CN113657665A - Unmanned aerial vehicle system state monitoring and early warning system based on artificial intelligence - Google Patents
Unmanned aerial vehicle system state monitoring and early warning system based on artificial intelligence Download PDFInfo
- Publication number
- CN113657665A CN113657665A CN202110936856.XA CN202110936856A CN113657665A CN 113657665 A CN113657665 A CN 113657665A CN 202110936856 A CN202110936856 A CN 202110936856A CN 113657665 A CN113657665 A CN 113657665A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- data
- neural network
- 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.)
- Withdrawn
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 36
- 238000012544 monitoring process Methods 0.000 title claims abstract description 17
- 238000013528 artificial neural network Methods 0.000 claims abstract description 60
- 230000004044 response Effects 0.000 claims abstract description 28
- 238000001514 detection method Methods 0.000 claims description 35
- 238000012549 training Methods 0.000 claims description 20
- 238000013480 data collection Methods 0.000 claims description 18
- 238000004140 cleaning Methods 0.000 claims description 15
- 238000007405 data analysis Methods 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 10
- 238000012502 risk assessment Methods 0.000 claims description 9
- 230000003068 static effect Effects 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 2
- 238000002474 experimental method Methods 0.000 claims description 2
- 210000005036 nerve Anatomy 0.000 claims description 2
- 210000002569 neuron Anatomy 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 238000004880 explosion Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241001155433 Centrarchus macropterus Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000025518 detection of mechanical stimulus involved in sensory perception of wind Effects 0.000 description 1
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D47/00—Equipment not otherwise provided for
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computer Security & Cryptography (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an unmanned aerial vehicle system state monitoring and early warning system based on artificial intelligence, which comprises a data real-time collecting module, a data real-time analyzing module, a system database, an early warning response module and an artificial intelligence neural network, wherein the data real-time collecting module is used for collecting data; the real-time monitoring is carried out on each hardware module and the surrounding environment of the unmanned aerial vehicle system, then the risk identification is carried out on the real-time data by utilizing the artificial intelligence neural network through the deep neural network constructed by the artificial intelligence on the historical big data of which the real-time data enters the database, the state of the unmanned aerial vehicle which is working at high altitude is monitored in real time, and the early warning and the intervention are extracted from the risk which possibly occurs to the unmanned aerial vehicle, so that the safe operation of the unmanned aerial vehicle is ensured, and the risks such as the explosion of the unmanned aerial vehicle are reduced.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle system state monitoring and early warning system based on artificial intelligence.
Background
Since the new century, with the continuous development and progress of society, science and technology has obtained huge development, multiple novel products have come to the end, unmanned aerial vehicle also is known to masses in recent years as the representative of novel science and technology, unmanned aerial vehicle, as the name suggests, does not need manned flying aircraft, utilizes radio remote control equipment and self-contained program control device to carry out the aircraft of controlling, does not have the cockpit on the aircraft, but installs equipment such as autopilot, program control device. Personnel on the ground, a naval vessel or a mother aircraft remote control station can track, position, remotely control, remotely measure and digitally transmit the personnel through equipment such as a radar and the like, can automatically land in the same way as a common aircraft landing process when recovering, can also recover through a parachute or a barrier for remote control, and can be repeatedly used for multiple times.
Unmanned aerial vehicle develops from the beginning, develops for the general public basically as military use, and with the technology more mature in recent years, more civilian unmanned aerial vehicle products are gradually popularized to the general public, are applied to a plurality of trades, for example: the system comprises a plurality of civil industries such as building undertaking, express delivery industry, clothing retail, vacation travel, sports media, security enforcement and the like.
Along with the continuous popularization of unmanned aerial vehicles, the requirement for the unmanned aerial vehicles is higher and higher in civil use, the unmanned aerial vehicles often operate in the field, the environment in the field is complex, particularly, the unmanned aerial vehicles are used in vacation and tourism, the operation environment comprises various environments of mountainous areas, gobi and grasslands, the unmanned aerial vehicles are variable and easy to influence the operation of the unmanned aerial vehicles, operation faults and even crash of the unmanned aerial vehicles are caused, the major faults are not only loss on property to people, for people in the surrounding environment, the risk of being hit by the falling unmanned aerial vehicles is easy to occur, and the personal health is threatened, so that the early warning system of the civil unmanned aerial vehicles is rapidly developed in recent years, the surrounding environment and the operation state of the civil unmanned aerial vehicles are detected and early warned, and major accidents are avoided.
In the prior art, because the unmanned aerial vehicle runs into the influence of various uncertain environmental factors, high-risk accidents such as a fryer often occur, and after the accidents occur, the accident positioning and the improvement are very long works, sometimes the accident positioning is difficult, and the overall improvement of the unmanned aerial vehicle system is not provided.
However, the existing unmanned aerial vehicle early warning system is simple, and early warning is performed by adopting a basic data comparison mode, so that different operation requirements caused by environment diversity cannot be met, and misjudgment possibly occurs, and therefore, how to intelligentize the early warning process and meet different early warning requirements under various environments becomes the problem to be solved by the unmanned aerial vehicle early warning system.
Disclosure of Invention
In order to solve the technical problems, the invention provides a real-time analysis early warning system which can extract and predict risks and prevent the risks, can quickly locate the problems after the risks caused by the situations never occur, realizes the continuous evolution of the unmanned aerial vehicle, and can early warn the situations in advance after artificial intelligence learns new risk factors.
In view of the problems in the prior art, the invention discloses an unmanned aerial vehicle system state monitoring and early warning system based on artificial intelligence, which adopts the technical scheme that the system comprises a data collection module, a data analysis and cleaning module, a system database, an artificial intelligence neural network and an early warning response module, wherein the data collection module collects and unifies the self running state of an unmanned aerial vehicle in operation and the running environment data of the unmanned aerial vehicle, the data analysis and cleaning module analyzes and processes the real-time data collected by the data collection module and turns to the system database for storage, the large data is formed by continuously expanding and updating the database, the intelligent updating of the data is realized, the data collection amount is increased, when the system database stores the real-time flight data, the data is input into a deep neural network constructed manually for deep learning, the training of the deep neural network is completed, the deep neural network is constructed to be used for intelligently and quickly identifying new input data, the neural network compares and analyzes the data received in real time with the deep neural network which is completed with learning in the network and big data in the deep neural network, whether the state of the deep neural network is in a safe working state range is judged, and whether early warning response is started or not and which mode of response is selected according to different analysis results by utilizing an early warning response module according to different judgment results.
As a preferred technical scheme of the invention, the artificial neural network consists of neurons and nerves, the artificial neural network can form a deep neural network by multiple layers, the neural network is more complex as the number of layers is larger, flight data of the unmanned aerial vehicle is constructed by adopting a unique neural network algorithm when the artificial neural network is constructed, the data is constructed into a neural network system, then the data of the unmanned aerial vehicle flying online is cleaned and then continuously provided for the neural network to carry out deep learning, the deep neural network is trained to identify the flight safety probability and risk early warning of the unmanned aerial vehicle, the artificial neural network carries out the deep learning of the neural network by using a mode of combining static training and dynamic training, the static training is used at the initial stage of the production of the unmanned aerial vehicle, the dynamic training is used at the later stage to continuously promote the neural network, so that the data content of the artificial neural network is continuously updated, the artificial neural network is trained using labeled samples.
As a preferred technical scheme of the invention, the data collection module comprises an unmanned aerial vehicle body detection module, an unmanned aerial vehicle flight state detection module, an unmanned aerial vehicle accessory detection module, an environment detection module and an operation information detection module, wherein the unmanned aerial vehicle body detection module realizes the detection of the voltage, flight power and self-operation temperature of the unmanned aerial vehicle so as to avoid accidents caused by overload of the unmanned aerial vehicle body in the operation process, the unmanned aerial vehicle flight state detection module realizes the detection of the rising state, the falling state, the level flight state and the hovering state of the unmanned aerial vehicle and detects whether the flight process is normal or not, the unmanned aerial vehicle accessory detection module realizes the detection of three axes of a propeller accelerometer, a gyroscope and a magnetometer, the real-time monitoring of accessories of the unmanned aerial vehicle is realized, the accidents with different degrees can be caused by the fault of a single accessory, the environment detection module comprises the detection of wind speed and external temperature and humidity, data combination is carried out to the running state data that matches in the different environment, improves the capacity and the diversification of sample, and operation information detection module monitors its position and operation information including the detection to GPS, big dipper and remote control information.
As a preferred technical scheme of the invention, the data analysis and cleaning module counts and analyzes the real-time data obtained by the data collection module, classifies, screens and cleans all information according to the analysis result, and then enters the unmanned aerial vehicle system database, wherein the unmanned aerial vehicle system database is divided into a basic database and a real-time expansion database, the basic database is initial experimental data and sample data, and preliminarily trains the initial neural network, the real-time expansion database comprises general real-time data and characteristic real-time data, wherein the general real-time data is used for storing the self operation data and the surrounding environment data of the unmanned aerial vehicle in the operation state by the cooperation of the data collection module and the data analysis and cleaning module and inputting the self operation data and the surrounding environment data into the neural network for learning, and simultaneously forms the real-time expansion database, and the characteristic data is the self operation state data of the unmanned aerial vehicle before emergency and even crash, the data are stored and input into a neural network for learning, a real-time expansion database is formed, the real-time expansion database is continuously updated, expanded and filled after data are cleaned according to real-time operation data of the unmanned aerial vehicle, the data volume in the database is enriched, meanwhile, the neural network is continuously and deeply learned, and the data are constructed into big data of the operation state of the unmanned aerial vehicle.
As a preferred technical scheme of the invention, the early warning response module analyzes and identifies the risk rating obtained by analyzing and identifying the real-time running state data according to the artificial intelligent neural network trained by big data, and selects whether to start the early warning response module and the response type of the response module.
As a preferred technical scheme of the invention, the risk rating is divided into a high probability major risk, a medium probability risk and a low probability major risk, the high probability major risk assessment mode shows that the operation state data is judged to be the high probability major risk after being detected by artificial intelligence, the medium probability major risk assessment mode shows that the operation state data is judged to be the medium probability major risk or the high probability middle or low risk after being detected by artificial intelligence, the low probability major risk assessment mode shows that the operation state data is judged to be the medium probability major risk or the low probability middle or low risk after being detected by artificial intelligence, the risks with different ratings correspond to different response modes, wherein the high probability major risk adopts an automatic emergency approach response mode to avoid the continuous occurrence of major accidents without reaching the operation to cause the serious damage, the medium probability major risk and the low probability major risk adopt a system feedback to the flier, reminding the user of paying attention to the risk and adjusting the response mode of the current operation, automatically selecting the operation mode according to the use condition, and properly adjusting to avoid accidents.
The invention has the beneficial effects that: the deep learning of the neural network is carried out through a static training mode at the initial stage of production and a dynamic training mode for continuously collecting, processing and storing the real-time running state and environmental data of the unmanned aerial vehicle at the later stage, so as to construct a deep artificial neural network, each hardware module and the surrounding environment of the unmanned aerial vehicle system are monitored in real time, the artificial intelligence trained by the continuously updated big data in the artificial neural network and a database is used for identifying the data risk, the state of the unmanned aerial vehicle working at high altitude is monitored in real time, the early warning and intervention are carried out on the possible risk of the unmanned aerial vehicle, so as to ensure the safe operation of the unmanned aerial vehicle, reduce the risk of the unmanned aerial vehicle such as explosion and the like, the database and the neural network are continuously increased along with the increase of the running time, the obtained data are continuously increased, the deep training of the neural network is more perfect, and the big data in the database are also more abundant, and the use early warning requirements under various environments are met.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention,
FIG. 2 is a schematic diagram of the data collection module of the present invention,
FIG. 3 is a schematic diagram of the database structure of the present invention,
FIG. 4 is a diagram of the artificial neural network of the present invention.
Detailed Description
As shown in figures 1 to 4, the invention discloses an artificial intelligence-based unmanned aerial vehicle system state monitoring and early warning system, which adopts the technical scheme that the system comprises a data collection module, a data analysis and cleaning module, a system database, an artificial intelligence neural network and an early warning response module, wherein the data collection module consisting of an unmanned body detection module, an unmanned aerial vehicle flight state detection module, an unmanned aerial vehicle accessory detection module, an environment detection module and an operation information detection module is used for collecting real-time data of the operation state of an unmanned aerial vehicle and environmental data of the operation state of the unmanned aerial vehicle, and the specific data comprise unmanned aerial vehicle voltage, unmanned aerial vehicle flight power, self-operation temperature, unmanned aerial vehicle ascending state, unmanned aerial vehicle descending state, unmanned aerial vehicle level flight state and magnetometer state, unmanned aerial vehicle propeller accelerometer, unmanned aerial vehicle gyroscope, unmanned aerial vehicle triaxial, and early warning response module, The wind speed, the external temperature and humidity of the working environment, and the GPS, the Beidou and the remote control information in the operation information.
The data analysis and cleaning module is used for analyzing and processing the unmanned aerial vehicle data information acquired by the unmanned aerial vehicle data collection module, screening and classifying and cleaning useless information, inputting the processed real-time data into a neural network constructed by artificial intelligence for deep learning, and inputting the processed real-time data into a system database to form big data.
As a preferred technical scheme of the invention, the training mode of the artificial intelligence constructed neural network comprises static training and dynamic training, wherein the static training is used for training the unmanned aerial vehicle by using a sample label at the initial production stage of the unmanned aerial vehicle, the dynamic training is carried out, the unmanned aerial vehicle data flying on line is continuously provided for the neural network for deep learning after being subjected to data cleaning, the dynamic training can carry out self-learning by continuously expanding the data at the later stage, the number of deep learning layers is large, the neural network is more complex, and after the construction of the neural network is finished, the real-time data can be rapidly and intelligently compared with the large data of the database after the data is input.
As a preferred technical scheme of the invention, the system database is divided into a basic database and a real-time expansion database, the basic database obtains the safe flight state data information of the unmanned aerial vehicle through experiments, the unmanned aerial vehicle real-time operation data is continuously updated, expanded and full after data cleaning according to the unmanned aerial vehicle real-time operation data, the data volume in the database is enriched, and large data of the unmanned aerial vehicle operation state are constructed.
As a preferred technical scheme of the invention, real-time data of unmanned aerial vehicle operation during high-altitude operation are identified by using a trained neural network, namely artificial intelligence trained by big data, risks are identified and given out, different early warning response modes are adopted according to different risk grades after the risk grades are obtained, the risk grades are divided into high-probability major risks, the high-probability major risk assessment mode shows that the running state data is judged to be about to have high-probability major risk after being subjected to artificial intelligence detection, the medium-probability major risk assessment mode shows that the running state data is judged to be about to have medium-probability major risk or have high-probability medium-low risk after being subjected to artificial intelligence detection, and the low-probability major risk assessment mode shows that the running state data is judged to have the medium-probability major risk or have high-probability medium-low risk after being subjected to artificial intelligence detection.
As a preferred technical scheme of the invention, different risk grades correspond to different early warning response modes, wherein the high-probability major risk adopts an automatic emergency forced landing response mode, the medium-probability major risk and the low-probability major risk adopt system feedback to the flyer to remind the flyer of paying attention to the risks and adjust the response mode of the current operation
Components not described in detail herein are prior art.
Although the present invention has been described in detail with reference to the specific embodiments, the present invention is not limited to the above embodiments, and various changes and modifications without inventive changes may be made within the knowledge of those skilled in the art without departing from the spirit of the present invention.
Claims (9)
1. The utility model provides an unmanned aerial vehicle system state monitoring and early warning system based on artificial intelligence which characterized in that: the system comprises a data collection module, a data analysis and cleaning module, a system database, an artificial intelligent neural network and an early warning response module; the data collection module is used for collecting the state of the unmanned aerial vehicle and the surrounding environment data; the data analysis and cleaning module analyzes and processes the real-time data collected by the data collection module and turns to a system database for storage, and the database is continuously expanded and updated to form big data, so that the intelligent updating of the data is realized, and the data collection amount is increased; when the system database stores real-time flight data, the data are input into a deep neural network constructed manually for deep learning, and the training of the deep neural network is completed; and the early warning response module selects whether to start to perform early warning response according to an analysis result obtained by comparison in the artificial intelligent neural network.
2. The unmanned aerial vehicle system condition monitoring and early warning system based on artificial intelligence of claim 1, characterized in that: the artificial neural network consists of neurons and nerves; the artificial neural network can form a deep neural network by multiple layers, and the neural network is more complex when the number of layers is more; the artificial neural network constructs an unmanned aerial vehicle flight data neural network system through a unique neural network algorithm, then data of the online flying unmanned aerial vehicle is cleaned and continuously provided for the neural network for deep learning, and the deep neural network is trained to recognize the flight safety probability and risk early warning of the unmanned aerial vehicle; the artificial neural network carries out deep learning of the neural network in a mode of combining static training and dynamic training, the static training is used in the initial stage of production of the unmanned aerial vehicle, and the neural network is continuously improved through the dynamic training in the later stage; the artificial neural network is trained using labeled samples.
3. The unmanned aerial vehicle system condition monitoring and early warning system based on artificial intelligence of claim 1, characterized in that: the data collection module comprises an unmanned aerial vehicle body detection module, an unmanned aerial vehicle flight state detection module, an unmanned aerial vehicle accessory detection module, an environment detection module and an operation information detection module.
4. The artificial intelligence based unmanned aerial vehicle system state monitoring and early warning system of claim 3, wherein: the unmanned aerial vehicle body detection module is used for detecting the voltage of the unmanned aerial vehicle, the flight power of the unmanned aerial vehicle and the self operating temperature; the unmanned aerial vehicle flight state detection module detects an ascending state, a descending state, a level flight state and a hovering state; the unmanned aerial vehicle accessory detection module is used for detecting a propeller accelerometer, a gyroscope and a three-axis magnetometer; the environment detection module detects wind speed and external temperature and humidity; the operation information detection module comprises detection of a GPS, a Beidou and remote control information.
5. The unmanned aerial vehicle system condition monitoring and early warning system based on artificial intelligence of claim 1, characterized in that: the data analysis and cleaning module is used for counting and analyzing the real-time data obtained by the data collection module, classifying, screening and cleaning all information according to the analysis result, and then entering an unmanned aerial vehicle system database.
6. The unmanned aerial vehicle system condition monitoring and early warning system based on artificial intelligence of claim 1, characterized in that: the system database comprises a basic database and a real-time expansion database; the basic database acquires the safe flight state data information of the unmanned aerial vehicle through experiments, and manually inputs the safe flight state data information into the database to form the basic database; the real-time expansion database comprises general real-time data and characteristic real-time data; the general real-time data is matched by the data collection module and the data analysis and cleaning module to store the self operation data and the ambient environment data of the unmanned aerial vehicle in an operation state, so as to form a real-time expanded database; the characteristic data is the running state data of the unmanned aerial vehicle before the unmanned aerial vehicle breaks down in an emergency; the real-time expansion database is continuously updated, expanded and full after data cleaning according to real-time operation data of the unmanned aerial vehicle, the data volume in the database is enriched, and big data of the operation state of the unmanned aerial vehicle are constructed.
7. The unmanned aerial vehicle system condition monitoring and early warning system based on artificial intelligence of claim 1, characterized in that: the artificial intelligence trained by the big data identifies the data, identifies risks and obtains risk ratings), and the early warning response module selects whether to start the early warning response module and the response type of the response module according to the risk ratings obtained by the artificial intelligence.
8. The artificial intelligence based unmanned aerial vehicle system state monitoring and early warning system of claim 7, wherein: the risk rating is divided into a high probability major risk, a medium probability risk, and a low probability major risk; the high-probability major risk assessment mode is characterized in that the running state data is judged to be about to have a high-probability major risk after being detected by artificial intelligence; the medium probability major risk assessment mode is characterized in that the running state data is judged to be the major risk of the medium probability or the medium or low risk of the medium or low probability after artificial intelligence detection; the low-probability major risk assessment mode is characterized in that the occurrence probability of major risks or low-and-medium risks is judged after artificial intelligence detection.
9. The artificial intelligence based unmanned aerial vehicle system state monitoring and early warning system of claim 8, wherein: the high-probability major risk, the medium-probability major risk and the low-probability major risk respectively adopt different response types; the high-probability major risk adopts a response mode of automatic emergency forced landing; and the medium-probability major risk and the low-probability major risk are fed back to the flyer by adopting a system, so that the flyer is reminded of paying attention to the risks and the response mode of the current operation is adjusted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110936856.XA CN113657665A (en) | 2021-08-16 | 2021-08-16 | Unmanned aerial vehicle system state monitoring and early warning system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110936856.XA CN113657665A (en) | 2021-08-16 | 2021-08-16 | Unmanned aerial vehicle system state monitoring and early warning system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113657665A true CN113657665A (en) | 2021-11-16 |
Family
ID=78479225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110936856.XA Withdrawn CN113657665A (en) | 2021-08-16 | 2021-08-16 | Unmanned aerial vehicle system state monitoring and early warning system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657665A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114545954A (en) * | 2022-03-01 | 2022-05-27 | 哈尔滨工业大学 | Unmanned aerial vehicle safe landing window prediction system and method for small ships |
| CN114584358A (en) * | 2022-02-25 | 2022-06-03 | 安捷光通科技成都有限公司 | Intelligent network security system, device and storage medium based on Bayesian regularization |
-
2021
- 2021-08-16 CN CN202110936856.XA patent/CN113657665A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114584358A (en) * | 2022-02-25 | 2022-06-03 | 安捷光通科技成都有限公司 | Intelligent network security system, device and storage medium based on Bayesian regularization |
| CN114584358B (en) * | 2022-02-25 | 2023-10-13 | 安捷光通科技成都有限公司 | Intelligent network security system, device and storage medium based on Bayesian regularization |
| CN114545954A (en) * | 2022-03-01 | 2022-05-27 | 哈尔滨工业大学 | Unmanned aerial vehicle safe landing window prediction system and method for small ships |
| CN114545954B (en) * | 2022-03-01 | 2022-07-26 | 哈尔滨工业大学 | Unmanned aerial vehicle safe landing window prediction system and method for small ships |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113657665A (en) | Unmanned aerial vehicle system state monitoring and early warning system based on artificial intelligence | |
| CN110059631B (en) | Contact net non-contact type monitoring defect identification method | |
| US11087632B1 (en) | Autonomous UAV obstacle avoidance using machine learning from piloted UAV flights | |
| CN106846729A (en) | A kind of fall detection method and system based on convolutional neural networks | |
| CN105956790B (en) | Low-altitude flight situation safety evaluation index and evaluation method thereof | |
| CN109979037A (en) | QAR parametric synthesis visual analysis method and system | |
| WO2018191730A1 (en) | System and method for automated prediction and detection of component and system failures | |
| CN106444800A (en) | External safety control apparatus, method and system for flight of multi-rotor unmanned plane | |
| CN113486938A (en) | Multi-branch time convolution network-based re-landing analysis method and device | |
| CN112379694A (en) | Emergency processing method and system for flight fault | |
| CN111464793B (en) | Method and system for monitoring and early warning experimental device based on artificial intelligence | |
| CN106548294A (en) | A kind of landing maneuver Performance Evaluation Methods and device based on flying quality | |
| CN106114880A (en) | The system for prompting of a kind of unmanned vehicle air crash and method thereof | |
| CN110737976A (en) | mechanical equipment health assessment method based on multi-dimensional information fusion | |
| CN109977546A (en) | A kind of online method for detecting abnormality of four-dimensional track based on unsupervised learning | |
| CN115064009A (en) | Method for grading risk of unmanned aerial vehicle and manned conflict in terminal area | |
| CN114118847A (en) | Chemical industry park danger source on-line monitoring platform | |
| CN106774411B (en) | Unmanned aerial vehicle middleware system based on PHM | |
| CN106127407B (en) | Airplane travel scoring method and system based on multi-sensor information fusion | |
| Lim et al. | A novel simulation environment for cognitive human factors engineering research | |
| Andrade et al. | What went wrong: A survey of wildfire uas mishaps through named entity recognition | |
| Kim et al. | Terminal airspace anomaly detection using temporal logic learning | |
| Mitkas et al. | Activity Identification using ADS-B data at General Aviation Airports | |
| CN115545398A (en) | Risk assessment method based on human, machine and environment data quantification | |
| CN115293225A (en) | Pilot flat drift ejector rod cause analysis method and device |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211116 |