CN110443399B - Intelligent scheduling method for aviation rescue of vehicle accident - Google Patents
Intelligent scheduling method for aviation rescue of vehicle accident Download PDFInfo
- Publication number
- CN110443399B CN110443399B CN201910421644.0A CN201910421644A CN110443399B CN 110443399 B CN110443399 B CN 110443399B CN 201910421644 A CN201910421644 A CN 201910421644A CN 110443399 B CN110443399 B CN 110443399B
- Authority
- CN
- China
- Prior art keywords
- rescue
- accident
- time
- aviation
- helicopter
- 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 29
- 238000011156 evaluation Methods 0.000 claims abstract description 43
- 230000000694 effects Effects 0.000 claims abstract description 15
- 230000006378 damage Effects 0.000 claims description 12
- 208000027418 Wounds and injury Diseases 0.000 claims description 11
- 208000014674 injury Diseases 0.000 claims description 11
- 238000013178 mathematical model Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 20
- 210000002569 neuron Anatomy 0.000 description 15
- 238000013528 artificial neural network Methods 0.000 description 9
- 230000004913 activation Effects 0.000 description 7
- 238000013139 quantization Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 210000004027 cell Anatomy 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
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"
-
- G06Q50/40—
Abstract
The invention discloses an aviation rescue intelligent scheduling method for vehicle accidents, which is characterized in that an accident priority description model based on rescue time is established based on accident alarm information; establishing an aviation rescue basic task time prediction model based on a rescue grid; constructing an evaluation function of the system aviation rescue effect; and searching the optimal solution of the evaluation function F by adopting a method of regional evaluation of the optimal solution, and determining the optimal scheduling scheme. Compared with the prior art, the method can intelligently analyze the basic task time of the aviation rescue before the planned route is determined, and utilize the basic task time to analyze the best rescue scheme under the state of a limited rescue helicopter in multiple accident places, thereby achieving the maximum rescue effect and finally realizing the intelligent scheduling of the aviation rescue.
Description
Technical Field
The invention relates to the technical field of vehicle accident rescue, in particular to an intelligent scheduling method for aviation rescue of vehicle accidents.
Background
With the increasing of the automobile holding capacity in China, the traffic accident amount also shows obvious increase, and due to the problems of traffic jam, undefined position report and the like after the accident, the rescue is not timely accurate, so that the rescue opportunity of the wounded is finally delayed, and the casualty rate is increased. Aviation rescue, particularly helicopter rescue, is increasingly emphasized by the industry as a high-efficiency rescue mode which is gradually popularized, but at the present stage, helicopter rescue resources are in short supply, the use efficiency is low, the helicopter rescue effect is severely limited, and the aviation rescue cost is high.
On the other hand, aviation rescue belongs to a special civil aviation flight plan, a pilot or an assignor needs to make a flight plan route within half an hour after receiving a task and report the approval of a military and civil aviation control department, and before the route is made, the basic task time (namely the time period from take-off of a helicopter to the time before a rescue task is executed at a task place) cannot be defined, so that the efficient and scientific scheduling of helicopter rescue resources is greatly hindered.
In the prior art, although a scheduling optimization method for rescue resources exists, a complex accident urgency degree evaluation system needs to be established, and the scheduling optimization effect needs to be established on the basis of accurate classification of accident grades, which is a task which is almost impossible to complete in a golden rescue time period at the initial stage of an accident. In addition, the method has the concern that the particularity of the aviation rescue is not fully considered on the aspect of optimal configuration of equivalent resources, and the practical utility is difficult to be played in an aviation rescue intelligent scheduling task.
Disclosure of Invention
The invention aims to solve the defects in the prior art, provides an intelligent scheduling method for aviation rescue of vehicle accidents, gives full play to the resource utilization rate of a limited rescue helicopter, and improves rescue effect.
In order to achieve the purpose, the invention is implemented according to the following technical scheme:
an intelligent scheduling method for aviation rescue of vehicle accidents comprises the following steps:
s1, establishing an accident priority description model based on rescue time based on accident alarm information;
s2, establishing an aviation rescue basic task time prediction model based on a rescue grid;
s3, constructing an evaluation function of the aviation rescue effect of the system;
and S4, searching the optimal solution of the evaluation function F by adopting a method of regional evaluation of the optimal solution, and determining the optimal scheduling scheme.
Further, the specific steps of S1 are:
by adopting an accident priority description method based on rescue time, a primary accident is specifically described as 4 dimensions: (1) Moment of receiving alarm
(ii) a (2) Injury grade->
(3) time tolerance->
(ii) a (4) Consequence severity rating>
Where i is the accident number, indicating the ith accident.
Further, the specific step of S2 is:
s21, establishing a coordinate system of a rescue grid graph based on a Geographic Information System (GIS) and describing each point in the coordinate system;
and S22, constructing an aviation rescue basic task time prediction mathematical model under the description of a grid graph coordinate system based on the established rescue grid graph.
Further, the specific step of S3 is:
s31, supposing that k helicopters in the actual rescue system start to participate in aviation rescue from the same or different geographical positions, and within a certain time period, q accidents needing aviation rescue occur in different areas
Scheduling according to the alarm receiving time;
s32, in
Then, according to S1, the priority model of the system in this process is described as:
wherein->
Representing the description of a priority model of the jth accident, and taking the rescue time as a focus point for evaluating the aviation rescue effect under the model; and has the following requirements:
(1) the rescue time of the system exceeds the time tolerance
The less the cases, the better and the consequence severity level->
The higher the occurrence exceeds the time tolerance>
The less the cases, the better;
(2) in order to facilitate the control degree of the system on a certain accident or the total accident in the system in a certain time period, an attention coefficient is set, and the attention coefficient can directly control an evaluation result according to a time tolerance threshold value;
(3) the evaluation system is a closed loop system which meets system constraint conditions;
the evaluation function F of the aviation rescue effect under the model is set as follows:
s33, the total rescue service time and the basic task time predicted value of the system meet the following relationship:
Further, the specific steps of S4 are:
s41, based on S2, respectively taking the takeoff point of each helicopter rescue task as an original point, establishing a rescue grid graph, and calculating description information of each accident site under a grid graph coordinate system taking the takeoff point of each task as the original point
Wherein
Indicates a fifth->
Taking a flying point as an origin point>
Represents on a fifth->
Description information of the ith accident site with the individual flying point as the origin;
s42, all the description information obtained in the S41
Is input into the mathematic model of basic task time prediction established in S2 to obtain the ^ th/greater than or equal to>
Basic task time ^ needed by an ith accident for rescue at a flying spot>
；
S43, calculating the area evaluation numerical values of the same accident site under the conditions of different origin points of the flying points, finding the minimum area evaluation value, wherein the corresponding flying point is the optimal rescue flying point of the accident preferred by the area at the moment, and the calculation formula of the area evaluation is as follows:
s44, after all the k helicopters are dispatched, calculating which helicopter comes back first according to the basic task time prediction of the k helicopters, and finding out the accident of which the optimal solution of the area is the helicopter, namely the next task of the helicopter;
s45, circularly executing S44 until all accidents arrange the helicopters according to the optimal regional solutions, summing all the optimal regional solutions at the moment, and judging whether the constraint conditions of the evaluation function F are met or not
If the constraint is met, the plan scheme is the optimal scheduling scheme; and if the constraint condition is not met, returning to the step S43, removing the area optimal solution of the planning scheme, selecting the suboptimal solution and continuing to execute the steps S44 and S45 until the planning scheme meets the constraint condition.
Compared with the prior art, the method can intelligently analyze the basic task time of the aviation rescue before the planned route is determined, and utilize the basic task time to analyze the best rescue scheme under the state of multiple accident sites and limited rescue helicopters, thereby achieving the maximum rescue effect and finally realizing the intelligent scheduling of the aviation rescue.
Drawings
FIG. 1 is a flow chart of the present invention.
Fig. 2 is a rescue square grid diagram of the embodiment of the invention.
Fig. 3 is a structural diagram of a BP neural network according to an embodiment of the present invention.
FIG. 4 is a flowchart of finding an optimal solution of an evaluation function Foptimal solution according to the method for area evaluation of an optimal solution of the present invention.
Detailed description of the preferred embodiments
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. The specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
As shown in fig. 1, the method for intelligently scheduling aviation rescue in case of vehicle accident in the embodiment includes the following specific steps:
s1, establishing an accident priority description model based on rescue time based on accident alarm information;
in the embodiment, an accident priority description method based on rescue time is adopted, and a primary accident is specifically described as 4 dimensions: (1) Moment of receiving alarm
(ii) a (2) Injury grade->
(3) time tolerance->
(ii) a (4) Consequence severity rating pick>
Where i is the accident number, indicating the ith accident.
Wherein:
the alarm receiving time refers to the time information of the alarm receiving personnel actually receiving the alarm seeking information;
the injury grade represents the serious condition of the injury of the accident wounded, and is divided into a first grade, a second grade and a third grade (the severity is increased in sequence), wherein the first grade represents the injury needing aviation rescue, and if the rescue is delayed, the injury is expanded; the second level indicates that the injured part is serious and continues to develop, which can cause the serious damage to the physical function of the injured person; the third level represents that the life is threatened, the development is continued, and the life safety of the wounded is seriously threatened. Under the model, the injury level is determined
Specifically quantizing the information: the first-level quantization is 1, the second-level quantization is 2, and the third-level quantization is 3;
and the time tolerance represents the objective tolerance condition of the accident to the rescue time. It should be noted that the time tolerance is not only related to the injury level, but also related to the nature of the task, for example, rescue in special occasions, rescue in special tasks, etc. although the injury level of the injured person may be the same, the time tolerance requirement is different. The quantification criterion is time period data, such as 30 minutes.
An outcome severity level, representing the severity of the outcome that would result if the event tolerance was exceeded. The method is divided into a first level, a second level and a third level (the severity is increased in sequence), wherein the first level indicates that the time tolerance is exceeded, the injury condition is expanded, and the emergency service experience of the wounded is seriously influenced; the second level indicates that the body function of the wounded is seriously damaged if the time tolerance is exceeded; third-level means that exceeding the time tolerance threatens the life safety of the wounded. Under the model, the severity level of the consequence
Specifically quantizing the information: the first-order quantization is 1, the second-order quantization is 2, and the third-order quantization is 3.
S2, establishing an aviation rescue basic task time prediction model based on a rescue grid;
s21, establishing a coordinate system of a rescue square grid graph and a description method of each point in the coordinate system based on a GIS (geographic information system);
referring to the attached figure 2, a longitude and latitude coordinate of a flying point of a helicopter for executing a rescue task is used as a coordinate origin O of a Cartesian rectangular coordinate system, a rescue grid network graph which can be infinitely expanded along a GIS map is built by using an equidistant grid network, and a scale r of the built rescue grid network graph = unit grid side length d/actual distance s represented by unit grids is synchronous with a scale in the GIS map. In practical use, it should be ensured that rescue time of each point in the same unit square is substantially consistent as much as possible, for example, in this embodiment, the side length of the unit square represents an actual distance of 200 meters, and the basic task time difference of helicopter rescue in the same unit square is within (-15 minutes, 15 minutes). The coordinate system of the built rescue grid graph is XOY, and the scale of the basic coordinate is the side length d of the unit grid.
In the coordinate system XOY, the description method of the accident site a is as follows:
wherein->
Area coordinates which indicate the accident location A>
And the included angle between the connecting line of the accident site A and the origin O and the positive direction of the X axis is shown.
It should be noted that, in the coordinate system XOY of the rescue grid diagram, a cell square is the smallest unit that can not be divided, i.e. a point set in the same cell square, and the area coordinates thereof are the same, and the difference is that
Different; coordinate->
The determination of (2) adopts a 'one-step method', namely, only one bit is advanced by a decimal point. The point set of each unit square grid comprises the left side, the lower side and points inside the square grid; for example, in fig. 2, three accident locations->
Respectively has a region coordinate of->
；
S22, constructing an aviation rescue basic task time prediction mathematical model under the description of a grid graph coordinate system based on the established rescue grid graph;
screening out a sufficient number of m (generally m) from historical rescue data>100 ) a group of sample data, according to the accident site, establishing the description information of each sample data under the coordinate system of the square grid graph as
Where i represents the ith set of samples. Thus, the input feature matrix consisting of m groups of sample data is ≥>
Corresponding result set of
Wherein->
Representing the basic task time recorded in the m groups of historical sample data;
and constructing an aviation rescue basic task time prediction mathematical model described by a square grid graph coordinate system by adopting a machine learning mode according to the input characteristics and the result set of the historical sample data.
In this embodiment, referring to fig. 3, a BP neural network is adopted, and according to the features of the input set and the result set, a neural network structure is constructed as follows:
the BP neural network structure comprises an input layer, a hidden layer I, a hidden layer II and an output layer, and is selected from m groups of sample data
And taking group data as a training set, determining the structural parameters of the BP neural network and defining variables: the input vector is
Thus, the input layer has 3 neurons, any of which is denoted by k; the output vector is
The output layer has only 1 neuron, and q is the iteration number; the number of neurons in the hidden layer I is P, wherein any neuron is represented by P; hidden layer II has J neurons, any of which is denoted by J. Connection right of input layer and hidden layer I
Indicating that the connection right of hidden layer I to hidden layer II is->
Indicating that the connection right of the hidden layer II to the output layer is>
And (4) showing. Before forward propagation, firstly randomly assigning initial values to a weight value and a threshold value; the forward propagation starts as follows:
the input and output of the hidden layer I neurons are respectively:
the input and output of the hidden layer II neurons are respectively:
the inputs and outputs of the output layer neurons are:
The activation function of the hidden layer adopts a sigmoid function:
the activation function of the output layer is based on a bipolar sigmoid function->
。
The training errors for the output layer neurons were:
wherein is present>
Is the desired output for each set of input values. And transmitting the error from back to front through back propagation, and correcting the weight and the threshold of each layer:
the weight and threshold modification from hidden layer II to output layer neuron is:
，
wherein is present>
Is a learning factor>
Is the activation function->
The derivative of (c).
The weight correction from hidden layer I to hidden layer II neurons is as follows:
，
wherein is present>
Is an activation function>
The derivative of (c).
The weight correction from the input layer to the neuron of the hidden layer I is as follows:
，
。
correcting the weight and the threshold value, detecting the current error, and finishing the training of the BP neural network if the error is smaller than the preset threshold value; otherwise, continuing to correct the detection. And testing the accuracy of the neural network by using the residual m-n groups of data after the training is finished, and if an expected value is reached, for example, the expected accuracy is 98.5% in the embodiment, establishing the mathematical model of the neural network is finished, and predicting the basic task time by using the neural network according to the input feature description.
S3, constructing an evaluation function of the aviation rescue effect of the system;
s31, supposing that k helicopters in the actual rescue system can participate in aviation rescue from the same or different geographical positions, and in a certain time period, q accidents needing aviation rescue occur in different areas
Meanwhile, the alarm receiving time is only required to be scheduled;
s32, in
Then, according to S1, the priority model of the system in this process is described as:
wherein->
A priority model description representing a jth incident; />
Since the priority model is established based on the rescue time in the embodiment, the evaluation of the aviation rescue effect under the model takes the rescue time as a focus; and has the following requirements:
(1) the rescue time of the system exceeds the time tolerance
The less the cases (a) the better, and the consequence severity level >>
The higher the occurrence exceeds the time tolerance>
The less the cases, the more preferable.
(2) In order to facilitate the control degree of the system on a certain accident or the total accident in the system in a certain time period, an attention coefficient needs to be set, and the attention coefficient can directly control the evaluation result according to a time tolerance threshold value.
(3) The evaluation system is a closed-loop system satisfying system constraints.
The evaluation function F of the aviation rescue effect under the model of the embodiment is set as follows:
S33, on the other hand, the total rescue service time and the predicted value of the basic task time of the system should meet the following relationship:
S4, searching the optimal solution of the evaluation function F by adopting a method of regional evaluation of the optimal solution, and determining an optimal scheduling scheme;
the optimal solution should make the evaluation function F obtain the minimum value, in the vehicle accident aviation rescue, the number of rescue helicopters and the vehicle accident needing the aviation rescue have the small sample discretization characteristic, the embodiment adopts the region traversal method to solve, and with reference to the attached figure 4, the specific steps are as follows:
still supposing that k helicopters in the actual rescue system can participate in aviation rescue from the same or different geographical positions, and within a certain time period, q accidents needing aviation rescue occur in different areas;
s41, based on S2, respectively taking the takeoff point of each helicopter rescue task as an original point, establishing a rescue grid graph, and calculating description information of each accident site under a grid graph coordinate system taking the takeoff point of each task as the original point
Wherein
Represents on a fifth->
Taking a flying point as an origin point>
Indicates a fifth->
Description information of the ith accident site with the individual flying point as the origin;
s42, all the description information obtained in the S41
Inputting the data into a mathematical model of basic task time prediction established in S2 to obtain the ^ th or greater than>
Basic task time->
；
S43, calculating the area evaluation numerical values of the same accident site under the conditions of different origin points of the takeoff points, finding out the minimum area evaluation value, wherein the corresponding takeoff point is the optimal rescue takeoff point of the accident which is preferred by the area, and the calculation formula of the area evaluation is as follows:
Sequentially calculating the region evaluation value of the ith accident of each flying point helicopter in rescue, and comparing to obtain the region optimal solution:
s44, after all the k helicopters are dispatched, calculating which helicopter comes back first according to the basic task time prediction of the k helicopters, and finding out the accident of which the optimal solution of the area is the helicopter, namely the next task of the helicopter;
and S45, circularly executing S44 until all accidents are scheduled to be helicopters according to the optimal solution of the area. At the moment, summing all the optimal solutions of the regions, and judging whether the constraint conditions of the evaluation function F are met
And if the constraint is met, the planning scheme is the optimal scheduling scheme. And if the constraint condition is not met, returning to the step S43, removing the area optimal solution of the planning scheme, selecting the suboptimal solution and continuing to execute the steps S44 and S45 until the planning scheme meets the constraint condition.
In conclusion, the aviation rescue intelligent scheduling method for the vehicle accident does not need to evaluate the accident accurately, and is very suitable for convenient description of the accident priority in the early stage of receiving the alarm; meanwhile, the problem that the basic task time of aviation rescue is different greatly due to different airspaces used by the task is not concerned.
The technical solution of the present invention is not limited to the limitations of the above specific embodiments, and all technical modifications made according to the technical solution of the present invention fall within the protection scope of the present invention.
Claims (1)
1. An intelligent scheduling method for aviation rescue of vehicle accidents is characterized by comprising the following steps:
s1, establishing an accident priority description model based on rescue time based on accident alarm information;
s2, establishing an aviation rescue basic task time prediction model based on a rescue grid;
s3, constructing an evaluation function of the aviation rescue effect of the system;
s4, searching the optimal solution of the evaluation function F by adopting a method of regional evaluation of the optimal solution, and determining an optimal scheduling scheme;
the specific steps of S1 are as follows:
by adopting an accident priority description method based on rescue time, a primary accident is specifically described as 4 dimensions: (1) Moment of receiving alarm
(ii) a (2) Injury grade->
(3) time tolerance->
(ii) a (4) Consequence severity rating pick>
Wherein i is an accident label and represents the ith accident;
the specific steps of S2 are as follows:
s21, establishing a coordinate system of a rescue grid graph based on a Geographic Information System (GIS) and describing each point in the coordinate system;
s22, constructing an aviation rescue basic task time prediction mathematical model under the description of a grid graph coordinate system based on the established rescue grid graph;
the specific steps of S3 are as follows:
s31, supposing that k helicopters in the actual rescue system start to participate in aviation rescue from the same or different geographical positions, and within a certain time period, q accidents needing aviation rescue occur in different areas
Scheduling according to the alarm receiving time;
s32, in
Then, according to step S1, the priority model of the system in this process is described as:
wherein->
Representing the description of a priority model of the jth accident, and taking the rescue time as a focus point for evaluating the aviation rescue effect under the model; and has the following requirements:
(1) the rescue time of the system exceeds the time tolerance
The less the cases, the better and the consequence severity level->
The higher the occurrence exceeding the time tolerance>
The less the cases, the better;
(2) in order to facilitate the control degree of the system on a certain accident or the total accident in the system in a certain time period, an attention degree coefficient is set, and the coefficient can directly control an evaluation result according to a time tolerance threshold value;
(3) the evaluation system is a closed loop system which meets system constraint conditions;
the evaluation function F of the aviation rescue effect under the model is set as follows:
s33, the total rescue service time of the system and the predicted value of the basic task time meet the following relation:
The S4 comprises the following specific steps:
s41, based on S2, respectively taking the takeoff point of each helicopter rescue task as an original point, establishing a rescue grid graph, and calculating description information of each accident site under a grid graph coordinate system taking the takeoff point of each task as the original point
Wherein->
Indicates a fifth->
Taking a flying point as an origin point>
Indicates a fifth->
Description information of the ith accident site with the individual flying point as the origin;
s42, all the description information obtained in the S41
Inputting the data into a mathematical model of basic task time prediction established in S2 to obtain the ^ th or greater than>
Basic task time ^ needed by an ith accident for rescue at a flying spot>
；
S43, calculating the area evaluation numerical values of the same accident site under the conditions of different origin points of the flying points, finding the minimum area evaluation value, wherein the corresponding flying point is the optimal rescue flying point of the accident preferred by the area at the moment, and the calculation formula of the area evaluation is as follows:
s44, after all the k helicopters are dispatched, calculating which helicopter comes back first according to the basic task time prediction of the k helicopters, and finding out the accident of the helicopter, namely the next task of the helicopter, of which the optimal solution of the area is the accident;
s45, circularly executing S44 until all accidents arrange the helicopters according to the optimal solution of the areas, summing all the optimal solutions of the areas at the moment, and judging whether the constraint conditions of the evaluation function F are met or not
If the constraint is met, the plan scheme is the optimal scheduling scheme; and if the constraint condition is not met, returning to the step S43, removing the area optimal solution of the planning scheme, selecting the suboptimal solution and continuing to execute the steps S44 and S45 until the planning scheme meets the constraint condition. />
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2019103541793 | 2019-04-29 | ||
| CN201910354179 | 2019-04-29 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110443399A CN110443399A (en) | 2019-11-12 |
| CN110443399B true CN110443399B (en) | 2023-04-07 |
Family
ID=68429107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910421644.0A Active CN110443399B (en) | 2019-04-29 | 2019-05-21 | Intelligent scheduling method for aviation rescue of vehicle accident |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110443399B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784990A (en) * | 2020-05-28 | 2020-10-16 | 上海擎感智能科技有限公司 | Vehicle accident rescue method and system and computer storage medium |
| CN114611938B (en) * | 2022-03-14 | 2023-06-20 | 王淑娟 | Emergency command method and system based on 3DGIS |
| CN114707770B (en) * | 2022-06-06 | 2022-10-18 | 中国民航大学 | Aviation emergency rescue decision optimization method based on rescue timeliness |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527160A (en) * | 2017-09-22 | 2017-12-29 | 海丰通航科技有限公司 | Aviation emergency management and rescue command scheduling management platform and emergency rescue system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2222830C1 (en) * | 2003-05-30 | 2004-01-27 | Общество с ограниченной ответственностью "Альтоника" | System of collection and analysis of data on road accident |
| US9046892B2 (en) * | 2009-06-05 | 2015-06-02 | The Boeing Company | Supervision and control of heterogeneous autonomous operations |
| US10540723B1 (en) * | 2014-07-21 | 2020-01-21 | State Farm Mutual Automobile Insurance Company | Methods of providing insurance savings based upon telematics and usage-based insurance |
| CN104166954A (en) * | 2014-07-30 | 2014-11-26 | 麦特汽车服务股份有限公司 | Vehicle dispatchment method and device |
| CN105809267A (en) * | 2014-12-31 | 2016-07-27 | 郑静晨 | Site rescue task decomposition method based on DSM |
| CN109190821B (en) * | 2018-08-30 | 2021-02-02 | 中国联合网络通信集团有限公司 | Disaster rescue scheduling method, device and system based on edge calculation |
-
2019
- 2019-05-21 CN CN201910421644.0A patent/CN110443399B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527160A (en) * | 2017-09-22 | 2017-12-29 | 海丰通航科技有限公司 | Aviation emergency management and rescue command scheduling management platform and emergency rescue system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110443399A (en) | 2019-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110443399B (en) | Intelligent scheduling method for aviation rescue of vehicle accident | |
| CN105426970B (en) | A kind of meteorological intimidation estimating method based on discrete dynamic Bayesian network | |
| CN106529306B (en) | Security of system appraisal procedure and device | |
| Mahdi et al. | Development of estimation and forecasting method in intelligent decision support systems | |
| CN106204392A (en) | Environment risk source early warning system | |
| CN106447107B (en) | Maintenance method based on aircraft structure health monitoring | |
| CN104835354A (en) | Control load management system and controller workload evaluation method | |
| CN105956336A (en) | Static and dynamic hybrid uncertainty-oriented non-probabilistic reliability optimization design method for ready-built structure | |
| CN111381166A (en) | Method and system for monitoring battery state | |
| CN111191926B (en) | Equipment rush repair efficiency cloud evaluation method based on extension uncertainty quantization method | |
| CN104732286A (en) | Method for sensing safety situation of urban rail transit station | |
| CN106526492A (en) | Lithium battery degradation modeling and life prediction method considering time-varying environment temperature influence | |
| CN105160201A (en) | Genetic algorithm back propagation (GABP) neural network based controller workload prediction method and system | |
| CN109947806A (en) | A kind of Super High construction safety accident emergency aid decision-making method of case-based reasioning | |
| CN111126672A (en) | High-voltage overhead transmission line typhoon disaster prediction method based on classification decision tree | |
| CN115293545A (en) | Typhoon disaster risk assessment method and system based on power grid district division and storage medium | |
| CN110794308B (en) | Method and device for predicting train battery capacity | |
| CN105118332A (en) | Air traffic control analog simulation abnormality detection method and device based on clustering analysis method | |
| CN105118333A (en) | Air traffic control analog simulation abnormality detection method and device based on multiple-regression model | |
| CN103197564B (en) | Digitizing man-machine interface monitor unit quantity optimization method and system | |
| Shao et al. | G-BDP-ADC model for effectiveness evaluation of low orbit satellite communication system in the context of poor information | |
| CN114723335B (en) | Method for evaluating service efficiency of marine supervision and rescue aircraft | |
| CN114266370A (en) | Method and system for generating fault handling plan of power grid equipment in typhoon meteorological environment on line and storage medium | |
| CN113449918B (en) | Emergency command aid decision-making method and system for sudden major pollution event | |
| CN104301388A (en) | Large running system monitoring and analyzing management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |