CN109117997A - The optimization method and system in the fire-fighting and rescue path based on integrated many algorithms - Google Patents
The optimization method and system in the fire-fighting and rescue path based on integrated many algorithms Download PDFInfo
- Publication number
- CN109117997A CN109117997A CN201810868708.7A CN201810868708A CN109117997A CN 109117997 A CN109117997 A CN 109117997A CN 201810868708 A CN201810868708 A CN 201810868708A CN 109117997 A CN109117997 A CN 109117997A
- Authority
- CN
- China
- Prior art keywords
- incident point
- fire brigade
- path
- fire
- information
- 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.)
- Granted
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 50
- 238000005457 optimization Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000010276 construction Methods 0.000 claims abstract description 17
- 238000013135 deep learning Methods 0.000 claims abstract description 11
- 238000012216 screening Methods 0.000 claims abstract description 11
- 239000003016 pheromone Substances 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 241000257303 Hymenoptera Species 0.000 claims description 3
- 230000000977 initiatory effect Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 206010000372 Accident at work Diseases 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Physics (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The optimization method and system in the fire-fighting and rescue path the invention discloses a kind based on integrated many algorithms, wherein method the following steps are included: S1, pass through Internet of Things obtain incident point；S2, according to incident point, pass through GIS information and calculate incident point periphery fire brigade address；S3, incident point is calculated to the linear distance of fire brigade, carry out fire brigade's sequence, based on apart from short, fire brigade's information of record preceding ten；According to fire brigade's information, and it is based on deep learning algorithm, filters out multiple qualified fire brigade's terminals；The ant group algorithm of S4, each fire brigade's terminal and optimization based on screening calculate incident point to the optimal path between each fire brigade's terminal；S5, it is based on dynamic factor, the smallest path length and optimal final path is selected from multiple optimal paths of calculating；The dynamic factor includes traffic, odd or even number, charge, newly-increased incident point, cancels incident point, road construction situation.
Description
Technical field
The present invention relates to path planning field more particularly to a kind of fire-fighting and rescue routes suitable for industrial accident
The optimization method in the fire-fighting and rescue path based on integrated many algorithms.
Background technique
Fire-fighting and rescue route is to determine an important factor for solving industrial accident quality and specific factor.Fire-fighting and rescue road
Line is with the dynamic changes such as vehicle flowrate, road planning on traffic information, road quality, road.
Present most of platforms, recommended route is the optimization route for considering the factors such as traffic congestion, charge on map.But it is based on
Particular safety production accident scene does not account for fire-fighting and rescue team responding situation, fire fighting truck etc. corresponding to spot.Existing portion
Dividing platform is only to show medical matters resource, fixed video, mobile video and topography and geomorphology based on GIS map, only group police nearby
Foundation is provided；Partial flats only show indoor two-dimentional drawing, identify escape route, select for user.
So far, in all trades and professions optimize route research refer to many algorithms, as dijkstra's algorithm, SAS algorithm,
Multi-objective Evolutionary Algorithm, heuritic approach, deep learning algorithm, ant group algorithm etc..
As the control of development and the safety in production of artificial intelligence technology is more and more stringent, has number to further excavate
According to value and promoted emergency system utilization rate.Based on this background, the optimization algorithm of the rescue route of industrial accident
Research is extremely important and significant.
Problem is that GIS data amount is big in the research of actual field optimal route, and optimization calculated performance is poor, is unable to satisfy user's
Demand.Therefore, selection algorithm has to consider this point.
Summary of the invention
Goal of the invention of the invention is that it is an object of the invention to provide one kind under major industrial accident scene
The rescue route methods of calculation optimization use convenient for related system.
The technical solution adopted by the present invention to solve the technical problems is:
There is provided a kind of optimization method in fire-fighting and rescue path based on integrated many algorithms, which is characterized in that including following
Step:
S1, incident point is obtained by Internet of Things；
S2, according to incident point, pass through GIS information and calculate incident point periphery fire brigade address；
S3, the linear distance that incident point arrives fire brigade is calculated, carries out fire brigade's sequence, based on apart from short, record preceding ten
Fire brigade's information；According to fire brigade's information, and it is based on deep learning algorithm, filters out multiple qualified fire brigade's terminals；
The ant group algorithm of S4, each fire brigade's terminal and optimization based on screening calculate incident point to each fire brigade's end
Optimal path between point；
S5, it is based on dynamic factor, the smallest path length and optimal final is selected from multiple optimal paths of calculating
Path；The dynamic factor includes traffic, odd or even number, charge, newly-increased incident point, cancels incident point, road construction situation；
The ant group algorithm that wherein optimizes specifically includes the following steps:
Use following formula (1) optimization initialization information element；
τxy(0)=W/ (dxy+deye) (1)
Wherein, τxyIt (0) is initialization information element intensity, deyeIt is the straight line vector distance of node y to terminal e；W is system
One normal number of setting；
Pass through the sigmiod function in neural networkWhen ant completes an iteration, then according to the overall situation
The update rule of pheromones only updates the pheromone concentration of this iteration optimal path solution, other do not need to update；When whole ants
After ant traversal is primary, LLocalMinIt is greater thanWhen, σ works as L closer to 0LocalMinMore hour, σ is closer to 1, therefore path length is cured
It is short, then the routing information element concentration of traversal can be stronger, and information content is cured with increasing when executing the update rule of global information element
Fastly；The update rule of global information element is following formula (2)
τxy(t+n)=τxy(t)+μσ△τxy (2)
Wherein,It is the average path length of the sum of locally optimal solution under current scene, LLocalMinIt is office in this iteration
Portion's optimal solution, LMinIt is the global shortest path length at this moment under current scene, μ is given parameters.
Above-mentioned technical proposal is connect, fire brigade's information includes whether fire brigade has fire fighting truck and responding personnel.
It connects above-mentioned technical proposal and is specifically based on GIS number when calculating linear distance of the incident point to fire brigade in step S3
According to by the Information Number value including building, road, wherein characterizing road with road segmental arc, node.
Above-mentioned technical proposal is connect, in step S5, when considering dynamic factor traffic, if the road selected path Zhong Mouduan
Road changes, then it is congested link that road information, which identifies this section of road, by incident point between corresponding fire brigade's terminal
Minimum path length of the minimum path length multiplied by a coefficient, after being adjusted；
When considering dynamic factor odd or even number and charge station, if being related to distinguishing odd-and-even license plate rule and receipts in selected path
Take station, the minimum path length of this scheme is constant；
In newly-increased incident point, current calculating process, return step S3, again operation are run parallel；Cancelling incident point
When, current calculating process is terminated, i.e. return value is 0；
When considering dynamic factor road construction situation, the transitable vehicle width in this section when assessing road construction, with fire-fighting
Vehicle vehicle width is compared, if this section available width is more than or equal to fire fighting truck vehicle width, optimal path is constant, if this section
Available width is less than fire fighting truck vehicle width, then this section is abnormal section.
Above-mentioned technical proposal is connect, incident point is specifically wrapped to the optimal path between one of fire brigade's terminal in step S4
Include following steps:
A) initiation parameter: pheromones intensity Q, maximum number of iterations, information heuristic greedy method α, expected heuristic value
β, parameter μ, initialization information element parameter normal number W, local updating pheromones volatilization factor ρ, given parameters q0With ant number
z；
Calculated result is incorporated into τ according to formula (1) initialization information prime matrix by b) calculate node distance matrixxy(0)；
C) according to node transition rule formula, each ant enters next node, and updates taboo list；
D) according to the pheromone concentration in local updating Policy Updates path, the optimal path of this iteration is obtained；Part is more
New rule are as follows: τxy(t+n)=(1- ρ) τxy(t)+ρ△τxy(t)；If ant is not by section xy, △ τxy(t)=0,
Otherwise △ τxy(t)=Q/Ld；Its ρ is pheromones volatilization factor, and t is the moment, and n indicates road circuit node, and Q is given parameters, LdIt is
The path length that the d ant is searched in current iteration；
E) after ant completes an iteration, with the optimal path for updating Policy Updates this time iteration of global information element
Pheromone concentration, so that optimal path is found, nc=nc+1；ncFor current iteration number, when initialization, nc=0；
If f) ncEqual to the maximum number of iterations of default, then search spread terminates, i.e., this iteration result is optimal
Path and minimal path length；Otherwise return step c.
G) the minimal path length obtained between incident point and the fire brigade is i1, optimal path is (m1,m2…mc)；
The present invention also provides a kind of optimization systems in fire-fighting and rescue path based on integrated many algorithms, comprising:
Incident point obtains module, for obtaining incident point by Internet of Things；
Fire brigade's address calculation module is used for according to incident point, with calculating incident point periphery fire brigade by GIS information
Location；
Fire brigade's screening module, the linear distance for calculating incident point to fire brigade, carry out fire brigade's sequence, based on away from
From short, fire brigade's information of record preceding ten；According to fire brigade's information, and it is based on deep learning algorithm, filters out and multiple meet item
Fire brigade's terminal of part；
Optimal path computation module calculates thing for the ant group algorithm of each fire brigade's terminal and optimization based on screening
Hair point arrives the optimal path between each fire brigade's terminal；
Final path calculation module selects the smallest road from multiple optimal paths of calculating for being based on dynamic factor
Line length and optimal final path；The dynamic factor includes traffic, odd or even number, charge, newly-increased incident point, cancels thing
Send out point, road construction situation；
The ant group algorithm of the optimization used in optimal path computation module specifically includes the following steps:
Use following formula (1) optimization initialization information element；
τxy(0)=W/ (dxy+deye) (1)
Wherein, τxyIt (0) is initialization information element intensity, deyeIt is the straight line vector distance of node y to terminal e；W is system
One normal number of setting；
Pass through sigmiod function common in neural networkWhen ant complete an iteration, then according to
The update rule of global information element only updates the pheromone concentration of this iteration optimal path solution, other do not need to update；When complete
After portion ant traversal is primary, LLocalMinIt is greater thanWhen, σ works as L closer to 0LocalMinMore hour, σ is closer to 1, therefore path length
Shorter, then the routing information element concentration of traversal can be stronger, and information content is cured with increasing when executing the update rule of global information element
Fastly；The update rule of global information element is following formula (2)
τxy(t+n)=τxy(t)+μσ△τxy (2)
Wherein,It is the average path length of the sum of locally optimal solution under current scene, LLocalMinIt is office in this iteration
Portion's optimal solution, LMinIt is the global shortest path length at this moment under current scene, μ is given parameters.
Above-mentioned technical proposal is connect, fire brigade's information includes whether fire brigade has fire fighting truck and responding personnel.
Above-mentioned technical proposal is connect, when calculating linear distance of the incident point to fire brigade in fire brigade's screening module, specific base
It will include the Information Number value of building, road, wherein characterizing road with road segmental arc, node in GIS data.
Above-mentioned technical proposal is connect, final path calculation module is when considering dynamic factor traffic, if selected path
In certain section of road change, then it is congested link that road information, which identifies this section of road, by incident point to corresponding fire brigade end
Minimum path length of the minimum path length multiplied by a coefficient, after being adjusted between point；
When considering dynamic factor odd or even number and charge station, if being related to distinguishing odd-and-even license plate rule and receipts in selected path
Take station, the minimum path length of this scheme is constant；
In newly-increased incident point, current calculating process, return step S3, again operation are run parallel；Cancelling incident point
When, current calculating process is terminated, i.e. return value is 0；When considering dynamic factor road construction situation, assess road construction when this
The transitable vehicle width in section, is compared with fire fighting truck vehicle width, if this section available width is more than or equal to fire fighting truck vehicle width,
Optimal path is constant, if this section available width is less than fire fighting truck vehicle width, this section is abnormal section.
The present invention also provides a kind of computer readable storage mediums, have the computer journey that can be executed by processor
Sequence, the computer program execute such as the fire-fighting and rescue path of any of claims 1-4 based on integrated many algorithms
Optimization method the step of.
The beneficial effect comprise that: the present invention is based on the behavioral characteristics of fire-fighting and rescue route, using optimization ant colony
Algorithm obtains static optimal route, meanwhile, in conjunction with deep learning algorithm and dynamic route adjustment algorithm, obtain dynamic optimal
Route.It joined direction guidance in initialization information element concentration, ant selection next node made to tend to the direction in terminal direction
Property；Sigmiod function is introduced as dynamic factor in global information element update, and each iteration optimal solution is adaptively adjusted
To the specific gravity of the Pheromone update in path, the shorter pheromones addition of optimal solution it is more, otherwise longer addition it is less, from
And keeping result more objective, more closing to reality situation more has practicability.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the flow chart of the optimization method in fire-fighting and rescue path of the embodiment of the present invention based on integrated many algorithms；
Fig. 2 is the structural representation of the optimization system in fire-fighting and rescue path of the embodiment of the present invention based on integrated many algorithms
Figure.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
The present invention is based on deep learning algorithm, optimization ant group algorithm and dynamic route adjustment algorithms to solve fire-fighting and rescue path
Optimization problem, main purpose is rapidly to find effective shortest path, reduce rate of loss in accident.Specific implementation step is as follows
It is described.
The optimization method in the fire-fighting and rescue path based on integrated many algorithms of the invention, as shown in Figure 1, specifically include with
Lower step:
Step 1: determining beginning and end first；
1, incident point a is obtained by Internet of Things；
2, incident point periphery fire brigade address is calculated by GIS information according to incident point；
3, the linear distance that incident point arrives fire brigade is calculated, fire brigade's sequence is carried out, based on apart from short, recordable preceding ten
Fire brigade's information, such as fire brigade b1, b2, and so on；
4, according to fire brigade's information, it is based on deep learning algorithm, screens the terminal of fire brigade.As whether fire brigade has fire-fighting
Vehicle and responding personnel, carry out adaptation fire brigade.B3 does not have fire fighting truck at this time, then terminal is b1, b2 and b4；
Step 2: being based on each terminal, the optimal path of this terminal is obtained；
5, the optimal path between a to fire brigade b1 is first calculated, step includes:
5.1 quantize by the cartographic information on the periphery starting point to the end b1 of a.It is whole for searching b1 nearby with equipment
Point, the range of the selected map that needs to quantize, is based on GIS data, by the Information Numbers value such as building, road, wherein with road arc
Section, node characterize road.
5.2, according to fire fighting truck vehicle model information, are based on deep learning algorithm, filter road.If having a lot of social connections for road cannot expire
The requirement of the such fire fighting truck vehicle of foot, then by such road markings at abnormal road；
5.3 are based on GIS information, using the ant group algorithm of optimization, obtain shortest path and the smallest path length.Specific packet
It includes:
A) initiation parameter: pheromones intensity Q=1, maximum number of iterations 500, information heuristic greedy method α=1.0, phase
Prestige heuristic greedy method β=1.0, parameter μ=2, initialization information element parameter (normal number) W=0.01, local updating pheromones are waved
Send out factor ρ=0.2, given parameters q0=0.5 and ant number z is 15.
Calculated result is incorporated into τ according to 1 initialization information prime matrix of formula by b) calculate node distance matrixxy(0)；
τxy(0)=W/ (dxy+deye) formula 1
Wherein, τxyIt (0) is initialization information element intensity, deyeIt is the straight line vector distance of node y to terminal e；W is system
One normal number of setting.
C) according to node transition rule formula, each ant enters next node, and updates taboo list；
D) according to the pheromone concentration of regular (formula 2) the more new route of local updating, the optimal path of this iteration is obtained；
τxy(t+n)=(1- ρ) τxy(t)+ρ△τxy(t) formula 2
If ant is not by section xy, △ τxy(t)=0, otherwise △ τxy(t)=Q/Ld。
Its ρ is pheromones volatilization factor, and t is the moment, and n indicates road circuit node, and Q is given parameters, LdIt is that the d ant exists
The path length of current iteration search.
E) after ant completes an iteration, the information of the optimal path of this iteration is updated with global rule (formula 3)
Plain concentration, so that optimal path is found, nc=nc+1；
τxy(t+n)=τxy(t)+μσ△τxyFormula 3
Wherein,It is the average path length of the sum of locally optimal solution under current scene, LLocalMinIt is office in this iteration
Portion's optimal solution, LMinIt is the global shortest path length at this moment under current scene, μ is given parameters.
If f) ncEqual to the maximum number of iterations of default, then search spread terminates, i.e., this iteration result is optimal
Path and minimal path length；Otherwise return step c.
G) a and b are obtained1Between minimal path length be i1, optimal path is (m1,m2…mc)；
It 6, is b based on terminal2And b4Scene, repeat step 5.Therefore, at this point, obtaining 3 optimal path schemes,
That is b2Corresponding minimal path length is i2, optimal path is (n1,n2…nc)；The corresponding minimal path length of b4 is i3, optimal
Path is (o1,o2…oc)。
Step 3: being based on dynamic factor, the smallest path length and optimal path are obtained；
7, expert assigns the rule of factor.For every group of a and b (b1,b2,b4) scene, adjust the length of minimum route.
Based on dynamic route adjustment algorithm, dynamic factor be traffic (stopping state: traffic lights and vehicle flowrate), odd or even number, charge,
Newly-increased incident point, cancellation incident point, road construction etc..It is such as based on traffic, if certain section of road becomes in selected path
Change, then road information identifies this section of road as congested link, and this scheme (a-b1Scheme) minimum path length multiplied by one
A coefficient is adjusted the minimum path length of this rear scheme；Based on odd or even number and charge station, if be related in selected path
It distinguishes odd-and-even license plate rule and charge station, the minimum path length of this scheme is constant；Based on newly-increased incident point, then running this parallel
Calculating process, return step 4, again operation；Based on incident point is cancelled, when same Internet of Things, which obtains, cancels incident point information, eventually
Calculating process here, i.e. return value are 0；Based on road construction, the transitable vehicle width in this section when assessing road construction in real time, with
Fire fighting truck vehicle width is compared, if this section available width is more than or equal to fire fighting truck vehicle width, optimal path is constant, if
This section available width is less than fire fighting truck vehicle width, then this section is abnormal section, return step 5.2.
8, optimal path and fire brigade's information are exported.After dynamic factor adjustment optimal path and minimum path length,
3 the smallest path lengths are compared, obtain rescue fire brigade's information and optimal path.Based on this, under this scene
Selecting emphasis is b2, optimal path is (n1,n2,w2…nc), minimal path length is w.
It is excellent the invention also provides the fire-fighting and rescue path based on integrated many algorithms in order to realize above-mentioned optimization method
Change system, as shown in Figure 2, comprising:
Incident point obtains module, for obtaining incident point by Internet of Things；
Fire brigade's address calculation module is used for according to incident point, with calculating incident point periphery fire brigade by GIS information
Location；
Fire brigade's screening module, the linear distance for calculating incident point to fire brigade, carry out fire brigade's sequence, based on away from
From short, fire brigade's information of record preceding ten；According to fire brigade's information, and it is based on deep learning algorithm, filters out and multiple meet item
Fire brigade's terminal of part；
Optimal path computation module calculates thing for the ant group algorithm of each fire brigade's terminal and optimization based on screening
Hair point arrives the optimal path between each fire brigade's terminal；
Final path calculation module selects the smallest road from multiple optimal paths of calculating for being based on dynamic factor
Line length and optimal final path；The dynamic factor includes traffic, odd or even number, charge, newly-increased incident point, cancels thing
Send out point, road construction situation；
The ant group algorithm of the optimization used in optimal path computation module specifically includes the following steps:
Use following formula optimization initialization information element；
τxy(0)=W/ (dxy+deye)
Wherein, τxyIt (0) is initialization information element intensity, deyeIt is the straight line vector distance of node y to terminal e；W is system
One normal number of setting；
Pass through sigmiod function common in neural networkWhen ant complete an iteration, then according to
The update rule of global information element only updates the pheromone concentration of this iteration optimal path solution, other do not need to update；When complete
After portion ant traversal is primary, LLocalMinIt is greater thanWhen, σ works as L closer to 0LocalMinMore hour, σ is closer to 1, therefore path length
Shorter, then the routing information element concentration of traversal can be stronger, and information content is cured with increasing when executing the update rule of global information element
Fastly；The update rule of global information element is following formula:
τxy(t+n)=τxy(t)+μσ△τxy
Wherein,It is the average path length of the sum of locally optimal solution under current scene, LLocalMinIt is office in this iteration
Portion's optimal solution, LMinIt is the global shortest path length at this moment under current scene, μ is given parameters.
Computer readable storage medium of the invention has the computer program that can be executed by processor, the computer
Program executes the step of optimization method such as the fire-fighting and rescue path based on integrated many algorithms of above-described embodiment.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (10)
1. a kind of optimization method in the fire-fighting and rescue path based on integrated many algorithms, which comprises the following steps:
S1, incident point is obtained by Internet of Things；
S2, according to incident point, pass through GIS information and calculate incident point periphery fire brigade address；
S3, incident point is calculated to the linear distance of fire brigade, carry out fire brigade's sequence, based on apart from short, the fire-fighting of record preceding ten
Team's information；According to fire brigade's information, and it is based on deep learning algorithm, filters out multiple qualified fire brigade's terminals；
The ant group algorithm of S4, each fire brigade's terminal and optimization based on screening, calculate incident point to each fire brigade's terminal it
Between optimal path；
S5, it is based on dynamic factor, the smallest path length and optimal final path is selected from multiple optimal paths of calculating；
The dynamic factor includes traffic, odd or even number, charge, newly-increased incident point, cancels incident point, road construction situation；
The ant group algorithm that wherein optimizes specifically includes the following steps:
Use following formula (1) optimization initialization information element；
τxy(0)=W/ (dxy+deye) (1)
Wherein, τxyIt (0) is initialization information element intensity, deyeIt is the straight line vector distance of node y to terminal e；W is default
A normal number；
Pass through the sigmiod function in neural networkWhen ant completes an iteration, then according to global information
The update rule of element only updates the pheromone concentration of this iteration optimal path solution, other do not need to update；When whole ants time
After going through once, LLocalMinIt is greater thanWhen, σ works as L closer to 0LocalMinMore hour, σ is closer to 1, therefore path length is shorter, that
When executing the update rule of global information element, the routing information element concentration of traversal can be stronger, and information content increases faster；It is global
The update rule of pheromones is following formula (2)
τxy(t+n)=τxy(t)+μσ△τxy (2)
Wherein,It is the average path length of the sum of locally optimal solution under current scene, LLocalMinIt is local optimum in this iteration
Solution, LMinIt is the global shortest path length at this moment under current scene, μ is given parameters.
2. optimization method according to claim 1, which is characterized in that fire brigade's information includes whether fire brigade has and disappear
Anti- vehicle and responding personnel.
3. optimization method according to claim 1, which is characterized in that straight line of the calculating incident point to fire brigade in step S3
Apart from when, be specifically based on GIS data, by include building, road Information Number value, wherein being characterized with road segmental arc, node
Road.
4. optimization method according to claim 1, which is characterized in that in step S5, considering dynamic factor traffic
When, if certain section of road changes in selected path, it is congested link that road information, which identifies this section of road, by incident point
Minimum path length to the minimum path length between corresponding fire brigade's terminal multiplied by a coefficient, after being adjusted；
When considering dynamic factor odd or even number and charge station, if being related to distinguishing odd-and-even license plate rule and charge in selected path
It stands, the minimum path length of this scheme is constant；
In newly-increased incident point, current calculating process, return step S3, again operation are run parallel；When cancelling incident point, eventually
Only current calculating process, i.e. return value are 0；
When considering dynamic factor road construction situation, the transitable vehicle width in this section when assessing road construction, with fire fighting truck vehicle
Width is compared, if this section available width is more than or equal to fire fighting truck vehicle width, optimal path is constant, if this section is available
Width is less than fire fighting truck vehicle width, then this section is abnormal section.
5. optimization method according to claim 1, which is characterized in that incident point is whole to one of fire brigade in step S4
Point between optimal path specifically includes the following steps:
A) initiation parameter: pheromones intensity Q, maximum number of iterations, information heuristic greedy method α, expected heuristic value β, ginseng
Number μ, initialization information element parameter normal number W, local updating pheromones volatilization factor ρ, given parameters q0With ant number z；
Calculated result is incorporated into τ according to formula (1) initialization information prime matrix by b) calculate node distance matrixxy(0)；
C) according to node transition rule formula, each ant enters next node, and updates taboo list；
D) according to the pheromone concentration in local updating Policy Updates path, the optimal path of this iteration is obtained；Local updating rule
Then are as follows: τxy(t+n)=(1- ρ) τxy(t)+ρ△τxy(t)；If ant is not by section xy, △ τxy(t)=0, otherwise
△τxy(t)=Q/Ld；Its ρ is pheromones volatilization factor, and t is the moment, and n indicates road circuit node, and Q is given parameters, LdIt is d
The path length that ant is searched in current iteration；
E) when ant complete an iteration after, with global information element update Policy Updates this time iteration optimal path information
Plain concentration, so that optimal path is found, nc=nc+1；ncFor current iteration number, when initialization, nc=0；
If f) ncEqual to the maximum number of iterations of default, then search spread terminates, i.e., this iteration result be optimal path and
Minimal path length；Otherwise return step c.
G) the minimal path length obtained between incident point and the fire brigade is i1, optimal path is (m1,m2…mc)。
6. a kind of optimization system in the fire-fighting and rescue path based on integrated many algorithms characterized by comprising
Incident point obtains module, for obtaining incident point by Internet of Things；
Fire brigade's address calculation module, for calculating incident point periphery fire brigade address by GIS information according to incident point；
Fire brigade's screening module, the linear distance for calculating incident point to fire brigade carry out fire brigade's sequence, are based on distance
It is short, fire brigade's information of record preceding ten；According to fire brigade's information, and it is based on deep learning algorithm, filtered out multiple eligible
Fire brigade's terminal；
Optimal path computation module calculates incident point for the ant group algorithm of each fire brigade's terminal and optimization based on screening
Optimal path between each fire brigade's terminal；
Final path calculation module selects the smallest route long for being based on dynamic factor from multiple optimal paths of calculating
Degree and optimal final path；The dynamic factor includes traffic, odd or even number, charge, newly-increased incident point, cancels incident
Point, road construction situation；
The ant group algorithm of the optimization used in optimal path computation module specifically includes the following steps:
Use following formula (1) optimization initialization information element；
τxy(0)=W/ (dxy+deye) (1)
Wherein, τxyIt (0) is initialization information element intensity, deyeIt is the straight line vector distance of node y to terminal e；W is default
A normal number；
Pass through sigmiod function common in neural networkWhen ant completes an iteration, then according to the overall situation
The update rule of pheromones only updates the pheromone concentration of this iteration optimal path solution, other do not need to update；When whole ants
After ant traversal is primary, LLocalMinIt is greater thanWhen, σ works as L closer to 0LocalMinMore hour, σ is closer to 1, therefore path length is cured
It is short, then the routing information element concentration of traversal can be stronger, and information content is cured with increasing when executing the update rule of global information element
Fastly；The update rule of global information element is following formula (2)
τxy(t+n)=τxy(t)+μσ△τxy (2)
Wherein,It is the average path length of the sum of locally optimal solution under current scene, LLocalMinIt is local optimum in this iteration
Solution, LMinIt is the global shortest path length at this moment under current scene, μ is given parameters.
7. optimization system according to claim 6, which is characterized in that fire brigade's information includes whether fire brigade has and disappear
Anti- vehicle and responding personnel.
8. optimization system according to claim 6, which is characterized in that calculate incident point in fire brigade's screening module to fire-fighting
When the linear distance of team, it is specifically based on GIS data, will include the Information Number value of building, road, wherein with road segmental arc, section
Point is to characterize road.
9. optimization system according to claim 6, which is characterized in that final path calculation module is considering dynamic factor friendship
When access condition, if certain section of road changes in selected path, it is congested link that road information, which identifies this section of road, will
Minimal path wire length of the incident point to the minimum path length between corresponding fire brigade's terminal multiplied by a coefficient, after being adjusted
Degree；
When considering dynamic factor odd or even number and charge station, if being related to distinguishing odd-and-even license plate rule and charge in selected path
It stands, the minimum path length of this scheme is constant；
In newly-increased incident point, current calculating process, return step S3, again operation are run parallel；When cancelling incident point, eventually
Only current calculating process, i.e. return value are 0；
When considering dynamic factor road construction situation, the transitable vehicle width in this section when assessing road construction, with fire fighting truck vehicle
Width is compared, if this section available width is more than or equal to fire fighting truck vehicle width, optimal path is constant, if this section is available
Width is less than fire fighting truck vehicle width, then this section is abnormal section.
10. a kind of computer readable storage medium, which is characterized in that it has the computer program that can be executed by processor, should
Computer program executes the optimization such as the fire-fighting and rescue path of any of claims 1-4 based on integrated many algorithms
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810868708.7A CN109117997B (en) | 2018-08-02 | 2018-08-02 | Fire rescue path optimization method and system based on integration of multiple algorithms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810868708.7A CN109117997B (en) | 2018-08-02 | 2018-08-02 | Fire rescue path optimization method and system based on integration of multiple algorithms |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109117997A true CN109117997A (en) | 2019-01-01 |
| CN109117997B CN109117997B (en) | 2022-04-08 |
Family
ID=64851608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810868708.7A Active CN109117997B (en) | 2018-08-02 | 2018-08-02 | Fire rescue path optimization method and system based on integration of multiple algorithms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109117997B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110264019A (en) * | 2019-07-19 | 2019-09-20 | 江西理工大学 | A kind of congested link method for optimizing route based on ant group algorithm |
| CN112138314A (en) * | 2020-09-25 | 2020-12-29 | 南京工程学院 | Artificial intelligence fire-extinguishing robot |
| CN113487164A (en) * | 2021-06-30 | 2021-10-08 | 武汉理工光科股份有限公司 | Fire rescue force intelligent dispatching method and device and storage medium |
| CN115994635A (en) * | 2023-03-23 | 2023-04-21 | 广东鉴面智能科技有限公司 | Belt optimal discharging transportation path detection method, system and medium |
| CN116046001A (en) * | 2022-11-26 | 2023-05-02 | 中国消防救援学院 | Rescue path planning method and system based on intelligent fire fighting |
| CN117745083A (en) * | 2024-02-20 | 2024-03-22 | 山东居安特消防科技有限公司 | Fire control management system and method based on big data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170017884A1 (en) * | 2014-06-23 | 2017-01-19 | International Business Machines Corporation | Solving vehicle routing problems using evolutionary computing techniques |
| CN106971245A (en) * | 2017-03-30 | 2017-07-21 | 广东工业大学 | A kind of determining method of path and system based on improvement ant group algorithm |
-
2018
- 2018-08-02 CN CN201810868708.7A patent/CN109117997B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170017884A1 (en) * | 2014-06-23 | 2017-01-19 | International Business Machines Corporation | Solving vehicle routing problems using evolutionary computing techniques |
| CN106971245A (en) * | 2017-03-30 | 2017-07-21 | 广东工业大学 | A kind of determining method of path and system based on improvement ant group algorithm |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110264019A (en) * | 2019-07-19 | 2019-09-20 | 江西理工大学 | A kind of congested link method for optimizing route based on ant group algorithm |
| CN110264019B (en) * | 2019-07-19 | 2022-11-01 | 江西理工大学 | Congestion road section path optimization method based on ant colony algorithm |
| CN112138314A (en) * | 2020-09-25 | 2020-12-29 | 南京工程学院 | Artificial intelligence fire-extinguishing robot |
| CN113487164A (en) * | 2021-06-30 | 2021-10-08 | 武汉理工光科股份有限公司 | Fire rescue force intelligent dispatching method and device and storage medium |
| CN116046001A (en) * | 2022-11-26 | 2023-05-02 | 中国消防救援学院 | Rescue path planning method and system based on intelligent fire fighting |
| CN116046001B (en) * | 2022-11-26 | 2024-04-26 | 中国消防救援学院 | Rescue path planning method and system based on intelligent fire fighting |
| CN115994635A (en) * | 2023-03-23 | 2023-04-21 | 广东鉴面智能科技有限公司 | Belt optimal discharging transportation path detection method, system and medium |
| CN115994635B (en) * | 2023-03-23 | 2023-06-16 | 广东鉴面智能科技有限公司 | Belt optimal discharging transportation path detection method, system and medium |
| CN117745083A (en) * | 2024-02-20 | 2024-03-22 | 山东居安特消防科技有限公司 | Fire control management system and method based on big data |
| CN117745083B (en) * | 2024-02-20 | 2024-05-24 | 山东居安特消防科技有限公司 | Fire control management system and method based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109117997B (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109117997A (en) | The optimization method and system in the fire-fighting and rescue path based on integrated many algorithms | |
| Dulebenets et al. | Exact and heuristic solution algorithms for efficient emergency evacuation in areas with vulnerable populations | |
| US10145699B2 (en) | System and methods for real-time escape route planning for fire fighting and natural disasters | |
| Sanchez-Silva et al. | A transport network reliability model for the efficient assignment of resources | |
| CN104317293B (en) | City rescue intelligent agent dynamic path planning method based on improved ant colony algorithm | |
| CN106846873B (en) | A kind of method and device of guidance | |
| Shang et al. | Resilience analysis of transport networks by combining variable message signs with agent-based day-to-day dynamic learning | |
| Misra et al. | S-nav: Safety-aware iot navigation tool for avoiding covid-19 hotspots | |
| CN112556714A (en) | Fire-fighting rescue intelligent path planning method and system | |
| CN113935108B (en) | Multi-type emergency vehicle combined address selection and configuration method, device and storage medium | |
| Li et al. | Dynamic sign guidance optimization for crowd evacuation considering flow equilibrium | |
| US10467888B2 (en) | System and method for dynamically adjusting an emergency coordination simulation system | |
| Kaviani et al. | A decision support system for improving the management of traffic networks during disasters | |
| Hara et al. | Geographical risk analysis based path selection for automatic, speedy, and reliable evacuation guiding using evacuees’ mobile devices | |
| CN117612413A (en) | GCN-based manned unmanned aerial vehicle fusion operation airspace key node identification method | |
| Idoudi et al. | Smart dynamic evacuation planning and online management using vehicular communication system | |
| CN113096479A (en) | Fire drill virtual training method | |
| Elbery et al. | VANET-based smart navigation for emergency evacuation and special events | |
| CN105704026A (en) | Method for distinguishing low-risk route in service network | |
| Idoudi et al. | Vehicular cloud computing for population evacuation optimization | |
| Lujak et al. | An Architecture for Safe Evacuation Route Recommendation in Smart Spaces. | |
| KR101273662B1 (en) | Method for human behavior pattern recognition using affordance-based agent model | |
| CN110232237B (en) | Traffic basic diagram-based evacuation traffic flow distribution method | |
| Gelenbe et al. | Near-optimal emergency evacuation with rescuer allocation | |
| Agarwal et al. | Route guidance map for emergency evacuation |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191121 Address after: 430000 East Lake New Technology Development Zone, Wuhan City, Hubei Province, 301, 3rd floor, Science Park, Wuhan University of Technology Applicant after: Hubei Beacon Fire Safety Intelligent Fire Fighting Technology Co., Ltd. Applicant after: Wuhan Ligong Guangke Co., Ltd. Address before: 430223, No. 23, University Road, East Lake hi tech Zone, Hubei, Wuhan Applicant before: Wuhan Ligong Guangke Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |