CN115759463B - Dynamic planning method for escape path of passenger on passenger ship - Google Patents
Dynamic planning method for escape path of passenger on passenger ship Download PDFInfo
- Publication number
- CN115759463B CN115759463B CN202211537037.9A CN202211537037A CN115759463B CN 115759463 B CN115759463 B CN 115759463B CN 202211537037 A CN202211537037 A CN 202211537037A CN 115759463 B CN115759463 B CN 115759463B
- Authority
- CN
- China
- Prior art keywords
- path
- particles
- particle
- evacuation
- escape
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 239000002245 particle Substances 0.000 claims abstract description 97
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000011156 evaluation Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 20
- 238000005457 optimization Methods 0.000 claims description 10
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000019771 cognition Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003094 perturbing effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention is applicable to the field of safety science, and provides a dynamic planning method for escape paths of passengers of a passenger ship, which comprises the following specific steps: step (1): constructing a ship escape route evacuation scene; step (2): initializing particles of a ship escape path and setting parameters, abstracting an evacuee into particles, initializing particle attributes including position and speed information of the particles, and dynamically updating the weight coefficient of the escape path according to the particle movement rule; step (3): planning an evacuation path and calculating an objective function; step (4): fitness function evaluation and speed and position updating of particles; step (5): and comparing the current position of the particles with the previous optimal position through an improved particle swarm algorithm, and continuously updating the position and speed information to realize the dynamic planning of the escape path.
Description
Technical Field
The invention belongs to the field of safety science, and particularly relates to a dynamic planning method for escape paths of passengers of a passenger ship.
Background
The large-scale of ships gradually becomes an important way and trend for improving shipping conveying capacity and passenger service quality, however, the large-scale of ships inevitably causes the complexity of ship structures, in the emergency of accidents, evacuation personnel often drastically reduce the cognitive decision level due to the tension and panic emotion, and passengers and crews need to abandon ships for escape in the emergency, so as to ensure that the passengers and crews can escape smoothly, congestion and confusion do not occur, and ship escape path information needs to be provided for the passengers and crews.
During the process of people evacuation, the dynamic path planning is an effective method. As evacuation models are developed, more and more research institutions are devoted to research and development thereof. The social force model of the helpers adopts a function planning method, and a differential equation is used for describing the behavior of personnel to be too complex, so that the model is not suitable for large-scale personnel evacuation; the cellular automaton model is a regular basic model, has good simulation effect, but lacks a theoretical basis; the Agent model algorithm is used for large-scale personnel evacuation, for example, the particle swarm optimization algorithm is a popular optimization calculation method, and is increasingly applied to path planning due to the ultra-strong calculation capability, high precision and good convergence, but the current particle swarm algorithm is coarser in behavior description due to the structural complexity of a ship escape channel and the environmental specificity of ship free motion.
In order to avoid the above-mentioned problems, it is necessary to provide a dynamic planning method for escape routes of passengers on a passenger ship to overcome the drawbacks of the prior art.
Disclosure of Invention
The invention aims to provide a dynamic planning method for escape paths of passengers on a passenger ship, and aims to solve the problem that a safe and effective escape dynamic path is difficult to find due to complex evacuation process of passengers on the passenger ship under emergency evacuation, and provides a dynamic planning method for escape paths of the passenger ship, which improves a particle swarm optimization algorithm.
The invention discloses a dynamic planning method for escape paths of passengers of a passenger ship, which comprises the following specific steps:
step (1): constructing a ship escape route evacuation scene, determining the positions and the number of outlets of ship escape channels according to the internal structural characteristics of the geometric space of the ship, and generating a ship escape channel node network graph G (V, E), wherein V is the boundary range of nodes and E representing escape paths;
step (2): initializing particles of a ship escape path and setting parameters, abstracting an evacuee into particles, initializing particle attributes including position and speed information of the particles, and dynamically updating the weight coefficient of the escape path according to the particle movement rule;
step (3): planning an evacuation path and calculating an objective function;
step (4): fitness function evaluation and speed and position updating of particles;
step (5): and comparing the current position of the particles with the previous optimal position through an improved particle swarm algorithm, and continuously updating the position and speed information to realize the dynamic planning of the escape path.
In a further technical scheme, in the step (3): the evacuation path planning is to select a path from a source node to an intermediate node passing through a terminal of a collection station, and divide the intermediate node into a plurality of stages by taking the shortest total evacuation time of all particles reaching the terminal as a target, wherein each particle is regarded as a movable special node, and the individual movement comprises path selection and moving speed;
the objective function calculation is to calculate the evacuation time through the length of the evacuation path, the evacuation speed of the evacuation personnel and the evacuation number on the evacuation path.
In a further technical scheme, in the step (4): the fitness function evaluation is based on the individual local path with the shortest path, and then based on the congestion degree of the channel, the fitness function evaluation is converted into a moving speed variable, and the advantages and disadvantages of evacuation paths are evaluated according to the global path of the group;
the speed and position updating of particles is based on a traditional particle swarm optimization algorithm, the free motion and channel congestion state information of a ship are considered, gaussian white noise is introduced into acceleration coefficients of the particle swarm algorithm, cognition and social acceleration coefficients are adjusted through random disturbance of particle motion, local optimal and global optimal path searching is based on the particle swarm optimization algorithm, the position and speed information of the particles are continuously updated, and an optimal escape path scheme is searched.
In a further aspect, in step (2), the position and velocity of the particle i in the m-dimensional decision space may be expressed as:
particle i current position:
particle i historical optimal position:
the velocity of particle i is:
。
in a further technical solution, in the step (3), the objective function is:
（6）
the moving speed of the person can be expressed as:
。
in a further technical scheme, in the step (4), the speed and position updating algorithm of the particles is as follows:
(8)
(9）。
according to a further technical scheme, the fitness function used for judging whether the particle reaches the end point in the step (4) is as follows:
，e/>} (12)。
compared with the prior art, the invention has the following beneficial effects:
the invention provides a dynamic planning method for a passenger escape path of a passenger ship, which is used for constructing an escape path evacuation scene of the ship, determining the positions and the number of outlets of an escape passage of the ship according to the internal structural characteristics of a geometric space of the ship, and generating a node network diagram of the escape passage of the ship;
the invention provides a dynamic planning method for escape paths of passengers on a passenger ship, which is based on a traditional particle swarm optimization algorithm, considers the free motion and channel congestion state information of the ship, introduces Gaussian white noise into acceleration coefficients of the particle swarm algorithm, adjusts cognition and social acceleration coefficients by randomly perturbing the particle motion, searches for locally optimal and globally optimal paths based on the particle swarm optimization algorithm, continuously updates the position and speed information of the particles, and searches for an optimal escape path scheme;
according to the passenger escape path dynamic planning method for the passenger ship, provided by the invention, the current position of particles is compared with the previous optimal position through an improved particle swarm algorithm, and the position and speed information are updated continuously, so that the escape path dynamic planning is realized.
Drawings
FIG. 1 is a block diagram of an evacuation path plan;
fig. 2 is a flowchart of a passenger evacuation path optimization algorithm for a passenger ship.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Specific implementations of the invention are described in detail below in connection with specific embodiments.
As shown in fig. 1, the method for dynamically planning the escape route of the passenger ship provided by the invention comprises the following specific steps:
(1) Constructing a ship escape passage node evacuation network diagram
According to the geometric space structure characteristics of the ship, the ship escape system is divided into a plurality of ship escape middle nodes according to escape outlets such as ship cabin outlets, corridor, stair outlets and the like. The individual passengers on the ship are regarded as particles in the group, the particles are randomly distributed in the cabin, and the initial position for evacuating people is set as a source node. The destination node is the destination station that reaches the designated secure egress or aggregation station. Connecting all intermediate nodes from a source node to a target node through an arc line to generate a static escape route evacuation network diagram, wherein G (V, E) represents all path sets from the source node to a collection station, V represents a node, and the node comprises the maximum passing capacity; e represents the boundary range of the escape route.
(2) Particle initialization and parameter setting
And initializing particles, setting the number of the particles, and randomly distributing initial positions of the particles.
Assuming that the particle swarm includes N particles, the decision space is m-dimensional, and the position and velocity of the particle i in the m-dimensional decision space can be expressed as:
particle i current position:
particle i historical optimal position:
the velocity of particle i is:
。
(3) Evacuation path planning, objective function calculation
The evacuation path planning refers to the path selection of intermediate nodes from a source node to a terminal of a terminal, and in the shortest time, the maximum number of people are evacuated to a safe place through the optimal path, namely, the shortest total evacuation time for all particles to reach the terminal is taken as a target. The intermediate node is divided into several phases, each particle being regarded as a specific node that is movable, and the individual movements include path selection and speed of movement. The evacuation time depends on the length of the evacuation path and the evacuation speed of the evacuees, and is related to the number of evacuees on the evacuation path. Let the total number of evacuation people be N, the evacuation speed is determined by the crowding degree of the channel and the inclination angle of the free movement of the ship. And a shortest-time evacuation model is adopted to realize dynamic evacuation. The objective function is:
（6）。
wherein,indicating the relative distance of evacuee from node i to node j,/->Indicating the relative speed of evacuee t from node i to node j, < >>The size is determined by crowd density and the degree of inclination of the vessel. />For determining whether particles select j node, particle evacuation select +.>The path is 1, otherwise 0.
Wherein the passenger ship passenger moving speed is related to the ship free motion and crowd density. The moving speed of the person can be expressed as:
。
wherein the method comprises the steps ofCongestion factor representing the particle from node i to node j,/->Inclination coefficient indicating the influence of the ship inclination angle on the moving speed,/->。
(4) Fitness function evaluation and particle speed and position updating rules
And comparing and evaluating the objective function values, considering the optimal local path of the individual based on the shortest path, converting the path to a moving speed variable based on the congestion degree of the channel, considering the optimal global path of the group, and evaluating the advantages and disadvantages of the evacuation path. If it isUpdating the best path->Updating the speed and position of the particles; ith particle velocity and location update principle: the velocity of the particles is influenced by the particle movement inertia, the particle history optimal solution and the group history optimal solution, and the particle position is determined by the particle movement velocity.
(8)
(9）。
Wherein,is an inertial factor, ++>As a particle cognition factor, a cognition decision factor of the particle moving to the optimal position according to the current state and future prediction; />Social factors are social decision factors of the particles in the global optimal position of the whole population; />Random number [0 1 ] representing uniformly distributed 0-1]。
In the algorithm, the influence of the free motion and the crowding degree of the ship on the path planning is considered, the acceleration coefficient is a dynamic parameter, the influence of the current motion state and the expected path is provided, the random disturbance on the acceleration coefficient based on adjustable Gaussian white noise is provided, and the adjustable parameter can be expressed as:
(10)
(11)。
(5) Particle optimal escape path scheme determination
And comparing the current position of the particles with the previous optimal position through the improved particle swarm algorithm, and continuously updating the position and speed information until the global optimal position is reached. Fitness function:
，e/>} (12)。
fitness functionFor determining whether the particle reaches the end pointWhen->，e/>Indicating that the particles do not reach the end point, dispersing all the particles to a safe area of the collection station, and ending the dispersing process. And recording the optimal path of the particles, calculating the total evacuation time, and realizing the dynamic planning of the escape path through an evacuation identification guiding system.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (1)
1. The dynamic passenger escape path planning method for the passenger ship is characterized by comprising the following specific steps:
step (1): constructing a ship escape route evacuation scene, determining the positions and the number of outlets of ship escape channels according to the internal structural characteristics of the geometric space of the ship, and generating a ship escape channel node network graph G (V, E), wherein V is the boundary range of nodes and E representing escape paths;
step (2): initializing particles of a ship escape path and setting parameters, abstracting an evacuee into particles, initializing particle attributes including position and speed information of the particles, and dynamically updating the weight coefficient of the escape path according to the particle movement rule;
step (3): planning an evacuation path and calculating an objective function;
step (4): fitness function evaluation and speed and position updating of particles;
step (5): comparing the current position of the particles with the previous optimal position through an improved particle swarm algorithm, and continuously updating the position and speed information to realize the dynamic planning of escape paths;
wherein, in the step (3):
the evacuation path planning is to select a path from a source node to an intermediate node passing through a terminal of a collection station, and divide the intermediate node into a plurality of stages by taking the shortest total evacuation time of all particles reaching the terminal as a target, wherein each particle is regarded as a movable special node, and the individual movement comprises path selection and moving speed;
the objective function calculation is to calculate the evacuation time through the length of the evacuation path, the evacuation speed of the evacuation personnel and the evacuation number on the evacuation path;
in the step (4):
the fitness function evaluation is based on the individual local path with the shortest path, and then based on the congestion degree of the channel, the fitness function evaluation is converted into a moving speed variable, and the advantages and disadvantages of evacuation paths are evaluated according to the global path of the group;
the speed and position updating of particles is based on a traditional particle swarm optimization algorithm, the free motion and channel congestion state information of a ship are considered, gaussian white noise is introduced into acceleration coefficients of the particle swarm algorithm, cognition and social acceleration coefficients are adjusted through random disturbance of particle motion, local optimal and global optimal path searching is based on the particle swarm optimization algorithm, the position and speed information of the particles are continuously updated, and an optimal escape path scheme is searched;
in step (2), the position and velocity of particle i in the m-dimensional decision space can be expressed as:
particle i current position:
X i ＝(x i1 ，x i2 ，x i3 ，…，x im )，i＝1，2，…，N (1)
particle i historical optimal position:
P i
＝(p i1 ，p i2 ，p i3 ，…，p im )，
the velocity of particle i is:
V i ＝
(v i1 ，v i2 ，v i3 ，…，v im )；
in step (3), the objective function is:
the moving speed of the person can be expressed as:
in step (4), the speed and position updating algorithm of the particles is as follows:
the fitness function used in step (4) to determine whether the particle has reached the endpoint is:
F 1 (X)＝d(X，E)＝min{d(X，e)，e∈E} (12)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211537037.9A CN115759463B (en) | 2022-12-02 | 2022-12-02 | Dynamic planning method for escape path of passenger on passenger ship |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211537037.9A CN115759463B (en) | 2022-12-02 | 2022-12-02 | Dynamic planning method for escape path of passenger on passenger ship |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115759463A CN115759463A (en) | 2023-03-07 |
| CN115759463B true CN115759463B (en) | 2023-11-17 |
Family
ID=85342687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211537037.9A Active CN115759463B (en) | 2022-12-02 | 2022-12-02 | Dynamic planning method for escape path of passenger on passenger ship |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115759463B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236473B (en) * | 2023-11-10 | 2024-01-30 | 华中科技大学 | Method and system for distributing paths of passenger co-riding vehicles in junction evacuation scene |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311028A (en) * | 2020-03-23 | 2020-06-19 | 河海大学常州校区 | Large-scale indoor personnel evacuation system based on improved particle swarm optimization algorithm |
| CN114397896A (en) * | 2022-01-10 | 2022-04-26 | 贵州大学 | Dynamic path planning method for improving particle swarm optimization |
| CN114626281A (en) * | 2022-03-16 | 2022-06-14 | 海南大学 | Ship escape mark guiding system and method |
-
2022
- 2022-12-02 CN CN202211537037.9A patent/CN115759463B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311028A (en) * | 2020-03-23 | 2020-06-19 | 河海大学常州校区 | Large-scale indoor personnel evacuation system based on improved particle swarm optimization algorithm |
| CN114397896A (en) * | 2022-01-10 | 2022-04-26 | 贵州大学 | Dynamic path planning method for improving particle swarm optimization |
| CN114626281A (en) * | 2022-03-16 | 2022-06-14 | 海南大学 | Ship escape mark guiding system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115759463A (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112904842B (en) | Mobile robot path planning and optimizing method based on cost potential field | |
| CN115759463B (en) | Dynamic planning method for escape path of passenger on passenger ship | |
| Szlapczynski | Evolutionary sets of safe ship trajectories: a new approach to collision avoidance | |
| Wong et al. | Optimized evacuation route based on crowd simulation | |
| CN113872661B (en) | Unmanned aerial vehicle network three-dimensional deployment method and system for accessing user classification service | |
| Wong et al. | A GA-based method for constructing fuzzy systems directly from numerical data | |
| CN112556714B (en) | Intelligent path planning method and system for firefighting and rescue | |
| CN113190037A (en) | Unmanned aerial vehicle optimal path searching method based on improved fluid disturbance and sparrow algorithm | |
| CN111610788A (en) | Hierarchical fuzzy-artificial potential field path planning method | |
| Liu et al. | A semantic data model for indoor navigation | |
| CN112231967A (en) | Crowd evacuation simulation method and system based on deep reinforcement learning | |
| CN114757014A (en) | Personnel evacuation simulation method based on fire of mail steamer and road section capacity limitation | |
| CN114812564B (en) | Multi-target unmanned aerial vehicle path planning method based on urban dynamic space-time risk analysis | |
| CN112866902A (en) | Dynamic dangerous shipborne environment self-adaptive emergency navigation method | |
| CN115270506A (en) | Method and system for predicting passing time of people going upstairs along stairs | |
| CN115933693A (en) | Robot path planning method based on adaptive chaotic particle swarm algorithm | |
| Zhang et al. | Dynamic path optimization with real-time information for emergency evacuation | |
| CN115103327A (en) | VANET clustering algorithm based on support vector machine | |
| CN108388752B (en) | Group simulation method suitable for emergency evacuation | |
| Wang et al. | Combining building and behavior models for evacuation planning | |
| CN111553404A (en) | Communication network node self-adaptive dynamic planning method | |
| CN112199747A (en) | Indoor personnel evacuation method and evacuation system based on queuing network | |
| CN114629769B (en) | Traffic map generation method of self-organizing network | |
| Varia et al. | Dynamic user equilibrium traffic assignment on congested multidestination network | |
| Scozzaro et al. | Noise abatement trajectories for a uav delivery fleet |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |