Ship ballast water adjusting method and system based on simulated annealing algorithm

Abstract

The application discloses a ship ballast water adjusting method and system based on a simulated annealing algorithm, and comprises the following steps: obtaining ship ballast tank information and the state of current ballast water, and constructing a target function according to the ballast tank information and the state of current ballast water; establishing a ballast water constraint condition for the target function; solving the target function according to the ballast water constraint condition by using the simulated annealing algorithm until an optimal solution is obtained, wherein the optimal solution is a ballast water adjusting scheme; and adjusting the current ballast water according to the ballast water adjusting scheme. The application simulates the ballast water of a ship by using the simulated annealing algorithm, utilizes the random search characteristic of the annealing algorithm, realizes the global optimization of ballast water allocation, improves the calculation efficiency of the ballast water adjusting scheme of the ship, and can adapt to different complex conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of ballast water calculation, and in particular to a ship ballast water regulation method and system based on a simulated annealing algorithm. Background Art

[0002] Ballast water allocation plays a vital role in a ship's navigation. Ballast water is used to adjust the ship's center of gravity, draft, and stability, ensuring it remains stable and safe under varying loads and sea conditions. Traditional ballast water allocation methods typically rely on manual calculations or pre-set rules. Crew members manually adjust the water volume in each ballast tank based on the ship's real-time status to control the ship's draft and stability. However, traditional manual ballast water allocation methods have significant drawbacks such as low efficiency, high computational burden, and insufficient accuracy when addressing complex operational requirements.

[0003] To overcome the shortcomings of traditional ballast water allocation methods, ballast water allocation technology has gradually developed towards automation and intelligence in recent years. For example, some ships are equipped with automatic ballast water allocation systems, which use computers and control systems to precisely control the water volume in each ballast tank. These improvements have improved the efficiency and accuracy of ballast water allocation to a certain extent, but the following limitations still exist: First, some automatic ballast water allocation systems rely on traditional optimization methods such as graph theory and moment balance to distribute water. Although effective, these methods are computationally complex, especially in multi-compartment or multi-objective optimization scenarios. The solution speed is slow and it is difficult to respond to the dynamic changes of the ship in real time. Second, many optimization methods are prone to falling into local optimal solutions during the solution process, resulting in the allocation solution failing to reach the global optimal solution. Consequently, the allocation of ballast water cannot be minimized, resulting in water waste and affecting the ship's stability and fuel efficiency. In addition, existing ballast water allocation methods often rely on preset algorithms and rules and lack the ability to adapt to the ship's real-time operating status and external environment. This makes the allocation process inflexible and unable to cope with complex and changing sea conditions and operating conditions. These limitations mean that there is still much room for improvement in the adaptability and computational efficiency of existing automatic allocation systems under complex conditions.

[0004] Therefore, there is a need for a method that can efficiently and accurately perform optimal ballast water allocation under complex sea conditions. Summary of the Invention

[0005] To solve the above problems, the present invention provides a ship ballast water regulation method and system based on a simulated annealing algorithm. The simulated annealing algorithm is used to optimize the calculation of ship ballast water, thereby solving the problems of low adaptability and computational efficiency of the existing ballast water allocation system and its easy fall into local optimal solutions.

[0006] To achieve the above object, the present invention provides the following technical solution: a ship ballast water regulation method based on a simulated annealing algorithm, comprising the following steps:

[0007] S1. Obtain the ship's ballast tank information and the current ballast water status, and construct an objective function based on the ballast tank information and the current ballast water status;

[0008] S2. Establish ballast water constraints for the objective function;

[0009] S3. Using a simulated annealing algorithm, solve the objective function according to the ballast water constraints until an optimal solution is obtained, which is the ballast water regulation solution;

[0010] S4. Adjust the current ballast water according to the ballast water adjustment plan.

[0011] Furthermore, in step S1, the ship ballast tank information includes the number of ballast tanks n, the maximum capacity of each ballast tank The current ballast water status includes the initial water volume in each ballast tank .

[0012] Furthermore, in step S1, the specific formula of the objective function is:

[0013]

[0014] in, represents the amount of water transferred from ballast tank i to ballast tank j, Represents the water transfer matrix between ballast tanks.

[0015] Furthermore, in step S2, the ballast water constraint conditions include: the final water volume of each ballast tank after allocation is equal to the initial water volume plus the transferred-in water volume minus the transferred-out water volume; the final water volume of each ballast tank does not exceed the maximum capacity of the compartment, nor is it less than 0; the total amount of ballast water in all ballast tanks remains unchanged.

[0016] Furthermore, the specific formula of the ballast water constraint condition is:

[0017]

[0018] in, represents the initial water volume of the jth ballast tank, represents the amount of water transferred from ballast tank i to ballast tank j;

[0019]

[0020] in, represents the current water volume of the j-th ballast tank, represents the maximum capacity of the jth ballast tank;

[0021]

[0022] represents the amount of water in the jth ballast tank, represents the initial water volume of the jth ballast tank.

[0023] Furthermore, the ballast water constraint condition also includes: heel angle constraint and pitch angle constraint. The specific formula of heel angle constraint is:

[0024]

[0025] The specific formula for the pitch angle constraint is:

[0026]

[0027] in, Respectively represent the cabin The vertical and horizontal positions, is the lateral metacentric height, is the hull length, represents the maximum allowable heel angle, Indicates the maximum allowable heel angle.

[0028] Furthermore, in step S3, the annealing algorithm is used to solve the objective function according to the ballast water constraint condition, and the specific implementation method is as follows: S31. Randomly generate a water transfer matrix between ballast tanks , the water transfer matrix Satisfy the ballast water constraints, preset the initial temperature T and cooling rate α;

[0029] S32 randomly selects two ballast tanks to transfer water randomly, performs a cooling according to the cooling rate, and obtains a new ballast water distribution plan , Compare to the ballast water constraints and The loss between The loss is less than When As a new ,when The loss is greater than When the probability As a new ;

[0030] S33. Repeat step S32 until the temperature is lower than the preset threshold, or the ballast water distribution plan If the number of times remains unchanged for more than the preset number, the calculation ends and the current ballast water distribution plan is This is the optimal ballast water result.

[0031] Furthermore, in step S32, the comparison and The specific implementation method includes: calculating The objective function value of , and the current ballast water allocation scheme The objective function value of For comparison, when > When The loss is less than .

[0032] Further, in step S32, the probability As a new , and its specific implementation method is: The calculation formula of probability P is:

[0033]

[0034] in, ;

[0035] Generate a random number n in the range of 0-1. When the random number n is greater than the probability P, As a new , when the random number n is less than the probability P, the ballast water allocation scheme remains unchanged.

[0036] Through the above technical solution, the present invention has the following beneficial effects: the ship's ballast water is tuned and simulated by a simulated annealing algorithm, and the random search characteristics of the annealing algorithm are utilized to achieve global optimization of ballast water allocation, and the computational efficiency of the ship's ballast water adjustment scheme is improved, and it can adapt to different complex conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The figure is a schematic diagram of the overall flow of a ship ballast water regulation method based on a simulated annealing algorithm according to the present invention.

[0038] Figure 2 Schematic diagram comparing the changes before and after optimization and adjustment of ship ballast water in an embodiment of the present invention.

[0039] Figure 3 Schematic diagram of the iteration of the simulated annealing algorithm in an embodiment of the present invention.

[0040] Figure 4 The figure is a structural schematic diagram of a ship ballast water regulation system based on a simulated annealing algorithm in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0042] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] Example 1

[0044] See also Figure 1 A ship ballast water regulation method based on a simulated annealing algorithm comprises the following steps:

[0045] S1. Obtain the ship's ballast tank information and the current ballast water status, and construct an objective function based on the ballast tank information and the current ballast water status;

[0046] S2. Establish ballast water constraints for the objective function;

[0047] S3. Using a simulated annealing algorithm, solve the objective function according to the ballast water constraints until an optimal solution is obtained, which is the ballast water regulation solution;

[0048] S4. Adjust the current ballast water according to the ballast water adjustment plan.

[0049] This invention solves the problem of ship ballast water allocation through mathematical modeling and intelligent optimization algorithms, focusing on addressing the computational complexity and slow response inherent in traditional ballast water allocation. First, a mathematical model for ballast water allocation is established based on the water allocation requirements of each ship's ballast tanks. This model transforms the water allocation process into an optimization problem, aiming to ensure ship stability by minimizing the amount of water transferred. The model is then solved using a simulated annealing algorithm. This algorithm avoids local optimal solutions through a global search, enabling rapid identification of the optimal ballast water allocation solution that meets the requirements.

[0050] like Figure 3 As shown, after optimization and adjustment, the heel angle and the pitch angle are greatly reduced, and the adjustment range of the water volume in the ship's ballast tank is small, which can effectively realize the adjustment of the water volume in the ship's ballast tank.

[0051] In an optional embodiment, in step S1, the ship ballast tank information includes the number of ballast tanks n, the maximum capacity of each ballast tank The current ballast water status includes the initial water volume in each ballast tank .

[0052] In an optional embodiment, in step S1, the specific formula of the objective function is:

[0053]

[0054] in, represents the amount of water transferred from ballast tank i to ballast tank j, Represents the water transfer matrix between ballast tanks.

[0055] The purpose of the objective function is to minimize the amount of water transferred between all ballast tanks and, through subsequent constraints, ensure that the ship's attitude is stable and does not tilt to a certain point.

[0056] In step S2, the ballast water constraints include: the final water volume of each ballast tank after allocation is equal to the initial water volume plus the transferred-in water volume minus the transferred-out water volume; the final water volume of each ballast tank does not exceed the maximum capacity of the tank and is not less than 0; the total amount of ballast water in all ballast tanks remains unchanged.

[0057] The specific formula of the ballast water constraint condition is:

[0058]

[0059] in, represents the initial water volume of the jth ballast tank, Represents the amount of water transferred from ballast tank i to ballast tank j; by limiting the balance of water in and out of the ballast tank, the water balance in each compartment is ensured.

[0060]

[0061] in, represents the current water volume of the j-th ballast tank, represents the maximum capacity of the jth ballast tank;

[0062]

[0063] represents the amount of water in the jth ballast tank, represents the initial water volume of the jth ballast tank.

[0064] In order to maintain the stability of the ship, the ship's heel angle and pitch angle must be controlled within an acceptable range. The ballast water constraint conditions also include: heel angle constraint and pitch angle constraint. The specific formula for the heel angle constraint is:

[0065]

[0066] The specific formula for the pitch angle constraint is:

[0067]

[0068] in, Respectively represent the cabin The vertical and horizontal positions, is the lateral metacentric height, is the hull length, represents the maximum allowable heel angle, Indicates the maximum allowable heel angle.

[0069] Through the above modeling, the ballast water allocation problem is transformed into a mathematical optimization problem to solve the optimal ballast water allocation plan. The focus of solving this model is how to minimize the water transfer amount while meeting all constraints.

[0070] In an optional embodiment, in step S3, the annealing algorithm is used to solve the objective function according to the ballast water constraint condition, and the specific implementation method is as follows: S31. Randomly generate a water transfer matrix between ballast tanks , the water transfer matrix To meet the ballast water constraint conditions, the initial temperature T and cooling rate α are preset. The initial temperature is generally selected to be as large as possible to ensure that the algorithm has enough iterations to escape the local optimal solution, and the cooling rate is selected to be 0.95.

[0071] S32 randomly selects two ballast tanks to transfer water randomly, and according to the cooling rate Perform a cooling operation to obtain a new ballast water distribution plan , Compare to the ballast water constraints and The loss between The loss is less than When As a new ,when The loss is greater than When the probability As a new ;

[0072] S33. Repeat step S32 until the temperature is lower than the preset threshold, or the ballast water distribution plan If the number of times remains unchanged for more than the preset number, the calculation ends and the current ballast water distribution plan is This is the optimal ballast water result.

[0073] The annealing algorithm is a random search and optimization algorithm that introduces randomness and temperature parameters by simulating the solid annealing process. In addition, the annealing algorithm allows the acceptance of inferior solutions by introducing probability, thereby improving the flexibility of the algorithm and avoiding falling into the local optimal solution.

[0074] In an optional embodiment, in step S32, the comparison and The specific implementation method includes: calculating The objective function value of , and the current ballast water allocation scheme The objective function value of For comparison, when > When The loss is less than .

[0075] The algorithm loss is determined by the objective function value. Since the purpose of the present invention is to minimize the ship ballast water adjustment amount, the objective function value of the new scheme is compared with the original scheme. When the function value of the new scheme is smaller than that of the original scheme, it means that the new scheme has smaller loss and is closer to the optimal solution.

[0076] In an optional embodiment, in step S32, the probability of As a new , and its specific implementation method is: The calculation formula of probability P is:

[0077]

[0078] in, ;

[0079] Generate a random number n in the range of 0-1. When the random number n is greater than the probability P, As a new , when the random number n is less than the probability P, the ballast water allocation scheme remains unchanged.

[0080] This method probabilistically decides whether to accept a randomly generated solution of lower quality. This allows the algorithm to escape existing local optima and flexibly select random solutions within the search space to find the global optimal solution. The simulated annealing algorithm effectively avoids local minima and ultimately approaches the global optimal solution by imbuing the search process with a time-varying probability that eventually approaches zero. Furthermore, as the temperature decreases, the probability of receiving a solution of lower quality decreases, ensuring the algorithm's computational efficiency.

[0081] like Figure 3As shown in the figure, according to the above rules and formulas, a complete annealing algorithm is performed with temperature and objective function iteration diagram.

[0082] Example 2

[0083] See also Figure 4 , a ship ballast water regulation system based on simulated annealing algorithm, comprising:

[0084] The state acquisition module is used to obtain the ship's ballast tank information and the current ballast water status, and construct an objective function based on the ballast tank information and the current ballast water status;

[0085] Constraint building module, used to establish ballast water constraints on the objective function;

[0086] An annealing simulation module is used to solve the objective function according to the ballast water constraint conditions using a simulated annealing algorithm until an optimal solution is obtained, which is the ballast water regulation solution;

[0087] The ballast water adjustment module is used to adjust the current ballast water according to the ballast water adjustment plan.

[0088] The embodiment disclosed in this specification is merely an illustration of one aspect of the present invention. The scope of protection of the present invention is not limited to this embodiment. Any other functionally equivalent embodiments fall within the scope of protection of the present invention. Those skilled in the art can make various other corresponding changes and modifications based on the technical solutions and concepts described above, and all such changes and modifications should fall within the scope of protection of the claims of the present invention.

Claims

1. A ship ballast water regulation method based on simulated annealing algorithm, characterized in that: The following steps are involved: S1. Obtain the ship's ballast tank information and the current ballast water status, the ship's ballast tank information includes the number of ballast tanks n, the maximum capacity of each ballast tank u j The current ballast water state includes the initial water volume v in each ballast tank 0j , where j represents the jth ballast tank, and the objective function is constructed based on the ballast tank information and the current ballast water status; S2. Establish ballast water constraints for the objective function. The specific formula of the objective function is: Among them, V ij represents the amount of water transferred from ballast tank i to ballast tank j, and V represents the water transfer matrix between ballast tanks; The ballast water constraints include: the final water volume of each ballast tank after allocation is equal to the initial water volume plus the amount of water transferred in minus the amount of water transferred out; the final water volume of each ballast tank does not exceed the maximum capacity of the tank and is not less than 0; the total amount of ballast water in all ballast tanks remains unchanged; S3. Solve the objective function based on the ballast water constraints using a simulated annealing algorithm. Specifically, S31. Randomly generate a water transfer matrix V between ballast tanks. The water transfer matrix V satisfies the ballast water constraints and pre-sets the initial temperature T and the cooling rate α. S32 randomly selects two ballast tanks to transfer water randomly, performs a cooling according to the cooling rate, and obtains a new ballast water distribution plan V new , the V new Compare V and V to meet the ballast water constraints. new The loss between new When the loss is less than V, V new As the new V, when V new When the loss is greater than V, V new As the new V; S33. Repeat step S32 until the temperature is lower than the preset threshold, or the ballast water allocation scheme V remains unchanged for more than a preset number of times, and then the calculation is terminated. The current ballast water allocation scheme V is the optimal ballast water result, and the optimal ballast water result is the ballast water adjustment scheme; S4. Adjust the current ballast water according to the ballast water adjustment plan.

2. A ship ballast water regulation method based on simulated annealing algorithm according to claim 1, characterized in that: The specific formula of the ballast water constraint condition is: Among them, v 0j represents the initial water volume of the jth ballast tank, V ij represents the amount of water transferred from ballast tank i to ballast tank j; Among them, v j represents the current water volume of the jth ballast tank, u j represents the maximum capacity of the jth ballast tank; v j represents the amount of water in the jth ballast tank, v 0j represents the initial water volume of the jth ballast tank.

3. A ship ballast water regulation method based on simulated annealing algorithm according to claim 2, characterized in that: The ballast water constraint conditions also include: heel angle constraint and pitch angle constraint. The specific formula for the heel angle constraint is: The specific formula for the pitch angle constraint is: Among them, x i ,y i denote the longitudinal and transverse positions of cabin i, GM tra is the transverse metacentric height, L is the hull length, φ max Indicates the maximum allowable heel angle, θ max Indicates the maximum allowable heel angle.

4. A ship ballast water regulation method based on simulated annealing algorithm according to claim 3, characterized in that: In step S32, V and V are compared. new The specific implementation method includes: calculating V new The objective function value q(V new ), compared with the objective function value q(V) of the current ballast water allocation scheme V, when q(V new )>q(V), that is, V new The loss is less than V.

5. A ship ballast water regulation method based on simulated annealing algorithm according to claim 4, characterized in that: In step S32, the probability of V new As the new V, its specific implementation method is: the calculation formula of probability P is: Where Δq=q(V new )-q(V); Generate a random number n in the range of 0-1. When the random number n is greater than the probability P, V new As the new V, when the random number n is less than the probability P, the ballast water allocation scheme remains unchanged.

6. A ship ballast water regulation system based on simulated annealing algorithm, characterized in that: include: The status acquisition module is used to obtain the ship's ballast tank information and the current ballast water status. The ship ballast tank information includes the number of ballast tanks n, the maximum capacity of each ballast tank u j The current ballast water state includes the initial water volume v in each ballast tank 0j , where j represents the jth ballast tank, and the objective function is constructed based on the ballast tank information and the current ballast water status; The constraint building module is used to establish ballast water constraint conditions for the objective function. The specific formula of the objective function is: Among them, V ij represents the amount of water transferred from ballast tank i to ballast tank j, and V represents the water transfer matrix between ballast tanks; The ballast water constraints include: the final water volume of each ballast tank after allocation is equal to the initial water volume plus the amount of water transferred in minus the amount of water transferred out; the final water volume of each ballast tank does not exceed the maximum capacity of the tank and is not less than 0; the total amount of ballast water in all ballast tanks remains unchanged; The annealing simulation module is used to utilize the simulated annealing algorithm, and its specific implementation method is as follows: S31. Randomly generate a water transfer matrix V between ballast tanks, wherein the water transfer matrix V satisfies the ballast water constraint condition, and presets the initial temperature T and the cooling rate α; S32 randomly selects two ballast tanks to transfer water randomly, performs a cooling according to the cooling rate, and obtains a new ballast water distribution plan V new , the V new Compare V and V to meet the ballast water constraints. new The loss between new When the loss is less than V, V new As the new V, when V new When the loss is greater than V, V new As the new V; S33. Repeat step S32 until the temperature is lower than the preset threshold, or the ballast water allocation scheme V remains unchanged for more than a preset number of times, and then the calculation is terminated. The current ballast water allocation scheme V is the optimal ballast water result, and the optimal ballast water result is the ballast water adjustment scheme; The ballast water adjustment module is used to adjust the current ballast water according to the ballast water adjustment plan.

Images