Risk-based polar region ship navigation path planning method and system

Abstract

The invention discloses a risk-based polar region ship navigation path planning method and system. The method comprises the following steps: acquiring polar navigation environment data and ship parameters, quantifying the collision risk and the ice trapping risk of a ship, and constructing a comprehensive risk function of polar ship navigation; establishing a dynamic risk field which changes along with time and space, constructing a multi-target cost function including navigation distance, comprehensive risk and time efficiency based on the dynamic risk field, and setting a path constraint condition of polar region ship navigation; and under the constraint condition, performing multi-objective optimization solution on the multi-objective cost function to obtain one or more optimal navigation paths, and realizing optimal balance among multiple objectives on the premise that the paths meet the constraint condition. According to the invention, by quantifying the interaction risk of the ship and the sea ice, the safety of path planning is improved; by fusing multi-dimensional physical constraints, the actual operability of the planned path is guaranteed; by constructing the space-time dynamic risk field, the adaptability and response capability to the polar region complex and changeable environment are enhanced.

Description

Technical Field

[0001] This invention relates to the field of ship navigation safety technology, and in particular to a risk-based polar ship navigation path planning method and system. Background Technology

[0002] The polar seas have a complex climate and variable ice conditions, including floating ice, thick ice belts, and moving ice currents. Ships face the following major risks during navigation: Collision risk: Ships may collide with large ice blocks or icebergs, causing damage to the hull structure or even sinking; Ice trap risk: Ships may become trapped in areas with high ice concentration, losing their maneuverability and seriously affecting safety and efficiency.

[0003] Current polar vessel route planning primarily relies on static ice condition maps or weather forecasts, which struggle to dynamically reflect risk distribution and lack quantitative modeling of the ship-ice interaction process. This results in unreliable recommended routes in complex environments. Therefore, there is an urgent need for a method that can achieve safe and efficient route planning based on dynamic risk fields. Summary of the Invention

[0004] Purpose of the invention: The purpose of this invention is to provide a risk-based polar vessel navigation path planning method and system, which enables quantitative assessment of collision risk and ice trap risk during vessel navigation, and thus generates an optimal route that balances safety and economy.

[0005] Technical Solution: To achieve the above objectives, the present invention provides a risk-based polar vessel navigation path planning method, comprising the following steps:

[0006] S1. Acquire polar navigation environment data and ship parameters;

[0007] S2. Calculate the collision risk based on the environmental data and ship parameters. and the risk of ice trap To further construct a comprehensive risk function for polar vessel navigation ;

[0008] S3. Discretize the target navigation area and time period into spatial grids and time slices. For the specific location of each grid cell in each time slice, use a comprehensive risk function. Calculate the comprehensive navigation risk value, construct a dynamic risk field that varies with time and space, and based on the dynamic risk field, establish a multi-objective cost function that includes distance, risk and timeliness;

[0009] S4. Construct constraints for polar vessel navigation paths, including vessel turning radius constraints, area no-entry constraints, and vessel performance constraints;

[0010] S5. Based on the constraints, perform multi-objective optimization on the multi-objective cost function to obtain one or more optimal navigation paths. The optimal navigation path is the path that achieves the best balance in multi-objective optimization under the constraints.

[0011] Preferably, the environmental data includes sea ice thickness, sea ice concentration, wind speed, and current speed; the ship parameters include ship speed and ice resistance rating.

[0012] Preferably, the comprehensive risk function Represented as:

[0013] ,

[0014] In the formula, Indicates the potential damage caused by the collision. This indicates the potential losses caused by ice.

[0015] Preferably, the collision risk Represented as:

[0016] ,

[0017] ,

[0018] In the formula, For the first Sea ice-like concentration This indicates the total number of sea ice concentration types. For a given ice resistance rating R, The actual speed of the ship. For reference speed, For sailing time; As a risk index, To introduce the effective risk index after speed is introduced.

[0019] Preferably, the risk of ice trapping Represented as:

[0020] ,

[0021] , , ,

[0022] In the formula, For ice resistance, This is the ice drag coefficient. For sea ice density, It is the acceleration due to gravity. For the ship's width, Sea ice thickness, in percentage. This refers to the effective power of the host unit. For propeller efficiency, For gearbox efficiency, For propeller efficiency, For minimum sailing speed, The ice-induced sensitivity coefficient. For sailing time; This refers to the ship's icebreaking capability coefficient. For sea ice concentration, This is the ship type coefficient.

[0023] Preferably, the multi-objective cost function is expressed as:

[0024] ,

[0025] In the formula, Representing path points and The distance between them; Representing path points exist The overall risk value at any given time; Indicates at the waypoint Ship speed at the location; , and These are the weighting coefficients; Indicates the total number of path points. Indicates the ordinal index of the path point.

[0026] Preferably, the ship turning radius constraint is calculated by taking three consecutive path points. , , The radius of the arc formed and the minimum turning radius of the ship in the current ice-water mixed environment. The comparison and the constraints are expressed as follows: ;

[0027] in, ,

[0028] ,

[0029] In the formula, For line segments and The included angle, Indicates the distance between two points; The channel protection coefficient. For ship speed, For the length between the ship's perpendiculars, For the ship's draft, This represents the actual water depth at present. This is the ice drag coefficient. For sea ice concentration, Sea ice thickness;

[0030] The region prohibition constraint: Assume that for a path point sequence... Define function Representing path points Is it in the restricted area? Within, the restricted area includes areas with dense icebergs, ecological protection zones, etc.; the collection of restricted areas can be written as... , This represents the total number of restricted areas, and the constraint is expressed as follows: ;

[0031] The ship performance constraint: the ship's speed at various points along the navigation path. The maximum safe speed shall not be exceeded based on the sea ice conditions at that point. The constraints are expressed as follows: ;

[0032] in, , This refers to sea ice concentration.

[0033] Preferably, the multi-objective cost function is solved by using a non-dominated sorting genetic algorithm, including: initializing and verifying the constraints of the constructed population individuals containing path coordinates and timestamps; calculating the fitness vector containing the travel distance, cumulative comprehensive risk, and travel time; performing non-dominated sorting, crowding calculation, and selection, crossover, mutation operations, and elite retention strategies based on the fitness vectors of the population individuals for iterative evolution until the termination condition is met; and finally selecting and outputting the optimal travel path from the Pareto front of the final population based on preferences.

[0034] Preferably, the population individuals are represented as ,

[0035] in, The coordinates of the path points, The estimated time for the ship to arrive at this point, starting point and the finish line fixed;

[0036] The fitness vector of an individual in the population is represented as Of which, total sailing distance The cumulative comprehensive risk is obtained by summing the Euclidean distances between all adjacent points in the path. The estimated sailing time is calculated by summing up the comprehensive risk values ​​experienced by the vessel at each waypoint along the entire route. It is calculated based on the ship's safe speed in each section of the voyage.

[0037] The risk-based polar vessel navigation path planning system of this invention includes the following modules:

[0038] Data collection module: used to acquire polar navigation environment data and ship parameters;

[0039] Integrated risk solution module: Calculates collision risk based on the environmental data and ship parameters. and the risk of ice trap To further construct a comprehensive risk function for polar vessel navigation ;

[0040] Multi-objective cost function construction module: Discretizes the target navigation area and time period into spatial grids and time slices. For the specific location of each grid cell in each time slice, it uses a comprehensive risk function. Calculate the comprehensive navigation risk value, construct a dynamic risk field that varies with time and space, and based on the dynamic risk field, establish a multi-objective cost function that includes distance, risk and timeliness;

[0041] Constraint Construction Module: Constructs constraints for polar vessel navigation paths, including vessel turning radius constraints, area no-entry constraints, and vessel performance constraints;

[0042] Optimal navigation path solution module: Based on the constraints, the module performs multi-objective optimization on the multi-objective cost function to obtain one or more optimal navigation paths. The optimal navigation path is the path that achieves the best balance in multi-objective optimization while satisfying the constraints.

[0043] Beneficial effects: The present invention has the following advantages: The present invention improves the safety of path planning by quantifying the interaction risks between ships and sea ice, and ensures the actual executability of the planned path by combining multi-dimensional physical constraints; In view of the problem that existing technologies rely on static data and cannot dynamically reflect the risk distribution, the present invention achieves accurate response to complex and ever-changing environments by constructing a spatiotemporal dynamic risk field. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0045] The technical solution of the present invention will be described in detail below with reference to the embodiments and accompanying drawings.

[0046] like Figure 1 As shown, a risk-based polar vessel navigation path planning method includes the following:

[0047] S1. Obtain polar navigation environment data and ship parameters. Environmental data includes sea ice thickness, sea ice concentration, wind speed, and current speed; ship parameters include ship speed and ice resistance rating.

[0048] S2, based on collision risk and the risk of ice trap Constructing a comprehensive risk assessment system for polar vessel navigation .

[0049] Among these, collision risk is calculated based on ship speed, ice resistance level, and environmental data. : (1) (2) (3)

[0050] in, For the first Sea ice-like concentration This indicates the total number of sea ice concentration types. For a given ice tolerance rating R (PC1-PC7), the risk value can be obtained by querying POLARIS. The actual speed of the ship. For reference speed, a value of 5 is generally taken. For sailing time; As a risk index, To introduce the effective risk index after speed is introduced.

[0051] Calculate the risk of ice stagnation based on ice concentration, ice thickness, wind speed, and current velocity. : (4)

[0052] (5)

[0053] (6)

[0054] (7)

[0055] in, For ice resistance, This is the ice drag coefficient. For sea ice density, It is the acceleration due to gravity. For the ship's width, Sea ice thickness, in percentage. This refers to the effective power of the host unit. For propeller efficiency, For gearbox efficiency, For propeller efficiency, For minimum sailing speed, The ice-induced sensitivity coefficient. For sailing time; This refers to the ship's icebreaking capability coefficient. For sea ice concentration, This is the hull form factor. In this expression, ice breaking resistance is linearly related to the square of the ship's speed, and also to the sea ice concentration. The power-law relationship is linear. Different ship types have different effects. The values ​​differ: recommendations for FPSOs and offshore vessels are as follows. Take option 3; for other ice-covered vessels, it is recommended to... Take 2.

[0056] Comprehensive Risks : (8)

[0057] in, Indicates the potential damage caused by the collision. This indicates the potential losses caused by ice-related issues; both constitute the total potential losses. Comprehensive risks It reflects the combined effect of collision risk and ice trapping risk in space, and reflects the comprehensive impact of different risks on navigation safety through potential losses.

[0058] S3. Map the comprehensive risk in a gridded manner in the spatial and temporal dimensions: First, discretize the target navigation area and time period into spatial grids and time slices; for each grid unit at its specific location in each time slice, calculate the comprehensive navigation risk value of the unit using formula (8) based on the corresponding environmental parameters such as sea ice concentration and sea ice thickness; construct a dynamic risk field that changes with time and space based on the risk values ​​of all network units at different times; and construct a multi-objective cost function based on this dynamic risk field: (9)

[0059] in, Representing path points and The distance between them; Representing path points exist The comprehensive risk value at a given time is calculated using Formula 8. Indicates at the waypoint Ship speed at the location; , and These are the weighting coefficients; Indicates the total number of path points. Indicates the ordinal index of the path point.

[0060] S4. Construct constraints for polar vessel navigation paths, including vessel turning radius constraints, area no-entry constraints, and vessel performance constraints.

[0061] Ship turning radius constraint: To ensure sufficient maneuverability when navigating in ice-covered areas, the path must meet the minimum turning radius requirement. This constraint is calculated by taking three consecutive path points. , , The radius of the arc formed and the minimum turning radius of the ship in the current ice-water mixed environment. Comparison implementation: (10)

[0062] We obtain the following by solving formulas (11)-(12): (11) (12)

[0063] in, path point , , The radius of the arc formed For line segments and The included angle, Indicates the distance between two points; The channel protection coefficient. For ship speed, For the length between the ship's perpendiculars, For the ship's draft, This represents the actual water depth at present. This is the ice drag coefficient. For sea ice concentration, This refers to the thickness of the sea ice.

[0064] Region no-entry constraint: Suppose that for a sequence of path points Define function Representing path points Is it in the restricted area? Within, the restricted area includes areas with dense icebergs, ecological protection zones, etc.; the collection of restricted areas can be written as... , To represent the total number of restricted areas, the constraint condition is written as: (13)

[0065] Ship performance constraints: the ship's speed at various points along its navigation path. The maximum safe speed shall not be exceeded based on the sea ice conditions at that point. Constraints can be written as: (14)

[0066] in, The solution obtained by formula (15) is as follows: (15)

[0067] in, This refers to sea ice concentration.

[0068] S5. Based on the constraints, the multi-objective cost function is solved using a non-dominated sorting genetic algorithm (NSGA-II). The implementation process includes:

[0069] Population Encoding and Initialization: A candidate navigation path from the starting point to the ending point is encoded as an individual, which consists of a series of ordered waypoints, represented as... .in, The coordinates of the path points, The estimated time of arrival for the vessel at this point is used to correlate dynamically changing environmental data; starting point and the finish line Fixed. During initialization, within the safe navigation area between the start and end points, path points are generated through hierarchical random sampling. Path connectivity, B-spline smoothing, and timestamp allocation techniques are then used to construct... Each initial path is generated and then constrained and repaired to ensure that it meets the turning radius constraint (Equation 10), the area no-entry constraint (Equation 13), and the ship performance constraint (Equation 14), thereby ensuring that all individuals in the initial population are feasible solutions.

[0070] Fitness assessment and constraint handling: for each individual in the population (i.e., each path). Calculate the fitness vector .

[0071] Total sailing distance It is obtained by summing the Euclidean distances between all adjacent points in the path, i.e. Cumulative comprehensive risk Based on formula (8), the comprehensive risk value is calculated by summing the risk values ​​experienced by the vessel at each point along the entire route. Estimated sailing time : Calculated based on the ship's safe speed in each segment of the journey, i.e. Among them, speed Performance constraints must be met.

[0072] Fast non-dominated sorting and crowding calculation: Individuals in the population are sorted non-dominatedly according to their fitness vectors and divided into different non-dominated levels (Front), where the first level (Front 1) is the Pareto optimal solution set; within the same non-dominated level, the crowding of each individual is calculated to measure its distribution density in the target space.

[0073] Selection, crossover, and mutation: A binary tournament selection is performed based on the non-dominated hierarchy and crowding, prioritizing individuals with better hierarchy (smaller numbers) or greater crowding; crossover operations (such as simulated binary crossover) and mutation operations (such as polynomial mutation) are performed on the selected individuals to generate a new offspring population;

[0074] Elite Preservation and Iterative Evolution: The parent and offspring populations are merged, and steps such as non-dominated sorting, crowding calculation, and selection are repeatedly performed to preserve elite individuals and form a new generation of populations; this evolutionary process is iteratively executed until the preset termination condition is met.

[0075] Optimal path output: After the algorithm terminates, one or more solutions are selected from the first non-dominated layer (Pareto front) of the final population based on actual needs or user-defined preferences (such as risk thresholds and time requirements). After decoding, the optimal navigation path is output or multiple Pareto optimal paths are provided for decision-making reference.

Claims

1. A risk-based polar vessel navigation path planning method, characterized in that, Includes the following steps: S1. Acquire polar navigation environment data and ship parameters; S2. Calculate the collision risk based on the environmental data and ship parameters. and the risk of ice trap To further construct a comprehensive risk function for polar vessel navigation ; S3. Discretize the target navigation area and time period into spatial grids and time slices. For the specific location of each grid cell in each time slice, use a comprehensive risk function. Calculate the comprehensive navigation risk value, construct a dynamic risk field that varies with time and space, and based on the dynamic risk field, establish a multi-objective cost function that includes distance, risk and timeliness; S4. Construct constraints for polar vessel navigation paths, including vessel turning radius constraints, area no-entry constraints, and vessel performance constraints; S5. Based on the constraints, perform multi-objective optimization on the multi-objective cost function to obtain one or more optimal navigation paths. The optimal navigation path is the path that achieves the best balance in multi-objective optimization under the constraints.

2. The risk-based polar vessel navigation path planning method according to claim 1, characterized in that, The environmental data includes sea ice thickness, sea ice concentration, wind speed, and current speed; the ship parameters include ship speed and ice resistance rating.

3. The risk-based polar vessel navigation path planning method according to claim 1, characterized in that, The comprehensive risk function Represented as: ， In the formula, Indicates the potential damage caused by the collision. This indicates the potential losses caused by ice.

4. The risk-based polar vessel navigation path planning method according to claim 2, characterized in that, The collision risk Represented as: ， ， ， In the formula, For the first Sea ice-like concentration This indicates the total number of sea ice concentration types. For a given ice resistance rating R, The actual speed of the ship. For reference speed, For sailing time; As a risk index, To introduce the effective risk index after speed is introduced.

5. The risk-based polar vessel navigation path planning method according to claim 2, characterized in that, The risk of ice trap Represented as: ， ， ， ， In the formula, For ice resistance, This is the ice drag coefficient. For sea ice density, It is the acceleration due to gravity. For the ship's width, Sea ice thickness, in percentage. This refers to the effective power of the host unit. For propeller efficiency, For gearbox efficiency, For propeller efficiency, For minimum sailing speed, The ice-induced sensitivity coefficient. For sailing time; This refers to the ship's icebreaking capability coefficient. For sea ice concentration, This is the ship type coefficient.

6. The risk-based polar vessel navigation path planning method according to claim 1, characterized in that, The multi-objective cost function is expressed as: ， In the formula, Representing path points and The distance between them; Representing path points exist The overall risk value at any given time; Indicates at the waypoint Ship speed at the location; , and These are the weighting coefficients; Indicates the total number of path points. Indicates the ordinal index of the path point.

7. The risk-based polar vessel navigation path planning method according to claim 1, characterized in that, The ship turning radius constraint is calculated by taking three consecutive path points. , , The radius of the arc formed and the minimum turning radius of the ship in the current ice-water mixed environment. The comparison and the constraints are expressed as follows: ; in, , ， In the formula, For line segments and The included angle, Indicates the distance between two points; The channel protection coefficient. For ship speed, For the length between the ship's perpendiculars, For the ship's draft, This represents the actual water depth at present. This is the ice drag coefficient. For sea ice concentration, Sea ice thickness; The region prohibition constraint: Assume that for a path point sequence... Define function Representing path points Is it in the restricted area? Within, the restricted area includes areas with dense icebergs, ecological protection zones, etc.; the collection of restricted areas can be written as... , This represents the total number of restricted areas, and the constraint is expressed as follows: ; The ship performance constraint: the ship's speed at various points along the navigation path. The maximum safe speed shall not be exceeded based on the sea ice conditions at that point. The constraints are expressed as follows: ; in, , This refers to sea ice concentration.

8. The risk-based polar vessel navigation path planning method according to claim 1, characterized in that, The multi-objective cost function is optimized using a non-dominated sorting genetic algorithm, including: initializing and verifying constraints of the constructed population individuals containing path coordinates and timestamps; calculating fitness vectors containing travel distance, cumulative comprehensive risk, and travel time; performing non-dominated sorting, crowding calculation, selection, crossover, mutation operations, and elite retention strategies based on the fitness vectors of the population individuals for iterative evolution until the termination condition is met; and finally selecting and outputting the optimal travel path from the Pareto front of the final population based on preferences.

9. The risk-based polar vessel navigation path planning method according to claim 8, characterized in that, The population individuals are represented as , in, The coordinates of the path points, The estimated time for the ship to arrive at this point, starting point and the finish line fixed; The fitness vector of an individual in the population is represented as Of which, total sailing distance The cumulative comprehensive risk is obtained by summing the Euclidean distances between all adjacent points in the path. The estimated sailing time is calculated by summing up the comprehensive risk values ​​experienced by the vessel at each waypoint along the entire route. It is calculated based on the ship's safe speed in each section of the voyage.

10. A risk-based polar vessel navigation path planning system, characterized in that, Includes the following modules: Data collection module: used to acquire polar navigation environment data and ship parameters; Integrated risk solution module: Calculates collision risk based on the environmental data and ship parameters. and the risk of ice trap To further construct a comprehensive risk function for polar vessel navigation ; Multi-objective cost function construction module: Discretizes the target navigation area and time period into spatial grids and time slices. For the specific location of each grid cell in each time slice, it uses a comprehensive risk function. Calculate the comprehensive navigation risk value, construct a dynamic risk field that varies with time and space, and based on the dynamic risk field, establish a multi-objective cost function that includes distance, risk and timeliness; Constraint Construction Module: Constructs constraints for polar vessel navigation paths, including vessel turning radius constraints, area no-entry constraints, and vessel performance constraints; Optimal navigation path solution module: Based on the constraints, the module performs multi-objective optimization on the multi-objective cost function to obtain one or more optimal navigation paths. The optimal navigation path is the path that achieves the best balance in multi-objective optimization while satisfying the constraints.

Images