A Ship Collision Avoidance Decision-Making Method and System Based on Arithmetic Optics Algorithms

Abstract

This invention relates to a collision avoidance decision-making method for ships based on arithmetic optical algorithms, comprising the following steps: Step S1: Acquire navigation data of the ship and the target ship, and determine whether the ship is the one to avoid collisions; if so, proceed to the next step; Step S2: Search for the optimal velocity angle and recovery time based on the arithmetic optical optimization algorithm to obtain a speed change scheme; Step S3: Control the ship to perform collision avoidance control according to the obtained speed change scheme. This invention can quickly obtain collision avoidance decision schemes, assist in collision avoidance, and improve the reliability of ship navigation.

Description

Technical Field

[0001] This invention relates to the field of ship collision avoidance, and specifically to a ship variable speed collision avoidance decision-making method and system based on arithmetic optical algorithms. Background Technology

[0002] Collision avoidance decision-making has always been a hot and challenging issue in the field of navigation safety, closely related to many factors such as the ship's own conditions, the navigation environment, and the crew's skills. Ship collision avoidance technology has evolved from geometric methods and radar to "expert systems" and finally to "intelligent collision avoidance." Initially, collision avoidance primarily employed geometric calculation methods, assessing the collision risk by calculating the nearest encounter distance and the time to reach it between ships. When a collision risk arises during navigation, the ship's navigator typically employs steering maneuvers as a course of action. The navigator determines the steering strategy based primarily on their own experience and skills, including the timing and magnitude of the turn. Shipborne radar and AIS equipment provide crucial support for collision avoidance actions. While these auxiliary devices can improve the safety and efficiency of collision avoidance decision-making, a fully mature collision avoidance system has not yet been developed, and ultimately, the crew must make the collision avoidance decision themselves. Summary of the Invention

[0003] In view of this, the purpose of this invention is to provide a ship speed-changing collision avoidance decision-making method based on arithmetic optical algorithms, in order to solve the above-mentioned problems.

[0004] To achieve the above objectives, the present invention adopts the following technical solution:

[0005] A collision avoidance decision-making method for ships with variable speeds based on arithmetic optics algorithms includes the following steps:

[0006] Step S1: Obtain navigation data of the current vessel and the target vessel, and determine whether the current vessel is a vessel that needs to avoid the target vessel; if so, proceed to the next step.

[0007] Step S2: Search for the optimal velocity angle and recovery time based on the arithmetic optics optimization algorithm to obtain the speed change scheme;

[0008] Step S3: Based on the obtained speed change scheme, control the ship to perform avoidance control.

[0009] Furthermore, step S2 specifically includes:

[0010] (1): Randomly initialize the population, let x1 represent the new speed, and x2 represent the time from the start of collision avoidance to the recovery of the original speed;

[0011] (2): Let the number of iterations n = 1

[0012] (3): Calculate fitness and find the optimal solution;

[0013] (4): Update MOA

[0014]

[0015] Where n is the current iteration number; T is the maximum number of iterations; Max and Min represent the maximum and minimum values ​​of the corresponding function values ​​of MOA, respectively;

[0016] (5): Update MOP

[0017]

[0018] (6): Generate random numbers r1, r2, r3, r4, r5, all of which are random numbers uniformly distributed between [0, 1]. If r1 > MOA, then perform individual exploration, calculated as follows:

[0019]

[0020] in, It is the i-th solution in the j-th dimension; ∈ is the smallest constant to prevent the denominator from being zero; UB j and LB j represents the upper and lower bounds of the optimal value in the j-th dimension, respectively; μ is a control parameter used to adjust the exploration process.

[0021] If r1 < MOA, then individual exploration is performed, and the calculation formula is as follows:

[0022]

[0023] (7): If r4 > 0.5, then update the individual position according to the principle of simulating convex lens imaging:

[0024]

[0025] (8): If r5>0.1, then the principle of double-slit interference is simulated, and the individual position is updated according to formula (12).

[0026] The condition for the appearance of bright and dark fringes in double-slit interference is that the distance difference satisfies the following:

[0027]

[0028] Where D is the distance from the double slits to the imaging plane, d is the distance between the double slits, and λ is the wavelength.

[0029] (9): n = n + 1. If n has not reached the maximum number of iterations, go to (3).

[0030] (10): Output the best solution representing the best collision avoidance scheme, adjust the speed to x1, and the time to restore the original speed after x2 time.

[0031] Furthermore, the fitness is calculated as follows:

[0032]

[0033] Where x1 represents the new velocity, x2 is the recovery time, and w1, w2, w3, and w4 are the weights of each sub-objective.

[0034] Furthermore, the selection of f needs to satisfy the following formula:

[0035]

[0036]

[0037] A ship collision avoidance decision system based on arithmetic optical algorithms includes a processor, a memory, and a computer program stored in the memory. When the processor executes the computer program, it specifically performs the steps in the ship collision avoidance decision method based on arithmetic optical algorithms as described above.

[0038] Compared with the prior art, the present invention has the following advantages:

[0039] This invention can quickly obtain collision avoidance decision-making schemes, assist in collision avoidance, and improve the reliability of ship navigation. Attached Figure Description

[0040] Figure 1 These are the accompanying drawings of the abstract of this invention;

[0041] Figure 2 This is a schematic diagram of double-slit interference in one embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of cross-collision avoidance in one embodiment of the present invention;

[0043] Figure 4 This is a schematic diagram of a collision avoidance maneuver in one embodiment of the present invention;

[0044] Figure 5 This is a schematic diagram of collision avoidance in one embodiment of the present invention;

[0045] Figures 6-11 This is a convergence graph of the optimization algorithm search in one embodiment of the present invention. Detailed Implementation

[0046] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0047] Please refer to Figure 1This invention provides a collision avoidance decision-making method for ships with variable speed based on arithmetic optics algorithms, comprising the following steps:

[0048] Step S1: Obtain navigation data of the current vessel and the target vessel, and determine whether the current vessel is a vessel that needs to avoid the target vessel; if so, proceed to the next step.

[0049] Step S2: Search for the optimal velocity angle and recovery time based on the arithmetic optics optimization algorithm to obtain the speed change scheme;

[0050] Step S3: Based on the obtained speed change scheme, control the ship to perform avoidance control.

[0051] In this embodiment, step S2 specifically includes:

[0052] (1): Randomly initialize the population, let x1 represent the new speed, and x2 represent the time from the start of collision avoidance to the recovery of the original speed;

[0053] (2): Let the number of iterations n = 1

[0054] (3): Calculate fitness and find the optimal solution. The fitness calculation formula is as follows:

[0055]

[0056] Where x1 represents the new velocity, x2 is the recovery time, and w1, w2, w3, and w4 are the weights of each sub-objective.

[0057] (4): Update MOA

[0058]

[0059] Where n is the current iteration number; T is the maximum number of iterations; Max and Min represent the maximum and minimum values ​​of the corresponding function values ​​of MOA, respectively; r1 is a random number uniformly distributed between [0, 1]. When r1 is greater than MOA, the exploration phase is performed. When r1 is less than or equal to MOA, the development phase is performed. In the original algorithm optimization algorithm, MOA determines the phase selection in the algorithm optimization process. The larger the MOA, the stronger the local search capability of the algorithm. The smaller the MOA, the stronger the global search capability of the algorithm. The linear increase of MOA described in the previous formula means that the local search capability of the algorithm decreases linearly.

[0060] (5): Update MOP. The mathematical optimizer probability (MOP) is a coefficient.

[0061]

[0062] (6): Generate random numbers r1, r2, r3, r4, r5, all of which are random numbers uniformly distributed between [0, 1]. If r1 > MOA, then perform individual exploration, calculated as follows:

[0063]

[0064] in, It is the i-th solution in the j-th dimension; ∈ is the smallest constant to prevent the denominator from being zero; UB j and LB j represents the upper and lower bounds of the optimal value in the j-th dimension, respectively; μ is a control parameter used to adjust the exploration process.

[0065] If r1 < MOA, then individual exploration is performed, and the calculation formula is as follows:

[0066]

[0067] (7): If r4 > 0.5, then update the individual position according to the principle of simulating convex lens imaging:

[0068]

[0069] To ensure To satisfy the original range constraints, the choice of f must satisfy the following formula:

[0070]

[0071] (8): If r5>0.1, then the principle of double-slit interference is simulated, and the individual position is updated according to formula (12).

[0072] The condition for the appearance of bright and dark fringes in double-slit interference is that the distance difference satisfies the following:

[0073]

[0074] Where D is the distance from the double slits to the imaging plane, d is the distance between the double slits, and λ is the wavelength.

[0075] (9): n = n + 1. If n has not reached the maximum number of iterations, go to (3).

[0076] (10): Output the best solution representing the best collision avoidance scheme, adjust the speed to x1, and the time to restore the original speed after x2 time.

[0077] The above description is only a preferred embodiment of the present invention. All equivalent changes and modifications made within the scope of the claims of the present invention should be included in the scope of the present invention.

Claims

1. A method for ship speed-changing collision avoidance decision based on arithmetic optical algorithm, characterized in that, The method comprises the following steps: Step S1: obtaining the sailing data of the target ship and the own ship, and determining whether the own ship is an avoiding ship; if yes, the next step is performed; Step S2: searching for an optimal speed angle and a recovery time based on an arithmetic-optical optimization algorithm to obtain a speed-changing scheme; Step S3: controlling the own ship to perform avoidance control according to the obtained speed-changing scheme; The step S2 specifically comprises: (1) randomly initializing a population, wherein x1 represents a new speed, and x2 represents a time from the start of collision avoidance to the recovery of the original speed; (2) setting an iteration number n = 1; (3) calculating an adaptability and finding a best solution; (4) updating MOA wherein n is a current iteration number; T is a maximum iteration number; Max and Min represent a maximum value and a minimum value of the MOA, respectively; (5) updating MOP (6) generating random numbers r1, r2, r3, r4 and r5, which are uniformly distributed between 0 and 1; if r1> MOA, individual exploration is performed, and a calculation formula is as follows: wherein, is the ith solution in the jth dimension; ∈ is the minimum constant to prevent the denominator from being zero; UB j and LB j denote the upper and lower bounds of the optimal value in the jth dimension, respectively; μ is a control parameter used to adjust the exploration process; if r1< MOA, individual exploration is performed, and a calculation formula is as follows: (7) if r4> 0.5, the position of the individual is updated according to the principle of simulated convex lens imaging: (8) if r5> 0.1, the position of the individual is updated according to the principle of simulated double-slit interference according to formula (12); The conditions for the appearance of bright fringes and dark fringes in double-slit interference are that the distance difference satisfies: wherein D is a distance from the double slit to an imaging plane; d is a distance between the double slits; and λ is a wavelength; (9) n = n + 1, and if the maximum iteration number is not reached, the step (3) is performed; (10) outputting a best solution representing a best collision avoidance scheme, adjusting the speed to x1, and recovering the original speed after x2 time.

2. The ship speed-changing collision avoidance decision method based on the arithmetic optical algorithm according to claim 1, characterized in that, The adaptability is calculated as follows wherein x1 represents a new speed, and x2 is a recovery time; w1, w2, w3 and w4 are weights of each sub-target.

3. The ship speed-changing collision avoidance decision method based on the arithmetic optical algorithm according to claim 1, characterized in that, The selection of f needs to satisfy the following formula:

4. A ship variable speed collision avoidance decision system based on an arithmetic optical algorithm, characterized in that, The computer program comprises a processor, a memory and a computer program stored on the memory, and the processor executes the computer program to specifically perform the steps in the ship speed-changing collision avoidance decision method based on the arithmetic-optical algorithm according to any one of claims 1-3.

Images