialized in a uniformly distributed random manner, and the random range is the navigation space range.

Among them, the completely random initialization expression is:

Among them, x ₀ and y ₀ represent the coordinates of the starting point, x _i and y _i represent the coordinates of the path point, d∈{-1,1} represents the direction, and the random numbers rand(x) and rand(y) do not exceed the latitude and longitude dimensions respectively. Start-stop span.

In addition, the initialization of the particle velocity is different according to the different initialization methods selected. In the non-completely random initialization, if the span of the longitude direction is larger than that of the latitude direction, the particle velocity initialization expression is:

Wherein, the size of the random number rand(v _xi ) does not exceed half of the span of the starting and ending points in the latitude dimension.

(2) Determine the penalty setting method and fitness function

Set the fitness function S=CD, where C is the penalty for passing through no-navigation areas, thunderstorm areas, excessive wind speed areas, and high obstacles. The initial value is set to 1, and D is the Euclidean distance of the planned path. Mercator is used for calculation The projection converts the latitude and longitude coordinates into coordinates in the Cartesian coordinate system, and then calculates the Euclidean distance of the path.

If passing through no-navigation areas, thunderstorm areas, areas with excessive wind speed, and near high obstacles, then C=1.7×10 ³⁰⁸ , D=1, D is the Euclidean distance of the planned path, and its mathematical expression is:

Among them, n represents the number of intermediate path points.

Meteorological forecast information is grid data, which mainly includes wind speed and rainfall information. According to the wind speed and rainfall values, it is judged whether it meets the flight requirements. When calculating the fitness value, interpolation sampling is performed for all route sections, and the sampling points are queried according to the principle of proximity If the weather information is not met, penalties will be imposed. Among them, the calculation method for the number of sampling points is: select the latitude and longitude values in the direction with a large span, calculate the difference in the corresponding dimension, divide by the resolution and round up, and the calculated value is the number of sampling points. This sampling method can ensure that the grid points passed by the path are traversed.

For the no-navigation area, use the Mercator projection to transform the latitude and longitude coordinates into a Cartesian coordinate system, traverse all the no-navigation areas and each route section of the route, and calculate whether to enter the no-navigation area, if entering the no-navigation area, let C= 1.7×10 ³⁰⁸ , D=1.

For height obstacles, according to the specified flight height, it is judged whether the height obstacles need to be circumvented. If it is necessary to avoid them, the obstacle is taken as the center and the radius is 100 meters, and it is treated as a circular no-flight zone.

(3) Iterative update

Update the velocity of the particles:

in, is the speed of the current particle i in the gth iteration; k is the shrinkage factor; w is the inertia factor, a non-negative number, used to adjust the search range of the solution space; /> is the speed of the current particle i in the g-1 iteration; P _i ^best and G ^best respectively represent the optimal value of the current particle i and the global optimal value; c ₁ and c ₂ represent the learning factors, which are used to adjust the learning maximum step Long, c ₁ ,c ₂ ∈(0,4]; r ₁ ,r ₂ ∈(0,1) represent random numbers, which are used to increase the randomness of the search;

The expression of shrinkage factor k is:

Among them, k ₀ is the set shrinkage factor coefficient, T _max is the maximum number of iterations, and t is the current number of iterations;

The expression of inertia factor w is:

Among them, w _min and w _max are the test parameters to be adjusted, which respectively represent the minimum and maximum values of the inertia factor, and the inertia factor w decreases with the number of iterations from w _max to w _min ;

The learning factor c ₁ decreases as the number of iterations increases, and c ₂ increases as the number of iterations increases. The parameter change formula is:

Among them, c _1start , c _1end , c _2start , and c _2start are parameters to be adjusted, respectively representing the initial value and final value of learning factor c ₁ and the initial value and final value of learning factor c ₂ ;

Update the particle's position:

in, is the position of the current particle i in the gth iteration, /> is the position of the current particle i in the g-1 iteration, and time represents the time factor, which is defined as:

Among them, _t0 is the parameter to be adjusted, which is a constant greater than 1, representing the initial step size of the time factor;

(4) Calculate the fitness value and update the local and global optimum:

According to the fitness function setting method of (2), calculate the particle fitness value, and then update the particle local and global optimal solution;

(5) Termination condition judgment:

If the set maximum number of iterations is reached or the particle does not update the global optimal solution for a certain number of times, the calculation will be terminated.

Step 5, perform fuel estimation according to the result of the planned path.

The navigation process is divided into three stages, the first stage is from the starting point to the mission point, the second stage is the mission area, and the third stage is from the mission point to the end point;

(1) The voyage of the first stage is

Among them, (x _nf ,y _nf ,z _nf ) represents the coordinates of the nfth path point including the starting point and task point in the Cartesian coordinate system, (x _nf+1 ,y _nf+1 ,z _nf+1 ) represents the coordinates of the nf+1th path point including the starting point and the task point under the Cartesian coordinate system, and NF represents that there are NF path nodes;

(2) The fuel consumption in the first stage is

FirstOil＝FirstDis/HighSpeed×HighOil,

Among them, HighSpeed and HighOil respectively represent the high-altitude flight speed and the fuel consumption per unit time during high-altitude flight;

(3) The fuel consumption calculation method of the third stage is the same as that of the first stage; if the sum of the fuel consumption of the first stage and the third stage exceeds the total amount of fuel carried by the helicopter, it means that the planning fails.

Step 6, calculate the maximum operation time in the task area according to the fuel estimation result.

The total fuel consumption of the first, second and third stages of the voyage cannot exceed the total fuel quantity, expressed as:

t×LowOil+t×ratio×HighOil≤TotalOil-FirstOil-ThirdOil

Among them, t represents the low-altitude operation time in the mission area, LowOil represents the fuel consumption per unit time during low-altitude flight, ratio is the ratio of high-altitude flight time to low-altitude flight time, and TotalOil represents the total amount of fuel carried by the helicopter;

Then the maximum working time of the task area is t+t·ratio.

Step 7: Output the calculation results of the planned route, remaining fuel consumption and maximum operating time in the task area; if the planning fails, output the corresponding decision reason and return value. Among them, the planning failure mainly includes the following reasons: the starting point is infeasible, the task point is infeasible, the end point is infeasible, and the environmental conditions are complex and harsh, making it impossible to fly. It is worth noting that if the environmental conditions are complex and harsh, and the inability to fly leads to the failure of no feasible path planning, it is only necessary to check whether the fitness value is 1.7×10 ³⁰⁸ , and there is no need to re-determine the feasibility of the planned path.

In order to verify the effectiveness of a helicopter route planning method based on weather forecast information proposed by the present invention, we have implemented the method based on the VC++ development platform. It is worth noting that this technology belongs to the development of back-end algorithms. In order to further increase the demonstrability of the effect, we performed matlab visualization based on the calculation results of the algorithm, and gave a 2D and 3D rendering of the planning results. In addition, it should be noted that the specific input data used in this embodiment, such as the specific value of forecast information, helicopter parameter information, starting point, mission point, end point latitude and longitude, etc., can be replaced by actual values, and the data used in this embodiment are only used for Examples and tests are given to illustrate the implementation steps and verify the effectiveness of the proposed method. Further description will be given below in conjunction with specific examples.

1. Navigation space structure

(1) Import the latitude and longitude coordinates of the selected start point, task point and end point respectively: 101.334°E, 9.687°N, 105.359°E, 10.750°N, 107.650°E, 12.900°N.

(2) The Mercator projection is used for coordinate conversion, and the range surrounded by the three-point coordinates is expanded by 0.4 times as the navigation space range.

Table 1 Latitude and longitude coordinate projection conversion results

point name latitude and longitude projected coordinates starting point (101.334°E, 9.687°N) (11280499.280, 1076341.309) task point (105.359°E, 10.750°N) (11728510.230, 1195803.211) end (107.650°E, 12.900°N) (11983543.184, 1438776.481)

2. Environmental information modeling

(1) Import the grid wind speed and rainfall data within the scope of navigation space. The data adopts a resolution of 0.1°×0.1° and is in the form of a discrete grid. In actual use, the measured forecast information can be imported, and the rainfall information in this embodiment Visualization shows that areas A, B, and C in Figure 2 are thunderstorm areas, and area D in Figure 2 is an area with excessive wind speed.

(2) Load the environmental information such as high-level obstacles and no-navigation areas. In Figure 2, areas E and G are high-level obstacles, and F is no-navigation areas.

(3) Import helicopter parameter information, wherein the helicopter parameter information includes the total fuel quantity carried by the helicopter, low-altitude flight speed, low-altitude flight fuel consumption, high-altitude flight speed, and high-altitude flight fuel consumption.

(4) Import helicopter flight height information. The flight altitudes of the first stage are all 300m, and the flight altitudes of each route section of the third stage are: 300m, 307m, 307m, 307m, 307m, 360m.

3. Feasibility analysis of the starting point, mission point, and ending point, judging whether the environmental forecast information at the starting point, mission point, and ending point meet the safety requirements, whether the three points are in the no-flight zone, and whether they are too close to high obstacles , if the planning requirements are not met, output the reason for the decision.

4. Run the particle swarm algorithm to calculate the path from the starting point to the task point and from the task point to the end point. See Table 2 and Table 3 for the planning results. The three-dimensional rendering of matlab is shown in Figure 3.

Table 2 Path planning results from the starting point to the mission point

point name latitude and longitude starting point (101.334°E, 9.687°N, 300m) Intermediate Waypoint 1 (102.032°E, 9.543°N, 300m) Intermediate Waypoint 2 (102.735°E, 9.301°N, 300m) Intermediate Waypoint 3 (103.438°E, 9.150°N, 300m) Intermediate Waypoint 4 (104.141°E, 9.950°N, 300m) Intermediate Waypoint 5 (104.843°E, 10.350°N, 300m) task point (105.359°E, 10.750°N, 300m)

Table 3 Path planning results from mission point to termination point

point name latitude and longitude starting point (105.359°E, 10.750°N, 300m) Intermediate Waypoint 1 (105.741°E, 11.357°N, 307m) Intermediate Waypoint 2 (106.123°E, 11.767°N, 307m) Intermediate Waypoint 3 (106.505°E, 11.887°N, 307m) Intermediate Waypoint 4 (106.887°E, 12.057°N, 307m) Intermediate Waypoint 5 (107.268°E, 12.400°N, 360m) task point (107.650°E, 12.900°N, 360m)

5. Calculate the maximum operating time of the voyage and task area

According to the above parameters, the fuel consumption in the first stage is calculated to be 517145.3L, the fuel consumption in the second stage is 356071.3L, the fuel consumption in the third stage is 26783.4L, and the maximum working time in the mission area is 2455 hours.

The above description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (9)

1. A helicopter route planning method based on weather forecast information is characterized by comprising the following steps:

step 1, constructing a navigation space according to a starting point, a task point and a termination point of a helicopter;

step 2, modeling environmental information in the constructed navigation space, wherein the environmental information comprises weather forecast information and geometric information;

step 3, carrying out feasibility analysis of a starting point, a task point and an ending point according to the environmental information;

step 4, under the condition of meeting feasibility, adopting a particle swarm algorithm to carry out route planning from a starting point to a task point and from the task point to an end point;

step 5, fuel oil estimation is carried out according to the planned path result;

step 6, calculating the maximum operation duration of the task area according to the fuel oil estimated result;

and 7, outputting a calculation result of the planned path, the residual oil consumption and the maximum operation duration of the task area.

2. A method of planning a route for a helicopter based on weather forecast information as claimed in claim 1, wherein the method of step 1 is as follows: and carrying out longitude and latitude coordinate conversion on the starting point, the task point and the ending point by adopting ink card support projection, calculating the range of the area by combining the coordinate information of the starting point, the task point and the ending point, and expanding a certain range to be used as a navigation space range.

3. A method of planning a route for a helicopter based on weather forecast information as claimed in claim 1, wherein the method of step 2 is as follows: discretizing weather forecast information in a navigation space by adopting a grid method; and extracting geometric information of the navigation forbidden region and the height obstacle in the navigation space by adopting a geometric modeling mode.

4. A method of planning a route for a helicopter based on weather forecast information as claimed in claim 1, wherein the method of step 3 is as follows: judging whether weather forecast information of a starting point, a task point and an ending point meets safety requirements, judging whether the three points are in a forbidden navigation area or not and are too close to a height barrier, and outputting decision reasons if the weather forecast information does not meet planning requirements.

5. The helicopter routing method based on weather forecast information according to claim 1, wherein in step 4, the routing method from the starting point to the task point and from the task point to the end point is the same, and the method comprises the following steps:

(1) Particle swarm initialization

Let the solution space of the particle swarm algorithm be M= [ M ] ₁ ,m ₂ ,...,m _N], wherein ,m_i Represents a planned path, i epsilon {1,2,..N., N represents the population number of the particle swarm; each planning path is composed of a plurality of path nodes, and each path node information is characterized by longitude and latitude high information, so that particle swarm initialization refers to the initialization of the longitude and latitude of the path node of each path;

(2) Determining punishment setting mode and fitness function

Setting a fitness function S=C.D, wherein C is punishment of passing through a navigation forbidden region, a thunderstorm region, a wind speed overlarge region and a height obstacle, setting an initial value as 1, D is a planned path Euclidean distance, converting longitude and latitude coordinates into coordinates under a Cartesian coordinate system by adopting Cartesian projection during calculation, and then calculating the path Euclidean distance;

(3) Iterative updating

Update the speed of the particles:

wherein ,the speed of the current particle i in the g-th iteration; k is a contraction factor; w represents an inertia factor, a non-negative number, for adjusting the search range of the solution space; />The speed of the current particle i in the g-1 iteration is the same as that of the current particle i; p (P) _i ^best And G ^best Respectively representing the optimal value and the global optimal value of the current particle i; c ₁ ,c ₂ Representing a learning factor for adjusting a learning maximum step size, c ₁ ,c ₂ ∈(0,4]；r ₁ ,r ₂ E (0, 1) represents a random number for increasing search randomness;

the contraction factor k is expressed as:

wherein ,k₀ For the set coefficient of contraction factor, T _max Representing the maximum iteration number, wherein t is the current iteration number;

the inertia factor w is expressed as:

wherein ,w_min and w_max For the test parameters to be adjusted, respectively representing the minimum value and the maximum value of an inertia factor, wherein the inertia factor w is expressed by w _max To w _min Decreasing with iteration times;

learning factor c ₁ Decreasing with increasing iteration number c ₂ Increasing with the increase of the iteration times, the parameter change formula is as follows:

wherein ,c_1start 、c _1end 、c _2start 、c _2start For the parameters to be adjusted, respectively represent the learning factors c ₁ Initial value, final value, learning factor c ₂ Initial value and final value of (a);

updating the position of the particles:

wherein ,for the position of the current particle i at the g-th iteration, and (2)>For the position of the current particle i at the g-1 th iteration, time represents a time factor defined as:

wherein ,t₀ The initial step length of the time factor is represented by a constant which is larger than 1 for the parameter to be adjusted;

(4) Calculating fitness value and updating local and global optima:

calculating a particle fitness value according to the fitness function setting mode of the step (2), and updating the local and global optimal solutions of the particles;

(5) Judging a termination condition:

if the set maximum iteration number or the particles exceed a certain number of times, the global optimal solution is not updated, and the calculation is terminated.

6. The helicopter routing method based on weather forecast information of claim 5, wherein the method for initializing the particle swarm is as follows: firstly, adopting a non-complete random initialization mode to process, namely: selecting the latitude with large span in the longitude and latitude directions, equally dividing the latitude, initializing the latitude in another latitude in a random mode, enabling random numbers to be uniformly distributed, wherein the random range is the corresponding latitude range of the navigation space; then, if the programming fails in the incomplete initialization mode, the initialization is performed in a completely random mode, namely: the longitude and the latitude are initialized in a uniformly distributed random mode, and the random range is a navigation space range.

7. A method of planning a route for a helicopter based on weather forecast information as recited in claim 1, wherein the method of step 5 is as follows: dividing the navigation process into three stages, wherein the first stage is a starting point to a task point, the second stage is a task area, and the third stage is a task point to a final stop point;

(1) The voyage of the first stage is

wherein ,(x_nf ,y _nf ,z _nf ) Representing coordinates of nf-th path point including the start point and the task point in the Cartesian coordinate system, (x) _nf+1 ,y _nf+1 ,z _nf+1 ) Representing coordinates of nf+1th path points including a starting point and a task point in a Cartesian coordinate system, wherein NF represents NF path nodes;

(2) The oil consumption in the first stage is

FirstOil＝FirstDis/HighSpeed×HighOil,

Wherein, highSpeed and Highoil respectively represent the high-altitude flight speed and the oil consumption in unit time during high-altitude flight;

(3) The oil consumption calculation method in the third stage is the same as the oil consumption calculation method in the first stage; and if the sum of the oil consumption of the first stage and the oil consumption of the third stage exceeds the total oil quantity carried by the helicopter, the planning is failed.

8. A method of planning a route for a helicopter based on weather forecast information as recited in claim 7, wherein the method of step 6 is as follows:

the total oil consumption of the first stage, the second stage and the third stage of the sailing process cannot exceed the total oil quantity, and the total oil consumption is expressed as follows:

t×LowOil+t×ratio×HighOil≤TotalOil-FirstOil-ThirdOil

wherein t represents low-altitude operation time in a task area, lowOil represents oil consumption in unit time during low-altitude flight, ratio is the ratio of high-altitude flight time to low-altitude flight time, and TotalOil represents total oil carried by a helicopter;

the maximum working time of the task area is t+t.ratio.

9. The method according to claim 1, wherein in step 7, if the planning fails, the corresponding decision reason and return value are output.