CN117252316A

CN117252316A - Emergency evacuation path planning method, device, equipment and storage medium

Info

Publication number: CN117252316A
Application number: CN202311198833.9A
Authority: CN
Inventors: 康健; 孙志成; 许晓平; 符盛; 胡怡婧
Original assignee: Caos Huazhi Iot Technology Qingdao Co ltd; Cosmoplat Industrial Intelligent Research Institute Qingdao Co Ltd
Current assignee: Caos Huazhi Iot Technology Qingdao Co ltd; Cosmoplat Industrial Intelligent Research Institute Qingdao Co Ltd
Priority date: 2023-09-15
Filing date: 2023-09-15
Publication date: 2023-12-19

Abstract

The invention discloses a method, a device, equipment and a storage medium for planning an emergency evacuation path. The method comprises the steps of obtaining current accident description information and current traffic conditions in a target park; determining a current danger level area in a target park according to the current accident description information, the pre-built park space node network and a pre-set accident result analysis model; determining an evacuation object and an evacuation starting point according to the current traffic condition and the current danger level area; and determining a target evacuation path starting from an evacuation starting point for the evacuation object through a preset path planning algorithm. The technical scheme of the invention provides a novel emergency evacuation path planning method, which combines the actual conditions of an intelligent chemical industry park, relies on an industrial Internet platform to monitor data in real time, and performs dynamic analysis according to the situation development to obtain reasonable evacuation decisions suitable for the chemical industry park, so as to improve the evacuation effect.

Description

Emergency evacuation path planning method, device, equipment and storage medium

Technical Field

The present invention relates to the field of security planning technologies, and in particular, to a method, an apparatus, a device, and a storage medium for planning an emergency evacuation path.

Background

The chemical industry park is used as an important carrier and a platform for high-quality development of the chemical industry, the chemical industry enterprises gather, the safety risk of dangerous chemicals is concentrated, the accident influence is extremely large, and unscientific emergency evacuation easily causes serious consequences.

In the prior art, although the scheme and the method for planning the emergency evacuation path of the chemical industry park exist, the actual condition of the chemical industry park is not combined, and the problem of poor evacuation effect caused by unreasonable evacuation decision of the chemical industry park due to insufficient evacuation decision consideration factors is solved.

Disclosure of Invention

The invention provides a method, a device, equipment and a storage medium for planning an emergency evacuation path, which are used for providing a new method for planning the emergency evacuation path, combining the actual situation of a chemical industry park, and dynamically analyzing according to the situation development to obtain reasonable evacuation decisions suitable for the chemical industry park and improve the evacuation effect.

According to an aspect of the present invention, there is provided an emergency evacuation path planning method, the method comprising:

acquiring current accident description information and current traffic conditions in a target park;

determining a current danger level area in the target park according to the current accident description information, a pre-built park space node network and a pre-set accident result analysis model;

Determining an evacuation object and an evacuation starting point according to the current traffic condition and the current danger level area;

and determining a target evacuation path starting from the evacuation starting point for the evacuation object through a preset path planning algorithm.

According to another aspect of the present invention, there is provided an emergency evacuation path planning apparatus comprising:

the current park condition acquisition module is used for acquiring current accident description information and current traffic conditions in the target park;

the current danger area determining module is used for determining a current danger level area in the target park according to the current accident description information, a pre-built park space node network and a pre-built accident result analysis model;

an evacuation object and starting point determining module, configured to determine an evacuation object and an evacuation starting point according to the current traffic condition and the current hazard level area;

the evacuation path determining module is used for determining a target evacuation path starting from the evacuation starting point for the evacuation object through a preset path planning algorithm.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the emergency evacuation path planning method according to any one of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the emergency evacuation path planning method according to any one of the embodiments of the present invention when executed.

According to the technical scheme, the current accident description information and the current traffic condition in the target park are obtained; determining a current danger level area in a target park according to the current accident description information, the pre-built park space node network and a pre-set accident result analysis model; determining an evacuation object and an evacuation starting point according to the current traffic condition and the current danger level area; the method comprises the steps of determining a target evacuation path from an evacuation starting point for an evacuation object through a preset path planning algorithm, solving the problems that the actual situation of a chemical industry park is not combined and the evacuation effect is poor due to unreasonable evacuation decision for the chemical industry park caused by insufficient evacuation decision consideration factors in the prior art, providing a new emergency evacuation path planning method, combining the actual situation of the chemical industry park, dynamically analyzing according to situation development, obtaining reasonable evacuation decision suitable for the chemical industry park, and improving the evacuation effect.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of an emergency evacuation path planning method according to a first embodiment;

fig. 2a is a flowchart of another emergency evacuation path planning method according to the second embodiment;

fig. 2b is a schematic diagram of a hierarchical evaluation model according to the second embodiment;

fig. 3 is a schematic structural diagram of an emergency evacuation path planning apparatus according to a third embodiment;

fig. 4 is a schematic structural diagram of an electronic device implementing the emergency evacuation path planning method of the present invention.

Detailed Description

In order that the manner in which the invention may be better understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of an emergency evacuation path planning method provided in the first embodiment, where the method may be implemented by an emergency evacuation path planning device, and the emergency evacuation path planning device may be implemented in hardware and/or software, and the emergency evacuation path planning device may be configured in a server or a server cluster. As shown in fig. 1, the method includes:

S110, acquiring current accident description information and current traffic conditions in the target park.

Wherein, the target campus may refer to a chemical industry park. The current incident description information may be information for describing a security incident currently occurring on the target campus, and may include a current incident occurrence point and a current incident type. The current traffic condition can refer to the traffic running condition in the target park after the current safety accident occurs; the current traffic condition can be determined according to the pre-reported obstacle area information and the real-time information of the vehicles and the people; wherein the obstacle zone information includes an accident obstacle zone and an operation obstacle zone; the real-time information of the man-car comprises the current position, the current moving direction and the current moving speed of the man-car. .

In this embodiment, when a security accident occurs in the target park, description information such as the place where the current accident occurs and the type of the accident can be obtained, and the current traffic condition in the target park after the accident occurs can also be obtained.

Specifically, the accident obstacle region may refer to an unvented region caused by a security accident occurring in the target park. For example, accident obstacle regions caused by the conditions of open circuit, house collapse, leakage substance spreading and the like can be marked on a GIS (Geographic Information System ) map by circular obstacle regions, linear obstacle regions, square obstacle regions and polygonal obstacle regions, and the obstacle regions cannot pass through after marking.

The operation obstacle zone may refer to an unvented zone caused by dangerous operation conditions occurring in the target park. For example, because dangerous operation conditions often exist in a chemical industry park, operation report and preparation can be performed in advance, operation time and operation influence areas are marked, operation obstacle identification is performed on an operation road section involved in an operation time period, and an obstacle area cannot pass through after the operation obstacle identification.

For real-time information of people and vehicles, in the embodiment, due to closed management of a chemical industry park, personnel positioning and vehicle positioning can be performed, so that accurate and real-time updated traffic condition analysis can be created by means of personnel and vehicle positioning data. Illustratively, the following is a basic step of traffic situation analysis for such data:

(1) And (3) data collection: a large amount of position data is collected from various sources (e.g., positioning system, video AI, cell phone signals, fixed or mobile sensors, etc.), including the position, speed of movement, direction of the car, and the position and speed of pedestrians.

(2) And (3) data processing: the position data is converted into flow information, for example, the number of vehicles or the flow of people passing through a specific road section is calculated, and the average speed of each direction is calculated.

(3) And (3) traffic state judgment: the current traffic status is rated according to a preset threshold, such as high congestion, medium congestion, clear, etc.

(4) Results show that: and graphically displaying the analysis result on the traffic map in real time.

(5) Continuous updating and optimizing: when new location data is received, the above steps are repeated to update the road conditions.

And S120, determining the current danger level area in the target park according to the current accident description information, the pre-built park space node network and the pre-built accident result analysis model.

The current accident description information may further include accident detailed description information, such as leakage type hazardous chemical substance leakage concentration, fire type combustion heat capacity, explosion type explosive amount, and the like. The preset campus space node network may be a map network established based on GIS and on the actual conditions within the campus. The preset accident result analysis model may be a model for simulating and analyzing accident results after the occurrence of the safety accident. The current danger level area may refer to an area classified according to a danger level, such as a serious danger area, a general safety area, a safety area, etc., after the safety accident of the target park occurs.

In this embodiment, according to the place, the accident type, the accident detailed description information, and the like of the current accident, the result analysis is performed on the current accident based on the pre-established park space node network through the pre-established accident result analysis model, and the current danger level area of the target park is determined on the pre-established park space node network.

In this embodiment, the pre-established park space node network may be established by adding the internal road network information and the internal management information of the target park to the geographic information system; the internal road network information comprises road description information and key position node description information; the internal management information includes campus boundary information, campus gate type information, campus lane type information, and campus classification area information.

The internal road network information may be road network data of the target park, and the internal management information may refer to closed management element information of the target park.

Illustratively, the following provides a set-up procedure for a pre-established park space node network:

1. supplementing and perfecting road network data of chemical industry park

Existing road network information may not include some more detailed or private chemical industry park internal road networks and may use a geographic information system to prepare, process and analyze road network data. And the method is used as a digital model for further tasks such as path planning, emergency decision and the like. The method comprises the steps of obtaining fine road network information in a park through means of comparison and analysis, comparison and analysis of design drawings, on-site investigation and the like by using high-resolution satellite pictures and aerial images, and adding and modifying elements to geographical entities such as a point surface on a geographical information system.

And (5) supplementing and perfecting road network data of the chemical industry park, and carrying out further analysis and research:

taking a road section of a target park as an edge, and taking a road intersection or turning point of the target park as a node to form a frame of a traffic network (a pre-building park space node network); adding attribute description information for the edges, including directions, distances, weights, types and the like; attribute description information including coordinates, names, and the like is added to the nodes.

Nodes and edges may also contain additional attribute information as follows:

a. for an edge, it may comprise:

the direction is: a road segment may be unidirectional or bidirectional.

Distance or weight: representing the distance or time from one node to another, may also indicate traffic difficulties, such as road congestion, road conditions, construction information, etc.

Type (2): each road may be of a different type, such as a highway, an urban road, a roadway, etc.

b. For a node, it may comprise:

coordinates: the precise location of the node on the geographic coordinate system.

Descriptive information: such as intersection names, landmark buildings, etc.

2. Closed management element information of paving park

Based on the aggregation risk of chemical industry garden and the advanced management experience of chemical industry garden, chemical industry garden actively promotes the closed construction of garden, standardizes and optimizes the people stream, commodity circulation and car stream travel path in and out the garden, needs to lay following factor restriction in road network information:

Perimeter: the park sealing range should be matched with the planning boundary of park wholesale and the current development of the park, and the park is physically sealed by utilizing the existing mountain system, water system, fence, enterprise fence, entrance guard/bayonet and the like of the park. A boundary line needs to be laid on the GIS data in a physically closed area, except that the position of the bayonet cannot cross the boundary line.

A bayonet: the bayonet arrangement needs to be divided into a comprehensive bayonet, a special bayonet, a common bayonet and an emergency bayonet according to a passenger-cargo separation principle. The dangerous chemicals transporting vehicle can only pass through the comprehensive bayonet and the special bayonet, and common personnel and vehicles can pass through the comprehensive bayonet and the common bayonet.

Planning a driving path: dividing routes in the park into dangerous chemical traffic lanes and common traffic lanes.

Hierarchical management area planning divides a chemical industry park into different risk areas and is used for comprehensively analyzing safety in subsequent emergency evacuation path planning:

general region division: and areas with lower risk, such as administrative office areas, life service areas, public and auxiliary facility areas and the like, outside the core control area and the key control area in the park.

Dividing key areas: and the areas with higher risks such as chemical production functional areas outside the inner core control area in the park, dangerous goods transportation vehicle parking lots, chemical pipe galleries and the like.

Core region division: and (3) determining a major risk source of the park in the regional security risk assessment, and mainly supervising a high-risk region in the dangerous chemical process set.

3. Converting spatial data into a geometric network map

The road network data of the chemical industry park can be converted into a node network diagram through the following steps:

(1) Identifying and marking nodes: in a road network, each intersection or critical location (e.g., an entrance, a road segment that must be traversed, an important facility, etc.) can be considered a node. Due to the nature of the encapsulation, all channels into and out of this area should be marked as nodes.

(2) Establishing connection: if there is road communication between the two nodes and there is no barrier, a connection should be established between the two nodes. These connections may represent lanes, manways, or any other type of available transmission path.

(3) Attribute assignment: each node and connection may possess some additional properties. For a node, it may contain information about its location in geographic coordinates, whether there is a facility, etc. These properties will directly affect the final path selection.

(4) Forming a directed graph: generally, due to conditions such as single-way traffic, the road network of the chemical industry park is more suitable to be expressed as a directed graph, and each connection has a definite direction.

(5) Establishing a block: some new geometric objects are generated to represent each region. This may include a point, line or plane. And defining block boundaries meeting requirements according to actual requirements. The boundary may be a macroscopic physical boundary, such as an enclosure, river, etc.; but also invisible logical boundaries such as bayonets, risk level changes.

(6) Setting a block boundary: and defining block boundaries meeting requirements according to actual requirements. The boundary may be a macroscopic physical boundary, such as an enclosure, river, etc.; but also invisible logical boundaries such as bayonets, risk level changes.

(7) Labeling characteristics: each block may be given a certain label or attribute, such as a risk level, a belonging area, a core attribute, etc., according to its characteristics.

(8) Updating nodes and connections: inside each block, the nodes and connections remain unchanged, except that they now carry the information of the block to which they belong. The cross-block connection will then be considered as a bridge connecting the blocks.

After the steps are completed, a chemical industry park geometric network diagram with block information can be obtained. This map will contain all walkable paths, all points of importance and their interrelationships within the chemical industry park and can be used for more high level analysis such as overall optimization of layout, detection of important nodes, etc. This will help in evacuation path planning in subsequent works.

In an optional implementation manner of this embodiment, determining the current risk level area in the target campus according to the current accident description information, the pre-established campus space node network and the pre-established accident result analysis model may include: determining associated accident description information according to the current accident occurrence point and the space node network of the pre-established park; the associated accident description information comprises an associated dangerous source and an associated accident type; determining a first target accident consequence analysis model from a preset accident consequence analysis model according to the current accident type, and carrying out consequence analysis on the current accident by using the first target accident consequence analysis model in a space node network of a pre-established park to obtain first expected damage distribution; determining a second target accident consequence analysis model from the preset accident consequence analysis model according to the associated accident type, and carrying out consequence analysis on the associated accident by using the second target accident consequence analysis model in the space node network of the pre-established park to obtain second expected damage distribution; the current risk level region is determined based on the first predicted damage profile and the second predicted damage profile.

The related accident description information may refer to related information of related accidents possibly caused by the current accident. The type of incident associated may or may not be consistent with the type of incident currently. The preset accident consequence analysis model may include analysis models of various accident types, such as a leakage model, a fire model, an explosion model. The first predicted damage profile is a predicted damage profile that matches the current incident. The second predicted damage profile is a predicted damage profile that matches the associated incident. The predicted damage profile may refer to dead zones, heavy and light areas, and the like. By way of example, for leak types, casualties distribution-dead, heavy and light zones may be expected; fire hazard zones-high, medium and low risk zones are identified based on the explosion limit concentrations. For fire types (large tank fire, fire jet, fireball, pool): the personnel risk distribution areas-death area, severe injury area, light injury area, and sensitive area, the equipment risk distribution areas-building failure area, steel failure area, lumber failure area, plastic failure area, and thin steel failure area are predicted. For explosion types (vapor cloud, pressure vessel, solid explosion), personnel injury zones-dead zones, heavy injury zones, light injury zones can be expected; and (5) according to the disaster damage subareas calculated by the accident result analysis model, people and vehicles at least need to be evacuated outside all accident influence circles.

Specifically, an analysis model matched with the accident type of the current accident can be obtained, the current accident is analyzed by combining with a space node network of a pre-established park, and a first expected damage distribution matched with the current accident is determined; similarly determining a second expected damage profile that matches the associated incident; the first projected damage distribution and the second projected damage distribution may be weighted and analyzed on the pre-established campus space node network to determine a current risk level area for the target campus.

The accident result analysis result can be rendered on the GIS graph, so that the potential hazard area and the influence level can be seen more intuitively. The method comprises the following steps:

(1) Generating a base layer: first, a base layer of a site is built in a GIS, which contains all important facilities, roads, equipment and boundary information.

(2) Locating an accident source: and determining the accident source position and marking on the GIS map.

(3) Generating model output data: the appropriate accident outcome analysis model is run and the data output by the model, typically the accident impact range, distribution and size, is collected.

(4) Conversion model results: the output results of the model are converted into a format understandable by the GIS, such as a vector (point, line, plane) or grid.

(5) Superposition of model results: the model results are superimposed and classified on the base layer, and are compared and correlated with existing devices, roads and equipment.

(6) Rendering colors and legends: different colors are used to represent different degrees of risk. While the meaning of the individual colors needs to be described with the addition of the necessary legend.

The preset accident consequence analysis model in the above embodiment may include a hazardous chemical substance leakage atmospheric diffusion analysis model, a fire analysis model, and an explosion analysis model;

the atmospheric diffusion analysis model of the hazardous chemical substance leakage is expressed asWherein C (x, y, z) represents the concentration of the hazardous chemical substance at the location corresponding to (x, y, z), q represents the leakage mass flow rate, μ represents the wind speed, σ _y Sum sigma _z The diffusion parameters of the hazardous chemical in the y-axis direction and the z-axis direction are respectively represented, and H represents the effective height of a leakage source;

the fire analysis model is expressed asWherein q' is radiant heat intensity (kW/m) ² ) Q represents combustion heat capacity (MJ or J), R represents distance from a fire source, and Rad represents effective radiation distance;

the explosion analysis model is expressed asWhere Ps represents overpressure, G represents the equivalent TNT explosive quantity (kg), ko represents dimensionless mechanical constant (various values are available; e.g., 1.036), and R represents the target-to-center linear distance (m).

S130, determining an evacuation object and an evacuation starting point according to the current traffic condition and the current danger level area.

In this embodiment, the people and vehicles gathering point may be determined according to the current position of the people and vehicles reported in advance in the current traffic condition; and determining an evacuation object and an evacuation starting point corresponding to the evacuation object according to the distance between the people and vehicle gathering point and the current danger level area.

Wherein an evacuation object may be an object at a plurality of aggregation points, e.g. aggregation point 1 may correspond to a batch of evacuation objects and aggregation point 2 may correspond to another batch of evacuation objects. The evacuation starting points corresponding to the evacuation objects at different aggregation points are different.

S140, determining a target evacuation path starting from an evacuation starting point for the evacuation object through a preset path planning algorithm.

The target evacuation path may refer to an optimal evacuation path from the evacuation starting point to the safety area of the evacuation object.

Example two

Fig. 2a is a flowchart of another emergency evacuation path planning method according to the second embodiment, where the operation of S140 is refined based on the foregoing embodiment. As shown in fig. 2a, the method comprises:

s210, acquiring current accident description information and current traffic conditions in the target park.

And S220, determining the current danger level area in the target park according to the current accident description information, the pre-built park space node network and the pre-built accident result analysis model.

S230, determining an evacuation object and an evacuation starting point according to the current traffic condition and the current danger level area.

S240, based on the pre-established park space node network and the pre-established evacuation conditions, determining an alternative evacuation path from the evacuation starting point to the safety area for the evacuation object through a shortest path algorithm.

The preset evacuation conditions may include, for example: the path involving the obstacle area is not passable; not directly traversing from the campus perimeter; the dangerous chemicals transporting vehicle can only pass through the comprehensive bayonet and the special bayonet, common personnel and vehicles can pass through the comprehensive bayonet and the common bayonet, and the emergency bayonet can also pass through in the evacuation process. The shortest path algorithm may be Dijkstra algorithm, floyd-Warshall algorithm, etc.

S250, analyzing the alternative evacuation paths through a hierarchical analysis method to determine a target evacuation path.

In an alternative embodiment, the analysis of the alternative evacuation path by the analytic hierarchy process, and the determination of the target evacuation path may include: acquiring a decision target and at least one decision consideration factor, and taking an alternative evacuation path as an object to be decided; determining the weight of at least one decision consideration factor to a decision target, and determining the weight of an object to be decided to each decision consideration factor; constructing a weight vector for each weight of the decision target according to each decision consideration factor; multiplying the weight of the object to be decided on each decision consideration factor by the weight vector to determine the evaluation score corresponding to the object to be decided; and determining a target evacuation path from the alternative evacuation paths according to the evaluation scores.

Based on the above-described alternative embodiments, determining the weight of the at least one decision consideration on the decision target may include: at least one decision consideration factor is compared pairwise under a decision target to obtain a corresponding comparison result, and the comparison result is used as a matrix element to construct a first judgment matrix; by passing throughAnd->Determining a weight of at least one decision consideration on a decision target; wherein W is _i Representing the ith decisionWeights of factors on decision targets are considered; i, j represent the rows and columns of the first judgment matrix, respectively; n represents the number of decision considerations and the order of the first decision matrix; a, a _ij Matrix elements representing the first judgment matrix.

Further, byDetermining the maximum eigenvalue of the first judgment matrix; wherein A represents a first judgment matrix; w= (W) ₁ ,W ₁ …W _i …W _n ) ^T W represents a weight vector; determining a consistency index according to the maximum characteristic value and the order of the first judgment matrix; and carrying out consistency check on the first judgment matrix according to the consistency index.

Further, determining the weight of the object to be decided on to each decision consideration factor may include: under the condition that the first judgment matrix passes consistency test, the objects to be decided are compared pairwise under each decision consideration factor, and a second judgment matrix corresponding to each decision consideration factor is respectively constructed; and determining the weight of the object to be decided on each decision consideration factor according to the matrix elements of the second judgment matrix.

A method of determining a target evacuation path is described below by way of example.

(1) Constructing a hierarchical evaluation model

Referring to fig. 2b, a hierarchical evaluation model is constructed according to a decision target (i.e., a target layer: selecting a best path), at least one decision consideration (i.e., a criterion layer: closing management compliance level C1, peripheral risk C2, accident consequence analysis influence C3, time C4, path C5), and an object to be decided (i.e., a solution layer: head 1, head 2, head 3, head 4, head 5, … …).

(2) Constructing a first judgment matrix

The first judgment matrix is constructed by comparing the factors of the criterion layer with each other in pairs, and determining the weight of the factors of the criterion layer to the target layer. The results of the pairwise comparisons can be given using the 1-9 scale method of Santy, as shown in Table 1:

TABLE 1

Scale with a scale bar	Meaning of
		1	Representing that the two elements are of equal importance in comparison
3	The former is slightly more important than the latter in terms of two elements
		5	The former is significantly more important than the latter in terms of the two elements
7	Representing the comparison of two elements, the former is extremely important than the latter
		9	The former is of greater importance than the latter, indicating that the two elements are compared
2,4,6,8	Intermediate value representing the above-mentioned adjacency judgment
		Reciprocal of 1 to 9	Representing the importance of the corresponding two-factor exchange order comparison

To compare the importance of C1, C2, C3, C4, C5 to target O, C _i :C _j ＝a _ij For the criterion layer, we can build a momentArrayWherein the elements in A satisfy: a, a _ij ＞0，/>a _ii ＝1。

For the criteria layer: the closing management accords with the degree, the peripheral risk, the analysis influence of accident results, the time and the distance, for example, a 5*5 judgment matrix as shown in the table 2 can be constructed:

TABLE 2

(3) Hierarchical single ordering and consistency checking

a. Hierarchical single ordering: the hierarchical single ranking refers to ranking all elements in the layer by two for a certain element in the previous layer, performing hierarchical ranking, and performing ranking of important sequences, wherein specific calculation can be performed according to a first judgment matrix a, and the calculation ensures that the elements can meet aw=λ _max Feature root and feature vector conditions for W. Here, the largest feature root of A is lambda _max Corresponding to lambda _max Is normalized by the feature vector W, W _i The component of W, which refers to the weight, corresponds to its respective element list ordering. And calculating the weight (weight coefficient) of each factor of the criterion layer to the target layer by using the first judgment matrix.

Weight vector W and maximum feature root lambda _max The calculation steps of (a) are shown in the following table:

for matrix A, the product is calculated according to the row elements, and then the product is calculatedPower of: />

Will W _i Normalization (making the sum of the elements in the vector equal to 1) is the sorting weight vector,let W (the element of W is the ranking weight of the same level factor relative importance to the factor of the previous level), then W= (W ₁ ,W ₁ …W _i …W _n ) ^T I.e., the feature vector that is sought, is also the result of the hierarchical single ordering of the first decision matrix,

maximum feature root of first judgment matrix

b. Solving the maximum characteristic root and CI value:

in the analytic hierarchy process, the consistency index of judgment can be checked with the following consistency index CI:calculating a consistency ratio based on the consistency index, when the consistency ratio CR<At 0.1, the degree of inconsistency of A is considered to be within the allowable range, and satisfactory consistency is found, passing the consistency test. At this time, the normalized eigenvector is used as the weight vector, otherwise, the first judgment matrix A needs to be reconstructed, and the weight of the first judgment matrix A is equal to that of the first judgment matrix a _ij And (5) adjusting.

Consistency test: and (3) checking the A by using a consistency index and a numerical table with a consistency ratio of <0.1 and a random consistency index.

For example, weight vector w= (0.263,0.475,0.055,0.090,0.110) ^T Consistency index ci= (5.073-5)/(5-1) =0.018, random consistency index ri=1.12 (look-up table), consistency ratio cr=0.018/1.12=0.016<0.1, and thus pass the consistency check.

(4) Solving the optimal evacuation path (i.e. the target evacuation path)

The weights of C1-C5 are shown in Table 3:

TABLE 3 Table 3

The roads from the evacuation starting point to the outside of the circle can be marked with the road1, the road2, the road3 and the road …, which need to exclude the road with the obstacle, and the pedestrian and the vehicle are needed to be distinguished when the personnel and the vehicle are planned for evacuation paths, and if the chemical industry park perimeter needs to be traversed, the roads need to pass through corresponding bayonets according to the rule of closed management.

Comparing each path with each other as shown in table 4 under C1-C5, and constructing a second judgment matrix of n×n for each of C1-C5:

TABLE 4 Table 4

And the weights of the schemes under the factors C1-C5 are compared in pairs through the hierarchical single ordering in the same way as the first judgment matrix, so that the weights can be used as scores of different roads under the factors.

For the sealing management conformity degree C1, the traffic rules of different lanes and sidewalks are regulated in the sealing management of the chemical industry park, but in order to avoid escaping from no place in an accident influence area, traffic can be performed incompletely according to the regulation, but the sealing management non-conformity degree needs to be calculated, the conformity degree judgment is performed on different vehicles and people according to the path length/path total length conforming to the sealing management, and the comparison value in A1 is obtained by performing pairwise direct proportion on different paths.

For the perimeter risk C2, weighting coefficients e are used to distinguish between risk areas of different levels within the path vertical direction 100m, as shown in table 5:

TABLE 5

General control zone e1	Key zone division e2	Core region division e3
			1	2	3

The perimeter risk R is obtained by multiplying the areas of the vertical direction 100m involving the risk areas of different classes by the class coefficient, r=s1×e1+s2×e2+s3×e3, and then inversely proportional to the pairs of different paths to obtain the contrast value in the A3 matrix.

For the analysis of the impact of the accident C3, it is necessary to calculate the gas concentration C (leakage model), the radiant heat flux q "(fire model), the shock wave pressure Ps (explosion model), the time t of the personnel/vehicle exposure, the gas concentration load tl=c×t, the radiant heat flux load ul=q×t, the shock wave pressure load ml=ps×t;

Taking a leakage model as an example, dividing an emergency evacuation path into a plurality of sections delta l, and setting sampling points according to the intervals of delta l. The gas concentration, radiant heat flux and shock wave pressure between adjacent sampling points are calculated by using the data of the previous sampling point, so that the emergency evacuation path is discretized into a path consisting of innumerable sections delta l, and the gas concentration load value on the path is as follows:wherein Δt is _n Representing the sampling time interval between adjacent sampling points, C _n Representing the concentration of gas between adjacent sampling points, v _n Representing the speed between passing adjacent sample points; n represents an nth sampling point, and m represents the total number of sampling points;

the load values of the radiant heat flux and the seismic pressure on different paths are obtained in the same way, and then the contrast value in the A3 judgment matrix is obtained by carrying out inverse proportion on the different paths.

For the time C4, the time of the person/vehicle in each section can be calculated by combining road condition information, and then the contrast value in the judgment matrix of A4 is obtained by carrying out inverse proportion on different paths.

For the path C5, the paths of different paths are inversely proportional to each other to obtain the contrast value in the A5 matrix.

The weights Wa1, wa2, wa3, wa4 and Wa5 of the road1, road2 and road3 … roadn to A1-A5 can be obtained.

For different path schemes, the score is Wa1 x W, wa2 x W, wa x W, wa x W, wa x W, and the score with high score is the best path (i.e. the target evacuation path).

And the ratio of each criterion of the criterion layer can be configured in a pairwise manner according to different requirements to highlight the influence importance degree of different factors of the closed management compliance degree, the peripheral risk, the accident result analysis influence, the time and the distance.

According to the technical scheme, the current accident description information and the current traffic condition in the target park are obtained; determining a current danger level area in a target park according to the current accident description information, the pre-built park space node network and a pre-set accident result analysis model; determining an evacuation object and an evacuation starting point according to the current traffic condition and the current danger level area; determining an alternative evacuation path from an evacuation starting point to a safety area for an evacuation object through a shortest path algorithm based on a pre-established park space node network and a pre-established evacuation condition; and analyzing the alternative evacuation path by using an analytic hierarchy process to determine a target evacuation path. The problem that the existing technology does not combine the actual condition of the chemical industry park and the evacuation decision consideration factor is insufficient to cause the unreasonable evacuation decision to the chemical industry park so as to cause the poor evacuation effect is solved, a new emergency evacuation path planning method is provided, the actual condition of the chemical industry park is combined, dynamic analysis is also carried out according to the situation development, the reasonable evacuation decision which is adapted to the chemical industry park is obtained, and the evacuation effect is improved.

Example III

Fig. 3 is a schematic structural diagram of an emergency evacuation path planning apparatus according to a third embodiment. As shown in fig. 3, the apparatus includes: a current campus condition acquisition module 310, a current hazard zone determination module 320, an evacuation object and origin determination module 330, and an evacuation path determination module 340. Wherein:

a current campus condition acquisition module 310, configured to acquire current accident description information and current traffic conditions in a target campus;

the current dangerous area determining module 320 is configured to determine a current dangerous level area in the target park according to the current accident description information, a preset park space node network and a preset accident result analysis model;

an evacuation object and start point determination module 330, configured to determine an evacuation object and an evacuation start point according to the current traffic condition and the current hazard level area;

an evacuation path determination module 340, configured to determine a target evacuation path for the evacuation object from the evacuation origin by using a preset path planning algorithm.

Optionally, the current accident description information comprises a current accident occurrence point and a current accident type;

the current traffic condition is determined according to the pre-reported obstacle area information and the real-time information of the vehicles; wherein the obstacle region information includes an accident obstacle region and an operation obstacle region; the real-time information of the man-vehicle comprises the current position, the current moving direction and the current moving speed of the man-vehicle;

the space node network of the pre-built park is established by adding the internal road network information and the internal management information of the target park to a geographic information system; the internal road network information comprises road description information and key position node description information; the internal management information includes campus boundary information, campus gate type information, campus lane type information, and campus classification area information.

Optionally, the current hazard zone determining module 320 may specifically be configured to:

determining associated accident description information according to the current accident occurrence point and a pre-established park space node network; the associated accident description information comprises an associated dangerous source and an associated accident type;

determining a first target accident consequence analysis model from the preset accident consequence analysis model according to the current accident type, and carrying out consequence analysis on the current accident by using the first target accident consequence analysis model in the space node network of the pre-established park to obtain first predicted damage distribution;

Determining a second target accident consequence analysis model from the preset accident consequence analysis model according to the associated accident type, and carrying out consequence analysis on the associated accident by using the second target accident consequence analysis model in the space node network of the pre-established park to obtain second predicted damage distribution;

and determining the current danger level area according to the first predicted damage distribution and the second predicted damage distribution.

Optionally, the preset accident result analysis model comprises a hazardous chemical substance leakage atmospheric diffusion analysis model, a fire analysis model and an explosion analysis model;

the fire analysis model is expressed asWherein q' is radiant heat intensity kW/m ² Q represents combustion heat capacity MJ or J, R represents distance from a fire source, and Rad represents effective radiation distance;

the explosion analysis model is expressed asWhere Ps represents overpressure, G represents equivalent TNT explosive quantity kg, ko represents dimensionless mechanical constant, R represents the linear distance m of the target to the center of explosion.

Optionally, the evacuation object and origin determining module 330 may specifically be configured to:

according to the current position of the person and vehicle, determining a person and vehicle gathering point;

and determining the evacuation object and an evacuation starting point corresponding to the evacuation object according to the distance between the people and vehicle gathering point and the current danger level area.

Optionally, the evacuation path determining module 340 may include:

an alternative evacuation path determination submodule, configured to determine an alternative evacuation path from the evacuation starting point to a safety area for the evacuation object through a shortest path algorithm based on the pre-established park space node network and a preset evacuation condition;

the target evacuation path determination submodule is used for analyzing the alternative evacuation path through an analytic hierarchy process and determining the target evacuation path.

Optionally, the target evacuation path determination submodule may include:

the information acquisition unit is used for acquiring a decision target and at least one decision consideration factor, and taking the alternative evacuation path as an object to be decided;

the weight determining unit is used for determining the weight of the at least one decision consideration factor to the decision target and determining the weight of the object to be decided to each decision consideration factor;

The weight vector determining unit is used for constructing a weight vector for each weight of the decision target according to each decision consideration factor;

the evaluation score determining unit is used for multiplying the weight of the object to be decided on each decision consideration factor by the weight vector to determine the evaluation score corresponding to the object to be decided;

and the target evacuation path determining unit is used for determining the target evacuation path from the alternative evacuation paths according to the evaluation scores.

Optionally, the weight determining unit may specifically be configured to:

the at least one decision consideration factor is compared pairwise under a decision target to obtain a corresponding comparison result, and the comparison result is used as a matrix element to construct a first judgment matrix;

by passing throughAnd->Determining a weight of the at least one decision consideration on the decision target; wherein W is _i Representing the weight of the ith decision consideration on the decision target; i, j represent the rows and columns of the first judgment matrix, respectively; n represents the number of decision considerations and the order of the first decision matrix; a, a _ij Matrix elements representing the first judgment matrix.

Optionally, the emergency evacuation path planning device further includes a consistency check module, configured to:

By passing throughDetermining the maximum eigenvalue of the first judgment matrix; wherein A represents a first judgment matrix; w= (W) ₁ ,W ₁ …W _i …W _n ) ^T W represents a weight vector;

determining a consistency index according to the maximum characteristic value and the order of the first judgment matrix;

and carrying out consistency check on the first judgment matrix according to the consistency index.

Optionally, the weight determining unit may be specifically further configured to:

under the condition that the first judgment matrix passes consistency test, the objects to be decided are subjected to pairwise comparison under each decision consideration factor, and a second judgment matrix corresponding to each decision consideration factor is respectively constructed;

and determining the weight of the object to be decided on each decision consideration factor according to the matrix elements of the second judgment matrix.

The emergency evacuation path planning device provided by the invention can execute the emergency evacuation path planning method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example IV

Fig. 4 shows a schematic diagram of an electronic device 400 that may be used to implement an embodiment of the invention. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 400 includes at least one processor 401, and a memory communicatively connected to the at least one processor 401, such as a Read Only Memory (ROM) 402, a Random Access Memory (RAM) 403, etc., in which the memory stores a computer program executable by the at least one processor, and the processor 401 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 402 or the computer program loaded from the storage unit 408 into the Random Access Memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 may also be stored. The processor 401, the ROM 402, and the RAM 403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

Various components in electronic device 400 are connected to I/O interface 405, including: an input unit 406 such as a keyboard, a mouse, etc.; an output unit 407 such as various types of displays, speakers, and the like; a storage unit 408, such as a magnetic disk, optical disk, etc.; and a communication unit 409 such as a network card, modem, wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

Processor 401 may be a variety of general purpose and/or special purpose processing components with processing and computing capabilities. Some examples of processor 401 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 401 performs the various methods and processes described above, such as the emergency evacuation path planning method.

In some embodiments, the emergency evacuation path planning method may be implemented as a computer program, which is tangibly embodied on a computer-readable storage medium, such as the storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 400 via the ROM 402 and/or the communication unit 409. When the computer program is loaded into RAM 403 and executed by processor 401, one or more steps of the emergency evacuation path planning method described above may be performed. Alternatively, in other embodiments, the processor 401 may be configured to perform the emergency evacuation path planning method by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. An emergency evacuation path planning method, comprising:

2. The method of claim 1, wherein the current incident description information includes a current incident occurrence point and a current incident type;

3. The method of claim 2, wherein determining the current risk level area within the target campus based on the current incident description information, a pre-established campus space node network, and a pre-established incident outcome analysis model comprises:

4. A method according to claim 3, wherein the pre-set accident outcome analysis model comprises a hazardous chemical leakage atmospheric diffusion analysis model, a fire analysis model and an explosion analysis model;

5. The method of claim 2, wherein determining an evacuation object and an evacuation origin from the current traffic condition and the current hazard level region comprises:

6. The method of claim 1, wherein determining a target evacuation path for the evacuation object starting from the evacuation origin point by a preset path planning algorithm comprises:

Determining an alternative evacuation path from the evacuation starting point to a safety area for the evacuation object through a shortest path algorithm based on the pre-established park space node network and a preset evacuation condition;

and analyzing the alternative evacuation path through an analytic hierarchy process to determine the target evacuation path.

7. The method of claim 6, wherein analyzing the alternative evacuation path by analytic hierarchy process to determine the target evacuation path comprises:

acquiring a decision target and at least one decision consideration factor, and taking the alternative evacuation path as an object to be decided;

determining the weight of the at least one decision consideration factor to the decision target, and determining the weight of the object to be decided to each decision consideration factor;

constructing a weight vector for each weight of the decision target according to each decision consideration factor;

multiplying the weight of the object to be decided on each decision consideration factor by the weight vector to determine the corresponding evaluation score of the object to be decided;

and determining the target evacuation path from the alternative evacuation paths according to the evaluation scores.

8. The method of claim 7, wherein determining the weight of the at least one decision consideration on the decision target comprises:

by passing throughAnd->Determining a weight of the at least one decision consideration on the decision target; wherein W is _i Representing the weight of the ith decision consideration to the decision targetWeighing; i, j represent the rows and columns of the first judgment matrix, respectively; n represents the number of decision considerations and the order of the first decision matrix; a, a _ij Matrix elements representing the first judgment matrix.

9. The method as recited in claim 8, further comprising:

10. The method of claim 9, wherein determining the weight of the object to be decided on for each decision consideration comprises:

11. An emergency evacuation path planning apparatus, comprising:

12. An electronic device, the electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the emergency evacuation path planning method of any one of claims 1-10.

13. A computer readable storage medium storing computer instructions for causing a processor to perform the emergency evacuation path planning method of any one of claims 1-10.