CN111382936B - Nuclear emergency evacuation optimal dispatching method and system based on network-connected unmanned vehicle - Google Patents
Nuclear emergency evacuation optimal dispatching method and system based on network-connected unmanned vehicle Download PDFInfo
- Publication number
- CN111382936B CN111382936B CN202010148732.0A CN202010148732A CN111382936B CN 111382936 B CN111382936 B CN 111382936B CN 202010148732 A CN202010148732 A CN 202010148732A CN 111382936 B CN111382936 B CN 111382936B
- Authority
- CN
- China
- Prior art keywords
- demand
- evacuation
- point
- cluster
- emergency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000009792 diffusion process Methods 0.000 claims abstract description 42
- 239000000126 substance Substances 0.000 claims abstract description 29
- 230000006870 function Effects 0.000 claims description 12
- 239000011824 nuclear material Substances 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 7
- 230000008569 process Effects 0.000 abstract description 5
- 230000006855 networking Effects 0.000 abstract description 2
- 230000005855 radiation Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Alarm Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a nuclear emergency evacuation optimal scheduling method and system based on a network-connected unmanned vehicle, wherein the optimal scheduling method comprises the following steps: after nuclear leakage occurs, detecting the wind direction, wind speed and concentration of nuclear substances leaked by a diffusion source in an emergency plan area; according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point, determining the evacuation risk of the corresponding demand point; according to the evacuation risk of the demand point, determining each evacuation target object; determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point; and (5) dispatching the corresponding number of the unmanned vehicles to evacuate residents in each evacuation target object to a safe emergency avoidance difficulty. The invention can obtain the minimum number of unmanned vehicles which come and go between each evacuation target object and the emergency refuge point, thereby realizing the nuclear emergency evacuation process based on the networking unmanned operation and reducing the cost to the maximum extent while ensuring the evacuation effect.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a nuclear emergency evacuation optimization scheduling method and system based on a network-connected unmanned vehicle.
Background
Nuclear energy has become an indispensable clean energy source in the world today and is increasingly important in the energy market. However, nuclear energy itself presents a certain risk, and once a nuclear leakage accident occurs, serious life and property losses are brought to residents around the nuclear power station. And nuclear accidents occur, evacuation is the most effective way to reduce loss and ensure the life safety of people.
However, the surrounding population of the nuclear power station is numerous, the regional range is large, the road traffic condition is complex, the evacuation is mainly carried out by means of motor vehicles such as buses, the nuclear power station has high danger, and the personal safety of drivers can be threatened greatly.
In recent years, with the development of technologies such as high-precision sensors, computer vision, and 5G high-speed communication, a networked unmanned technology has become possible, and will come into the life of people in the foreseeable future. The bus is automatically driven to evacuate based on networking, so that the damage to drivers can be avoided, evacuation targets can be realized in a more coordinated and orderly mode, and an effective means is provided for nuclear emergency evacuation.
However, the networked automatic driving vehicle has higher cost, and meanwhile, different places in the emergency planning area of the nuclear power station are affected by nuclear radiation to different degrees, so that the problems of different evacuation priorities and time limits, namely, how to reduce the cost to the greatest extent while ensuring the evacuation requirement and organizing evacuation more efficiently are considered.
Disclosure of Invention
In order to solve the problems in the prior art, namely to reduce the cost to the maximum extent while ensuring the evacuation effect, the invention aims to provide a nuclear emergency evacuation optimizing and dispatching method and system based on a network-connected unmanned vehicle.
In order to solve the technical problems, the invention provides the following scheme:
a nuclear emergency evacuation optimal scheduling method based on a network-connected unmanned vehicle, the optimal scheduling method comprising:
after nuclear leakage occurs, detecting the wind direction, wind speed and concentration of nuclear substances leaked by a diffusion source in an emergency plan area;
according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point, determining the evacuation risk of the corresponding demand point; the demand points are resident points in the emergency planning area;
according to the evacuation risk of the demand point, determining each evacuation target object;
determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
and (5) dispatching the corresponding number of the unmanned vehicles to evacuate residents in each evacuation target object to a safe emergency avoidance difficulty.
Optionally, the determining the evacuation risk of the corresponding demand point according to the wind direction, the wind speed, the concentration of the nuclear material leaked by the diffusion source and the population number of each demand point in the emergency planning area specifically includes:
modeling an emergency planning area into an (x, y, z) three-dimensional space according to a Gaussian formula and a Fick diffusion law, and assuming that nuclear leakage accidents occur under the condition of wind, the wind direction is along the x-axis direction, and the wind speed is u;
determining the nuclear species concentration C (x, y, z, t) at each spatial point at time t:
wherein P is 0 Is the concentration of the nuclear material leaked by the diffusion source, k is the diffusion coefficient;
calculating the nuclear material concentration threshold C reached by the demand point i 0 Time threshold T of (2) i ：
According to the time threshold T i And population number of the demand point i, determining evacuation risk R of the demand point i i ：
Wherein Pop i Is the population number of the demand point i.
Optionally, the determining each evacuation target object according to the evacuation risk of the demand point specifically includes:
determining an initial clustering center according to the evacuation risk of the demand points;
and adjusting the demand points of each cluster based on the initial clustering center until the clustering center of the cluster is not changed, determining each demand point cluster, wherein each demand point cluster is an evacuation target object, the clustering center of each demand point cluster is an evacuation gathering point, and the transportation route among the demand point clusters and the route to the emergency avoidance point are unique.
Optionally, determining an initial clustering center according to the evacuation risk of the demand point specifically includes:
randomly selecting K groups of demand points to form corresponding K virtual clustering center clusters;
for each virtual cluster center cluster C j ；
Randomly selecting R demand points as a first sample, and calculating the distance d between the demand points R and each virtual clustering center j rj ，j∈C j ：
Wherein, (x) r ，y r )，(x j ，y j ) The demand point r and the virtual cluster center j are respectively represented in two-dimensional space coordinates (x,y), R r For the evacuation risk of the demand point R, R j The evacuation risk of the virtual cluster center j is represented by alpha and beta, which are weight coefficients respectively;
for each demand point, calculating the nearest distance min d between the demand point and each virtual clustering center j rj ；
Selecting a demand point with the largest nearest distance from each virtual cluster center j from all the demand points as an initial cluster center C l ：C l ＝argmax r (mind rj )；
Where max is a maximum function, argmax represents the value of the variable that takes the maximum, l=1, 2.
Optionally, the adjusting the demand point of each cluster based on the initial cluster center specifically includes:
n demand points are randomly selected as the second samples,
for each point of need to be addressed,
calculating a demand point n and each initial clustering center C l Distance measure d between nl ：
Wherein n=1, 2, N, α, β are weight coefficients, respectively; (x) n ，y n )，(x l ，y l ) Respectively a demand point n and an initial clustering center C l At a spatial coordinate point of two-dimensional spatial coordinates (x, y), R n For evacuation risk at demand point n, R l For the initial cluster center C l Is a risk of evacuation;
selecting a cluster center with the smallest distance as a cluster center cluster C to which the demand point n belongs m ：
n∈C m ＝ar gmin l d nl ，l＝1，2，...，K；
Wherein min is a minimum function, argmin represents the value of the variable with the minimum value;
more according to the following formulaClustering center cluster C of new demand points m ：
Wherein, |C m I represents cluster center cluster C m The number of the demand points in the system is S is all the demand points belonging to C m Is defined by a triplet (x s ，y s ，R s ) And (3) representing.
Optionally, the determining the number of unmanned vehicles that make a round trip between each evacuation target object and the emergency shelter specifically includes:
determining the number of unmanned vehicles according to the following constraint conditions, wherein the objective function is min B:
x s，e，f ≥x s，e，f+1 (2)
wherein B is the number of required unmanned vehicles, S s，e，f，c A variable of 0-1, wherein if an e-car starting from an S avoidance difficulty point goes to a c demand point cluster in f strokes, the value of the e-car is 1, otherwise, the e-car is 0; b (B) s Representing the total number of vehicles in the S avoidance difficulty point; x is x s，e，f A variable of 0-1, which means that if f strokes of the e-car starting from the s avoidance difficulty occur, the value is 1, otherwise, the value is 0; c (C) s，e The bearing capacity of an e-car starting from the s-avoidance difficulty point is represented, namely the number of people capable of being transported at one time; d (D) c Representing the evacuation requirement of a requirement point cluster c, namely the total number of people in the cluster; ct (ct) s，e，f-1 Representing the accumulated time of the e-car from the S difficulty point in the previous f-1 strokes; τ c A clear time limit for the demand point cluster c is represented, namely the latest time for which personnel evacuation is allowed to be completed completely;
constraint (1) indicates that all unmanned vehicles in the emergency avoidance difficulty are to be used for evacuation; constraint (2) indicates that each trip must occur until the preamble trip has been completed; constraint (3) indicates that the total load capacity of all vehicles must be not less than the total demand at all demand points; constraint (4) indicates that only x s，e，f When 1, s s，e，f，c It is possible to be 1; constraint (5) indicates that the total pick-up to the demand cluster c must be no less than the demand for that point; constraint (6) indicates that the emptying time of each demand point cluster cannot exceed the emptying time limit; the constraint (7) is used to solve for the number of unmanned vehicles required.
Optionally, the optimized scheduling method further includes:
and receiving a nuclear accident alarm, and determining that nuclear leakage occurs.
In order to solve the technical problems, the invention also provides the following scheme:
a nuclear emergency evacuation optimal dispatch system based on a networked unmanned vehicle, the optimal dispatch system comprising:
the detection unit is used for detecting the wind direction and the wind speed in the emergency plan area and the concentration of nuclear substances leaked by the diffusion source after nuclear leakage occurs;
the risk determining unit is used for determining the evacuation risk of the corresponding demand point according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point; the demand points are resident points in the emergency planning area;
the target determining unit is used for determining each evacuation target object according to the evacuation risk of the demand point;
a number determination unit for determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
the dispatching unit is used for dispatching the corresponding number of the unmanned vehicles and evacuating residents in each evacuating target object to a safe emergency difficulty avoidance point.
In order to solve the technical problems, the invention also provides the following scheme:
a nuclear emergency evacuation optimizing and dispatching system based on an internet-connected unmanned vehicle comprises a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
after nuclear leakage occurs, detecting the wind direction, wind speed and concentration of nuclear substances leaked by a diffusion source in an emergency plan area;
according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point, determining the evacuation risk of the corresponding demand point; the demand points are resident points in the emergency planning area;
according to the evacuation risk of the demand point, determining each evacuation target object;
determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
and (5) dispatching the corresponding number of the unmanned vehicles to evacuate residents in each evacuation target object to a safe emergency avoidance difficulty.
In order to solve the technical problems, the invention also provides the following scheme:
a computer-readable storage medium storing one or more programs that, when executed by an electronic device comprising a plurality of application programs, cause the electronic device to:
after nuclear leakage occurs, detecting the wind direction, wind speed and concentration of nuclear substances leaked by a diffusion source in an emergency plan area;
according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point, determining the evacuation risk of the corresponding demand point; the demand points are resident points in the emergency planning area;
according to the evacuation risk of the demand point, determining each evacuation target object;
determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
and (5) dispatching the corresponding number of the unmanned vehicles to evacuate residents in each evacuation target object to a safe emergency avoidance difficulty.
According to the embodiment of the invention, the following technical effects are disclosed:
according to the method, the evacuation risk of the corresponding demand point is determined according to the wind direction and the wind speed in the emergency planning area, the nuclear substance concentration leaked by the diffusion source and the population quantity of the demand point, each evacuation target object is further determined according to the evacuation risk, and the unmanned vehicles are planned, so that the minimum quantity of unmanned vehicles which come and go between each evacuation target object and the emergency refuge point is obtained, the nuclear emergency evacuation process based on the networked unmanned vehicles can be realized, the evacuation effect is ensured, and meanwhile, the cost is reduced to the greatest extent.
Drawings
FIG. 1 is a flow chart of the nuclear emergency evacuation optimization scheduling method based on the network-linked unmanned vehicle of the invention;
fig. 2 is a schematic block diagram of a nuclear emergency evacuation optimization scheduling system based on a network-connected unmanned vehicle.
Symbol description:
the system comprises a detection unit-1, a risk determination unit-2, a target determination unit-3, a quantity determination unit-4 and a scheduling unit-5.
Detailed Description
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
The invention aims to provide a nuclear emergency evacuation optimal dispatching method based on network-connected unmanned vehicles, which is used for determining evacuation risks of corresponding demand points according to wind directions, wind speeds and nuclear substance concentrations leaked by diffusion sources in an emergency plan area and population numbers of the demand points, further determining each evacuation target object according to the evacuation risks, planning the unmanned vehicles, and further obtaining the minimum number of unmanned vehicles which come and go between each evacuation target object and an emergency refuge point, so that the cost is furthest reduced while the evacuation effect is ensured in the nuclear emergency evacuation process based on network-connected unmanned vehicles.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
As shown in fig. 1, the nuclear emergency evacuation optimization scheduling method based on the internet-connected unmanned vehicle comprises the following steps:
step 100: after nuclear leakage occurs, detecting the wind direction, wind speed and concentration of nuclear substances leaked by a diffusion source in an emergency plan area;
step 200: according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point, determining the evacuation risk of the corresponding demand point; the demand points are resident points in the emergency planning area;
step 300: according to the evacuation risk of the demand point, determining each evacuation target object;
step 400: determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
step 500: and (5) dispatching the corresponding number of the unmanned vehicles to evacuate residents in each evacuation target object to a safe emergency avoidance difficulty.
Preferably, the nuclear emergency evacuation optimization scheduling method based on the network-connected unmanned vehicle further comprises the following steps: and receiving a nuclear accident alarm, and determining that nuclear leakage occurs.
Once the nuclear leakage accident is detected, the nuclear material leakage concentration and the wind power and wind direction of the emergency planning area are immediately monitored and uploaded to an emergency command center, and then the evacuation risk in the emergency planning area is estimated and predicted according to the information. The evacuation risk is determined by the time the corresponding region predicts that the nuclear material reaches a certain concentration and its population.
Specifically, in step 200, the determining the evacuation risk of the corresponding demand point according to the wind direction, the wind speed, the concentration of the nuclear material leaked by the diffusion source and the population number of each demand point in the emergency planning area includes:
step 201: according to the Gaussian formula and Fick's (Fick) diffusion law, an emergency planning area is modeled as (x, y, z) three-dimensional space, and the wind direction is along the x-axis direction and the wind speed is u under the assumption that nuclear leakage accidents occur in the presence of wind.
Step 202: the nuclear species concentration C (x, y, z, t) at each spatial point at time t is determined (without consideration of other factors such as ground reflection):
wherein P is 0 Is the concentration of the nuclear species leaked from the diffusion source, and k is the diffusion coefficient.
Step 203: calculating the nuclear material concentration threshold C reached by the demand point i 0 Time threshold T of (2) i 。
Since the evacuation risk of a demand point is related not only to the extent of influence by nuclear radiation, but also to the evacuation pressure of the corresponding point, i.e. the population of the point, the time threshold T can be calculated by the following equation i ：
Step 204: according to the time threshold T i And population number of the demand point i, determining evacuation risk R of the demand point i i ：
Wherein Pop i Is the population number of the demand point i.
In integer resource planning, the optimal value of the system is often far away from the optimal value of the relaxation problem of the system due to integer constraint, for example, if P+1 people exist at a certain demand point, and an unmanned vehicle can only transport P people at a time, 2 times of vehicles still need to be evacuated in resource planning solution, and resource waste is easy to cause. For this reason, preferably, on the basis of the above process, the present invention combines the evacuation risk and the similarity of the geographical positions of different areas, and clusters the similar areas based on KMeans algorithm.
Specifically, in step 300, the determining each evacuation target object according to the evacuation risk of the demand point specifically includes:
step 310: determining an initial clustering center according to the evacuation risk of the demand points;
step 320: and adjusting the demand points of each cluster based on the initial clustering center until the clustering center of the cluster is not changed, determining each demand point cluster, wherein each demand point cluster is an evacuation target object, the clustering center of each demand point cluster is an evacuation gathering point, and the transportation route among the demand point clusters and the route to the emergency avoidance point are unique.
Optionally, in step 310, determining an initial clustering center according to the evacuation risk of the demand point specifically includes:
step 311: randomly selecting K groups of demand points to form corresponding K virtual clustering center clusters;
step 312: for each virtual cluster center cluster C j ；
Randomly selecting R demand points as a first sample, and calculating the distance d between the demand points R and each virtual clustering center j rj ，j∈C j ：
Wherein, (x) r ，y r )，(x j ，y k ) The space coordinate points of the demand point R and the virtual clustering center j in two-dimensional space coordinates (x, y) are respectively R r For the evacuation risk of the demand point R, R j The evacuation risk of the virtual cluster center j is represented by alpha and beta, which are weight coefficients respectively;
step 313: for each demand point, calculating the nearest distance min d between the demand point and each virtual clustering center j rj ；
Step 314: selecting a demand point with the largest nearest distance from each virtual cluster center j from all the demand points as an initial cluster center C l ：C l ＝ar gmax r (mind rj )；
Where max is a maximum function, argmax represents the value of the variable that takes the maximum, l=1, 2.
In step 320, the adjusting the demand point of each cluster based on the initial cluster center specifically includes:
step 321: n demand points are randomly selected as the second samples,
step 322: for each point of need to be addressed,
calculating a demand point n and each initial clustering center C l Distance measure d between nl ：
Wherein n=1, 2, N, α, β are weight coefficients, respectively; (x) n ，y n )，(x l ，y l ) Respectively a demand point n and an initial clustering center C l At a spatial coordinate point of two-dimensional spatial coordinates (x, y), R n For evacuation risk at demand point n, R l For the initial cluster center C l Is to be thinnedRisk of dispersion;
step 323: selecting a cluster center with the smallest distance as a cluster center cluster C to which the demand point n belongs m ：
n∈C m ＝ar gmin l d nl ，l＝1，2，...，K；
Wherein min is a minimum function, argmin represents the value of the variable with the minimum value;
step 324: updating the cluster center cluster C of the demand points according to the following formula m ：
Wherein, |C m I represents cluster center cluster C m The number of the demand points in the system, s is all the demand points belonging to C m Is defined by a triplet (x s ，y s ，R s ) And (3) representing.
Further, in step 400, the determining the number of unmanned vehicles that shuttle between each evacuation target object and the emergency shelter specifically includes:
determining the number of unmanned vehicles according to the following constraint conditions, wherein the objective function is min B:
x s，e，f ≥x s，e，f+1 (2)
wherein B is the number of required unmanned vehicles, s s，e，f，c A variable of 0-1, wherein if an e-car starting from an s-avoidance difficulty point goes to a c-demand point cluster in f strokes, the value of the e-car is 1, otherwise, the e-car is 0; b (B) s Representing the total number of vehicles in the s avoidance difficulty point; x is x s，e，f A variable of 0-1, which means that if f strokes of the e-car starting from the s avoidance difficulty occur, the value is 1, otherwise, the value is 0; c (C) s，e The bearing capacity of an e-car starting from the s-avoidance difficulty point is represented, namely the number of people capable of being transported at one time; d (D) c Representing the evacuation requirement of a requirement point cluster c, namely the total number of people in the cluster; ct (ct) s，e，f-1 Representing the accumulated time of an e-car starting from the s difficulty point in the previous f-1 strokes; τ c A clear time limit for the demand point cluster c is represented, namely the latest time for which personnel evacuation is allowed to be completed completely;
constraint (1) indicates that all unmanned vehicles in the emergency avoidance difficulty are to be used for evacuation; constraint (2) indicates that each trip must occur until the preamble trip has been completed; constraint (3) indicates that the total load capacity of all vehicles must be not less than the total demand at all demand points; constraint (4) indicates that only x s，e，f When 1, s s，e，f，c It is possible to be 1; constraint (5) indicates that the total pick-up to the demand cluster c must be no less than the demand for that point; constraint (6) indicates that the emptying time of each demand point cluster cannot exceed the emptying time limit; the constraint (7) is used to solve for the number of unmanned vehicles required.
Assuming that the people mouth in the cluster remains unchanged, the transportation route between the two points is fixed, the transportation time data required in the formula can be obtained through experience and historical data, and then can be solved through a CPLEX linear programming solver or a branch-and-bound method, and the optimal value under the given input condition can be obtained, namely the required minimum unmanned vehicle number.
Based on the solution to the above problem, not only the optimal value of the problem but also the optimal solution of the problem can be obtained, even if the decision variable s of B is optimal s，i，j，c Etc., will s s，i，j，c Analyzing, and organizing the unmanned vehicle evacuation according to the travel with the value of 1 to obtain an optimized unmanned vehicle dispatching strategy, so that the evacuation requirement is met under the condition of the given number of vehicles.
According to the invention, by combining the characteristic of similar gas diffusion of nuclear leakage and scattering, a Gaussian diffusion model is selected and combined with the geographical information around the nuclear power station to predict the risk degree of each demand point (namely living point) affected by radiation, and the risk of evacuation is evaluated according to the risk degree. Secondly, to simplify the problem scale, the residential points are clustered based on a KMeas method by combining the geographical position similarity and the evacuation risk similarity among different residential points and more conveniently organizing the residential points into groups for evacuation. And finally, planning unmanned vehicle resources based on mixed integer programming, calculating the minimum number of unmanned vehicles required for evacuating clustered demand points under a series of constraint conditions, and obtaining an optimal unmanned vehicle running sequence. Through the method, the nuclear emergency evacuation process based on the networked unmanned can be effectively planned, and the cost can be reduced to the greatest extent while the evacuation effect is ensured.
In addition, the invention also provides a nuclear emergency evacuation optimizing and dispatching system based on the network-connected unmanned vehicle, which can reduce the cost to the maximum extent while guaranteeing the evacuation effect.
As shown in fig. 2, the nuclear emergency evacuation optimizing dispatching system based on the internet-connected unmanned vehicle comprises a detection unit 1, a risk determination unit 2, a target determination unit 3, a quantity determination unit 4 and a dispatching unit 5.
The detection unit 1 is used for detecting the wind direction and the wind speed in the emergency planning area and the concentration of nuclear substances leaked by the diffusion source after nuclear leakage occurs;
the risk determination unit 2 is used for determining evacuation risks of corresponding demand points according to wind directions and wind speeds in an emergency planning area, the concentration of nuclear substances leaked by a diffusion source and population numbers of each demand point; the demand points are resident points in the emergency planning area;
the target determining unit 3 is configured to determine each evacuation target object according to evacuation risks of the demand points;
the number determining unit 4 is used for determining the number of unmanned vehicles which come and go between each evacuation target object and the emergency refuge point;
the dispatching unit 5 is used for dispatching the corresponding number of the unmanned vehicles and evacuating residents in each evacuating target object to a safe emergency avoidance difficulty point.
The invention also provides the following scheme:
a nuclear emergency evacuation optimizing and dispatching system based on an internet-connected unmanned vehicle comprises a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
after nuclear leakage occurs, detecting the wind direction, wind speed and concentration of nuclear substances leaked by a diffusion source in an emergency plan area;
according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point, determining the evacuation risk of the corresponding demand point; the demand points are resident points in the emergency planning area;
according to the evacuation risk of the demand point, determining each evacuation target object;
determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
and (5) dispatching the corresponding number of the unmanned vehicles to evacuate residents in each evacuation target object to a safe emergency avoidance difficulty.
The invention also provides the following scheme:
a computer-readable storage medium storing one or more programs that, when executed by an electronic device comprising a plurality of application programs, cause the electronic device to:
after nuclear leakage occurs, detecting the wind direction, wind speed and concentration of nuclear substances leaked by a diffusion source in an emergency plan area;
according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point, determining the evacuation risk of the corresponding demand point; the demand points are resident points in the emergency planning area;
according to the evacuation risk of the demand point, determining each evacuation target object;
determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
and (5) dispatching the corresponding number of the unmanned vehicles to evacuate residents in each evacuation target object to a safe emergency avoidance difficulty.
Compared with the prior art, the nuclear emergency evacuation optimizing and dispatching system and the computer-readable storage medium based on the network-connected unmanned vehicle have the same beneficial effects as the nuclear emergency evacuation optimizing and dispatching method based on the network-connected unmanned vehicle, and are not repeated here.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will fall within the scope of the present invention.
Claims (8)
1. The nuclear emergency evacuation optimal scheduling method based on the network-connected unmanned vehicle is characterized by comprising the following steps of:
after nuclear leakage occurs, detecting the wind direction, wind speed and concentration of nuclear substances leaked by a diffusion source in an emergency plan area;
according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point, determining the evacuation risk of the corresponding demand point; the demand points are resident points in the emergency planning area;
according to the evacuation risk of the demand point, determining each evacuation target object;
the method specifically comprises the following steps: determining an initial clustering center according to the evacuation risk of the demand points; based on the initial clustering center, adjusting the demand points of each cluster until the clustering center of the cluster is not changed, determining each demand point cluster, wherein each demand point cluster is an evacuation target object, the clustering center of each demand point cluster is an evacuation gathering point, and the transportation route among the demand point clusters and the route to the emergency avoidance point are unique;
randomly selecting K groups of demand points to form corresponding K virtual clustering center clusters;
for each virtual cluster center cluster C j ；
Randomly selecting R demand points as a first sample, and calculating the distance d between the demand points R and each virtual clustering center j rj ，j∈C j ：
Wherein, (x) r ，y r )，(x j ，y j ) The space coordinate points of the demand point R and the virtual clustering center j in two-dimensional space coordinates (x, y) are respectively R r For the evacuation risk of the demand point R, R j The evacuation risk of the virtual cluster center j is represented by alpha and beta, which are weight coefficients respectively;
for each demand point, calculating the nearest distance min d between the demand point and each virtual clustering center j rj ；
Selecting a demand point with the largest nearest distance from each virtual cluster center j from all the demand points as an initial cluster center C l ：
C l ＝argmax r (mind rj )；
Wherein max is a maximum function, argmax represents the value of the variable that takes the maximum, l=1, 2,..k;
determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
and (5) dispatching the corresponding number of the unmanned vehicles to evacuate residents in each evacuation target object to a safe emergency avoidance difficulty.
2. The optimal dispatching method for nuclear emergency evacuation based on the network-connected unmanned vehicle according to claim 1, wherein the determining the evacuation risk of the corresponding demand point according to the wind direction, the wind speed, the nuclear substance concentration leaked by the diffusion source and the population number of each demand point in the emergency plan area specifically comprises:
modeling an emergency planning area into an (x, y, z) three-dimensional space according to a Gaussian formula and a Fick diffusion law, and assuming that nuclear leakage accidents occur under the condition of wind, the wind direction is along the x-axis direction, and the wind speed is u;
determining the nuclear species concentration C (x, y, z, t) at each spatial point at time t:
wherein P is 0 Is the concentration of the nuclear material leaked by the diffusion source, k is the diffusion coefficient;
calculating the nuclear material concentration threshold C reached by the demand point i 0 Time threshold T of (2) i ：
According to the time threshold T i And population number of the demand point i, determining evacuation risk R of the demand point i i ：
Wherein Pop i Is the population number of the demand point i.
3. The method for optimizing and dispatching the nuclear emergency evacuation based on the network-connected unmanned vehicle according to claim 1, wherein the method for adjusting the demand point of each cluster based on the initial cluster center comprises the following steps:
n demand points are randomly selected as the second samples,
for each point of need to be addressed,
calculating a demand point n and each initial clustering center C l Distance measure d between nl ：
Wherein n=1, 2, N, α, β are weight coefficients, respectively; (x) n ，y n )，(x l ，y l ) Respectively a demand point n and an initial clustering center C l At a spatial coordinate point of two-dimensional spatial coordinates (x, y), R n For evacuation risk at demand point n, R l For the initial cluster center C l Is a risk of evacuation;
selecting a cluster center with the smallest distance as a cluster center cluster C to which the demand point n belongs m ：
n∈C m ＝argmin l d nl ，l＝1，2，…，K；
Wherein min is a minimum function, argmin represents the value of the variable with the minimum value;
updating the cluster center cluster C of the demand points according to the following formula m ：
Wherein, |C m I represents cluster center cluster C m The number of the demand points in the system, s is all the demand points belonging to C m Is used for the point of need of (1),triads (x) consisting of coordinates combined with evacuation risk s ，y s ，R s ) And (3) representing.
4. The method for optimizing and dispatching nuclear emergency evacuation based on network-connected unmanned vehicles according to claim 1, wherein the determining the number of unmanned vehicles to and from each evacuation target object and the emergency refuge point specifically comprises:
determining the number of unmanned vehicles according to the following constraint conditions, wherein the objective function is min B:
x s，e，f ≥x s，e，f+1 (2)
wherein B is the number of required unmanned vehicles, S s，e，f，c A variable of 0-1, indicating that if the e-car from the s-avoidance difficulty point goes to c in f strokesThe value of the demand point cluster is 1 when the demand point cluster occurs, otherwise, the value is 0; b (B) s Representing the total number of vehicles in the s avoidance difficulty point; x is x s，e，f A variable of 0-1, which means that if f strokes of the e-car starting from the s avoidance difficulty occur, the value is 1, otherwise, the value is 0; c (C) s，e The bearing capacity of an e-car starting from the s-avoidance difficulty point is represented, namely the number of people capable of being transported at one time; d (D) c Representing the evacuation requirement of a requirement point cluster c, namely the total number of people in the cluster; ct (ct) s，e，f-1 Representing the accumulated time of an e-car starting from the s difficulty point in the previous f-1 strokes; τ c A clear time limit for the demand point cluster c is represented, namely the latest time for which personnel evacuation is allowed to be completed completely;
constraint (1) indicates that all unmanned vehicles in the emergency avoidance difficulty are to be used for evacuation; constraint (2) indicates that each trip must occur until the preamble trip has been completed; constraint (3) indicates that the total load capacity of all vehicles must be not less than the total demand at all demand points; constraint (4) indicates that only x s，e，f When 1 is, S s，e，f，c It is possible to be 1; constraint (5) indicates that the total pick-up to the demand cluster c must be no less than the demand for that point; constraint (6) indicates that the emptying time of each demand point cluster cannot exceed the emptying time limit; the constraint (7) is used to solve for the number of unmanned vehicles required.
5. The nuclear emergency evacuation optimization scheduling method based on the internet-connected unmanned vehicle according to any one of claims 1 to 4, wherein the optimization scheduling method further comprises:
and receiving a nuclear accident alarm, and determining that nuclear leakage occurs.
6. A nuclear emergency evacuation optimal scheduling system based on an internet-connected unmanned vehicle, which is characterized in that the optimal scheduling system comprises:
the detection unit is used for detecting the wind direction and the wind speed in the emergency plan area and the concentration of nuclear substances leaked by the diffusion source after nuclear leakage occurs;
the risk determining unit is used for determining the evacuation risk of the corresponding demand point according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point; the demand points are resident points in the emergency planning area;
the target determining unit is used for determining each evacuation target object according to the evacuation risk of the demand point and determining an initial clustering center;
the method specifically comprises the following steps: determining an initial clustering center according to the evacuation risk of the demand points; based on the initial clustering center, adjusting the demand points of each cluster until the clustering center of the cluster is not changed, determining each demand point cluster, wherein each demand point cluster is an evacuation target object, the clustering center of each demand point cluster is an evacuation gathering point, and the transportation route among the demand point clusters and the route to the emergency avoidance point are unique;
randomly selecting K groups of demand points to form corresponding K virtual clustering center clusters;
for each virtual cluster center cluster C j ；
Randomly selecting R demand points as a first sample, and calculating the distance d between the demand points R and each virtual clustering center j rj ，j∈C j ：
Wherein, (x) r ，y r )，(x j ，y j ) The space coordinate points of the demand point R and the virtual clustering center j in two-dimensional space coordinates (x, y) are respectively R r For the evacuation risk of the demand point R, R j The evacuation risk of the virtual cluster center j is represented by alpha and beta, which are weight coefficients respectively;
for each demand point, calculating the nearest distance min d between the demand point and each virtual clustering center j rj ；
Selecting a demand point with the largest nearest distance from each virtual cluster center j from all the demand points as an initial cluster center C l ：
C l ＝argmax r (mind rj )；
Wherein max is a maximum function, argmax represents the value of the variable that takes the maximum, l=1, 2,..k;
a number determination unit for determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
the dispatching unit is used for dispatching the corresponding number of the unmanned vehicles and evacuating residents in each evacuating target object to a safe emergency difficulty avoidance point.
7. A nuclear emergency evacuation optimization dispatch system based on a networked unmanned vehicle, comprising:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
after nuclear leakage occurs, detecting the wind direction, wind speed and concentration of nuclear substances leaked by a diffusion source in an emergency plan area;
according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point, determining the evacuation risk of the corresponding demand point; the demand points are resident points in the emergency planning area;
according to the evacuation risk of the demand point, each evacuation target object is determined, and an initial clustering center is determined;
the method specifically comprises the following steps: determining an initial clustering center according to the evacuation risk of the demand points; based on the initial clustering center, adjusting the demand points of each cluster until the clustering center of the cluster is not changed, determining each demand point cluster, wherein each demand point cluster is an evacuation target object, the clustering center of each demand point cluster is an evacuation gathering point, and the transportation route among the demand point clusters and the route to the emergency avoidance point are unique;
randomly selecting K groups of demand points to form corresponding K virtual clustering center clusters;
for each virtual cluster center cluster C j ；
Randomly selecting R demand points as a first sample, and calculating the demand points R and each virtual cluster center jDistance d between rj ，j∈C j ：
Wherein, (x) r ，y r )，(x j ，y j ) The space coordinate points of the demand point R and the virtual clustering center j in two-dimensional space coordinates (x, y) are respectively R r For the evacuation risk of the demand point R, R j The evacuation risk of the virtual cluster center j is represented by alpha and beta, which are weight coefficients respectively;
for each demand point, calculating the nearest distance min d between the demand point and each virtual clustering center j rj ；
Selecting a demand point with the largest nearest distance from each virtual cluster center j from all the demand points as an initial cluster center C l ：
C l ＝argmax r (mind rj )；
Wherein max is a maximum function, argmax represents the value of the variable that takes the maximum, l=1, 2,..k;
determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
and (5) dispatching the corresponding number of the unmanned vehicles to evacuate residents in each evacuation target object to a safe emergency avoidance difficulty.
8. A computer-readable storage medium storing one or more programs that, when executed by an electronic device comprising a plurality of application programs, cause the electronic device to:
after nuclear leakage occurs, detecting the wind direction, wind speed and concentration of nuclear substances leaked by a diffusion source in an emergency plan area;
according to the wind direction and the wind speed in the emergency planning area, the concentration of nuclear substances leaked by the diffusion source and the population quantity of each demand point, determining the evacuation risk of the corresponding demand point; the demand points are resident points in the emergency planning area;
according to the evacuation risk of the demand point, each evacuation target object is determined, and an initial clustering center is determined;
the method specifically comprises the following steps: determining an initial clustering center according to the evacuation risk of the demand points; based on the initial clustering center, adjusting the demand points of each cluster until the clustering center of the cluster is not changed, determining each demand point cluster, wherein each demand point cluster is an evacuation target object, the clustering center of each demand point cluster is an evacuation gathering point, and the transportation route among the demand point clusters and the route to the emergency avoidance point are unique;
randomly selecting K groups of demand points to form corresponding K virtual clustering center clusters;
for each virtual cluster center cluster C j ；
Randomly selecting R demand points as a first sample, and calculating the distance d between the demand points R and each virtual clustering center j rj ，j∈C j ：
Wherein, (x) r ，y r )，(x j ，y j ) The space coordinate points of the demand point R and the virtual clustering center j in two-dimensional space coordinates (x, y) are respectively R r For the evacuation risk of the demand point R, R j The evacuation risk of the virtual cluster center j is represented by alpha and beta, which are weight coefficients respectively;
for each demand point, calculating the nearest distance min d between the demand point and each virtual clustering center j rj ；
Selecting a demand point with the largest nearest distance from each virtual cluster center j from all the demand points as an initial cluster center C l ：
C l ＝argmax r (mind rj )；
Wherein max is a maximum function, argmax represents the value of the variable that takes the maximum, l=1, 2,..k;
determining the number of unmanned vehicles coming and going between each evacuation target object and the emergency refuge point;
and (5) dispatching the corresponding number of the unmanned vehicles to evacuate residents in each evacuation target object to a safe emergency avoidance difficulty.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010148732.0A CN111382936B (en) | 2020-03-05 | 2020-03-05 | Nuclear emergency evacuation optimal dispatching method and system based on network-connected unmanned vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010148732.0A CN111382936B (en) | 2020-03-05 | 2020-03-05 | Nuclear emergency evacuation optimal dispatching method and system based on network-connected unmanned vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111382936A CN111382936A (en) | 2020-07-07 |
| CN111382936B true CN111382936B (en) | 2024-02-02 |
Family
ID=71222665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010148732.0A Active CN111382936B (en) | 2020-03-05 | 2020-03-05 | Nuclear emergency evacuation optimal dispatching method and system based on network-connected unmanned vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111382936B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101309396A (en) * | 2008-06-27 | 2008-11-19 | 中国安全生产科学研究院 | Emergency cooperative monitoring system for dangerous chemical leakage accident and method thereof |
| CN102393925A (en) * | 2011-07-05 | 2012-03-28 | 万达信息股份有限公司 | Emergent vehicle scheduling and personnel evacuation method oriented to hazardous gas diffusion |
| CN104346657A (en) * | 2014-11-10 | 2015-02-11 | 张江华 | Optimal evacuation method and system for dangerous chemical leakage |
| CN108280575A (en) * | 2018-01-22 | 2018-07-13 | 哈尔滨工业大学 | A kind of multiple batches of scheduling decision method of emergency evacuation vehicle |
| CN110329319A (en) * | 2019-06-28 | 2019-10-15 | 卡斯柯信号有限公司 | A kind of fully automatic operation system towards wisdom urban rail |
-
2020
- 2020-03-05 CN CN202010148732.0A patent/CN111382936B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101309396A (en) * | 2008-06-27 | 2008-11-19 | 中国安全生产科学研究院 | Emergency cooperative monitoring system for dangerous chemical leakage accident and method thereof |
| CN102393925A (en) * | 2011-07-05 | 2012-03-28 | 万达信息股份有限公司 | Emergent vehicle scheduling and personnel evacuation method oriented to hazardous gas diffusion |
| CN104346657A (en) * | 2014-11-10 | 2015-02-11 | 张江华 | Optimal evacuation method and system for dangerous chemical leakage |
| CN108280575A (en) * | 2018-01-22 | 2018-07-13 | 哈尔滨工业大学 | A kind of multiple batches of scheduling decision method of emergency evacuation vehicle |
| CN110329319A (en) * | 2019-06-28 | 2019-10-15 | 卡斯柯信号有限公司 | A kind of fully automatic operation system towards wisdom urban rail |
Non-Patent Citations (3)
| Title |
|---|
| 张亚平 ; 牛建军 ; 张淑琼 ; .有毒化学物质瞬时泄漏无风大气扩散的危害后果模拟分析.职业卫生与应急救援.2007,第25卷(第01期),第5-9页. * |
| 李强 ; 陈翔 ; 陈晋 ; 唐巧 ; .考虑危险源的城市应急交通疏散风险评价模型.科学通报.2009,(第16期),第2431-2436页. * |
| 王鹤儒.核电厂核事故放射性核素辐射剂量估算及应急疏散模拟研究.《中国优秀硕士学位论文全文数据库（电子期刊）》.2016,(第第1期期),第28-54页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111382936A (en) | 2020-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109116867B (en) | Unmanned aerial vehicle flight obstacle avoidance method and device, electronic equipment and storage medium | |
| CN108280575B (en) | Multi-batch dispatching decision method for emergency evacuation vehicles | |
| WO2015062343A1 (en) | Cloud platform-based logistics storage management method and system | |
| CN108764579B (en) | Storage multi-robot task scheduling method based on congestion control | |
| CN111415026A (en) | Unmanned equipment scheduling device, system and method | |
| CN116957345B (en) | Data processing method for unmanned system | |
| CN115511412A (en) | Intelligent unmanned vehicle distribution system and method based on digital twins | |
| CN111445176A (en) | Operation method, device, equipment, storage medium and system of logistics unmanned aerial vehicle | |
| CN118034272A (en) | Multi-AGV path planning method and system based on dynamic obstacle avoidance | |
| CN111382936B (en) | Nuclear emergency evacuation optimal dispatching method and system based on network-connected unmanned vehicle | |
| CN114138005B (en) | Urban mass logistics unmanned aerial vehicle flight path planning method and device based on improved A-algorithm | |
| CN114005297B (en) | Vehicle team coordinated driving method based on Internet of vehicles | |
| CN115310792A (en) | Task cooperation method, device and equipment for multi-target unmanned swarm | |
| CN117078020B (en) | Logistics transportation data management system based on unmanned aerial vehicle | |
| CN117236637A (en) | Internet logistics scheduling method, system, equipment and storage medium based on artificial intelligence industry | |
| Ezaki et al. | Drone-based vertical delivery system for high-rise buildings: Multiple drones vs. a single elevator | |
| WO2023103459A1 (en) | Vehicle control method, decision server, and storage medium | |
| CN113743739B (en) | AGV scheduling method based on mixed integer programming and combined optimization algorithm | |
| CN115061489A (en) | Unmanned aerial vehicle distribution planning method, device and system | |
| CN116386365B (en) | Traffic path induction method and system for improving harbor road safety | |
| CN116946884A (en) | Portal crane load anti-collision control method and device based on 2D laser SLAM | |
| CN118274846B (en) | Unmanned aerial vehicle group collaborative path planning method and system for road hidden trouble investigation | |
| WO2023013188A1 (en) | Information processing method, information processing device, and program | |
| CN118072521B (en) | Method, system and equipment for cooperatively controlling multi-vehicle-type vehicles and road resources under internet connection | |
| CN117612074A (en) | Logistics safe driving detection method and device based on lightweight improved YOLOv5 |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Tan Ke Inventor after: Wang Feiyue Inventor after: Wang Xiao Inventor after: Liu Xin Inventor before: Tan Ke Inventor before: Wang Feiyue Inventor before: Wang Xiao Inventor before: Liu Xinyi |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |