Integrated multifunctional unmanned aerial vehicle safety monitoring system and application thereof
By designing an integrated multi-functional drone safety monitoring system and using drones for real-time patrol and monitoring, the existing wildfire monitoring methods are solved, and efficient fire detection and prevention effects are achieved.
Patent Information
- Application Number
- CN202510296701.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-13
- Publication Date
- 2025-06-10
AI Technical Summary
The existing wildfire monitoring methods are inefficient, have poor prevention effects, and have poor emergency response capabilities, and need to be improved.
Design an integrated multi-functional UAV safety monitoring system, including a main control center and a UAV. The main control center has a control module, communication module, storage module, data processing module and route planning module. The UAV is equipped with a communication module, a flight control module, a monitoring module and an anti-interference module.
Through real-time patrol and monitoring of drones, fire conditions can be discovered in a timely manner, the prevention effect of wildfire prevention and control can be improved, and monitoring efficiency and emergency response capabilities can be improved.
Smart Images
Figure CN120126274A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to an integrated multifunctional unmanned aerial vehicle safety monitoring system and application thereof. Background Art
[0002] The occurrence of wildfire disasters not only endangers the property safety of the people, but also endangers the personal safety of the people. The probability of causing wildfires is also closely related to the surrounding environmental factors. Specific wind force and wind direction may cause power system failure, causing aluminum metal in the wire to melt and insulating materials to catch fire. During the scattering process, weeds and shrubs on the surrounding ground will be ignited, and the fire will spread under the influence of wind. Therefore, monitoring of wildfire disasters is very necessary. At present, wildfire monitoring in mountainous areas is mostly done by manual inspection or installing surveillance cameras at fixed locations for monitoring. This is inefficient, has poor prevention effects, and poor emergency response capabilities, and needs to be improved. Summary of the invention
[0003] The purpose of the present invention is to provide an integrated multifunctional unmanned aerial vehicle safety monitoring system and its application to solve the problems raised in the above-mentioned background technology.
[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an integrated multifunctional UAV safety monitoring system and its application, including a main control center and a UAV, wherein the main control center includes: A control module, wherein the control module is connected to a control panel, and the control panel provides an operation interface for an operator to control the entire system; A first communication module, which is used to connect to the drone, send command signals to the drone and receive information data sent back by the drone; A storage module, wherein the storage module is used to store data information required by the system; A data processing module, which is used to process and analyze the information data sent back by the drone; A route planning module, which is used to calculate and plan the patrol flight route of the UAV; The drone includes: A second communication module, the second communication module is connected to the first communication module and is used to receive a command signal sent by the main control center and send the captured information data; A flight control module, the flight control module is used to control the flight of the UAV device according to the patrol flight route designed by the route planning module in the received command signal; A monitoring module, which includes a camera and multiple sensors for environmental monitoring of the patrol flight route; An anti-interference module, wherein the anti-interference module is used to shield interference signals.
[0005] Preferably, the connection methods of the first communication module and the second communication module include radio frequency communication, cellular network, satellite communication, and data transmission radio station.
[0006] Preferably, the data processing module includes: A preprocessing unit, which is used to preprocess the data sent back by the drone. The preprocessing methods include data cleaning, data fusion, and data standardization. Among them, data cleaning is applicable to removing invalid and incorrect data, data fusion is used to combine data from different sources and types to improve the availability of data, and data standardization is to ensure the consistency of data formats; A detection and positioning unit, which conducts hotspot detection, identifies heat anomaly points, and determines possible fire source locations; A fire spread prediction unit, which predicts the future development of the fire according to the current conditions and the fire spread model; A risk assessment unit, which contains a fire prediction model for predicting the likelihood of a fire; A decision support unit, which is used to provide suggestions for fire extinguishing and rescue operations, optimize the allocation of rescue resources and personnel, and send fire alarms and update information to relevant personnel.
[0007] Preferably, the fire spread model is stored in the model library of the storage module and includes multiple fire spread models.
[0008] Preferably, the steps for the fire spread prediction unit to predict the fire spread are as follows: S1: Feature extraction, extracting key features affecting the fire spread from the preprocessed data; S2: Model training, using historical fire data and current fire scene data to train the prediction model; S3: Fire spread prediction, using the trained model to predict the fire spread situation according to the current conditions; S4: Result output, outputting a prediction map or prediction report of the fire spread for decision-makers to refer to.
[0009] Preferably, the fire prediction module is usually constructed based on statistical or machine learning algorithms. The specific calculation formula depends on the type of model used. The following is a calculation formula for a simplified fire prediction model based on logistic regression: Where: is the probability of the event when the given feature vector occurs, e is the base of the natural logarithm, is the intercept term, are the model coefficients corresponding to the feature , is the input feature of the model.
[0010] Preferably, when the route planning module plans the patrol flight route, it first prepares data, including terrain data, meteorological data, vegetation data, historical fire data, no-fly zones and restricted areas (ensuring that the drone does not enter these areas); the patrol flight route needs to ensure that all high-risk areas are covered, find the route with the shortest total path, and complete the patrol task within the endurance time. Multiple drones can work together and tasks can be reasonably allocated; then use the path planning algorithm to plan and design the route, and then check whether the path avoids all no-fly zones. If the path is not ideal, re-run the algorithm.
[0011] Preferably, the monitoring module includes: Thermal infrared sensor to detect fire sources and hot anomaly points; Visible light camera to provide real-time video stream and high-definition images; Multispectral / hyperspectral camera to monitor the vegetation health status and post-fire vegetation recovery; Gas sensor to detect smoke and harmful gases, and devices to obtain meteorological information such as wind speed, wind direction, temperature, and humidity.
[0012] Preferably, the anti-interference module includes: Protection hardware, which reduces electromagnetic interference by wrapping key electronic components with electromagnetic shielding materials, installs filters on power and signal lines to filter out interference signals; uses multiple antennas to receive and send signals, improves the signal quality and anti-interference ability, receives signals through multiple antennas, and selects the best signal for communication; Frequency interference protection unit, which makes the drone radio communication system constantly change the communication frequency through frequency hopping technology to prevent being interfered by fixed frequencies. Among them, a frequency hopping transmitter is used to send signals according to a predetermined frequency hopping sequence, a frequency hopping receiver is used to synchronize with the frequency hopping sequence of the transmitter and receive signals, and a frequency hopping controller is used to control the generation and synchronization of the frequency hopping sequence; Signal encryption unit, which includes an encryption element and a decryption element. The encryption element encrypts the information data when the second communication module sends it, and the decryption element decrypts the information data received by the second communication module. The AES encryption algorithm is used therein.
[0013] Compared with the prior art, the beneficial effects of the present invention are: An integrated multi-functional UAV safety monitoring system and its application proposed by the present invention conduct real-time patrol and monitoring of mountainous areas through a UAV device. The patrol range is large and the efficiency is high. It can detect fires in a timely manner and take corresponding measures, playing a good preventive effect on wildfire prevention and control. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 It is a schematic structural diagram of the system of the present invention.
[0015] Figure 2 It is a schematic structural diagram of the data processing module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0017] Please refer to Figures 1 to 2 , the present invention provides a technical solution: an integrated multi-functional UAV safety monitoring system and its application, including a main control center and a UAV. The main control center includes: A control module, the control module is connected to a control panel. The control panel provides an operation interface for operators to control and operate the entire system; A first communication module, the first communication module is used to connect to the UAV, and is used to send command signals to the UAV and receive information data sent back by the UAV; A storage module, the storage module is used to store the data information required by the system; A data processing module, the data processing module is used to process and analyze the information data sent back by the UAV; A route planning module, the route planning module is used to calculate and plan the patrol flight route of the UAV; The UAV includes: A second communication module, the second communication module is connected to the first communication module, and is used to receive the command signal sent by the main control center and send the captured information data; A flight control module, the flight control module is used to control the flight of the UAV device according to the patrol flight route designed by the route planning module in the received command signal; A monitoring module, the monitoring module includes a camera and various sensors, and is used to monitor the environment of the patrol flight route; An anti-interference module, the anti-interference module is used to shield interference signals.
[0018] The connection methods between the first communication module and the second communication module include radio frequency communication, cellular network, satellite communication, data radio, etc. Among them, radio frequency (RF) communication is the most common way in UAV communication, including radio waves, microwaves, etc., and can use the ISM band (such as 2.4 GHz or 5.8 GHz) for communication, and these bands can be used without permission; when using the cellular network, the UAV can perform remote communication through 4G or 5G. This method is suitable for long-distance communication and can cover a wide geographical area; in areas without ground communication network coverage, the UAV can use satellite communication, which is suitable for applications such as military, border patrol, and marine monitoring; data radios are radio devices dedicated to data transmission and usually work on custom frequencies. They can provide stable long-distance communication but may require corresponding frequency licenses; there are many specific communication methods, and the communication system design of the UAV needs to consider various factors, including communication distance, environmental conditions, data transmission rate, delay, power consumption, and cost, and can be selected according to requirements.
[0019] After the first communication module receives the information data sent back by the UAV, it sends these information data to the data processing module, and the data processing module includes: A preprocessing unit, which is used to preprocess the data sent back by the UAV. The preprocessing methods include data cleaning, data fusion, and data standardization. Among them, data cleaning is suitable for removing invalid and incorrect data, data fusion is used to combine data from different sources and types to improve the availability of data, and data standardization is to ensure the consistency of data formats; A detection and positioning unit, which performs hotspot detection, identifies heat anomaly points, and determines the possible fire source locations; A fire spread prediction unit, which predicts the future development of the fire according to the current conditions and the fire spread model; A risk assessment unit, which contains a fire prediction model and uses technologies such as machine learning and artificial intelligence to predict the possibility of a fire occurring; A decision support unit, which is used to provide suggestions for fire extinguishing and rescue operations, optimize the allocation of rescue resources and personnel, and send fire alarms and update information to relevant personnel.
[0020] The fire spread model is stored in the model library of the storage module and contains various fire spread models, such as physics-based models, statistical models, etc.
[0021] The steps for the fire spread prediction unit to predict the fire are as follows: S1: Feature extraction, extracting key features that affect the fire spread from the preprocessed data, such as wind speed, wind direction, temperature, humidity, vegetation density, etc.; S2: Model training. Use historical fire data and current fire scene data to train a prediction model. Here, the random forest algorithm is used to train the model. Random forest is an ensemble learning method that improves the prediction accuracy by constructing multiple decision trees and voting. S3: Fire spread prediction. Use the trained model to predict the spread of the fire according to the current conditions. When a new wildfire occurs, collect the data of the current fire scene and use the trained random forest model for prediction. The model will predict the areas where the fire may spread in the next few hours based on the current environmental conditions. S4: Result output. Output the prediction map or prediction report of the fire spread for decision-makers' reference. The prediction results are presented to the fire control center and relevant departments in the form of a heat map or a dynamic spread map to help them formulate fire extinguishing and evacuation plans. In this way, the fire spread prediction module can provide important decision-making support for wildfire response. It should be noted that the accuracy and reliability of the prediction model depend on the quality of the data, the representativeness of the features, and the selection and optimization of the algorithm.
[0022] The fire prediction module is usually constructed based on statistical or machine learning algorithms. The specific calculation formula depends on the type of model used. The following is a calculation formula for a simplified fire prediction model based on logistic regression: where: is the given feature vector when the event occurs, the probability, e is the base of the natural logarithm (approximately equal to 2.71828), is the intercept term, are the model coefficients corresponding to the feature . These model coefficients represent the degree and direction of the influence of each feature on the model prediction result. For example, the coefficients of wind speed, temperature, and humidity are 0.3, 0.5, and -0.2 respectively. These coefficients are used to train the model by using the gradient descent algorithm. First, initialize the coefficients. Assume that we randomly initialize the coefficients to 0. Then calculate the loss function. We use the negative log-likelihood function as the loss function. Then calculate the gradient. For each coefficient, we calculate the gradient of the loss function and then update the coefficients. Use the following formula to update the coefficients: where, is the learning rate, is the loss function, is the index representing the coefficient. After a series of iterations, the above three values are obtained. Among them, the coefficient of wind speed is 0.3, which means that for every 1 unit increase in wind speed, the log odds of a fire occurrence increase by 0.3, that is, the probability of a fire occurrence increases. This example is very simplified. In actual applications, data preprocessing, model training, and coefficient interpretation are more complex. are the input features of the model, such as wind speed, temperature, humidity, etc.
[0023] When the route planning module plans the patrol flight route, it first prepares data, including terrain data (including elevation, slope, aspect, etc., used to evaluate the difficulty of flight), meteorological data (wind speed, wind direction, temperature, humidity, etc., affecting the flight performance and monitoring effect of the UAV), vegetation data (vegetation type, density, etc., closely related to the wildfire risk), historical fire data (location, time, scale, etc. of historical fire occurrences, used to identify high-risk areas), no-fly zones and restricted areas (ensuring that the UAV does not enter these areas); the patrol flight route needs to ensure that all high-risk areas are covered, find the route with the shortest total path, and complete the patrol task within the endurance time. Multiple UAVs can work together and tasks can be reasonably allocated; then use a path planning algorithm to plan and design the route, such as the A* algorithm. The A* algorithm is used because it combines the shortest path search and heuristic methods and is suitable for complex terrains. Then check whether the path avoids all no-fly zones. If the path is not ideal, re-run the algorithm.
[0024] The monitoring module includes: Thermal infrared sensors to detect fire sources and thermal anomaly points; Visible light cameras to provide real-time video streams and high-definition images; Multispectral / hyperspectral cameras to monitor the vegetation health status and post-fire vegetation recovery; Gas sensors to detect smoke and harmful gases, and devices to obtain meteorological information such as wind speed, wind direction, temperature, and humidity.
[0025] The anti-interference module includes: Protection hardware. By using electromagnetic shielding materials to wrap key electronic components, electromagnetic interference is reduced. Filters are installed on power and signal lines to filter out interference signals; multiple antennas are used to receive and send signals to improve the signal quality and anti-interference ability. Signals are received through multiple antennas, and the best signal is selected for communication; Frequency interference protection unit. Through frequency hopping technology, the UAV radio communication system will continuously change the communication frequency to prevent being interfered by fixed frequencies. Among them, a frequency hopping transmitter is used to be responsible for sending signals according to a predetermined frequency hopping sequence, a frequency hopping receiver is used to synchronize with the frequency hopping sequence of the transmitter to receive signals, and a frequency hopping controller is used to control the generation and synchronization of the frequency hopping sequence; A signal encryption unit includes an encryption element and a decryption element. The encryption element encrypts data when the second communication module sends information data, and the decryption element decrypts the information data received by the second communication module. The AES encryption algorithm is used therein.
[0026] In actual use, the drone device is used to conduct real-time patrol and monitoring of mountainous areas. The patrol range is large and the efficiency is high. It can detect fires in a timely manner and take corresponding measures, which has a good preventive effect on mountain fire prevention and control.
[0027] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. An integrated multifunctional UAV safety monitoring system and its application, including a main control center and a UAV, characterized in that: The main control center includes: A control module, wherein the control module is connected to a control panel, and the control panel provides an operation interface for an operator to control the entire system; A first communication module, which is used to connect to the drone, send command signals to the drone and receive information data sent back by the drone; A storage module, wherein the storage module is used to store data information required by the system; A data processing module, which is used to process and analyze the information data sent back by the drone; A route planning module, which is used to calculate and plan the patrol flight route of the UAV; The drone includes: A second communication module, the second communication module is connected to the first communication module and is used to receive a command signal sent by the main control center and send the captured information data; A flight control module, the flight control module is used to control the flight of the UAV device according to the patrol flight route designed by the route planning module in the received command signal; A monitoring module, which includes a camera and multiple sensors for environmental monitoring of the patrol flight route; An anti-interference module, wherein the anti-interference module is used to shield interference signals.
2. The integrated multifunctional unmanned aerial vehicle safety monitoring system and its application according to claim 1 is characterized in that: The connection modes of the first communication module and the second communication module include wireless radio frequency communication, cellular network, satellite communication, and digital radio station.
3. The integrated multifunctional unmanned aerial vehicle safety monitoring system and its application according to claim 1 is characterized by: The data processing module includes: A preprocessing unit, which is used to preprocess the data sent back by the drone. The preprocessing methods include data cleaning, data fusion and data standardization. Data cleaning is suitable for removing invalid and erroneous data, data fusion is used to combine data from different sources and types to improve data availability, and data standardization is to ensure the consistency of data format; A detection and positioning unit, which performs hot spot detection, identifies thermal anomalies, and determines possible fire source locations; A fire prediction unit, wherein the fire prediction unit predicts future fire development based on current conditions and a fire spread model; A risk assessment unit, wherein the risk assessment unit includes a fire prediction model for predicting the possibility of fire occurrence; A decision support unit is used to provide recommendations for fire fighting and rescue actions, optimize the allocation of rescue resources and personnel, and send fire alarms and update information to relevant personnel.
4. The integrated multifunctional unmanned aerial vehicle safety monitoring system and its application according to claim 3 is characterized by: The fire spread model is stored in a model library of the storage module, and includes a variety of fire spread models.
5. The integrated multifunctional unmanned aerial vehicle safety monitoring system and its application according to claim 3 is characterized by: The fire prediction unit performs the following steps in fire prediction: S1: Feature extraction, extracting key features that affect fire spread from preprocessed data; S2: Model training, using historical fire data and current fire data to train the prediction model; S3: Fire prediction, using the trained model to predict the spread of fire based on current conditions; S4: Output the results, output the fire spread prediction map or prediction report for reference by decision makers.
6. The integrated multifunctional unmanned aerial vehicle safety monitoring system and its application according to claim 3 is characterized by: The fire prediction module is usually constructed based on statistical or machine learning algorithms. The specific calculation formula depends on the type of model used. The following is a calculation formula for a simplified fire prediction model based on logistic regression: in: is a given eigenvector Time, Event The probability of occurrence, e is the base of natural logarithms, is the intercept term, are the model coefficients, corresponding to the features , are the input features of the model.
7. The integrated multifunctional unmanned aerial vehicle safety monitoring system and its application according to claim 1 is characterized by: When planning the patrol flight route, the route planning module first prepares data, including terrain data, meteorological data, vegetation data, historical fire data, no-fly zones and restricted areas (to ensure that the drone does not enter these areas); the patrol flight route needs to ensure that all high-risk areas are fully covered, find the shortest route in total, and complete the patrol mission within the flight time. Multiple drones can be used to work together and reasonably allocate tasks; Then use the path planning algorithm to plan and design the route, and then check whether the path avoids all no-fly zones. If the path is not ideal, rerun the algorithm.
8. The integrated multifunctional unmanned aerial vehicle safety monitoring system and its application according to claim 1 is characterized by: The monitoring module includes: Thermal infrared sensors to detect fire sources and thermal anomalies; Visible light camera, providing real-time video streaming and high-definition images; Multispectral / hyperspectral cameras to monitor vegetation health and post-fire vegetation recovery; Gas sensors detect smoke and harmful gases, as well as equipment to obtain meteorological information such as wind speed, wind direction, temperature, and humidity.
9. The integrated multifunctional unmanned aerial vehicle safety monitoring system and its application according to claim 1 is characterized by: The anti-interference module includes: Protect hardware by wrapping key electronic components with electromagnetic shielding materials to reduce electromagnetic interference, and install filters on power and signal lines to filter out interference signals; use multiple antennas to receive and send signals to improve signal quality and anti-interference capabilities, receive signals through multiple antennas, and select the best signal for communication; The frequency interference protection unit uses frequency hopping technology to make the UAV radio communication system constantly change the communication frequency to prevent interference from fixed frequencies. A frequency hopping transmitter is used to send signals according to a predetermined frequency hopping sequence, a frequency hopping receiver is used to synchronize with the frequency hopping sequence of the transmitter, receive signals, and a frequency hopping controller is used to control the generation and synchronization of the frequency hopping sequence; The signal encryption unit includes an encryption element and a decryption element. The encryption element encrypts the data when the second communication module sends the information data, and the decryption element decrypts the information data received by the second communication module, wherein the AES encryption algorithm is used.