CN113867391A - Unmanned aerial vehicle low-altitude safety early warning and monitoring method and system based on digital twins - Google Patents
Unmanned aerial vehicle low-altitude safety early warning and monitoring method and system based on digital twins Download PDFInfo
- Publication number
- CN113867391A CN113867391A CN202111181277.5A CN202111181277A CN113867391A CN 113867391 A CN113867391 A CN 113867391A CN 202111181277 A CN202111181277 A CN 202111181277A CN 113867391 A CN113867391 A CN 113867391A
- Authority
- CN
- China
- Prior art keywords
- risk
- unmanned aerial
- aerial vehicle
- data
- early warning
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000003062 neural network model Methods 0.000 claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 15
- 238000012502 risk assessment Methods 0.000 claims description 13
- 241000282414 Homo sapiens Species 0.000 claims description 11
- 238000013507 mapping Methods 0.000 abstract description 2
- 230000002195 synergetic effect Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 11
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000669618 Nothes Species 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013349 risk mitigation 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a digital twin-based unmanned aerial vehicle low-altitude safety early warning and monitoring method and system, and solves the problems of unmanned aerial vehicle low-altitude safety early warning and safety monitoring in the field of unmanned aerial vehicles. Relevant data related to the operation of the unmanned aerial vehicle is acquired and preprocessed, wherein the relevant data comprises basic data of the operation track and the operation performance of the unmanned aerial vehicle, operation geographic environment data of the unmanned aerial vehicle, information data of the actual condition and the spatial position of the operation meteorological environment of the unmanned aerial vehicle, operation limited area data of the unmanned aerial vehicle and the like; the low-altitude safety risk of the unmanned aerial vehicle is evaluated by combining a pre-trained neural network model, so that the integrated monitoring of the operation of the unmanned aerial vehicle is realized, the early warning of the operation risk is completed, and the maneuver evasion measures are taken in time. The invention realizes the low-altitude safety early warning and dynamic monitoring of the unmanned aerial vehicle by mapping the real running state of the unmanned aerial vehicle in real time through the digital twin platform, thereby helping the unmanned aerial vehicle system to run and achieving the synergistic effect of cost reduction and intelligent safe running.
Description
Technical Field
The invention relates to a digital twin-based unmanned aerial vehicle low-altitude safety early warning and monitoring method and system, and belongs to the technical field of unmanned aerial vehicle operation safety.
Background
In recent years, the rapid development and application of unmanned aerial vehicles show the well-jet type growth, and the low-altitude safe operation problem of the unmanned aerial vehicles is urgently needed to be solved because the limit of the operating airspace of the unmanned aerial vehicles and the related system are still in the process of further improvement. The good unmanned aerial vehicle operation risk management technology is one of important guarantees for reducing the unmanned aerial vehicle operation risk and is also the key for guaranteeing healthy, ordered and reasonable airspace resources. The low-altitude safe operation risk relates to the risks in many aspects such as unmanned aerial vehicle and unmanned aerial vehicle, unmanned aerial vehicle and manned machine, unmanned aerial vehicle and ground building, unmanned aerial vehicle and ground personnel and unmanned aerial vehicle and unknown flyers. Once the unsafe event of the unmanned aerial vehicle occurs, the threat of the unmanned aerial vehicle operation cost, life safety and even social stability is brought.
The low-altitude safe operation of the unmanned aerial vehicle system relates to the aspects of the unmanned aerial vehicle system, the operation environment thereof and the like. With the continuous development and fusion of technologies such as a big data technology, an artificial intelligence technology, an IoT technology and a 5G technology, the realization of digital twin low-altitude safety early warning and monitoring of the unmanned aerial vehicle becomes possible. Through real-time supervision unmanned aerial vehicle dynamic data, in time predict and assess the risk that exists in the unmanned aerial vehicle operation process, formulate corresponding measure fast through the assessment result, control the risk to minimum, improve the reliability of unmanned aerial vehicle low latitude operation safety.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method and the system for the low-altitude safety early warning and monitoring of the unmanned aerial vehicle based on the digital twin are provided, the low-altitude running safety state of the unmanned aerial vehicle is monitored and early warned in real time, the low-altitude running risk of the unmanned aerial vehicle is reduced, and the running safety of the unmanned aerial vehicle is improved.
The invention adopts the following technical scheme for solving the technical problems:
an unmanned aerial vehicle low-altitude safety early warning and monitoring method based on digital twins comprises the following steps:
step 1, collecting relevant data of unmanned aerial vehicle operation in real time, wherein the relevant data comprises unmanned aerial vehicle operation track and operation performance data, unmanned aerial vehicle operation geographic environment data, unmanned aerial vehicle operation meteorological environment live and spatial position information data and unmanned aerial vehicle operation restricted area data;
step 2, preprocessing the relevant data of the unmanned aerial vehicle operation collected in real time;
step 3, determining the operation risk type of the unmanned aerial vehicle according to the preprocessed operation related data of the unmanned aerial vehicle;
step 4, selecting a pre-trained neural network model corresponding to the determined unmanned aerial vehicle operation risk type in the step 3, inputting the pre-processed unmanned aerial vehicle operation related data into the neural network model, and predicting risk occurrence probability to obtain a risk prediction result;
step 5, grading the low-altitude safety risk of the unmanned aerial vehicle operation according to the risk prediction result to complete risk grade evaluation;
and 6, carrying out risk early warning according to the risk grade evaluation result.
As a preferred scheme of the method of the present invention, in step 3, the operation risk types of the unmanned aerial vehicle include a risk of collision between the unmanned aerial vehicle and the unmanned aerial vehicle, a risk of collision between the unmanned aerial vehicle and a human, a risk of collision between the unmanned aerial vehicle and a ground building, a risk of collision between the unmanned aerial vehicle and ground personnel, and a risk of collision between the unmanned aerial vehicle and other flying objects.
As a preferred scheme of the method of the present invention, in step 4, the pre-trained neural network model corresponding to the operation risk type of the unmanned aerial vehicle is specifically as follows:
when the unmanned aerial vehicle operation risk type is the collision risk between the unmanned aerial vehicle and the unmanned aerial vehicle, the model is defined as follows:
PU-U′＝{lU,lU′,EU,EU′,dUU′,f}
wherein, PU-U′Represents a model of the risk of collision between the unmanned aerial vehicle and the unmanned aerial vehicle, lURepresents the maximum characteristic length, l, of the drone UU′Represents the maximum characteristic length of the unmanned plane U', EUMaximum kinetic energy for unmanned plane U impact，EU′Represents the maximum kinetic energy of the unmanned plane during U' impact, dUU′Represents the distance between drones U and U', and f represents other possibilities that cause operational risks to the drones;
when the unmanned aerial vehicle operation risk type is the collision risk between the unmanned aerial vehicle and the human machine, the model is defined as follows:
PU-C＝{lU,lC,EU,EC,dUC,f}
wherein, PU-CModel representing risk of collision between unmanned aerial vehicle and humanURepresents the maximum characteristic length, l, of the drone UCDenotes the maximum characteristic length of the manned machine C, EURepresents the maximum kinetic energy of the unmanned plane during U impact, ECRepresents the maximum kinetic energy of the human-machine C at impact, dUCRepresents the distance between drone U and drone C, and f represents other possibilities that cause operational risks to the drone;
when the operation risk type of the unmanned aerial vehicle is the collision risk between the unmanned aerial vehicle and a ground building, the model is defined as follows:
PU-B＝{lU,EU,ρB,dUB,f}
wherein, PU-BModel representing risk of collision between unmanned aerial vehicle and ground structure, lUMaximum characteristic length, E, of unmanned plane UURepresents the maximum kinetic energy, rho, of the unmanned plane during U impactBRepresenting ground building density, dUBRepresents the distance between the drone U and the ground structure, and f represents other possibilities that cause operational risks to the drone;
when the operation risk type of the unmanned aerial vehicle is the collision risk between the unmanned aerial vehicle and ground personnel, the model is defined as follows:
PU-M＝{lU,EU,ρM,dUM,f}
wherein, PU-MModel representing risk of collision between unmanned aerial vehicle and ground personnel, |UMaximum characteristic length, E, of unmanned plane UURepresents the maximum kinetic energy, rho, of the unmanned plane during U impactMRepresenting the ground personnel density, dUMExpress unmanned aerial vehicle U and groundThe distance between the persons, f, represents other possibilities that cause operational risks to the drone;
when the operation risk type of the unmanned aerial vehicle is the collision risk of the unmanned aerial vehicle and other flying objects, the model is defined as follows:
PU-O＝{lU,lO,EU,EO,dUO,f}
wherein, PU-OModel representing risk of collision of unmanned aerial vehicle with other flying objects,/URepresents the maximum characteristic length, l, of the drone UORepresenting the maximum characteristic length of other flying objects, EURepresents the maximum kinetic energy of the unmanned plane during U impact, EORepresenting the maximum kinetic energy of other flying objects upon impact, dUOIndicating the distance between the drone and other flying objects, and f indicating other possibilities that cause operational risks to the drone.
As a preferred scheme of the method of the present invention, in step 5, when the risk prediction result, i.e. the predicted risk occurrence probability, is [0, 0.2], the risk level is level I, and the risk is characterized as low risk; when the risk prediction result, namely the predicted risk occurrence probability is (0.2, 0.4), the risk grade is II grade, the risk is characterized as general risk, when the risk prediction result, namely the predicted risk occurrence probability is (0.4, 0.6), the risk grade is III grade, the risk is characterized as medium risk, when the risk prediction result, namely the predicted risk occurrence probability is (0.6, 0.8), the risk grade is IV grade, the risk is characterized as major risk, and when the risk prediction result, namely the predicted risk occurrence probability is (0.8, 1), the risk grade is V grade, and the risk is characterized as catastrophic risk.
As a preferable scheme of the method of the present invention, in the step 6, when the risk level is level I, no measures need to be taken; when the risk level is II level, the risk can be accepted, and corresponding measures are taken to reduce the risk occurrence possibility or eliminate the risk; when the risk level is level III, the risk can be accepted, and effective emergency measures are taken; when the risk level is IV level, the risk cannot be accepted, and corresponding measures are taken to reduce the potential consequences related to the occurrence of the risk; when the risk level is V, the risk is not acceptable, and all measures with risk levels of II, III and IV are taken.
The unmanned aerial vehicle low-altitude safety early warning and monitoring system based on the digital twin comprises a data acquisition and preprocessing module, a safety risk assessment module and a safety early warning module, wherein the data acquisition and preprocessing module comprises a data acquisition unit and a data preprocessing unit, and the safety risk assessment module comprises a risk type determination unit, a risk prediction unit and a risk assessment unit;
the data acquisition unit is used for acquiring relevant data of the operation of the unmanned aerial vehicle in real time, and the data comprises the operation track and operation performance data of the unmanned aerial vehicle, the operation geographic environment data of the unmanned aerial vehicle, the actual weather environment and spatial position information data of the operation of the unmanned aerial vehicle and the operation limit area data of the unmanned aerial vehicle;
the data preprocessing unit is used for preprocessing the relevant data of the unmanned aerial vehicle operation collected in real time;
the risk type determining unit is used for determining the operation risk type of the unmanned aerial vehicle according to the preprocessed unmanned aerial vehicle operation related data;
the risk prediction unit is used for selecting a pre-trained neural network model corresponding to the determined operation risk type of the unmanned aerial vehicle, inputting the preprocessed unmanned aerial vehicle operation related data into the neural network model, and predicting the risk occurrence probability to obtain a risk prediction result;
the risk evaluation unit is used for grading the low-altitude safety risk of the unmanned aerial vehicle operation according to the risk prediction result to complete risk grade evaluation;
the monitoring unit is used for visually monitoring the operation state of the unmanned aerial vehicle;
and the early warning unit is used for carrying out risk early warning according to the risk grade evaluation result.
Compared with the prior art, the invention adopting the technical scheme has the following technical effects:
according to the invention, the low-altitude operation risk of the unmanned aerial vehicle is predicted and evaluated by performing real-time dynamic visual display on the low-altitude operation of the unmanned aerial vehicle and combining a 5G technology, an artificial intelligence technology and other advanced technologies, and a safety early warning is sent out in time, so that the integration of low-altitude safe operation monitoring is realized; the unmanned aerial vehicle operation risk source can be rapidly locked by visually displaying the operation risk, the probability of the occurrence of the operation risk is calculated, the maneuver evading measures are timely taken through risk grade evaluation, and the cooperation of safe operation and cost reduction of the unmanned aerial vehicle is effectively realized.
Drawings
Fig. 1 is a schematic flow chart of a digital twin-based unmanned aerial vehicle low-altitude safety early warning and monitoring method provided by the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As shown in fig. 1, a schematic flow chart of a digital twin-based unmanned aerial vehicle low-altitude safety early warning and monitoring method provided by the invention is shown. The method works according to the following steps:
s1, collecting and preprocessing unmanned aerial vehicle operation related data from multiple sources, wherein the data include data collected by an unmanned aerial vehicle operation sensor, data collected by an unmanned aerial vehicle camera, data collected by a radar, and data collected by ADS-B, and the data include unmanned aerial vehicle operation track and operation performance basic data, unmanned aerial vehicle operation geographic environment data, unmanned aerial vehicle operation meteorological environment live and spatial position information data, unmanned aerial vehicle operation restricted area data and the like;
s2, evaluating the low-altitude safety risk of the unmanned aerial vehicle by combining intelligent methods such as machine learning and big data technology according to the preprocessed unmanned aerial vehicle operation related data;
step S2 combines intelligent methods such as machine learning, big data technology to evaluate unmanned aerial vehicle low latitude safety risk, and the concrete step includes:
s21, Risk type
Determining the operation risk type of the unmanned aerial vehicle according to the preprocessed operation related data of the unmanned aerial vehicle, wherein the operation risk type comprises collision risk of the unmanned aerial vehicle and the unmanned aerial vehicle, collision risk of the unmanned aerial vehicle and the human-machine, collision risk of the unmanned aerial vehicle and a ground building, collision risk of the unmanned aerial vehicle and ground personnel and collision risk of the unmanned aerial vehicle and other flying objects (such as kites and the like).
S22, risk prediction
After the risk types are determined, the deep learning algorithm is combined, the preprocessed unmanned aerial vehicle operation related data are used as input and input into a pre-trained neural network model corresponding to the determined unmanned aerial vehicle operation risk types, risk occurrence probability is predicted, and a risk prediction result is obtained.
Unmanned aerial vehicle and unmanned aerial vehicle collision risk PU-U′Mainly related to factors such as distance, maximum characteristic length and kinetic energy between two unmanned aerial vehicles, its model definition is as follows:
PU-U′＝{lU,lU′,EU,EU′,dUU′,f}
wherein, PU-U′Represents a model of the risk of collision between the unmanned aerial vehicle and the unmanned aerial vehicle, lURepresents the maximum characteristic length, l, of the drone UU′Represents the maximum characteristic length of the unmanned plane U', EURepresents the maximum kinetic energy of the unmanned plane during U impact, EU′Represents the maximum kinetic energy of the unmanned plane during U' impact, dUU′Indicating the distance between drones U and U', and f indicating other possibilities that cause operational risks to the drones, such as flight hand operational artifacts.
Risk of collision between unmanned aerial vehicle and manned vehicle PU-CMainly with unmanned aerial vehicle and have the distance between the people's machine, unmanned aerial vehicle and the biggest characteristic length of people's machine and unmanned aerial vehicle and have the kinetic energy of people's machine etc. factor relevant, its model definition is as follows:
PU-C＝{lU,lC,EU,EC,dUC,f}
wherein, PU-CModel representing risk of collision between unmanned aerial vehicle and humanURepresents the maximum characteristic length, l, of the drone UCDenotes the maximum characteristic length of the manned machine C, EURepresents the maximum kinetic energy of the unmanned plane during U impact, ECRepresents the maximum kinetic energy of the human-machine C at impact, dUCIndicates that there is noThe distance between the human machine U and the human machine C, and f represents other possibilities that may cause operational risks to the unmanned aerial vehicle, such as the operational human factors of the flyer or the human pilot.
Risk of collision between unmanned aerial vehicle and ground building PU-BMainly with the distance between unmanned aerial vehicle and the ground building, unmanned aerial vehicle maximum characteristic length, unmanned aerial vehicle kinetic energy, ground building density etc. factor relevant, its model definition is as follows:
PU-B＝{lU,EU,ρB,dUB,f}
wherein, PU-BModel representing risk of collision between unmanned aerial vehicle and ground structure, lUMaximum characteristic length, E, of unmanned plane UURepresents the maximum kinetic energy, rho, of the unmanned plane during U impactBRepresenting ground building density, dUBIndicating the distance between the drone U and the ground structure, and f indicating other possibilities that cause operational risks to the drone, such as the flight hand operational human factor.
Risk of collision of unmanned aerial vehicle with ground personnel PU-MMainly relevant with factors such as unmanned aerial vehicle and ground personnel's distance, unmanned aerial vehicle maximum characteristic length, unmanned aerial vehicle kinetic energy, ground population density, its model definition is as follows:
PU-M＝{lU,EU,ρM,dUM,f}
wherein, PU-MModel representing risk of collision between unmanned aerial vehicle and ground personnel, |UMaximum characteristic length, E, of unmanned plane UURepresents the maximum kinetic energy, rho, of the unmanned plane during U impactMRepresenting the ground personnel density, dUMIndicating the distance between the drone U and ground personnel, and f indicating other possibilities that cause operational risks to the drone, such as flight-hand operational artifacts.
Risk of collision between unmanned aerial vehicle and other flying objects (such as kite and the like) PU-OMainly with the distance between unmanned aerial vehicle and other flight thing, unmanned aerial vehicle and the biggest characteristic length of other flight thing and unmanned aerial vehicle and the kinetic energy of other flight thing etc. factor relevant, its model definition is as follows:
PU-O＝{lU,lO,EU,EO,dUO,f}
wherein, PU-OModel representing risk of collision of unmanned aerial vehicle with other flying objects,/URepresents the maximum characteristic length, l, of the drone UORepresenting the maximum characteristic length of other flying objects, EURepresents the maximum kinetic energy of the unmanned plane during U impact, EORepresenting the maximum kinetic energy of other flying objects upon impact, dUOIndicating the distance between the drone and other flying objects, and f indicating other possibilities that may cause operational risks to the drone, such as the operation of the flyer or human pilot human factors.
S23, risk assessment
And grading the low-altitude safety risk of the unmanned aerial vehicle operation according to the risk prediction result, and finishing risk grade evaluation, wherein the risk evaluation grade is mainly graded according to the risk prediction occurrence probability, and the risk grade evaluation matrix in the table 1 can be obtained by assuming that the risk occurrence probability interval is [0,1 ].
TABLE 1
| Risk rating | Predicted probability of occurrence of risk | Risk characterization |
| Class I | [0，0.2] | Low risk |
| Class II | (0.2，0.4] | General risks |
| Class III | (0.4，0.6] | Moderate risk |
| Grade IV | (0.6，0.8] | Major risk |
| Class V | (0.8，1] | Catastrophic risk |
S3, according to the safety risk assessment module result, performing real-time visual dynamic monitoring on low-altitude operation of the unmanned aerial vehicle, performing early warning on the unmanned aerial vehicle according to the risk assessment grade, taking risk mitigation measures in time, and guaranteeing the low-altitude operation safety of the unmanned aerial vehicle.
And in the step S3, performing operation risk early warning on the risk evaluation grade result, interactively feeding back and updating the dynamic data of the unmanned aerial vehicle according to the preprocessed unmanned aerial vehicle operation related data, visualizing the operation state of the unmanned aerial vehicle in the digital twin platform, and realizing interactive mapping between the physical world and the virtual environment.
According to the operation integrated monitoring and operation risk early warning result, the low risk is acceptable, risk relieving measures are taken for the rest four levels of risks, and the risk relieving measures of each level are shown in table 2. The unmanned aerial vehicle management, control, operation and maintenance guarantee are completed, and the low-altitude operation safety of the unmanned aerial vehicle is guaranteed.
TABLE 2
The invention further provides a digital twin-based unmanned aerial vehicle low-altitude safety early warning and monitoring system which comprises a data acquisition and preprocessing module, a safety risk assessment module and a safety early warning module.
The data acquisition and processing module is the basis of the unmanned aerial vehicle risk assessment method based on the digital twin and is used for collecting and processing relevant data of the operation of the unmanned aerial vehicle from multiple parties; comprises a data acquisition unit and a data preprocessing unit.
The safety risk evaluation module is the core of the unmanned aerial vehicle risk evaluation method based on the digital twin, evaluates the low-altitude safety risk of the unmanned aerial vehicle according to the preprocessed data, and comprises a risk type determination unit, a risk prediction unit and a risk evaluation unit.
The safety early warning module is a main body of the unmanned aerial vehicle risk assessment method based on the digital twin, displays on a digital twin platform according to a safety risk assessment result, realizes integrated monitoring and early warning on the safe operation of the unmanned aerial vehicle, and takes evasive measures in time.
The above embodiments are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the protection scope of the present invention.
Claims (6)
1. An unmanned aerial vehicle low-altitude safety early warning and monitoring method based on digital twins is characterized by comprising the following steps:
step 1, collecting relevant data of unmanned aerial vehicle operation in real time, wherein the relevant data comprises unmanned aerial vehicle operation track and operation performance data, unmanned aerial vehicle operation geographic environment data, unmanned aerial vehicle operation meteorological environment live and spatial position information data and unmanned aerial vehicle operation restricted area data;
step 2, preprocessing the relevant data of the unmanned aerial vehicle operation collected in real time;
step 3, determining the operation risk type of the unmanned aerial vehicle according to the preprocessed operation related data of the unmanned aerial vehicle;
step 4, selecting a pre-trained neural network model corresponding to the determined unmanned aerial vehicle operation risk type in the step 3, inputting the pre-processed unmanned aerial vehicle operation related data into the neural network model, and predicting risk occurrence probability to obtain a risk prediction result;
step 5, grading the low-altitude safety risk of the unmanned aerial vehicle operation according to the risk prediction result to complete risk grade evaluation;
and 6, carrying out risk early warning according to the risk grade evaluation result.
2. The method for low-altitude safety early warning and monitoring of unmanned aerial vehicles based on digital twins as claimed in claim 1, wherein in step 3, the operation risk types of unmanned aerial vehicles include the risk of collision between unmanned aerial vehicles and unmanned aerial vehicles, the risk of collision between unmanned aerial vehicles and human beings, the risk of collision between unmanned aerial vehicles and ground buildings, the risk of collision between unmanned aerial vehicles and ground personnel, and the risk of collision between unmanned aerial vehicles and other flying objects.
3. The method for early warning and monitoring the unmanned aerial vehicle low altitude safety based on the digital twin according to claim 2, wherein in the step 4, the pre-trained neural network model corresponding to the unmanned aerial vehicle operation risk type is specifically as follows:
when the unmanned aerial vehicle operation risk type is the collision risk between the unmanned aerial vehicle and the unmanned aerial vehicle, the model is defined as follows:
PU-U′＝{lU,lU′,EU,EU′,dUU′,f}
wherein, PU-U′Represents a model of the risk of collision between the unmanned aerial vehicle and the unmanned aerial vehicle, lURepresents the maximum characteristic length, l, of the drone UU′Represents the maximum characteristic length of the unmanned plane U', EURepresents the maximum kinetic energy of the unmanned plane during U impact, EU′Represents the maximum kinetic energy of the unmanned plane during U' impact, dUU′Represents the distance between drones U and U', and f represents other possibilities that cause operational risks to the drones;
when the unmanned aerial vehicle operation risk type is the collision risk between the unmanned aerial vehicle and the human machine, the model is defined as follows:
PU-C＝{lU,lC,EU,EC,dUC,f}
wherein, PU-CModel representing risk of collision between unmanned aerial vehicle and humanURepresents the maximum characteristic length, l, of the drone UCDenotes the maximum characteristic length of the manned machine C, EURepresents the maximum kinetic energy of the unmanned plane during U impact, ECRepresents the maximum kinetic energy of the human-machine C at impact, dUCRepresents the distance between drone U and drone C, and f represents other possibilities that cause operational risks to the drone;
when the operation risk type of the unmanned aerial vehicle is the collision risk between the unmanned aerial vehicle and a ground building, the model is defined as follows:
PU-B＝{lU,EU,ρB,dUB,f}
wherein, PU-BModel representing risk of collision between unmanned aerial vehicle and ground structure, lUMaximum characteristic length, E, of unmanned plane UURepresents the maximum kinetic energy, rho, of the unmanned plane during U impactBRepresenting ground building density, dUBRepresents the distance between the drone U and the ground structure, and f represents other possibilities that cause operational risks to the drone;
when the operation risk type of the unmanned aerial vehicle is the collision risk between the unmanned aerial vehicle and ground personnel, the model is defined as follows:
PU-M＝{lU,EU,ρM,dUM,f}
wherein, PU-MModel representing risk of collision between unmanned aerial vehicle and ground personnel, |UMaximum characteristic length, E, of unmanned plane UURepresents the maximum kinetic energy, rho, of the unmanned plane during U impactMRepresenting the ground personnel density, dUMRepresents the distance between the unmanned plane U and ground personnel, and f represents other possibilities that cause operational risks to the unmanned plane;
when the operation risk type of the unmanned aerial vehicle is the collision risk of the unmanned aerial vehicle and other flying objects, the model is defined as follows:
PU-O＝{lU,lO,EU,EO,dUO,f}
wherein, PU-OModel representing risk of collision of unmanned aerial vehicle with other flying objects,/URepresents the maximum characteristic length, l, of the drone UORepresenting the maximum characteristic length of other flying objects, EURepresents the maximum kinetic energy of the unmanned plane during U impact, EORepresenting the maximum kinetic energy of other flying objects upon impact, dUOIndicating the distance between the drone and other flying objects, and f indicating other possibilities that cause operational risks to the drone.
4. The method for early warning and monitoring the low altitude safety of the unmanned aerial vehicle based on the digital twin according to claim 1, wherein in the step 5, when the risk prediction result, namely the predicted risk occurrence probability is [0, 0.2], the risk grade is grade I, and the risk is characterized as low risk; when the risk prediction result, namely the predicted risk occurrence probability is (0.2, 0.4), the risk grade is II grade, the risk is characterized as general risk, when the risk prediction result, namely the predicted risk occurrence probability is (0.4, 0.6), the risk grade is III grade, the risk is characterized as medium risk, when the risk prediction result, namely the predicted risk occurrence probability is (0.6, 0.8), the risk grade is IV grade, the risk is characterized as major risk, and when the risk prediction result, namely the predicted risk occurrence probability is (0.8, 1), the risk grade is V grade, and the risk is characterized as catastrophic risk.
5. The method for low-altitude safety early warning and monitoring of the unmanned aerial vehicle based on the digital twin as claimed in claim 1, wherein in the step 6, when the risk level is level I, no measures are taken; when the risk level is II level, the risk can be accepted, and corresponding measures are taken to reduce the risk occurrence possibility or eliminate the risk; when the risk level is level III, the risk can be accepted, and effective emergency measures are taken; when the risk level is IV level, the risk cannot be accepted, and corresponding measures are taken to reduce the potential consequences related to the occurrence of the risk; when the risk level is V, the risk is not acceptable, and all measures with risk levels of II, III and IV are taken.
6. The unmanned aerial vehicle low-altitude safety early warning and monitoring system based on the digital twin is characterized by comprising a data acquisition and preprocessing module, a safety risk assessment module and a safety early warning module, wherein the data acquisition and preprocessing module comprises a data acquisition unit and a data preprocessing unit, the safety risk assessment module comprises a risk type determination unit, a risk prediction unit and a risk assessment unit, and the safety early warning module comprises a monitoring unit and an early warning unit;
the data acquisition unit is used for acquiring relevant data of the operation of the unmanned aerial vehicle in real time, and the data comprises the operation track and operation performance data of the unmanned aerial vehicle, the operation geographic environment data of the unmanned aerial vehicle, the actual weather environment and spatial position information data of the operation of the unmanned aerial vehicle and the operation limit area data of the unmanned aerial vehicle;
the data preprocessing unit is used for preprocessing the relevant data of the unmanned aerial vehicle operation collected in real time;
the risk type determining unit is used for determining the operation risk type of the unmanned aerial vehicle according to the preprocessed unmanned aerial vehicle operation related data;
the risk prediction unit is used for selecting a pre-trained neural network model corresponding to the determined operation risk type of the unmanned aerial vehicle, inputting the preprocessed unmanned aerial vehicle operation related data into the neural network model, and predicting the risk occurrence probability to obtain a risk prediction result;
the risk evaluation unit is used for grading the low-altitude safety risk of the unmanned aerial vehicle operation according to the risk prediction result to complete risk grade evaluation;
the monitoring unit is used for visually monitoring the operation state of the unmanned aerial vehicle;
and the early warning unit is used for carrying out risk early warning according to the risk grade evaluation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111181277.5A CN113867391B (en) | 2021-10-11 | 2021-10-11 | Unmanned aerial vehicle low-altitude safety early warning and monitoring method and system based on digital twinning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111181277.5A CN113867391B (en) | 2021-10-11 | 2021-10-11 | Unmanned aerial vehicle low-altitude safety early warning and monitoring method and system based on digital twinning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113867391A true CN113867391A (en) | 2021-12-31 |
| CN113867391B CN113867391B (en) | 2023-10-31 |
Family
ID=78998851
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111181277.5A Active CN113867391B (en) | 2021-10-11 | 2021-10-11 | Unmanned aerial vehicle low-altitude safety early warning and monitoring method and system based on digital twinning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113867391B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115167530A (en) * | 2022-09-08 | 2022-10-11 | 国网浙江省电力有限公司金华供电公司 | Live working investigation data processing method and system based on multi-dimensional sensing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150105659A (en) * | 2014-03-07 | 2015-09-18 | 순천대학교 산학협력단 | Unmanned aerial vehicle based structure safety inspection system using multi-sensor |
| CN204926552U (en) * | 2015-08-14 | 2015-12-30 | 成都翼比特科技有限责任公司 | Unmanned aerial vehicle low latitude early warning management system |
| CN110223539A (en) * | 2019-07-09 | 2019-09-10 | 飞牛智能科技（南京）有限公司 | Early warning range real time acquiring method suitable for low latitude unmanned plane |
| CN111882202A (en) * | 2020-07-24 | 2020-11-03 | 武汉建工集团股份有限公司 | Group building synchronous construction risk management system based on BP neural network |
| CN212723339U (en) * | 2020-07-20 | 2021-03-16 | 国蓉科技有限公司 | Low-altitude microminiature unmanned aerial vehicle monitoring system for complex urban environment |
-
2021
- 2021-10-11 CN CN202111181277.5A patent/CN113867391B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150105659A (en) * | 2014-03-07 | 2015-09-18 | 순천대학교 산학협력단 | Unmanned aerial vehicle based structure safety inspection system using multi-sensor |
| CN204926552U (en) * | 2015-08-14 | 2015-12-30 | 成都翼比特科技有限责任公司 | Unmanned aerial vehicle low latitude early warning management system |
| CN110223539A (en) * | 2019-07-09 | 2019-09-10 | 飞牛智能科技（南京）有限公司 | Early warning range real time acquiring method suitable for low latitude unmanned plane |
| CN212723339U (en) * | 2020-07-20 | 2021-03-16 | 国蓉科技有限公司 | Low-altitude microminiature unmanned aerial vehicle monitoring system for complex urban environment |
| CN111882202A (en) * | 2020-07-24 | 2020-11-03 | 武汉建工集团股份有限公司 | Group building synchronous construction risk management system based on BP neural network |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115167530A (en) * | 2022-09-08 | 2022-10-11 | 国网浙江省电力有限公司金华供电公司 | Live working investigation data processing method and system based on multi-dimensional sensing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113867391B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111177851B (en) | Assessment method for ground risk in unmanned aerial vehicle operation safety risk assessment | |
| CN115063020B (en) | Multi-dimensional safety scheduling device and method for cascade hydropower station based on risk monitoring fusion | |
| CN109979037A (en) | QAR parametric synthesis visual analysis method and system | |
| CN107292517A (en) | The civil aviaton's security information service system analyzed based on big data | |
| CN108256447A (en) | A kind of unmanned plane video analysis method based on deep neural network | |
| CN109118039B (en) | Inland water area oriented ship self-sinking important risk identification, prevention and control device and method | |
| CN112085869A (en) | Civil aircraft flight safety analysis method based on flight parameter data | |
| CN114117322A (en) | Method for evaluating network capacity of urban low-altitude unmanned logistics transportation airway | |
| CN111506974B (en) | Unmanned aerial vehicle ultra-low altitude flight area classification planning method | |
| CN113867391A (en) | Unmanned aerial vehicle low-altitude safety early warning and monitoring method and system based on digital twins | |
| CN110097223B (en) | Early warning method for damage of power transmission line under typhoon disaster | |
| CN112488584A (en) | Safety early warning method for electric power emergency disposal of hazardous chemical substance accident | |
| CN114584597A (en) | Intelligent monitoring fire-fighting system based on cloud system | |
| CN114237110A (en) | Multi-mode data driving-based general aviation fleet reliability monitoring and early warning system | |
| CN111146866A (en) | Power transmission channel control method | |
| CN116128197A (en) | Intelligent airport management system and method | |
| CN105096661A (en) | Air traffic flow management system based on vertical profile view and method | |
| Penkova et al. | On-line control of the state of technosphere and environment objects in Krasnoyarsk region based on monitoring data | |
| CN113487914A (en) | Low landing operation standard identification and alarm method based on airport meteorological messages | |
| Rentian et al. | Cause Analysis of Consumer‑Grade UAV Accidents Based on Grounded Theory‑Bayesian Network. | |
| Sheng et al. | A lightning disaster risk assessment model based on SVM | |
| Rentian et al. | Aviation Accident Causation Analysis Based on Complex Network Theory. | |
| Dong et al. | Australian bushfires in the background-UAV optimization allocation model | |
| Wang | High risk section identification of transmission lines based on historical warning data | |
| Xing et al. | Discovering Latent Themes in Aviation Safety Reports Using Text Mining and Network Analytics |
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 |