CN115129081A - Emergency data collection network and method based on wavelet neural fuzzy inference system - Google Patents
Emergency data collection network and method based on wavelet neural fuzzy inference system Download PDFInfo
- Publication number
- CN115129081A CN115129081A CN202210798011.3A CN202210798011A CN115129081A CN 115129081 A CN115129081 A CN 115129081A CN 202210798011 A CN202210798011 A CN 202210798011A CN 115129081 A CN115129081 A CN 115129081A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- iotd
- data
- jth
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013480 data collection Methods 0.000 title claims abstract description 33
- 230000001537 neural effect Effects 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 42
- 238000004891 communication Methods 0.000 claims abstract description 15
- 230000006870 function Effects 0.000 claims description 37
- 238000005265 energy consumption Methods 0.000 claims description 36
- 238000013528 artificial neural network Methods 0.000 claims description 25
- 238000003860 storage Methods 0.000 claims description 18
- 239000011541 reaction mixture Substances 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 239000000725 suspension Substances 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 230000002265 prevention Effects 0.000 claims description 7
- 150000001875 compounds Chemical class 0.000 claims description 6
- 238000003306 harvesting Methods 0.000 claims description 6
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000001556 precipitation Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000001953 sensory effect Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000013531 bayesian neural network Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 208000020442 loss of weight Diseases 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/104—Simultaneous control of position or course in three dimensions specially adapted for aircraft involving a plurality of aircrafts, e.g. formation flying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2291—User-Defined Types; Storage management thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/14—Relay systems
- H04B7/15—Active relay systems
- H04B7/185—Space-based or airborne stations; Stations for satellite systems
- H04B7/18502—Airborne stations
- H04B7/18506—Communications with or from aircraft, i.e. aeronautical mobile service
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/04—Large scale networks; Deep hierarchical networks
- H04W84/06—Airborne or Satellite Networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Astronomy & Astrophysics (AREA)
- Software Systems (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an emergency data collection network and method based on a wavelet neural fuzzy inference system, which are used for carrying out data acquisition and wireless energy supply on an emergency hydrological monitoring point by using an unmanned aerial vehicle group when a traditional communication infrastructure and a power facility are damaged in a large area, have very important significance in an emergency disaster relief environment, can supply energy to sensor nodes of the emergency hydrological monitoring point, acquire sensing data of a disaster area in real time and provide data support for flood fighting and disaster relief decisions. The invention provides a flight path planning method based on a depth wavelet neural fuzzy inference system aiming at the characteristics of urgency and credibility of emergency decision in flood fighting and disaster relief.
Description
Technical Field
The invention relates to the technical field of new-generation information, in particular to an emergency data collection network and method based on a wavelet neural fuzzy inference system.
Background
Flood disasters in China are wide in distribution region and high in occurrence frequency, and damage and loss of weight are caused. Therefore, the critical communication and calculation technology in emergency rescue is urgently needed to be broken through, the damage of disaster accidents is reduced, and the life and property safety of people is completely protected.
When flood disasters occur, data such as water level, flow speed, water pressure, rainfall and the like need to be monitored through a plurality of emergency hydrological monitoring points. However, communication infrastructures fixed in flood areas are often damaged in a large area, and a traditional data acquisition mode based on a base station cannot be effectively implemented, so that a more flexible and mobile data acquisition mode is urgently needed. Meanwhile, the traditional power facilities can be damaged in flood disasters, and the energy of the sensor of the emergency hydrological monitoring point is difficult to be effectively supplemented.
Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle auxiliary emergency data collection network based on a wavelet neural fuzzy inference system, which consists of an aerial unmanned aerial vehicle group, an emergency hydrological monitoring point and a ground control command center, wherein the monitoring data of the emergency hydrological monitoring point is collected by utilizing the high mobility of the unmanned aerial vehicle, and the sensor of the emergency hydrological monitoring point is wirelessly powered.
The second purpose of the invention is to provide an interpretable unmanned aerial vehicle flight path planning method based on a wavelet neural fuzzy inference system, which can provide on-line trajectory planning for the unmanned aerial vehicle, and can generate a fuzzy inference rule in a self-adaptive manner to interpret an output result.
In order to achieve the purpose, the invention provides the following technical scheme:
the invention provides an unmanned aerial vehicle auxiliary emergency data collection network based on a wavelet neural fuzzy inference system, which comprises an aerial unmanned aerial vehicle group, an emergency hydrological monitoring point and a ground control command center;
the aerial unmanned aerial vehicle cluster comprises a plurality of unmanned aerial vehicles, and each unmanned aerial vehicle comprises a first central controller, a rotor wing, a first battery, a motor, a first storage, a first wireless module and a wireless energy supply module; the rotor, the first battery, the motor, the first storage, the first wireless module and the wireless energy supply module are all connected with the first central controller; the unmanned aerial vehicle can be flexibly deployed in the air according to the specific position of the emergency hydrological monitoring point, quickly acquire data and wirelessly supply energy to the sensor of the emergency hydrological monitoring point through the wireless energy supply module;
the emergency hydrological monitoring points comprise a plurality of monitoring points, the monitoring points comprise a second central controller, a second battery, a second wireless module, a second storage, a wireless energy receiving module and a sensor, and the second battery, the second wireless module, the second storage, the wireless energy receiving module and the sensor are all connected with the second central controller; the sensors comprise a water level sensor, a flow velocity sensor, a water pressure sensor and a precipitation sensor; the wireless energy receiving module can receive energy to charge a second battery of a monitoring point;
the ground control command center comprises a flood prevention database, a scheduling module and a communication module, wherein the flood prevention database is used for storing data of emergency hydrological monitoring points in a flood disaster area; the scheduling module comprises a wavelet neural fuzzy inference system and is used for making scheduling decision on the unmanned aerial vehicle group; the communication module transmits the track planning, data acquisition and wireless energy transmission time planning commands of the unmanned aerial vehicle network to the unmanned aerial vehicle cluster in the network, and simultaneously accesses the related data to the remote flood control cloud platform.
When the edge computing service is provided, the flight path of the unmanned aerial vehicle group needs to be planned in a unified mode, a reasonable time planning and distribution scheme for data acquisition and wireless energy transmission needs to be designed, on-line real-time decision needs to be provided considering the urgency of rescue work, and interpretable decision results are often needed.
The invention also provides an interpretable unmanned aerial vehicle flight path planning method based on the wavelet neural fuzzy inference system, which comprises the following steps:
s1, defining an unmanned aerial vehicle auxiliary emergency data collection network, wherein when the traditional communication facilities and the electric power facilities are damaged, the unmanned aerial vehicles in the network are used for collecting emergency data;
s2, defining a flight path model of the unmanned aerial vehicle;
s3, defining a data collection model of the unmanned aerial vehicle;
s4, defining an energy consumption model of the unmanned aerial vehicle;
s5, solving the data acquisition time and the wireless energy supply time of the unmanned aerial vehicle based on the model and the variables defined in S1-S4;
s6, defining an optimization objective function, wherein the optimization objective function is the objective of path planning;
s7, solving the path planning of the unmanned aerial vehicle based on the depth wavelet neural fuzzy inference system, and explaining an output result by using a module inference system in the unmanned aerial vehicle.
Preferably, in step S1, the defining an auxiliary emergency data collection network for the unmanned aerial vehicle is specifically:
the unmanned aerial vehicle auxiliary emergency data collection network is composed of N emergency hydrology monitoring points, a ground control command center and M unmanned aerial vehicles with half-duplex access points, the unmanned aerial vehicles start from the ground control command center and fly right above each IoTD in sequence, the flight height of the unmanned aerial vehicle is H, wireless energy is transmitted to the IoTD through a time division duplex mode, the IoTD is charged, and hydrology data are collected from the IoTD.
Step S1 describes the composition of the unmanned aerial vehicle auxiliary emergency data collection network, and steps S2-S4 describe a flight path model, a data collection model and an energy consumption model of the unmanned aerial vehicle.
Preferably, in step S2, the defining the flight trajectory model of the unmanned aerial vehicle specifically includes:
fixed position r of jth unmanned aerial vehicle from ground control command center j [0]Takeoff (0,0, H) and then sequentially flying to each IoTD to collect data; the jth unmanned aerial vehicle completes a data acquisition task according to a preset flight track, and returns to the same ground control command center after a flight period:
r j [S j ]＝r j [0] (1)
in the formula (1), r j [t]Represents the t time slot on the jth unmanned aerial vehicle flight path, an
Jth UAV common service S j A hang-off point;
the ith IoTD only needs to transmit sensor data to the unmanned aerial vehicle once, and the following equation needs to be satisfied:
in the formula (2), a ij [t]I {0,1} is the user association of the i iotds and the jth drone, a ij [t]1 means that the jth drone collects data in the ith IoTD at the tth slot, otherwise a ij [t]＝0；
Assuming that each drone can fly straight from one suspension point to another, the flight time of the jth drone
The calculation is as follows:
in the formula (3), | | r j [t+1]-r j [t]|| 1 Is the point of suspension r j [t+1]And suspension point r j [t]Euclidean distance of, V j Is the flight speed of the drone;
hover time of jth drone
The calculation is as follows:
in formula (4), T ij Indicating the hovering time of the jth drone at the ith IoTD.
Preferably, in step S3, the defining the data collection model of the drone specifically includes:
in order to ensure that the IoTD has enough electric quantity for transmitting sensor data, a data acquisition task of the unmanned aerial vehicle can be divided into an energy charging stage and a data transmission stage;
in the energy charging stage, the unmanned aerial vehicle transmits power through the fixed P C Transmitting a radio frequency signal to an IoTD, the ith IoTD carrying power in the radio frequency signal received at the jth drone
Expressed as:
in the formula (5), the reaction mixture is,
represents the downlink power gain from the jth drone to the ith IoTD;
harvesting power of ith IoTD at jth drone
Comprises the following steps:
in the formula (6), the reaction mixture is,
represents a maximum output Direct Current (DC) power; a and b represent characteristic parameters of the energy harvesting system;
therefore, the ith IoTD obtains energy from the jth unmanned aerial vehicle
Can be calculated as:
in the formula (7), the reaction mixture is,
is the wireless energizing time for the ith IoTD to collect energy from the jth drone;
in the data transmission stage, the uploading data rate R from the ith IoTD to the jth unmanned aerial vehicle ij Can be expressed as:
in the formula (8), the reaction mixture is,
represents the uplink power gain; b is the bandwidth; sigma 2 Is gaussian white noise power;
is the data acquisition time from the jth drone to the ith IoTD;
to ensure that the IoTD successfully uploads its sensory data to the drone, the following inequality needs to be satisfied:
in the formula (9), d i Is the amount of sensor data on the ith IoTD.
Preferably, in step S4, the defining the energy consumption model of the unmanned aerial vehicle specifically includes:
assuming that the energy consumption of the unmanned aerial vehicle includes flight energy consumption, hovering energy consumption and wireless energy supply energy consumption, the flight energy consumption of the jth unmanned aerial vehicle
The calculation is as follows:
in the formula (10), P F Is the flight power of the drone;
calculating hovering energy consumption of jth unmanned aerial vehicle
Comprises the following steps:
in the formula (11), P H Is the hover power of the drone;
is the hover time of the jth drone;
calculate jth unmanned aerial vehicle's wireless energy supply energy consumption
Comprises the following steps:
in the formula (12), the reaction mixture is,
is the power transmission time of the jth drone;
therefore, the total energy consumption of the jth drone can be expressed as:
because the data storage capacity and the battery capacity of the unmanned aerial vehicle are limited, the total energy consumption of the unmanned aerial vehicle is required not to exceed the battery capacity E of the unmanned aerial vehicle j,max The collected data does not exceed the storage capacity C j,max Therefore, these inequalities need to be satisfied:
E j ≤E j,max (14)
preferably, in step S5, the solving of the data acquisition time and the wireless power supply time of the drone specifically includes: solving the data acquisition time and the wireless power supply time of the unmanned aerial vehicle according to formulas (16) and (17), wherein models and variables defined in S1-S4 are required in the solved formula;
due to the fact that
In relation to the data acquisition time and the wireless power supply time,
related to the wireless energy supply time, the data acquisition time is solved according to the following formula
And wireless energy supply time
In the formula (16), the compound represented by the formula,
is a lambertiw function;
preferably, in step S6, the planned path satisfies an optimization objective function, where the optimization objective function P0 is:
in equation (18), m is the number of drones used for data collection;
representing the flight trajectory of the drone.
Preferably, in step S7, the solving of the path plan of the unmanned aerial vehicle by the neural fuzzy inference system based on depth wavelet specifically includes:
(7.1) a feature extraction part based on a Transformer model;
firstly, coordinate and data volume information (x) of IoTD i ,y i ,d i ) Putting the encoder module of a Transformer model into the encoder module to obtain the self-attention feature h of each IoTD i Then, the average self-attention feature h of all IoTD is obtained c ；
Defining the input signal of the fuzzy inference system as
Wherein h is c Mean of self-attention features for all IoTD; h is pre The self-attention feature of the last IoTD in the flight track; e res The current residual energy of the unmanned aerial vehicle; c res The current remaining data space of the unmanned aerial vehicle;
(7.2) a fuzzy inference system part;
an fuzzification module:
wherein, C ki The center of the Gaussian fuzzy membership function input to the k semantic item is used as the ith input; sigma ki 2 The width of a Gaussian fuzzy membership function input to the kth semantic item is set; l is the number of semantic items;
a fuzzy rule module:
an inference module:
in the formula (19), the compound represented by the formula (I),
is the output of the deep wavelet neural network;
obtaining a defuzzification module:
(7.3) a deep wavelet neural network portion;
defining r hidden layers in the depth wavelet neural network, the output of the theta layer is expressed as:
in formula (20), Ψ θ Representing hidden layers of the theta-th layerOutput, ω θ Is the weight of the theta-th layer wavelet function, a θ ,b θ Respectively a scale variable and a displacement variable of a theta-th layer wavelet function;
in order to improve the nonlinear modeling capability of the wavelet neural network, the wavelet functions of different hidden layers can be different wavelet functions;
thus, the output of the deep wavelet neural network is
Wherein phi r A depth wavelet neural network output representing an r-th layer;
an integration module:
o (7) the next flight node position r of the jth unmanned aerial vehicle in the flight track is obtained after the integer is taken j [t]Outputting the result;
according to calculated r j [t]Updating
If E is res Or C res If not, the current jth unmanned aerial vehicle flies back to the ground control command center and is reset
Wherein h is 0 Controlling the self-attention feature of a command center for the ground; e max The maximum battery capacity of the unmanned aerial vehicle; c max The maximum storage capacity of the unmanned aerial vehicle;
in the deep wavelet neural fuzzy inference system, the fuzzy inference system can model an inference process into a fuzzy plan through the learning of a deep wavelet neural network and explain a final output result through a fuzzy rule;
and planning the path of the next unmanned aerial vehicle until all the IoTD data are acquired by the unmanned aerial vehicle and the path planning of all the unmanned aerial vehicles is finished.
S1-S6 define the network composition, mathematical model and optimization goal of path planning, and S7 is a specific method for solving paths.
According to the invention, under the condition that ground communication infrastructures and power facilities in a flood area are damaged in a large scale, the data of sensors of emergency hydrological monitoring points in the flood area are collected by using the unmanned aerial vehicle auxiliary emergency data collection network, and meanwhile, the sensors of the emergency hydrological monitoring points are charged wirelessly through a wireless energy supply technology, so that the method has very important research significance and application prospect.
Compared with the prior art, the invention has the following advantages:
1) the invention provides an unmanned aerial vehicle auxiliary emergency data collection network based on a wavelet neural fuzzy inference system, which is used for carrying out data acquisition and wireless energy supply on an emergency hydrological monitoring point by using an unmanned aerial vehicle group when a traditional communication infrastructure and an electric power facility are damaged in a large area, has very important significance in an emergency disaster relief environment, can supply energy to sensor nodes of the emergency hydrological monitoring point, acquires sensing data of a disaster area in real time and provides data support for a flood fighting and disaster relief decision.
2) The invention provides a flight path planning method based on a depth wavelet neuro-fuzzy inference system aiming at the characteristics of urgency and credibility of emergency decision in flood fighting and disaster relief.
3) In order to improve the decision-making capability of the flight trajectory of the unmanned aerial vehicle group, the neural fuzzy inference system makes two improvements: firstly, a transducer module of a Transformer model is adopted to extract self-attention characteristics of sensor equipment of an emergency hydrological monitoring point, so that the characteristic expression capability of input data is improved; secondly, a deep wavelet neural network is introduced to carry out nonlinear learning of flight characteristics. Different from the traditional deep neural network which uses the same activation function in the whole network, a plurality of wavelet functions are used as the activation functions of different nodes of the deep wavelet neural network, and the multi-scale learning capability of the system is further improved.
Drawings
Fig. 1 is a block diagram of an unmanned aerial vehicle assisted emergency data collection network.
Fig. 2 is a block diagram of a wavelet neuro-fuzzy inference system.
Detailed Description
The invention will be further illustrated with reference to the following specific examples and the accompanying drawings:
the invention provides an unmanned aerial vehicle auxiliary emergency data collection network based on a wavelet neural fuzzy inference system, which comprises an aerial unmanned aerial vehicle group, an emergency hydrological monitoring point and a ground control command center;
the unmanned aerial vehicle cluster comprises a plurality of unmanned aerial vehicles, and each unmanned aerial vehicle comprises a first central controller, a rotor wing, a first battery, a motor, a first storage, a first wireless module and a wireless energy supply module; the rotor, the first battery, the motor, the first storage, the first wireless module and the wireless energy supply module are all connected with the first central controller; the unmanned aerial vehicle can be flexibly deployed in the air according to the specific position of the emergency hydrological monitoring point, quickly acquire data and wirelessly supply energy to the sensor of the emergency hydrological monitoring point through the wireless energy supply module;
the emergency hydrological monitoring points comprise a plurality of monitoring points, the monitoring points comprise a second central controller, a second battery, a second wireless module, a second storage, a wireless energy receiving module and a sensor, and the second battery, the second wireless module, the second storage, the wireless energy receiving module and the sensor are all connected with the second central controller; the sensors comprise a water level sensor, a flow velocity sensor, a water pressure sensor and a precipitation sensor; the wireless energy receiving module can receive energy to charge a second battery of the monitoring point;
the ground control command center comprises a flood prevention database, a scheduling module and a communication module, wherein the flood prevention database is used for storing data of emergency hydrological monitoring points in flood disaster areas; the scheduling module comprises a wavelet neural fuzzy inference system and is used for making scheduling decision on the unmanned aerial vehicle group; the communication module transmits the track planning, data acquisition and wireless energy transmission time planning commands of the unmanned aerial vehicle network to the unmanned aerial vehicle cluster in the network, and simultaneously accesses the related data to the remote flood control cloud platform.
Example 1
The invention provides an interpretable unmanned aerial vehicle flight path planning method based on a wavelet neural fuzzy inference system, which comprises the following steps:
the unmanned aerial vehicle auxiliary emergency data collection network consists of N emergency hydrological monitoring points (IoTD for short), a ground control command center and M unmanned aerial vehicles with half-duplex access points, wherein the unmanned aerial vehicles start from the ground control command center and sequentially fly right above each IoTD, the flying height of each unmanned aerial vehicle is H, wireless energy is transmitted to the IoTD through a time division duplex mode, the IoTD is charged, and hydrological data are collected from the IoTD;
step 2, defining a flight path model of the unmanned aerial vehicle;
fixed position r of jth unmanned aerial vehicle from ground control command center j [0]Takeoff (0,0, H) and then sequentially flying to each IoTD to collect data; the jth unmanned aerial vehicle completes a data acquisition task according to a preset flight track, and returns to the same ground control command center after a flight period:
r j [S j ]＝r j [0] (1)
in the formula (1), r j [t]Represents the t time slot on the jth unmanned aerial vehicle flight path, an
Jth UAV common service S j A hang-off point;
the ith IoTD only needs to transmit sensor data to the drone once, and needs to satisfy the following equation:
in the formula (2), a ij [t]I-i iota iotao iota i iota i iota i iota i iota i ij [t]1 means that the jth drone collects data in the ith IoTD at the tth slot, otherwise a ij [t]＝0；
Assuming that each drone can fly straight from one suspension point to another, the flight time of the jth drone
The calculation is as follows:
in the formula (3), | | r j [t+1]-r j [t]|| 1 Is the point of suspension r j [t+1]And a suspension point r j [t]Euclidean distance of, V j Is the flight speed of the drone;
hover time of jth drone
The calculation is as follows:
in the formula (4), T ij Indicating the hovering time of the jth unmanned aerial vehicle at the ith IoTD;
step 3, defining a data collection model of the unmanned aerial vehicle;
in order to ensure that the IoTD has enough electric quantity for transmitting sensor data, a data acquisition task of the unmanned aerial vehicle can be divided into an energy charging stage and a data transmission stage;
in the energy charging stage, the unmanned aerial vehicle transmits power through the fixed P C Transmitting a radio frequency signal to an IoTD, the ith IoTD carrying power in the radio frequency signal received at the jth drone
Expressed as:
in the formula (5), the reaction mixture is,
represents the downlink power gain from the jth drone to the ith IoTD;
harvesting power of ith IoTD at jth drone
Comprises the following steps:
in the formula (6), the reaction mixture is,
represents a maximum output Direct Current (DC) power; a and b represent characteristic parameters of the energy harvesting system;
therefore, the ith IoTD obtains energy from the jth unmanned aerial vehicle
Can be calculated as:
in the formula (7), the reaction mixture is,
is the wireless energizing time for the ith IoTD to collect energy from the jth drone;
in the data transmission stage, the uploading data rate R from the ith IoTD to the jth UAV ij Can be expressed as:
in the formula (8), the reaction mixture is,
represents the uplink power gain; b is the bandwidth; sigma 2 Is gaussian white noise power;
is the data acquisition time from the jth drone to the ith IoTD;
to ensure that the IoTD successfully uploads its sensory data to the drone, the following inequality needs to be satisfied:
in the formula (9), d i Is the sensor data amount on the ith IoTD;
step 4, defining an energy consumption model of the unmanned aerial vehicle;
assuming that the energy consumption of the unmanned aerial vehicle includes flight energy consumption, hovering energy consumption and wireless energy supply energy consumption, the flight energy consumption of the jth unmanned aerial vehicle
The calculation is as follows:
in the formula (10), P F Is the flight power of the drone;
calculating hovering energy consumption of jth unmanned aerial vehicle
Comprises the following steps:
in the formula (11), P H Is the hover power of the drone;
is the hover time of the jth drone;
calculate jth unmanned aerial vehicle's wireless energy supply energy consumption
Comprises the following steps:
in the formula (12), the reaction mixture is,
is the power transmission time of the jth drone;
therefore, the total energy consumption of the jth drone can be expressed as:
because the data storage capacity and the battery capacity of the unmanned aerial vehicle are limited, the total energy consumption of the unmanned aerial vehicle is required not to exceed the battery capacity E of the unmanned aerial vehicle j,max The collected data does not exceed the storage capacity C j,max Therefore, these inequalities need to be satisfied:
E j ≤E j,max (14)
step 5, solving the data acquisition time and the wireless energy supply time of the unmanned aerial vehicle according to the formulas (16) and (17);
due to the fact that
In relation to the data acquisition time and the wireless power supply time,
in relation to the wireless energy supply time, the data acquisition time is first solved according to the following formula
And wireless energy supply time
In the formula (16), the compound represented by the formula (I),
is a lambertiw function;
step 6, defining an optimization objective function, wherein the optimization objective function refers to a path planning objective, specifically, the planned path satisfies a formula (18), and the optimization objective function P0 is:
in equation (18), m is the number of drones used for data collection;
representing the flight trajectory of the unmanned aerial vehicle;
step 7, solving the path planning of the unmanned aerial vehicle based on the depth wavelet neural fuzzy inference system, and explaining an output result by using a module inference system in the path planning;
(7.1) a feature extraction part based on a Transformer model;
firstly, coordinate and data volume information (x) of IoTD i ,y i ,d i ) Putting the encoder module of the Transformer model into the encoder module to obtain the self-attention feature h of each IoTD i Then, the average self-attention feature h of all IoTD is obtained c ；
Defining the input signal of the fuzzy inference system as
Wherein h is c Mean of self-attention features for all IoTD; h is pre The self-attention feature of the last IoTD in the flight trajectory; e res The current residual energy of the unmanned aerial vehicle; c res The current remaining data space of the unmanned aerial vehicle;
(7.2) a fuzzy inference system part;
an fuzzification module:
wherein, C ki The center of the Gaussian fuzzy membership function input to the k semantic item is used as the ith input; sigma ki 2 The width of a Gaussian fuzzy membership function input to the kth semantic item is set; l is the number of semantic items;
a fuzzy rule module:
an inference module:
in the formula (19), the compound represented by the formula (I),
is the output of the deep wavelet neural network;
obtaining a defuzzification module:
(7.3) a deep wavelet neural network portion;
the depth wavelet neural network is defined to have r hidden layers, and the output of the theta layer is expressed as follows:
in formula (20), Ψ θ Denotes the output of the theta-th hidden layer, omega θ Is the weight of the theta-th layer wavelet function, a θ ,b θ Respectively representing a scale variable and a displacement variable of the theta-th layer wavelet function;
in order to improve the nonlinear modeling capability of the wavelet neural network, the wavelet functions of different hidden layers can be different wavelet functions;
thus, the output of the deep wavelet neural network is
Wherein phi is r A depth wavelet neural network output representing an r-th layer;
an integration module:
o (7) the position r of the next flight node of the jth unmanned aerial vehicle in the flight track is obtained after the rounding j [t]Outputting the result;
according to calculated r j [t]Updating
If E is res Or C res If not, the current jth unmanned aerial vehicle flies back to the ground control command center and is reset
Wherein h is 0 Controlling the self-attention feature of a command center for the ground; e max The maximum battery capacity of the unmanned aerial vehicle; c max The maximum storage capacity of the unmanned aerial vehicle;
in the deep wavelet neural fuzzy inference system, the fuzzy inference system can model an inference process into a fuzzy plan through the learning of a deep wavelet neural network and explain a final output result through a fuzzy rule;
and planning the path of the next unmanned aerial vehicle until all the IoTD data are acquired by the unmanned aerial vehicle and the path planning of all the unmanned aerial vehicles is finished.
Example 2
A simulation experiment is carried out on the unmanned aerial vehicle auxiliary emergency data collection network based on the wavelet neural fuzzy inference system, the designed wavelet neural fuzzy inference system is adopted to train in a ground control command center, and flight path planning of an unmanned aerial vehicle cluster in the unmanned aerial vehicle auxiliary emergency data collection network is guided.
The embodiment combines the method and other classical optimization algorithms: genetic Algorithm (GA), long and short time memory network (LSTM), Bayesian Neural Network (BNN) and Fuzzy Neural Network (FNN) are compared, and the experimental results are shown in Table 1:
table 1 this example shows the results of simulation experiments using this method and other classical optimization algorithms
| Algorithm | Calculating time (seconds) | Value of objective function |
| Algorithm of the invention | 0.387 | 254.32 |
| GA | 42.27 | 258.61 |
| LSTM | 0.685 | 284.16 |
| BNN | 0.572 | 294.91 |
| FNN | 0.583 | 267.42 |
The objective function value in the experiment table is the energy consumption of all the user equipment, and the smaller the value is, the smaller the energy consumption of the user equipment in the network is. According to experimental results, the algorithm can better operate in an unmanned aerial vehicle auxiliary emergency data collection network, and lower energy consumption can be obtained with higher efficiency.
According to the invention, under the condition that ground communication infrastructures and power facilities in a flood area are damaged in a large scale, the data of sensors of emergency hydrological monitoring points in the flood area are collected by using the unmanned aerial vehicle auxiliary emergency data collection network, and meanwhile, the sensors of the emergency hydrological monitoring points are charged wirelessly through a wireless energy supply technology, so that the method has very important research significance and application prospect.
Claims (9)
1. An unmanned aerial vehicle auxiliary emergency data collection network based on a wavelet neuro-fuzzy inference system is characterized by comprising an aerial unmanned aerial vehicle group, an emergency hydrological monitoring point and a ground control command center;
the aerial unmanned aerial vehicle cluster comprises a plurality of unmanned aerial vehicles, and each unmanned aerial vehicle comprises a first central controller, a rotor wing, a first battery, a motor, a first storage, a first wireless module and a wireless energy supply module; the rotor, the first battery, the motor, the first storage, the first wireless module and the wireless energy supply module are all connected with the first central controller; the unmanned aerial vehicle can be flexibly deployed in the air according to the specific position of the emergency hydrological monitoring point, quickly acquire data and wirelessly supply energy to the sensor of the emergency hydrological monitoring point through the wireless energy supply module;
the emergency hydrological monitoring points comprise a plurality of monitoring points, the monitoring points comprise a second central controller, a second battery, a second wireless module, a second storage, a wireless energy receiving module and a sensor, and the second battery, the second wireless module, the second storage, the wireless energy receiving module and the sensor are all connected with the second central controller; the sensors comprise a water level sensor, a flow velocity sensor, a water pressure sensor and a precipitation sensor; the wireless energy receiving module can receive energy to charge a second battery of a monitoring point;
the ground control command center comprises a flood prevention database, a scheduling module and a communication module, wherein the flood prevention database is used for storing data of emergency hydrological monitoring points in a flood disaster area; the scheduling module comprises a wavelet neural fuzzy inference system and is used for making scheduling decision on the unmanned aerial vehicle group; and the communication module transmits a time planning command of trajectory planning, data acquisition and wireless energy transmission of the unmanned aerial vehicle network to the unmanned aerial vehicle group in the network, and simultaneously accesses related data to the remote flood prevention cloud platform.
2. An interpretable unmanned aerial vehicle flight path planning method based on a wavelet neural fuzzy inference system is characterized by comprising the following steps:
s1, defining an unmanned aerial vehicle auxiliary emergency data collection network, wherein when the traditional communication facilities and the electric power facilities are damaged, the unmanned aerial vehicles in the network are used for collecting emergency data;
s2, defining a flight path model of the unmanned aerial vehicle;
s3, defining a data collection model of the unmanned aerial vehicle;
s4, defining an energy consumption model of the unmanned aerial vehicle;
s5, solving the data acquisition time and the wireless energy supply time of the unmanned aerial vehicle based on the model and the variables defined in S1-S4;
s6, defining an optimization objective function, wherein the optimization objective function is the objective of path planning;
s7, solving the path planning of the unmanned aerial vehicle based on the depth wavelet neural fuzzy inference system, and explaining an output result by using a module inference system in the unmanned aerial vehicle.
3. The method for planning the flight path of an interpretable unmanned aerial vehicle based on the wavelet neuro-fuzzy inference system according to claim 2, wherein in step S1, the defining the unmanned aerial vehicle-assisted emergency data collection network specifically comprises:
the unmanned aerial vehicle auxiliary emergency data collection network is composed of N emergency hydrological monitoring points, a ground control command center and M unmanned aerial vehicles with half-duplex access points, the unmanned aerial vehicles start from the ground control command center and sequentially fly right above each IoTD, the flying height of each unmanned aerial vehicle is H, wireless energy is transmitted to the IoTD through a time division duplex mode, the IoTD is charged, and hydrological data are collected from the IoTD.
4. The method for planning the flight path of the interpretable unmanned aerial vehicle based on the wavelet neural fuzzy inference system according to claim 2, wherein in step S2, the defining the flight trajectory model of the unmanned aerial vehicle specifically comprises:
fixed position of jth unmanned aerial vehicle slave ground control command centerPut r j [0]Takeoff at (0,0, H) and then sequentially fly to each IoTD to collect data; the jth unmanned aerial vehicle finishes a data acquisition task according to a preset flight track, and returns to the same ground control command center after a flight period:
r j [S j ]＝r j [0] (1)
in the formula (1), r j [t]Represents the t time slot on the jth unmanned aerial vehicle flight path, an
Jth UAV common service S j A hang-off point;
the ith IoTD only needs to transmit sensor data to the unmanned aerial vehicle once, and the following equation needs to be satisfied:
in the formula (2), a ij [t]I-i iota iotao iota i iota i iota i iota i iota i ij [t]1 means that the jth drone collects data in the ith IoTD at the tth slot, otherwise a ij [t]＝0；
Time of flight for jth drone, assuming each drone can fly straight from one hover point to another, time of flight
The calculation is as follows:
in the formula (3), | | r j [t+1]-r j [t]|| 1 Is the point of suspension r j [t+1]And suspension point r j [t]Euclidean distance of, V j Is the flight speed of the drone;
hover time for jth drone
The calculation is as follows:
in the formula (4), T ij Indicating the hovering time of the jth drone at the ith IoTD.
5. The method for planning the flight path of an interpretable unmanned aerial vehicle based on the wavelet neuro-fuzzy inference system according to claim 2, wherein in step S3, the data collection model of the unmanned aerial vehicle is defined, specifically:
in order to ensure that the IoTD has enough electric quantity for transmitting sensor data, a data acquisition task of the unmanned aerial vehicle can be divided into an energy charging stage and a data transmission stage;
in the energy charging stage, the unmanned aerial vehicle transmits power through the fixed P C Transmitting a radio frequency signal to an IoTD, the ith IoTD carrying power in the radio frequency signal received at the jth drone
Expressed as:
in the formula (5), the reaction mixture is,
represents the downlink power gain from the jth drone to the ith IoTD;
harvesting power of ith IoTD at jth drone
Comprises the following steps:
in the formula (6), the reaction mixture is,
represents a maximum output Direct Current (DC) power; a and b represent characteristic parameters of the energy harvesting system;
therefore, the ith IoTD obtains energy from the jth unmanned aerial vehicle
Can be calculated as:
in the formula (7), the reaction mixture is,
is the wireless energizing time for the ith IoTD to collect energy from the jth drone;
in the data transmission stage, the uploading data rate R from the ith IoTD to the jth unmanned aerial vehicle ij Can be expressed as:
in the formula (8), the reaction mixture is,
represents the uplink power gain; b is the bandwidth; sigma 2 Is the gaussian white noise power;
is from the firstAcquiring data from j unmanned aerial vehicles to the ith IoTD;
to ensure that the IoTD successfully uploads its sensory data to the drone, the following inequality needs to be satisfied:
in the formula (9), d i Is the amount of sensor data on the ith IoTD.
6. The method for planning the flight path of the interpretable unmanned aerial vehicle based on the wavelet neuro-fuzzy inference system according to claim 2, wherein in step S4, the energy consumption model of the unmanned aerial vehicle is defined, specifically:
assuming that the energy consumption of the unmanned aerial vehicle includes flight energy consumption, hovering energy consumption and wireless energy supply energy consumption, the flight energy consumption of the jth unmanned aerial vehicle
The calculation is as follows:
in the formula (10), P F Is the flight power of the drone;
calculating hovering energy consumption of jth unmanned aerial vehicle
Comprises the following steps:
in the formula (11), P H Is the hover power of the drone;
is the jth oneA hover time of the human machine;
calculate jth unmanned aerial vehicle's wireless energy supply energy consumption
Comprises the following steps:
in the formula (12), the reaction mixture is,
is the power transmission time of the jth drone;
therefore, the total energy consumption of the jth drone can be expressed as:
because the data storage capacity and the battery capacity of the unmanned aerial vehicle are limited, the total energy consumption of the unmanned aerial vehicle is required not to exceed the battery capacity E of the unmanned aerial vehicle j，max The collected data does not exceed the storage capacity C j，max Therefore, these inequalities need to be satisfied:
E j ≤E j，max (14)
7. the method for planning the flight path of the interpretable unmanned aerial vehicle based on the wavelet neuro-fuzzy inference system according to claim 2, wherein in step S5, the solving of the data acquisition time and the wireless power supply time of the unmanned aerial vehicle is specifically as follows:
due to the fact that
And dataThe acquisition time is related to the wireless energy supply time,
in relation to the wireless energy supply time, the data acquisition time is first solved according to the following formula
And wireless energy supply time
In the formula (16), the compound represented by the formula,
is a lambert w function;
8. the method for planning the flight path of an interpretable unmanned aerial vehicle based on the wavelet neuro-fuzzy inference system as claimed in claim 2, wherein in step S6, the planned path satisfies an optimization objective function, and the optimization objective function P0 is:
in equation (18), m is the number of drones used for data collection;
representing the flight trajectory of the drone.
9. The method for planning the flight path of the unmanned aerial vehicle interpretable based on the wavelet neural fuzzy inference system according to claim 2, wherein in step S7, the method for solving the path plan of the unmanned aerial vehicle based on the depth wavelet neural fuzzy inference system comprises:
(7.1) a Transformer model-based feature extraction section;
firstly, coordinate and data volume information (x) of IoTD i ，y i ，d i ) Putting the encoder module of the Transformer model into the encoder module to obtain the self-attention feature h of each IoTD i Then, the average self-attention feature h of all IoTD is obtained c ；
Defining the input signal of the fuzzy inference system as
Wherein h is c Mean of self-attention features for all IoTDs; h is pre The self-attention feature of the last IoTD in the flight trajectory; e res The current residual energy of the unmanned aerial vehicle; c res The current remaining data space of the unmanned aerial vehicle;
(7.2) a fuzzy inference system part;
an fuzzification module:
wherein, C ki The center of the Gaussian fuzzy membership function input to the k semantic item is used as the ith input; sigma ki 2 The width of a Gaussian fuzzy membership function input to the kth semantic item is set; l is the number of semantic items;
a fuzzy rule module:
reasoning modelBlock (b):
in the formula (19), the compound represented by the formula (I),
is the output of the deep wavelet neural network;
obtaining a defuzzification module:
(7.3) a deep wavelet neural network portion;
defining r hidden layers in the depth wavelet neural network, the output of the theta layer is expressed as:
in the formula (20), psi θ Representing the output of the hidden layer of the theta-th layer, omega θ Is the weight of the theta-th layer wavelet function, a θ ，b θ Respectively representing a scale variable and a displacement variable of the theta-th layer wavelet function;
in order to improve the nonlinear modeling capability of the wavelet neural network, the wavelet functions of different hidden layers can be different wavelet functions;
thus, the output of the deep wavelet neural network is
Wherein phi r A depth wavelet neural network output representing an r-th layer;
an integration module:
o (7) the jth flight path is obtained after the roundingUnmanned aerial vehicle's next flight node position r j [t]Outputting the result;
according to calculated r j [t]Updating
If E res Or C res If not, the current jth unmanned aerial vehicle flies back to the ground control command center and is reset
Wherein h is 0 Controlling the self-attention feature of a command center for the ground; e max The maximum battery capacity of the unmanned aerial vehicle; c max The maximum storage capacity of the unmanned aerial vehicle;
in the deep wavelet neural fuzzy inference system, the fuzzy inference system can model the inference process into a fuzzy plan through the learning of a deep wavelet neural network, and explain a final output result through a fuzzy rule;
and planning the path of the next unmanned aerial vehicle until all the IoTD data are acquired by the unmanned aerial vehicle and the path planning of all the unmanned aerial vehicles is finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210798011.3A CN115129081B (en) | 2022-07-06 | 2022-07-06 | Emergency data collection network and method based on wavelet neural fuzzy inference system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210798011.3A CN115129081B (en) | 2022-07-06 | 2022-07-06 | Emergency data collection network and method based on wavelet neural fuzzy inference system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115129081A true CN115129081A (en) | 2022-09-30 |
| CN115129081B CN115129081B (en) | 2024-06-18 |
Family
ID=83381175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210798011.3A Active CN115129081B (en) | 2022-07-06 | 2022-07-06 | Emergency data collection network and method based on wavelet neural fuzzy inference system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115129081B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180267524A1 (en) * | 2016-05-24 | 2018-09-20 | Wuhan University Of Science And Technology | Air-ground heterogeneous robot system path planning method based on neighborhood constraint |
| CN113031647A (en) * | 2021-02-25 | 2021-06-25 | 浙江工业大学 | Power supply type unmanned aerial vehicle optimal path planning method based on fuzzy comprehensive evaluation |
| US20210255641A1 (en) * | 2019-09-30 | 2021-08-19 | South China University Of Technology | Method for designing three-dimensional trajectory of unmanned aerial vehicle based on wireless power transfer network |
-
2022
- 2022-07-06 CN CN202210798011.3A patent/CN115129081B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180267524A1 (en) * | 2016-05-24 | 2018-09-20 | Wuhan University Of Science And Technology | Air-ground heterogeneous robot system path planning method based on neighborhood constraint |
| US20210255641A1 (en) * | 2019-09-30 | 2021-08-19 | South China University Of Technology | Method for designing three-dimensional trajectory of unmanned aerial vehicle based on wireless power transfer network |
| CN113031647A (en) * | 2021-02-25 | 2021-06-25 | 浙江工业大学 | Power supply type unmanned aerial vehicle optimal path planning method based on fuzzy comprehensive evaluation |
Non-Patent Citations (6)
| Title |
|---|
| 吴法辉: "空地融合携能通信网的传输策略设计与研究", 《博士电子期刊》, no. 01, 15 January 2021 (2021-01-15) * |
| 周灵叶: "基于任务的无人机协同路径规划方法设计与实现", 《硕士电子期刊》, no. 01, 15 January 2022 (2022-01-15) * |
| 李航琪: "具有能量收集的认知中继网络功率分配问题研究", 《博士电子期刊》, no. 08, 15 August 2020 (2020-08-15) * |
| 王春雨;钟嘉奇;王博超;王昱文;: "多旋翼无人机在水利行业中的应用", 黑龙江水利科技, no. 01, 30 January 2020 (2020-01-30) * |
| 谌慧敏: "无人机集群协作支持的物联网数据收集方法研究", 《硕士电子期刊》, no. 01, 15 January 2022 (2022-01-15) * |
| 陈侠;刘子龙;: "基于模糊小波神经网络的空中目标威胁评估", 战术导弹技术, no. 03, 3 May 2018 (2018-05-03) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115129081B (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kurunathan et al. | Machine learning-aided operations and communications of unmanned aerial vehicles: A contemporary survey | |
| US11029168B2 (en) | Method for identifying optimal vehicle paths when energy is a key metric or constraint | |
| US11755882B2 (en) | Method, apparatus and system for recommending location of robot charging station | |
| Li et al. | Multi-robot mission planning with static energy replenishment | |
| CN113433967A (en) | Chargeable unmanned aerial vehicle path planning method and system | |
| CN113552867B (en) | Planning method for motion trail and wheeled mobile device | |
| CN111582740A (en) | Risk assessment system for multi-rotor unmanned aerial vehicle | |
| CN109018424A (en) | A kind of third party's unmanned plane continuation of the journey base station | |
| Sujit et al. | Joint route planning for UAV and sensor network for data retrieval | |
| Khamidehi et al. | Reinforcement-learning-aided safe planning for aerial robots to collect data in dynamic environments | |
| Biswas et al. | A particle swarm optimization based path planning method for autonomous systems in unknown terrain | |
| CN115129081B (en) | Emergency data collection network and method based on wavelet neural fuzzy inference system | |
| rico Petritoli et al. | Takagi-Sugeno Discrete Fuzzy Modeling: An IoT Controlled ABS for UAV | |
| CN113242077B (en) | Method for providing communication service for ground user by using unmanned aerial vehicle cluster as aerial base station | |
| Çaşka et al. | An algorithm for collaborative patrolling systems with unmanned air vehicles and unmanned ground vehicles | |
| Elfatih et al. | Navigation and Trajectory Planning Techniques for Unmanned Aerial Vehicles Swarm | |
| CN116414153B (en) | Unmanned aerial vehicle take-off and landing correction method based on artificial intelligence | |
| Singh et al. | Energy-efficient uav trajectory planning in rechargeable iot networks | |
| Shmelova et al. | Optimization of Flows and Flexible Redistribution of Autonomous UAV Routes in Multilevel Airspace. | |
| CN115016540A (en) | Multi-unmanned aerial vehicle disaster situation detection method and system | |
| KR20200058947A (en) | Method and apparatus of prediction for unmanned aerial vehicle traffic management | |
| Hanna et al. | A uav-based algorithm to assist ground sar teams in finding lost persons living with dementia | |
| CN113110558A (en) | Hybrid propulsion unmanned aerial vehicle demand power prediction method | |
| Krusniak et al. | A multiple UAV path-planning approach to small object counting with aerial images | |
| Wang et al. | Rechargeable UAV Trajectory Optimization for Real-Time Persistent Data Collection of Large-Scale Sensor Networks |
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 |