CN114527757B - Ocean passenger ship personnel emergency evacuation path planning algorithm based on virtual nodes - Google Patents
Ocean passenger ship personnel emergency evacuation path planning algorithm based on virtual nodes Download PDFInfo
- Publication number
- CN114527757B CN114527757B CN202210170583.7A CN202210170583A CN114527757B CN 114527757 B CN114527757 B CN 114527757B CN 202210170583 A CN202210170583 A CN 202210170583A CN 114527757 B CN114527757 B CN 114527757B
- Authority
- CN
- China
- Prior art keywords
- evacuation
- node
- virtual
- nodes
- passenger
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 claims abstract description 51
- 230000008569 process Effects 0.000 claims abstract description 40
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 11
- 238000010586 diagram Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000001125 extrusion Methods 0.000 claims description 4
- 230000006872 improvement Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 101150064138 MAP1 gene Proteins 0.000 claims description 2
- 101150009249 MAP2 gene Proteins 0.000 claims description 2
- 230000006399 behavior Effects 0.000 claims description 2
- 230000005284 excitation Effects 0.000 claims description 2
- 230000035484 reaction time Effects 0.000 claims description 2
- 238000010845 search algorithm Methods 0.000 claims description 2
- 238000004088 simulation Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 241000254158 Lampyridae Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Alarm Systems (AREA)
- Emergency Lowering Means (AREA)
Abstract
The invention provides a planning algorithm for personnel emergency evacuation paths of ocean-going passenger vessels based on virtual nodes, which solves the problems of balanced personnel exit distribution under the condition of a plurality of exits in the passenger vessel evacuation process and simulation of the ordered evacuation process. Because the passenger ship has a plurality of symmetrical outlets, the efficiency of adopting the straight line distance to judge the straight line is low, and the problem of low path quality is easily caused. According to the invention, based on the node network map, virtual nodes are introduced on the basis of the original map node network, the nodes are connected with all outlets, the virtual nodes are used as target nodes, all outlets are used as intermediate nodes, algorithm searching is performed, the searching time of the algorithm is reduced, on the basis, the problem of uneven personnel distribution is solved, the virtual nodes are dynamically updated, and the problem of uneven personnel distribution of multiple outlets is further solved. And finally, constructing a social force model based on a guiding path, simulating the evacuation process of the crowd, and dynamically reflecting the evacuation track of the personnel to effectively guide the evacuation.
Description
Technical Field
The invention relates to a passenger ocean vessel personnel emergency evacuation path planning algorithm based on virtual nodes, and belongs to the field of safety science.
Background
Passenger ships have higher mortality rate than other ships after accidents due to high passenger density, complex types and the like. Meanwhile, due to the special working environment that the passenger ships are relatively independent and closed, external rescue is often difficult to obtain in time when accidents occur, and even under the condition that external ships participate in rescue before, rescue work on water is more difficult than rescue work on land. Therefore, at the beginning of accident, all passengers are quickly gathered and boarding the lifeboat, and the lifeboat has an important effect on improving the survival rate of personnel on the ship. The path planning technology is one of important technologies in the field of motion planning, and has wide application in many fields. The path planning technology is applied to the field of ship evacuation, so that an evacuation path can be quickly generated when the emergency situation is faced, passengers are guided to be quickly evacuated, the safety of the passengers is ensured, guidance can be provided for personnel evacuation in the rescue evacuation process, and the passenger evacuation efficiency is improved.
The existing path planning can be divided into traditional algorithms such as an A-type algorithm, a D-type algorithm, an artificial potential field method, a random search tree algorithm and the like and group intelligent optimization algorithms such as an ant colony algorithm, an artificial bee colony algorithm, a particle swarm algorithm, a genetic algorithm, a firefly algorithm and the like, but the existing algorithm is mainly applicable to path planning of outdoor open scenes in the field of pedestrian navigation, and when the existing algorithm is applied to a ship evacuation scene, the traditional algorithm is fast in planning speed but cannot adapt to dynamic environment and personnel characteristics in the evacuation scene; while the group intelligent optimization algorithm can reflect dynamic factors in a scene to a certain extent, the complexity of the algorithm is higher, and the overall optimal path output quality is poorer. Thus, in evacuation problems, global and local algorithms are considered in combination and still remain to be further investigated.
The invention provides a passenger ship symmetrical multi-exit environment structure based on analysis of the existing planning algorithm and passenger ship environment, and provides a passenger ship personnel emergency evacuation path planning algorithm based on virtual nodes, wherein virtual nodes are introduced on the basis of an original map node network, the nodes are connected with all exits, the virtual nodes are used as target nodes, all the exits are used as intermediate nodes, and the algorithm search is performed, so that the algorithm is prevented from expanding the exits for multiple times, and the algorithm efficiency is improved. On the basis, aiming at the problem of uneven personnel distribution, the virtual nodes are dynamically updated, and personnel are distributed to all outlets in a balanced manner to alleviate the situation of congestion of the outlets. And finally, constructing a social force model based on a guiding path, simulating the evacuation process of the crowd, and dynamically reflecting the evacuation track of the personnel to effectively guide the evacuation.
Disclosure of Invention
The invention provides a planning algorithm of a passenger ship personnel emergency evacuation path based on virtual nodes, which mainly solves the problems of balanced personnel exit distribution under the condition of a plurality of exits in the passenger ship evacuation process and simulation of the ordered evacuation process. Reasonable distribution of passenger and ship personnel to each exit through an evacuation planning algorithm, and input a path drawn by the algorithm into an evacuation model to simulate the evacuation process of personnel, thereby completing the instruction of the evacuation process.
The purpose of the invention is realized in the following way: the method comprises the following steps:
Step one: acquiring an evacuation communication diagram: collecting relevant data of a passenger ship, constructing a passenger ship structure map, simplifying the ship structure map, extracting the center position, the exit position, the corridor corner, the escape exit position and the feasible region nodes in part of feasible space of each room in the structure map, and constructing a communication map;
Step two: constructing an evacuation network topological graph added with equidistant virtual target nodes: based on the communication graph, calculating the position of a virtual node through the position of each outlet, adding the virtual node into a communication network, and establishing an evacuation network topology graph of the ship;
Step three: initializing a passenger position, and accessing the passenger position into an evacuation network topological graph;
step four: on the basis of an evacuation network topological graph, taking the initial position of a passenger as a starting point, taking a virtual target node as a planning terminal point, and adopting an A-based algorithm of a virtual node network to perform path searching to obtain the evacuation path of the current passenger;
Step five: judging whether all passengers finish planning, if not, dynamically updating the virtual node position according to the exit position selected by the current passenger, starting the planning process of the next passenger, and repeating the steps three to five until the planning task of all passengers is finished, and outputting the evacuation paths of all passengers;
Step six: the method comprises the steps of constructing a social force model based on path guidance, inputting all evacuation paths output by a planning algorithm into the social force model, taking each point in the path output by the planning algorithm as a driving point operation model for evacuating individuals in the model, and outputting a final dynamic evacuation path.
The invention also includes such structural features:
1. (1) Virtual node network construction
When a plurality of outlets exist, if one outlet expansion is performed on each outlet, the planning efficiency is low, so that an equidistant virtual node is designed to convert the problem of multiple outlets into a searching process of the virtual node. Constructing an evacuation network topological graph added with equidistant virtual target nodes:
the virtual node is a simulated space node, and the calculated position has no direct relation with the space characteristic of the real space, and is designed for reducing the multiple expansion of the algorithm. In order not to affect the final result of the actual planned path, the node needs to have the following characteristics: the node is only communicated with the final evacuation outlet, and has no communication relation with other nodes; the node, although participating in the path search process, does not output in the final path node; the initial cost of the node to each exit is consistent.
For the average distribution of evacuation exit positions, the calculation method of the initial virtual node can be calculated by the following formula:
Where [ x, y ] represents the location of the virtual node, goal represents the egress node location, and N represents the total number of egress.
(2) Evacuation search algorithm expansion
Initializing a passenger position, accessing the passenger position into a communication network, taking the passenger initial position as a starting point and a virtual target node as a planning terminal point on the basis of an evacuation network topological graph, and adopting an A-algorithm to search a path until all passengers are planned.
In the process, the cost value of the original A-type algorithm is adopted for node expansion, so that excessive searching of useless nodes is caused, when the virtual nodes are taken as targets for node expansion, negative excitation is required to be adopted for searching of the target nodes, the negative number of the distance from the expanded nodes to the virtual nodes is adopted as the cost value of node expansion, and the calculation formula of the cost value is as follows:
hv(n)＝L-h(n)
Where h (n) represents the straight line distance from the intermediate node to the virtual node, L is a relatively suitable positive value and the cost value is avoided as a negative number.
2. The dynamic updating mode in the fifth step specifically comprises the following steps:
when the number of passengers is increased and the passenger densities of all the areas are not equal, the congestion condition of individual exits is caused, the balance adjustment weight is introduced for the condition that the passenger densities of all the areas are not equal, when the passengers arrive at one exit, one weight of the exit is adjusted, and the position of the virtual node is updated at the same time, so that the cost from the virtual node to each exit is changed, the passengers select the exit with less personnel under the condition of equal distance cost, and the condition of balanced personnel distribution is achieved.
The distance cost from the virtual node at the initial position to each exit is equal, and when a person escapes from the exit, the virtual node updates the position in a mode of approaching the exit, so that the cost value of the virtual node is increased. In order to ensure that the influence on the planning process of other outlets is as small as possible after the virtual node is updated, the position is updated by adopting the reverse extension line of the connection line of the virtual node and the outlet, and the position updating equation of the virtual node is as follows:
Wherein: l represents the forward extension distance, which is determined by the map size and the number of people, k represents the slope between the links, (x 0,y0) represents the original virtual node position, (x goal,ygoal) represents the position of the exit selected by the previous planning.
3. The social force model construction in the sixth step specifically comprises the following steps:
(1) Basic model construction
The social force model expresses the decision behaviors of the individuals in the evacuation process in a force mode, quantitatively describes the psychological activities of the individuals by adopting mathematical modeling, and the model equation is as follows:
wherein, Representing the driving force of the individual per se,/>Representing the interaction force between a person and the environment,/>Representing the person-to-person interaction force.
Where τ i represents the step reaction time of the individual i, i.e. the time it takes for the movement state of the pedestrian to change.The actual movement speed and direction of the individual i at time t are indicated. /(I)Indicating the desired speed at which the individual is advanced to the target point without external disturbance. /(I)A unit vector representing the desired direction of the individual i at time t.
Wherein A iexp[(rij-dij)/Bi]nij represents psychological acting force of an individual at a certain distance from other surrounding individuals, A i represents acting intensity coefficient, B i represents repulsive force range coefficient, and the coefficients are constant;
k 1g(rij-dij)nij represents the extrusion force between individuals, k 1 represents the extrusion coefficient, r ij represents the distance between the individuals i and j, n ij represents the normalized vector from the individual i to the individual j, perpendicular to t ij, t ij represents the tangential direction perpendicular to n ij, and d ij represents the center distance between the two individuals; represents the sliding friction between individuals, and k 2 represents the coefficient of friction.
Wherein d iw represents the shortest distance between the individual i and the obstacle w; n iw represents a unit vector from the obstacle w to the centroid of the pedestrian i; t iw is a unit vector of a rubbing direction when a pedestrian contacts an obstacle.
(2) Joining planning guidance
1) Map architecture
The route planning adopts a route network extracted from an actual map as a planning basis, and the evacuation model adopts an actual continuous map as a display basis. It is necessary to abstract the map into two levels:
the first layer is a path planning Map layer, denoted Map1 (x, y). The layer is a topological network formed by feasible paths, comprises various key nodes and passable path segments between the key nodes, and is mainly used for a data base of path searching in a path planning process, and is not displayed in a visual layer.
The second layer is an evacuation model demonstration layer, denoted Map2 (x, y). The layer is a continuous map, mainly records the environmental information of the actual evacuation scene such as the space structure of the environment, the accident place, the exit position, the position information of personnel and the like, and is mainly used for displaying the actual position of personnel evacuation and the environmental information of the evacuation scene.
2) Node conversion
The original model adopts the guidance of single-to-single key nodes, the nodes selected by personnel in the guidance process are unique, a path planned and output by a path generally has a plurality of nodes, the traditional model is easy to generate severe change of speed when the guidance of a plurality of intermediate nodes is converted, the individual path guidance mode needs to be improved, and the conversion is added among the path nodes, so that each intermediate node is smoothly transited. The process is divided into the following two parts:
And (3) adding guide point conversion judgment: when the person moves from the current position to the guide point, if the distance between the current position and the current guide point is smaller than a certain threshold value, the person is switched to the next guide point, the process is continued until the current node is the last path guide node, when the current node is the last path node, the switching judgment is skipped, and when the current node reaches the target node, the judgment is ended.
Guide equation improvement: when the number of the guide points is multiple, if the original driving equation is adopted, speed mutation and the like can occur when each guide point is converted, and the complexity of an algorithm and a model is greatly improved by adding a method for slowing down the speed mutation by a plurality of intermediate guide points. Therefore, the method adopts a mode of modifying the guiding equation to slow down the abrupt change of the speed, and when the guiding point conversion threshold is approaching, the speed is converted in advance to slow down the trend of the abrupt change of the speed, and the modified guiding equation is as follows:
wherein: f now denotes an attractive force of the current guidance point, f next denotes an attractive force of the next guidance point, ω 1、ω2 is a weight coefficient, R denotes a distance from the person to the current driving point, and R denotes a conversion radius.
Compared with the prior art, the invention has the beneficial effects that: the invention mainly solves the problem of the simulation of the balanced distribution of personnel exits and ordered evacuation processes under the condition of a plurality of exits in the passenger ship evacuation process. Because the passenger ship has a plurality of symmetrical outlets, the efficiency of adopting the straight line distance to judge the straight line is low, and the problem of low path quality is easily caused. According to the invention, based on the node network map, virtual nodes are introduced on the basis of the original map node network, the nodes are connected with all outlets, the virtual nodes are used as target nodes, all outlets are used as intermediate nodes, algorithm searching is performed, the searching time of the algorithm is reduced, on the basis, the problem of uneven personnel distribution is solved, the virtual nodes are dynamically updated, and the problem of uneven personnel distribution of multiple outlets is further solved. And finally, constructing a social force model based on a guiding path, simulating the evacuation process of the crowd, and dynamically reflecting the evacuation track of the personnel to effectively guide the evacuation.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
FIG. 2 (a) is a view showing an actual structure of a passenger ship;
FIG. 2 (b) is a simplified block diagram of a passenger ship;
FIG. 3 is an evacuation network diagram;
FIG. 4 is a person position profile;
FIG. 5 (a) is a 10s personnel evacuation process diagram;
FIG. 5 (b) is a 20s personnel evacuation process diagram;
FIG. 5 (c) is a 30s personnel evacuation process diagram;
FIG. 6 (a) is an average and dispersed person position profile;
FIG. 6 (b) is an average and dense personnel position profile;
fig. 6 (c) is an uneven and dense personnel position distribution map.
Detailed Description
The invention is described in further detail below with reference to the drawings and the detailed description.
The invention relates to a passenger ocean vessel personnel emergency evacuation path planning algorithm based on virtual nodes. Aiming at the multi-exit symmetrical passenger ship environment, virtual nodes are added in nodes of an evacuation network, the algorithm expansion times are reduced, meanwhile, the positions of the virtual nodes are dynamically updated to realize balanced distribution of personnel, and finally, a planned path is combined with a social force model to obtain a dynamic evacuation process, so that the evacuation process is guided.
The invention is further described below with reference to the accompanying drawings:
the invention relates to a planning algorithm of an ocean-going passenger ship personnel emergency evacuation path based on virtual nodes, and fig. 1 is a flow chart of the invention, and the specific steps comprise:
(1) Collecting evacuation environment information and constructing a simplified structural network;
(2) Constructing virtual nodes and adding an evacuation network;
(3) And accessing the node where the personnel are to the network, adopting an A-algorithm to expand and search, adopting an outlet node as an intermediate node in the node expansion process, adopting a virtual node as a target node, and adopting the sum of the distance cost from the initial point to the intermediate node and the negative correlation distance cost from the intermediate node to the virtual node as a total cost function of node expansion.
(4) In order to further balance the personnel number of each outlet, calculating the position of the virtual node in a dynamic updating mode;
(5) Constructing a social force model, and expressing the interaction between people and between people and environment in the evacuation process in a personnel speed mode through a mechanical formula;
(6) Combining and constructing an evacuation network and a social force model, carrying out personnel position coordinate correspondence on the evacuation network and an evacuation structure diagram in a coordinate correspondence mode, and realizing the smoothness of node conversion in the evacuation process through conversion judgment and an equation;
(7) Inputting the evacuation path result planned in the node network into the model to obtain a final planning result.
The present embodiments are intended to be illustrative, but not limiting, of the present invention, and any modifications and variations made thereto within the spirit of the invention and the scope of the appended claims fall within the scope of the invention.
And (3) performing simulation experiments by adopting MATLAB simulation software to verify the reliability of the designed planning method, and performing simulation analysis by combining examples. Taking a sample section of a cabin layer in a passenger ship deck as an example, the length is 40m, and the width is 55m. The constructed structure is shown in fig. 2, white represents a feasible space, and black represents a wall; the constructed evacuation network is shown in fig. 3, and red line segments represent the evacuation network; the personnel position distribution is shown in fig. 4, and red color indicates the personnel position.
The evacuation process of people after the accident happens is simulated, the evacuation process is shown as a figure, the figure 5 (a) is a personnel position distribution diagram at the 10 th s of the accident, the figure 5 (b) is a personnel position distribution diagram at the 20 th s of the accident, and the figure 5 (c) is a personnel position distribution diagram at the 30 th s of the accident, so that all simulated personnel can be distributed to a nearest path leading to an outlet, a reasonable evacuation path can be planned for all personnel under a regular scene by the designed algorithm, and meanwhile, the evacuation phenomena such as crowding, moving towards the outlet and the like in the evacuation process can be simulated accurately by the model.
Further, the time of the planning algorithm is compared with the time of the model for evacuation according to the planned path, and the evacuation planning is performed by adopting a direct straight line distance judging method, a virtual node method and a virtual weight node method according to the conditions of average and dispersed personnel distribution in fig. 6 (a), average and dense personnel distribution in fig. 6 (b) and uneven personnel distribution in fig. 6 (c), wherein the time required for performing multi-exit judgment by adopting the straight line distance is the most, the time required for performing multi-exit planning by adopting the virtual node is the shortest, the influence of adding the balance weight on the planning time on the basis of the virtual node is not great, and the time is basically the same as the planning time of the virtual node, so that the evacuation planning algorithm designed by the invention is verified to have certain improvement on the time level.
Table 1 algorithm planning time comparison
Inputting the paths marked by the three algorithms into a guiding model for simulation verification, and evaluating and analyzing the guiding paths marked by the algorithms by simulating the time of the evacuation process of the personnel through the model.
The people evacuation time is compared with that shown in table 2, when the distribution of the people positions is average, as shown in fig. 6 (a) and fig. 6 (b), the time for evacuating the guide path marked by people according to each algorithm is not much different, when the distribution of the people positions is uneven and people are gathered, as shown in fig. 6 (c), the conventional multi-exit is not much different from the guide evacuation time only added with virtual nodes, but after the balance weight is added, the people path nodes are not simply determined by distance factors any more, and meanwhile, the people can be more evenly distributed to each exit, and the evacuation time of the people is less according to the guide path, so that the people can be more reasonably distributed by adopting the balance distribution algorithm for multi-exit personnel path planning, thereby achieving the purpose of reducing the evacuation time.
Table 2 model evacuation time comparison
As can be seen from table 1 and table 2, compared with the conventional multi-outlet allocation algorithm, the virtual node is added to improve the planning time of the algorithm to a certain extent, and the balanced allocation algorithm improves the mass improvement of the group evacuation path in the scene of uneven personnel distribution.
In summary, in a scene with regular distribution of exits such as passenger ships, the evacuation method combining the evacuation network and the social force model, which is designed by the invention, has high planning efficiency and path output quality, and can further dynamically simulate the evacuation process.
Claims (4)
1. The ocean-going passenger ship personnel emergency evacuation path planning algorithm based on the virtual nodes is characterized by comprising the following steps:
Step one: acquiring an evacuation communication diagram: collecting relevant data of a passenger ship, constructing a passenger ship structure map, simplifying the ship structure map, extracting the center position, the exit position, the corridor corner, the escape exit position and the feasible region nodes in part of feasible space of each room in the structure map, and constructing a communication map;
Step two: constructing an evacuation network topological graph added with equidistant virtual target nodes: based on the communication graph, calculating the position of a virtual node through the position of each outlet, adding the virtual node into a communication network, and establishing an evacuation network topology graph of the ship;
Step three: initializing a passenger position, and accessing the passenger position into an evacuation network topological graph;
step four: on the basis of an evacuation network topological graph, taking the initial position of a passenger as a starting point, taking a virtual target node as a planning terminal point, and adopting an A-based algorithm of a virtual node network to perform path searching to obtain the evacuation path of the current passenger;
Step five: judging whether all passengers finish planning, if not, dynamically updating the virtual node position according to the exit position selected by the current passenger, starting the planning process of the next passenger, and repeating the steps three to five until the planning task of all passengers is finished, and outputting the evacuation paths of all passengers;
Step six: the method comprises the steps of constructing a social force model based on path guidance, inputting all evacuation paths output by a planning algorithm into the social force model, taking each point in the path output by the planning algorithm as a driving point operation model for evacuating individuals in the model, and outputting a final dynamic evacuation path.
2. The ocean-going passenger vessel personnel emergency evacuation path planning algorithm based on the virtual node according to claim 1, wherein the second step specifically comprises:
(1) Virtual node network construction
Designing an equidistant virtual node to convert the multi-outlet problem into a searching process of the virtual node, and constructing an evacuation network topological graph added with equidistant virtual target nodes:
the calculation method formula of the initial virtual node aiming at the average distribution of the evacuation outlet positions is as follows:
Wherein [ x, y ] represents the position of the virtual node, goal represents the exit node position, and N represents the total number of exits;
(2) Evacuation search algorithm expansion
Initializing a passenger position, accessing the passenger position into a communication network, taking the passenger initial position as a starting point and a virtual target node as a planning terminal point on the basis of an evacuation network topological graph, and adopting an A-algorithm to search a path until all passengers are planned;
In the process, the cost value of the original A-type algorithm is adopted for node expansion, so that excessive searching of useless nodes is caused, when the virtual nodes are taken as targets for node expansion, negative excitation is required to be adopted for searching of the target nodes, the negative number of the distance from the expanded nodes to the virtual nodes is adopted as the cost value of node expansion, and the calculation formula of the cost value is as follows:
hv(n)＝L-h(n)
Where h (n) represents the straight line distance from the intermediate node to the virtual node, L is a relatively suitable positive value and the cost value is avoided as a negative number.
3. The ocean-going passenger vessel personnel emergency evacuation path planning algorithm based on the virtual node according to claim 1, wherein the dynamic updating mode in the fifth step specifically comprises: when the number of passengers is increased and the passenger densities of all the areas are not equal, the congestion situation of individual exits is caused, balanced adjustment weights are introduced for the situation that the passenger densities of all the areas are not equal, when the passengers arrive at one exit, one weight of the exit is adjusted, and the positions of virtual nodes are updated at the same time, so that the cost from the virtual nodes to all the exits is changed, the passengers select the exits with less personnel numbers under the condition of equal distance cost, and the situation of balanced personnel distribution is achieved;
the cost of the distance from the virtual node at the initial position to each outlet is equal, when a person escapes from the outlet, the virtual node performs position update in a mode of approaching to the outlet, so that the cost value of the virtual node is increased, the position update is performed by adopting the reverse extension line of the connection line of the virtual node and the outlet, and the position update equation of the virtual node is as follows:
Wherein: l represents the forward extension distance, which is determined by the map size and the number of people, k represents the slope between the links, (x 0,y0) represents the original virtual node position, (x goal,ygoal) represents the position of the exit selected by the previous planning.
4. The ocean-going passenger vessel personnel emergency evacuation path planning algorithm based on the virtual nodes according to claim 1, wherein the social force model construction based on the guiding path in the sixth step specifically comprises:
(1) Basic model construction
The social force model expresses the decision behaviors of the individuals in the evacuation process in a force mode, quantitatively describes the psychological activities of the individuals by adopting mathematical modeling, and the model equation is as follows:
wherein, Representing the driving force of the individual per se,/>Representing the interaction force between a person and the environment,/>Representing the interaction force from person to person;
Where τ i represents the step reaction time of individual i, i.e. the time it takes for the pedestrian's motion state to change; The actual movement speed and direction of the individual i at the time t are represented; /(I) Representing a desired speed of the individual advancing to the target point without external disturbance; /(I)A unit vector representing the desired direction of the individual i at time t;
Wherein A i exp[(rij-dij)/Bi]nij represents psychological acting force of an individual at a certain distance from other surrounding individuals, A i represents acting intensity coefficient, B i represents repulsive force range coefficient, and the coefficients are constant; k 1g(rij-dij)nij represents the extrusion force between individuals, k 1 represents the extrusion coefficient, r ij represents the distance between the individuals i and j, n ij represents the normalized vector from the individual i to the individual j, perpendicular to t ij, t ij represents the tangential direction perpendicular to n ij, and d ij represents the center distance between the two individuals; representing the sliding friction between individuals, k 2 representing the coefficient of friction;
Wherein d iw represents the shortest distance between the individual i and the obstacle w; n iw represents a unit vector from the obstacle w to the centroid of the pedestrian i; t iw is a unit vector of a friction direction when a pedestrian contacts an obstacle;
(2) Joining planning guidance
1) Map architecture
Abstracting a map into two layers: the first layer is a path planning Map layer, denoted Map1 (x, y); the first layer is a topological network formed by feasible paths, and comprises various key nodes and passable path segments between the key nodes; the second layer is an evacuation model demonstration layer and is expressed as Map2 (x, y); the second layer is a continuous map, records the environmental information of the actual evacuation scene, and is used for displaying the actual position of personnel evacuation and the environmental information of the evacuation scene;
2) Node conversion
And (3) guide point conversion judgment: when a person moves from the current position to the guide point, if the distance between the current position and the current guide point is smaller than a certain threshold value, switching to the next guide point, continuing the process until the current node is the last path guide node, skipping switching judgment when the current node is the last path node, and ending judgment when the current node reaches a target node;
Guide equation improvement: the guiding equation is modified to slow down the abrupt change of the speed, when approaching the guiding point conversion threshold value, the speed is converted in advance to slow down the trend of the abrupt change of the speed, and the modified guiding equation is as follows:
wherein: f now denotes an attractive force of the current guidance point, f next denotes an attractive force of the next guidance point, ω 1、ω2 is a weight coefficient, R denotes a distance from the person to the current driving point, and R denotes a conversion radius.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210170583.7A CN114527757B (en) | 2022-02-24 | 2022-02-24 | Ocean passenger ship personnel emergency evacuation path planning algorithm based on virtual nodes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210170583.7A CN114527757B (en) | 2022-02-24 | 2022-02-24 | Ocean passenger ship personnel emergency evacuation path planning algorithm based on virtual nodes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114527757A CN114527757A (en) | 2022-05-24 |
| CN114527757B true CN114527757B (en) | 2024-05-31 |
Family
ID=81624242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210170583.7A Active CN114527757B (en) | 2022-02-24 | 2022-02-24 | Ocean passenger ship personnel emergency evacuation path planning algorithm based on virtual nodes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114527757B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115046565A (en) * | 2022-06-16 | 2022-09-13 | 广西大学 | Real-time dynamic planning algorithm for large-scale scenic spot tourist emergency evacuation line |
| CN115862273B (en) * | 2022-11-23 | 2023-09-29 | 中国十七冶集团有限公司 | Intelligent monitoring method for toxic gas |
| CN116109014B (en) * | 2023-04-11 | 2023-08-01 | 广东广宇科技发展有限公司 | Simulation fire-fighting evacuation method for urban rail transit large transfer station |
| CN116523160A (en) * | 2023-05-10 | 2023-08-01 | 南华大学 | Crowd emergency evacuation simulation method based on social force model and A star algorithm |
| CN117168466B (en) * | 2023-10-30 | 2024-02-02 | 南京深业智能化系统工程有限公司 | Escape route planning method, escape route planning device and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133704A (en) * | 2017-06-23 | 2017-09-05 | 南京师范大学 | Follow the analogy method of the dynamic emergency evacuation of large-scale crowd of optimal-forgetting rules |
| CN107368934A (en) * | 2017-08-29 | 2017-11-21 | 李颖 | Ship evacuating personnel decision system based on geographical information technology |
| RU2658232C1 (en) * | 2017-07-25 | 2018-06-19 | федеральное государственное автономное образовательное учреждение высшего образования "Санкт-Петербургский национальный исследовательский университет информационных технологий, механики и оптики" (Университет ИТМО) | Method of the crew and passengers evacuation process control in the occurrence of marine accidents |
| CN110555961A (en) * | 2019-10-15 | 2019-12-10 | 西安科技大学 | LORA-based intelligent evacuation method for commercial complex |
| WO2020187668A1 (en) * | 2019-03-15 | 2020-09-24 | Luxembourg Institute Of Science And Technology (List) | Ship evacuation system |
| CN111985067A (en) * | 2020-07-29 | 2020-11-24 | 河海大学 | Multi-strategy combined evacuation network planning method |
| CN112380678A (en) * | 2020-11-02 | 2021-02-19 | 上海申博信息系统工程有限公司 | Intelligent auxiliary decision-making platform and decision-making method for emergency evacuation of large passenger ship |
| CN112862192A (en) * | 2021-02-08 | 2021-05-28 | 青岛理工大学 | Crowd evacuation auxiliary decision-making system based on ant colony algorithm and improved social model |
| CN112866902A (en) * | 2021-01-12 | 2021-05-28 | 武汉理工大学 | Dynamic dangerous shipborne environment self-adaptive emergency navigation method |
| CN113988408A (en) * | 2021-10-27 | 2022-01-28 | 青岛理工大学 | Multi-objective planning-based artificial guidance method for passenger flow evacuation in subway station |
-
2022
- 2022-02-24 CN CN202210170583.7A patent/CN114527757B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133704A (en) * | 2017-06-23 | 2017-09-05 | 南京师范大学 | Follow the analogy method of the dynamic emergency evacuation of large-scale crowd of optimal-forgetting rules |
| RU2658232C1 (en) * | 2017-07-25 | 2018-06-19 | федеральное государственное автономное образовательное учреждение высшего образования "Санкт-Петербургский национальный исследовательский университет информационных технологий, механики и оптики" (Университет ИТМО) | Method of the crew and passengers evacuation process control in the occurrence of marine accidents |
| CN107368934A (en) * | 2017-08-29 | 2017-11-21 | 李颖 | Ship evacuating personnel decision system based on geographical information technology |
| WO2020187668A1 (en) * | 2019-03-15 | 2020-09-24 | Luxembourg Institute Of Science And Technology (List) | Ship evacuation system |
| CN110555961A (en) * | 2019-10-15 | 2019-12-10 | 西安科技大学 | LORA-based intelligent evacuation method for commercial complex |
| CN111985067A (en) * | 2020-07-29 | 2020-11-24 | 河海大学 | Multi-strategy combined evacuation network planning method |
| CN112380678A (en) * | 2020-11-02 | 2021-02-19 | 上海申博信息系统工程有限公司 | Intelligent auxiliary decision-making platform and decision-making method for emergency evacuation of large passenger ship |
| CN112866902A (en) * | 2021-01-12 | 2021-05-28 | 武汉理工大学 | Dynamic dangerous shipborne environment self-adaptive emergency navigation method |
| CN112862192A (en) * | 2021-02-08 | 2021-05-28 | 青岛理工大学 | Crowd evacuation auxiliary decision-making system based on ant colony algorithm and improved social model |
| CN113988408A (en) * | 2021-10-27 | 2022-01-28 | 青岛理工大学 | Multi-objective planning-based artificial guidance method for passenger flow evacuation in subway station |
Non-Patent Citations (2)
| Title |
|---|
| 基于Dijkstra-ACO混合算法的应急疏散路径动态规划;曹祥红;李欣妍;魏晓鸽;李森;黄梦溪;李栋禄;电子与信息学报;20201231(第006期);全文 * |
| 郭磊;任鸿翔;朱耀辉.基于操控行为和A*算法的船舶人员疏散仿真.大连海事大学学报.第43卷(第2期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114527757A (en) | 2022-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114527757B (en) | Ocean passenger ship personnel emergency evacuation path planning algorithm based on virtual nodes | |
| Gu et al. | A metaverse-based teaching building evacuation training system with deep reinforcement learning | |
| CN107480320B (en) | Crowd evacuation simulation method and system based on topological map and visual influence | |
| CN107480821B (en) | Multi-Agent cooperation crowd evacuation simulation method and device based on example learning | |
| Ha et al. | Cell-based evacuation simulation considering human behavior in a passenger ship | |
| CN107133704B (en) | Simulation method for large-scale crowd dynamic emergency evacuation following optimal-forgetting rule | |
| CN110737968A (en) | Crowd trajectory prediction method and system based on deep convolutional long and short memory network | |
| CN102646166A (en) | Indoor emergency evacuation simulation method for complex building | |
| CN110503257A (en) | A kind of marine personnel's emergency escape paths planning method based on MSC | |
| CN109866798B (en) | Rail transit station passenger evacuation method based on guide member | |
| CN111611749A (en) | RNN-based indoor crowd evacuation automatic guiding simulation method and system | |
| CN107862930B (en) | Operation and maintenance training and assessment system for offshore wind power plant and risk assessment method thereof | |
| CN113359849B (en) | Multi-unmanned aerial vehicle collaborative rapid search method for moving target | |
| CN111339668B (en) | Crowd evacuation visualization method based on emotion cognition | |
| CN112231967A (en) | Crowd evacuation simulation method and system based on deep reinforcement learning | |
| CN115545359B (en) | Dynamic intelligent evacuation method and device for complex building fire | |
| CN110517424A (en) | A kind of indoor fire-fighting emergency evacuation route analogy method | |
| CN114757014A (en) | Personnel evacuation simulation method based on fire of mail steamer and road section capacity limitation | |
| Liu et al. | Intelligent optimization method for the evacuation routes of dense crowds on cruise ships | |
| Guo et al. | Simulation of aircraft cabin evacuation strategy based on exit flow equilibrium | |
| CN117371760B (en) | Layered passenger ship personnel emergency evacuation method considering deadline and congestion relief | |
| CN112597802A (en) | Pedestrian motion simulation method based on visual perception network deep learning | |
| Cheng et al. | A modified particle swarm optimization-based human behavior modeling for emergency evacuation simulation system | |
| Hassan et al. | Using Heuristic search with pedestrian simulation statistics to find feasible spatial layout design elements | |
| CN117631667B (en) | Dynamic guiding obstacle avoidance evacuation method applied to multi-storey building personnel |
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 |