Ship heuristic search algorithm and system based on multi-objective model
Through the ship heuristic search algorithm based on multi-objective model, comprehensively considering crew safety, evacuation time and evacuation distance, the problem of traditional evacuation planning neglecting safety and path rationality is solved, and efficient evacuation path optimization is achieved in emergency situations .
Patent Information
- Application Number
- CN202411139201.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-08-20
AI Technical Summary
Traditional ship evacuation planning often only considers a single goal, such as evacuation time, which ignores crew safety and rationality of evacuation paths, resulting in limited results in complex emergencies.
Using a ship heuristic search algorithm based on a multi-objective model, we search for the optimal evacuation path in the state space by determining optimization goals, designing heuristic functions and implementing heuristic search algorithms, and comprehensively considering crew safety, evacuation time and evacuation distance. Dynamically update the heuristic value to optimize the evacuation path.
Finding an optimal evacuation path within a limited time improves the efficiency and safety of ship evacuation, and provides a new and efficient evacuation planning method suitable for emergency evacuation of various ships in emergency situations.
Smart Images

Figure CN118658335B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of ship safety, and in particular to a ship heuristic search algorithm and system based on a multi-objective model. Background Art
[0002] With the continuous increase in global shipping volume, the safety and evacuation efficiency of ships have become important issues that the shipping industry needs to solve urgently. At sea, ships face various potential risks, such as fire, pirate attacks, collisions, etc., and timely and effective evacuation of crew members has become a key link in ensuring ship safety. However, traditional ship evacuation planning often only considers a single goal, such as evacuation time, while ignoring the safety of crew members and the rationality of evacuation routes, resulting in limited effectiveness in the face of complex and changing emergencies.
[0003] In order to solve this problem, researchers and ship safety managers have been seeking a new ship evacuation planning method that comprehensively considers multiple optimization objectives. This method needs to be able to find the best evacuation path in a short time to ensure the safety of the crew, while minimizing the evacuation time and distance to ensure the safety and evacuation efficiency of the ship. Summary of the invention
[0004] The present invention aims at the deficiencies in the prior art and proposes a ship heuristic search algorithm and system based on a multi-objective model.
[0005] The present invention provides a ship heuristic search algorithm based on a multi-objective model, comprising the following steps:
[0006] S1. Objective definition: determine the optimization objectives and establish a multi-objective optimization model;
[0007] S2, state space definition: the internal structure of the ship is abstracted into a state space, where each state includes the position and state of the crew in the ship;
[0008] S3, heuristic function design: design a heuristic function to evaluate each state according to the multi-objective optimization model and provide heuristic information for the search process;
[0009] S4, search algorithm implementation: using heuristic search algorithm to search for the optimal evacuation path in the state space;
[0010] S5. Path evaluation and selection: Based on the search results, evaluate the pros and cons of each evacuation path and select the optimal evacuation path to achieve safe and rapid evacuation of the crew.
[0011] Furthermore, the optimization objectives include crew safety, evacuation time and evacuation distance.
[0012] Furthermore, a multi-objective optimization model is constructed based on the objective functions corresponding to crew safety, evacuation time and evacuation distance, which is expressed as: ,in, is the weight coefficient of crew safety, is the weight coefficient of evacuation time, is the weight coefficient of the evacuation distance, and All are positive weights, which are used to adjust the influence of each objective function in the comprehensive goal; Represents crew safety, Represents evacuation time, Represents the evacuation distance.
[0013] Furthermore, S2 specifically includes:
[0014] S21. Define status: define the status inside the ship, including the position of the crew, the action status of the crew, the open and closed status of the cabin, and the environmental conditions inside the ship;
[0015] S22, state space modeling: various states inside the ship are organized into a state space, and the state space is represented in the form of a graph or a network, wherein a node represents a state and an edge represents a transfer relationship between states. The state space modeling is used to describe the state inside the ship and the position distribution of the crew;
[0016] S23. Define state transition rules: According to each state, define the state transition rules, that is, determine the method and conditions from the current state to the next state, and define the state transition rules through the state transition function f. The state transition function f takes the current state C and the action as input and returns the next state C' as output; the state transition function is expressed as: f: C×A→C', where A represents the action space, the elements in A represent the actions that the crew can take, C represents the state space, and C={ , ,……, }, =( , , ), Indicates states, each state It is represented by a vector, which includes the position and action status of the crew. represents the horizontal coordinate position of the crew member, represents the ordinate position of the crew member, Indicates the crew's action status;
[0017] S24, state space initialization: by initializing the state space, determining the initial state, providing a starting point for the search algorithm; the initial state includes the crew's starting position and initial action state;
[0018] S25. Target state definition: define the target state, i.e. the state where the crew successfully escapes to a safe area. This state is a specific location or a specific state.
[0019] Furthermore, the heuristic function evaluates each state according to the multi-objective optimization model and provides heuristic information for the search process, including:
[0020] S31. Objective function conversion: The objective function in the multi-objective optimization model is converted into a heuristic function, that is, the heuristic value is calculated according to the characteristics of each state and the current situation, and the optimal path length from the current state to the target state is estimated according to the heuristic value. The value of each objective function is linearly mapped to a fixed range, that is, [0,1]. The implementation formula is as follows:
[0021]
[0022] Where: represents the value of the objective function, Represents the value after mapping, and Respectively represent the minimum and maximum values of the objective function;
[0023] S32, state assessment: according to each state S, the safety, evacuation time and evacuation distance of the crew in the current state are assessed according to the internal conditions of the ship and the location distribution of the crew;
[0024] S33, heuristic value calculation: According to the state evaluation in S32, the values of each optimization target of the current state are obtained, and the values of each mapped objective function are weighted and summed according to the weight coefficient to obtain the value of the heuristic function. The calculation formula is as follows:
[0025]
[0026] In the formula, Represents the heuristic function value, which reflects the estimated quality of the current state to the target state. The larger the value, the better. The objective function value representing the safety of the crew after mapping, represents the objective function value of the evacuation time after mapping, represents the objective function value of the evacuation distance after mapping; , and The value range of is [0, 1]. The closer the value is to 1, the better the target is. and The closer the value is to 0, the better;
[0027] S34, heuristic value update: During the search process, the heuristic value is dynamically updated according to the changes in the current state.
[0028] Furthermore, in S4, based on the heuristic function, the A* algorithm in the heuristic search algorithm is used to search for the optimal evacuation path in the state space.
[0029] The present invention also provides a ship heuristic search system based on a multi-objective model, comprising:
[0030] Multi-objective optimization model: used to determine and quantify multiple evacuation optimization objectives and transform them into objective functions;
[0031] State space definition module: abstracts the internal structure of the ship into a state space and provides the function of transferring between states.
[0032] Heuristic function design module: designs and implements heuristic functions, evaluates each state according to the multi-objective optimization model, and provides heuristic information;
[0033] Search algorithm implementation module: uses heuristic search algorithm to search for the optimal evacuation path in the state space;
[0034] Path evaluation and selection module: Based on the search results, evaluate the advantages and disadvantages of each evacuation path and select the optimal evacuation path.
[0035] The invention discloses an application of a ship heuristic search algorithm based on a multi-objective model, which is used to improve the efficiency and safety of ship evacuation. The algorithm is applicable to various types of ships, including but not limited to merchant ships, passenger ships, and tankers, and provides reliable technical support in the face of emergencies.
[0036] Compared with the prior art, the present invention has at least the following beneficial effects:
[0037] The algorithm of the present invention can not only comprehensively consider multiple objectives such as crew safety, evacuation time and evacuation distance, but also find a better evacuation path within a limited time through intelligent search strategies. This provides a new and efficient ship evacuation planning method for ship safety managers, which is expected to play an important role in actual ship emergency evacuation. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 A schematic diagram of a flow chart of an embodiment of the present invention;
[0039] Figure 2This is a schematic diagram of the possible state space during the ship evacuation process. In this diagram, the nodes represent different states, and the arrows represent the transition relationship between states.
[0040] Figure 3 The figure is a flowchart of the A* search algorithm. DETAILED DESCRIPTION
[0041] The principles and features of the present invention are described below in conjunction with all the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.
[0042] An embodiment of the present invention provides a ship heuristic search algorithm based on a multi-objective model.
[0043] Reference Figures 1 to 3 , a ship heuristic search algorithm based on a multi-objective model, including the following steps:
[0044] S1. Objective definition: Determine the optimization objectives and establish a multi-objective optimization model.
[0045] Specifically, multiple optimization objectives are first identified, including crew safety, evacuation time, and evacuation distance, etc. In order to quantify these objectives, they are transformed into objective functions, and a multi-objective optimization model is established to comprehensively consider these objectives in the search process.
[0046] Furthermore, S1 specifically includes:
[0047] S11. Objective function definition.
[0048] Specifically, three optimization goals are set, including crew safety, evacuation time and evacuation distance. Crew safety is to ensure that all crew members can be evacuated to the designated safe area as safely as possible; evacuation time is to shorten the time required for all crew members to complete the evacuation as much as possible; evacuation distance is the distance all members need to move during the evacuation process.
[0049] A multi-objective optimization model is constructed based on the objective functions corresponding to crew safety, evacuation time and evacuation distance, which is expressed as: ,in, is the weight coefficient of crew safety, is the weight coefficient of evacuation time, is the weight coefficient of the evacuation distance, and All are positive weights, which are used to adjust the influence of each objective function in the comprehensive goal; Represents crew safety, Represents evacuation time, Represents the evacuation distance.
[0050] S12. Establishment of multi-objective optimization model.
[0051] Specifically, the goal is to find an evacuation route that maximizes crew safety, minimizes evacuation time, and minimizes evacuation distance. To achieve this goal, it is necessary to weigh and balance multiple goals to find an optimal solution that comprehensively considers each goal.
[0052] By adjusting the weight coefficient , , The value of can adjust the importance of each objective function in the comprehensive objective.
[0053] S2. State space definition: The internal structure of the ship is abstracted into a state space, where each state represents the position and state of the crew in the ship.
[0054] Specifically, the internal structure of the ship is abstracted into a state space, where each state represents the position and state of the crew inside the ship. The definition of this state space is based on the layout of the ship and the distribution of the crew. Through such abstraction, various situations and possible actions inside the ship can be effectively represented during the search process.
[0055] Furthermore, S2 specifically includes the following steps:
[0056] S21. Define status: define the status inside the ship, including the position of the crew, the action status of the crew (such as walking, waiting, escaping, etc.), the open and closed status of the cabin and the environmental conditions inside the ship (such as temperature, smoke concentration, etc.).
[0057] Specifically, C represents the state space, C={ , ,……, }, =( , , ),in Indicates states, each state It is represented by a vector, which includes the position and action status of the crew. represents the horizontal coordinate position of the crew member, represents the ordinate position of the crew member, Indicates the crew's action status.
[0058] S22. State space modeling.
[0059] Specifically, various states inside the ship are organized into a state space, and the state space is represented in the form of a graph or a network, where nodes represent states and edges represent transition relationships between states, such as Figure 2 As shown, through the modeling of the state space, the state inside the ship and the position distribution of the crew can be clearly described.
[0060] S23. Define state transition rules.
[0061] Specifically, the state transition rule is a key step in the search algorithm, which determines the path selection during the search process. For each state, it is necessary to define the state transition rule, that is, to determine the way and conditions from the current state to the next state. These rules can be based on the physical characteristics and safety regulations inside the ship, such as the mobility of the crew, the accessibility of the cabin, the availability of the evacuation channel, etc. The state transition function f takes the current state C and the action as input and returns the next state C' as output; where the state transition function is expressed as: f: C×A→C', where A represents the action space and the elements in A represent the actions that the crew can take.
[0062] S24, state space initialization.
[0063] Specifically, before the search algorithm starts, the state space needs to be initialized to determine the initial state, which usually represents the crew's starting position and initial action state. By initializing the state space and determining the initial state, a starting point is provided for the search algorithm, so that the search process can start smoothly.
[0064] S25. Target state definition.
[0065] Specifically, defining the target state helps the search algorithm find a suitable path so that the crew can escape the ship safely. Therefore, it is also necessary to define the target state, that is, the state in which the crew successfully escapes and reaches a safe area. This state is usually represented as a specific position or a specific state. Through such a state space definition, we can better understand the internal structure of the ship and the position distribution of the crew, and provide effective state representation and transition rules for the subsequent multi-objective optimization search algorithm.
[0066] Through the above steps, the internal structure of the ship and the position distribution of the crew can be abstracted into a clear state space, which provides effective state representation and transition rules for the subsequent multi-objective optimization search algorithm.
[0067] S3. Heuristic function design.
[0068] In order to improve the search efficiency, a heuristic function is designed in the multi-objective optimization heuristic search algorithm for improving ship evacuation. This heuristic function can evaluate each state according to the multi-objective optimization model and provide heuristic information for the search process, such as the distance information between the state and the target, safety assessment information, evacuation time estimation, and the complexity of the path during the evacuation process when a dangerous state occurs. The design of the heuristic function can help the algorithm to more effectively select the next state so as to find the optimal evacuation path faster.
[0069] Furthermore, the heuristic function evaluates each state according to the multi-objective optimization model and provides heuristic information for the search process. S3 specifically includes:
[0070] S31. Objective function transformation.
[0071] The objective function in the multi-objective optimization model is converted into a heuristic function, that is, the heuristic value is calculated according to the characteristics of each state and the current situation, and the optimal path length from the current state to the target state is estimated according to the heuristic value. The value of each objective function is linearly mapped to a fixed range, that is, [0,1]. The implementation formula is as follows:
[0072]
[0073] Where: represents the value of the objective function, Represents the value after mapping, and They represent the minimum and maximum values of the objective function respectively.
[0074] S32. Status assessment.
[0075] Specifically, according to each state S, the safety, evacuation time and evacuation distance of the crew in the current state are evaluated according to the situation inside the ship and the position distribution of the crew. Safety can take into account factors such as the distance between the crew and the safe exit, obstacles on the passage path, and environmental conditions inside the ship. The evacuation time can take into account the time required for the crew to reach the safe exit and the possible length of the evacuation path. The evacuation distance can directly represent the distance the crew needs to reach the safe exit.
[0076] S33, heuristic value calculation.
[0077] Specifically, according to the state evaluation in S32, the values of each optimization target of the current state are obtained, and the values of each mapped objective function are weighted and summed according to the weight coefficient to obtain the value of the heuristic function. The calculation formula is as follows:
[0078]
[0079] In the formula, Represents the heuristic function value, which reflects the estimated quality of the current state to the target state. The larger the value, the better. The objective function value representing the safety of the crew after mapping, represents the objective function value of the evacuation time after mapping, The objective function value representing the evacuation distance after mapping; less time means better status, so that the heuristic value increases when the time decreases.
[0080] The objective functions corresponding to crew safety, evacuation time and evacuation distance are represented by S, T and D respectively. , and The value range of is [0, 1]. The closer the value is to 1, the better the target is. and The closer the value is to 0, the better.
[0081] Crew safety is a dimensionless indicator used to measure the safety of personnel in their current state. It can be evaluated based on the concentration of fire smoke and the presence or absence of obstacles in the evacuation route.
[0082] Assume that the value range of crew safety is [0,100], the value range of evacuation time is [0,200], and the value range of evacuation distance is [0, 500]. The weight coefficients are =0.4, =0.3, =0.3.
[0083] For a specific state C, assuming that the crew safety is S=80, the evacuation time is T=150 seconds, and the evacuation distance is D=300 meters. After linear mapping, the values of each objective function are =0.8, =0.75, =0.6.
[0084] Finally, according to the weighted summation formula, the value of the heuristic function is calculated as:
[0085] h(s)=0.8×0.4-0.75×0.3-0.6×0.3=0.32-0.225-0.18=0.085.
[0086] S34: Update the heuristic value.
[0087] Specifically, during the search process, the heuristic value needs to be dynamically updated according to the changes in the current state. This can be achieved by real-time monitoring of the internal conditions of the ship and based on the feedback information of the search algorithm. By continuously updating the heuristic value, it can be ensured that the algorithm can make appropriate decisions in different situations.
[0088] S4. Search algorithm implementation: Based on the heuristic function, the A* algorithm in the heuristic search algorithm is used to search for the optimal evacuation path in the state space.
[0089] Specifically, based on the heuristic function, the A* algorithm in the heuristic search algorithm is used to search for the optimal evacuation path in the state space. These algorithms can find a better solution in a limited time through a reasonable search strategy, thereby improving the evacuation efficiency.
[0090] S5. Path evaluation and selection.
[0091] Specifically, according to the search results, it is necessary to evaluate each evacuation path and select the optimal evacuation path to achieve the goal of safe and rapid evacuation of the crew. This involves comprehensively considering the weights of various optimization objectives, thereby weighing and selecting between multiple objectives to achieve the best evacuation effect.
[0092] The A* search algorithm is used, and the state space, heuristic function, and search strategy are optimized to improve the search efficiency and the accuracy of the evacuation path. Below is a simplified example code showing a possible implementation of the heuristic algorithm for improving ship evacuation.
[0093] classState:
[0094] def__init__(self, position, cost, heuristic):
[0095] self.position = position# Crew position
[0096] self.cost = cost# path cost
[0097] self.heuristic = heuristic # Heuristic evaluation value
[0098] classAStar:
[0099] def__init__(self, graph):
[0100] self.graph = graph# Ship internal structure diagram
[0101] defheuristic(self, current, target):
[0102] # Heuristic function: Estimate the optimal cost from the current state to the target state
[0103] # In practical applications, heuristic functions can be designed based on factors such as crew distribution and cabin structure.
[0104] return0# here is simplified to 0
[0105] defsearch(self, start, target):
[0106] open_set = {start}
[0107] closed_set = set()
[0108] while open_set:
[0109] current = min(open_set, key=lambda x: x.cost + x.heuristic)
[0110] open_set.remove(current)
[0111] if current == target:
[0112] returnTrue# Find the target state
[0113] closed_set.add(current)
[0114] for neighbor in self.graph.neighbors(current):
[0115] if neighbor in closed_set:
[0116] continue
[0117] tentative_cost = current.cost + self.graph.cost(current, neighbor)
[0118] neighbor.heuristic = self.heuristic(neighbor, target)
[0119] neighbor.cost = tentative_cost
[0120] if neighbor notin open_set:
[0121] open_set.add(neighbor)
[0122] returnFalse# Target status not found
[0123] # Example graph class
[0124] classGraph:
[0125] def __init__(self):
[0126] pass
[0127] defneighbors(self, state):
[0128] pass
[0129] defcost(self, state1, state2):
[0130] pass
[0131] # Sample code usage instructions
[0132] graph = Graph()# Initialize the internal structure of the ship
[0133] start_state = State(start_position, 0, 0) # Set the starting state
[0134] target_state = State(target_position, float('inf'), 0) # Set the target state
[0135] astar = AStar(graph) # Initialize A* search algorithm
[0136] if astar.search(start_state, target_state):
[0137] print("Find the best path")
[0138] else:
[0139] print("No optimal path found")
[0140] In this code, the State class represents the state of the search algorithm, which contains information such as crew positions, path costs, and heuristic evaluation values.
[0141] The AStar class implements the A* search algorithm, where the heuristic method is used to calculate the heuristic evaluation value and the search method is used to execute the search process.
[0142] The Graph class represents the internal structure of the ship. The neighbors method is used to obtain adjacent states, and the cost method is used to calculate the cost of moving between states.
[0143] In the sample code, you need to implement the specific functions of the Graph class according to the actual situation, including the definition of the state space and the calculation of the path cost.
[0144] Finally, the starting state and target state are set according to the actual situation, and the A* search algorithm is called to perform path search.
[0145] The embodiment of the present invention also provides a ship heuristic search system based on a multi-objective model.
[0146] A ship heuristic search system based on a multi-objective model, comprising:
[0147] Multi-objective optimization model: used to determine and quantify multiple evacuation optimization objectives and transform them into objective functions;
[0148] State space definition module: abstracts the internal structure of the ship into a state space and provides the function of transferring between states.
[0149] Heuristic function design module: designs and implements heuristic functions, evaluates each state according to the multi-objective optimization model, and provides heuristic information;
[0150] Search algorithm implementation module: uses heuristic search algorithm to search for the optimal evacuation path in the state space;
[0151] Path evaluation and selection module: Based on the search results, evaluate the advantages and disadvantages of each evacuation path and select the optimal evacuation path.
[0152] The embodiment of the present invention also provides an application of a ship heuristic search algorithm based on a multi-objective model, which is used to improve the efficiency and safety of ship evacuation. The algorithm is applicable to various types of ships, including but not limited to merchant ships, passenger ships, tankers, etc., and provides reliable technical support in the face of emergencies.
[0153] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A ship heuristic search algorithm based on a multi-objective model, characterized in that: The following steps are involved: S1. Objective definition: determine the optimization objectives and establish a multi-objective optimization model; S2, state space definition: the internal structure of the ship is abstracted into a state space, where each state includes the position and state of the crew in the ship; S3, heuristic function design: design a heuristic function to evaluate each state according to the multi-objective optimization model and provide heuristic information for the search process; S4, search algorithm implementation: using heuristic search algorithm to search for the optimal evacuation path in the state space; S5. Path evaluation and selection: Based on the search results, evaluate the pros and cons of each evacuation path and select the optimal evacuation path to achieve safe and rapid evacuation of the crew; S2 specifically includes: S21. Define status: define the status inside the ship, including the position of the crew, the action status of the crew, the open and closed status of the cabin, and the environmental conditions inside the ship; S22, state space modeling: various states inside the ship are organized into a state space, and the state space is represented in the form of a graph or a network, wherein a node represents a state and an edge represents a transfer relationship between states. The state space modeling is used to describe the state inside the ship and the position distribution of the crew; S23. Define state transition rules: According to each state, define the state transition rules, that is, determine the method and conditions from the current state to the next state, and define the state transition rules through the state transition function f. The state transition function f takes the current state C and the action as input and returns the next state C' as output; the state transition function is expressed as: f: C×A→C', where A represents the action space, the elements in A represent the actions that the crew can take, C represents the state space, and C={ , ,……, }, =( , , ),in Indicates states, each state It is represented by a vector, which includes the position and action status of the crew. represents the horizontal coordinate position of the crew member, represents the ordinate position of the crew member, Indicates the crew's action status; S24, state space initialization: by initializing the state space, determining the initial state, providing a starting point for the search algorithm; the initial state includes the crew's starting position and initial action state; S25. Target state definition: define the target state, i.e. the state where the crew successfully escapes to a safe area, which is a specific location or a specific state; In S3, the heuristic function evaluates each state according to the multi-objective optimization model and provides heuristic information for the search process, including: S31. Objective function conversion: The objective function in the multi-objective optimization model is converted into a heuristic function, that is, the heuristic value is calculated according to the characteristics of each state and the current situation, and the optimal path length from the current state to the target state is estimated according to the heuristic value. The value of each objective function is linearly mapped to a fixed range, that is, [0,1]. The implementation formula is as follows: Where: represents the value of the objective function, Represents the value after mapping, and Respectively represent the minimum and maximum values of the objective function; S32, status assessment: according to each status C, the safety, evacuation time and evacuation distance of the crew in the current status are assessed according to the internal conditions of the ship and the location distribution of the crew; S33, heuristic value calculation: According to the state evaluation in S32, the values of each optimization target of the current state are obtained, and the values of each mapped objective function are weighted and summed according to the weight coefficient to obtain the value of the heuristic function. The calculation formula is as follows: ; In the formula, Represents the heuristic function value, which reflects the estimated quality of the current state to the target state. The larger the value, the better. The objective function value representing the safety of the crew after mapping, represents the objective function value of the evacuation time after mapping, represents the objective function value of the evacuation distance after mapping, , and The value range of is [0, 1]. The closer the value is to 1, the better the target is. and The closer the value is to 0, the better; is the weight coefficient of crew safety, is the weight coefficient of evacuation time, is the weight coefficient of the evacuation distance, and All are positive weights, which are used to adjust the influence of each objective function in the comprehensive goal; S34, heuristic value update: During the search process, the heuristic value is dynamically updated according to the changes in the current state.
2. A ship heuristic search algorithm based on a multi-objective model according to claim 1, characterized in that: The optimization objectives include crew safety, evacuation time and evacuation distance, and the objective functions corresponding to crew safety, evacuation time and evacuation distance are represented by S, T and D respectively.
3. The ship heuristic search algorithm based on a multi-objective model according to claim 2 is characterized in that: A multi-objective optimization model is constructed based on the objective functions corresponding to crew safety, evacuation time and evacuation distance, which is expressed as: ,in, Represents crew safety, Represents evacuation time, Represents the evacuation distance.
4. The ship heuristic search algorithm based on a multi-objective model according to claim 1 is characterized in that: In S4, based on the heuristic function, the A* algorithm in the heuristic search algorithm is used to search for the optimal evacuation path in the state space.
5. The ship heuristic search algorithm based on a multi-objective model according to claim 1 is characterized in that: It is used to improve the efficiency and safety of ship evacuation and is applicable to all types of ships, including but not limited to merchant ships, passenger ships, and tankers, providing reliable technical support in the face of emergencies.
6. A ship heuristic search system based on a multi-objective model, characterized in that: The ship heuristic search algorithm based on a multi-objective model as described in claim 1 comprises: Multi-objective optimization model: used to determine and quantify multiple evacuation optimization objectives and transform them into objective functions; State space definition module: abstracts the internal structure of the ship into a state space and provides the function of transferring between states; Heuristic function design module: designs and implements heuristic functions, evaluates each state according to the multi-objective optimization model, and provides heuristic information; Search algorithm implementation module: uses heuristic search algorithm to search for the optimal evacuation path in the state space; Path evaluation and selection module: Based on the search results, evaluate the advantages and disadvantages of each evacuation path and select the optimal evacuation path.
