Airport bird strike and unmanned aerial vehicle intrusion prevention integrated fusion method and system

Abstract

The invention relates to the technical field of airport safety protection, and discloses an airport bird strike and unmanned aerial vehicle intrusion prevention integrated fusion method and system. The method comprises the following steps: acquiring dynamic image data, radar monitoring data and runway use state data of an airport surrounding area; generating bird flock and unmanned aerial vehicle activity characteristic parameters by using a preset model, generating a fusion risk coefficient through multi-source data fusion processing, and dividing early warning levels; a dynamic prevention strategy is generated in combination with the data, and a bird repelling device and unmanned aerial vehicle countering equipment are controlled; and collecting equipment operation feedback data, updating an early warning level and adjusting a prevention strategy. The system comprises a data acquisition module, an identification analysis module, a strategy generation module, an equipment control module and a feedback adjustment module. According to the invention, integrated fusion of bird strike and unmanned aerial vehicle intrusion prevention is realized, the risk is accurately evaluated, the airport safety guarantee capability is improved, and the air transportation safety is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of airport security prevention, and in particular to a method and system for integrating airport bird strike and drone intrusion prevention. Background Art

[0002] With the rapid development of the aviation transportation industry, airport operational safety faces many challenges. Among them, bird strikes and drone intrusions are becoming increasingly prominent, posing a serious threat to aircraft flight safety and the normal operation of airports.

[0003] Bird strikes have always been a major aviation safety risk. Birds' movements are random and unpredictable. They often forage and roost around airports, significantly increasing the probability of collisions during takeoff and landing. According to statistics, bird strikes cause hundreds of millions of dollars in economic losses worldwide each year, and even more serious accidents can result in aircraft crashes and fatalities. Traditional bird-repelling methods, such as scarecrows and firecrackers, are limited in effectiveness and lack real-time monitoring of bird flock dynamics, making them inadequate for modern airports' bird-strike prevention needs.

[0004] At the same time, the widespread adoption of drone technology has also posed new threats to airport security. Illegal drone intrusions can disrupt aircraft takeoff and landing, or even cause a direct collision. Due to the small size and high speed of drones, existing airport security systems struggle to effectively identify and intercept them. For example, around some major airports, drones have repeatedly intruded into no-fly zones, causing flight delays or cancellations and severely disrupting normal airport operations. Existing drone countermeasures often suffer from slow response times and ineffective interference, making them ineffective in addressing the security risks posed by drone intrusions.

[0005] Furthermore, airports currently rely on independent monitoring and prevention systems for bird strikes and drone intrusions, lacking an effective integrated mechanism. This prevents the sharing of monitoring data and the coordination of preventative measures, resulting in low overall prevention efficiency. Faced with an increasingly complex security landscape, there is an urgent need for a method and system that can integrate bird strike and drone intrusion prevention to enhance airport security capabilities and ensure the safety and smooth operation of air transportation. Summary of the Invention

[0006] The purpose of the present invention is to provide an integrated method and system for preventing bird strikes and drone intrusions at airports to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for integrated fusion of bird strike and drone intrusion prevention at airports, the method comprising: Acquire dynamic image data and radar monitoring data of the area surrounding the airport based on a preset monitoring period, input the dynamic image data into a preset bird flock recognition model, and input the radar monitoring data into a preset drone recognition model to generate bird flock activity characteristic parameters and drone activity characteristic parameters, respectively; Performing multi-source data fusion processing on the bird flock activity characteristic parameters and the drone activity characteristic parameters to generate a fusion risk coefficient, and dividing the warning level according to the fusion risk coefficient; Based on the preset monitoring cycle, the airport runway usage status data is obtained, and a dynamic prevention strategy is generated by combining the current warning level and runway usage status data; Control the preset bird repellent device activation mode and the response intensity of the drone countermeasure equipment according to the dynamic prevention strategy; Collect operational feedback data from bird-repellent devices and drone countermeasure equipment in real time, update the warning level based on the current fusion risk factor, and dynamically adjust the prevention strategy.

[0008] Preferably, the dynamic image data includes visible light images and infrared thermal imaging data, the radar monitoring data includes the drone reflection signal intensity and motion trajectory parameters; the fusion risk coefficient includes the bird flock density risk value and the drone intrusion risk value; Obtaining visible light images, infrared thermal imaging data, and radar monitoring data based on a preset monitoring period, performing background noise removal processing on the visible light images, and performing temperature threshold segmentation processing on the infrared thermal imaging data to generate pre-processed dynamic image data; The pre-processed dynamic image data is input into the bird flock recognition model to calculate the density, flight height and movement direction of the bird flock and generate the characteristic parameters of the bird flock activity; The radar monitoring data is subjected to signal filtering processing to extract the drone's reflected signal strength and motion trajectory parameters, which are input into the drone identification model to calculate the drone type, flight speed and intrusion distance, and generate drone activity characteristic parameters.

[0009] Preferably, the multi-source data fusion processing is performed on the bird flock activity characteristic parameters and the drone activity characteristic parameters to generate a fusion risk coefficient, and the warning level is divided according to the fusion risk coefficient, including: Normalize the bird flock density, flight altitude, movement direction, drone type, flight speed, and invasion distance to calculate the bird flock density risk value. and drone invasion risk value ; Risk value based on bird population density and drone invasion risk value , calculate the fusion risk coefficient through the weighted fusion formula ,in: , and To dynamically adjust the weight coefficient; According to the fusion risk factor The warning level is divided into numerical ranges.

[0010] Preferably, the method of acquiring airport runway usage status data based on a preset monitoring period and generating a dynamic prevention strategy in combination with the current warning level and the runway usage status data includes: Obtain current runway usage status data, including flight take-off and landing times, runway occupancy status, and weather conditions; Match the preset prevention strategy template according to the warning level, adjust the deployment area of ​​the bird repellent device based on the runway occupancy status, and adjust the signal coverage of the drone countermeasure equipment based on the weather conditions; Generate a dynamic prevention strategy that includes the activation frequency of bird repellent devices, the power level of drone countermeasure equipment, and the response priority.

[0011] Preferably, the controlling of the preset bird-repelling device activation mode and the response strength of the drone countermeasure device according to the dynamic prevention strategy includes: Control the output frequency of the sound wave generator and the coverage angle of the directional speaker according to the activation frequency of the bird repellent device; Adjust the emission intensity of the electromagnetic interference signal according to the power level of the drone countermeasure equipment, and determine the countermeasure order of different invading drones based on the response priority.

[0012] Preferably, the real-time collection of operational feedback data from the bird-repelling device and the drone countermeasure equipment, updating of the warning level in combination with the current fusion risk coefficient, and dynamic adjustment of the prevention strategy include: Collect data on the number of effective bird repellents and changes in coverage areas by bird repellent devices, as well as the number of successful interceptions and signal interference range by drone countermeasures. Calculate the prevention efficiency coefficient based on the number of effective expulsions and successful interceptions, combined with the current fusion risk coefficient Update alert levels; Recalculate the dynamic adjustment weight coefficient based on the updated warning level and prevention efficiency coefficient and , and iteratively optimize dynamic prevention strategies.

[0013] Preferably, the fusion risk coefficient is calculated by the weighted fusion formula , wherein the method for determining the sum of the dynamically adjusted weight coefficients includes: Based on historical bird flock activity data and drone intrusion event data, the bird flock density risk value under different meteorological conditions is calculated. and drone invasion risk value relevance; Match correlation parameters according to current meteorological conditions and dynamically adjust and The value of the fusion risk coefficient Reflects the comprehensive risk level in a real-time environment.

[0014] Preferably, the background noise removal process on the visible light image includes: Adaptive filtering algorithm is used to model the dynamic background in visible light images and separate moving targets from static background noise. Morphological processing is performed on the separated moving targets to eliminate isolated noise points in the image and extract the outline features of the bird flock.

[0015] Preferably, the adjusting the emission intensity of the electromagnetic interference signal includes: Match the corresponding communication frequency band and modulation mode according to the drone type to generate targeted electromagnetic interference signals; Adjust the signal transmission power based on the drone intrusion distance to ensure that the interference signal reaches the preset strength threshold in the target area.

[0016] Preferably, the present invention further includes an integrated system for preventing bird strikes and drone intrusions at airports, the system comprising: Data acquisition module: used to obtain dynamic image data, radar monitoring data and airport runway usage status data of the airport surrounding area based on a preset monitoring cycle; Identification and analysis module: inputs the dynamic image data into a preset bird flock identification model, inputs the radar monitoring data into a preset drone identification model, generates bird flock activity characteristic parameters and drone activity characteristic parameters respectively, performs multi-source data fusion processing on the bird flock activity characteristic parameters and drone activity characteristic parameters, generates a fusion risk coefficient, and divides the warning level according to the fusion risk coefficient; Strategy generation module: Generates dynamic prevention strategies based on airport runway usage data obtained during a preset monitoring period and the current warning level; Equipment control module: controls the preset bird repellent device activation mode and the response intensity of the drone countermeasure device according to the dynamic prevention strategy; Feedback adjustment module: collects operational feedback data from bird-repellent devices and drone countermeasure equipment in real time, updates the warning level based on the current fusion risk factor, and dynamically adjusts prevention strategies.

[0017] Compared with the prior art, the present invention has the following beneficial effects: In terms of data processing and risk assessment, dynamic imagery and radar monitoring data are acquired, and pre-set models are used to generate characteristic parameters for bird flocks and drone activity, respectively. Multi-source data is then fused to generate a fused risk coefficient and assign warning levels. This process enables a precise quantitative assessment of risk. Compared to traditional, single-source monitoring methods, this approach provides a more comprehensive and accurate picture of bird and drone activity around airports. For example, traditional methods may only detect the presence of birds or drones but fail to assess the actual risk they pose. This approach, by comprehensively analyzing multi-dimensional parameters such as bird density, flight altitude, and movement direction, as well as drone type, flight speed, and intrusion distance, accurately calculates risk values, providing a reliable basis for the formulation of subsequent prevention strategies. In generating dynamic prevention strategies, runway usage data (such as flight takeoff and landing times, runway occupancy status, and weather conditions) is combined with warning levels to enable tailored strategies tailored to local and current circumstances. During the peak period of flight takeoff and landing, if the warning level is high, the deployment and operation intensity of bird-repellent devices and drone counter-measures equipment can be strengthened in a targeted manner; the signal coverage range of drone counter-measures equipment can be adjusted according to different meteorological conditions to ensure that the equipment can perform at its best even in complex environments, effectively improve the scientific nature and effectiveness of prevention measures, avoid waste of resources, and improve prevention efficiency.

[0018] The device control phase precisely controls bird-repelling devices and drone countermeasures based on dynamic prevention strategies. For example, the sonic generator output frequency and directional speaker coverage angle are controlled according to the bird-repelling device's activation frequency, effectively repelling flocks of birds. Targeted electromagnetic interference signals are generated by matching the communication frequency band and modulation method to the drone type, and the transmission power is adjusted based on the intrusion distance to ensure that the interference signal reaches the preset intensity threshold in the target area. This enables precise countermeasures against different types of drones, significantly improving the ability to respond to bird strikes and drone intrusions.

[0019] The feedback and adjustment mechanism is crucial. It collects real-time feedback from equipment operations, integrates it with risk factors, updates warning levels, and dynamically adjusts prevention strategies. By calculating the prevention efficiency coefficient, the actual effectiveness of preventive measures can be promptly understood. Based on this information, the dynamic weight coefficients are recalculated and adjusted, and dynamic prevention strategies are iteratively optimized. This allows the entire prevention system to continuously improve and optimize based on actual conditions, adapt to the complex and ever-changing airport security environment, and continuously ensure safe airport operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a working principle diagram of the integrated method for preventing bird strikes and UAV intrusions at airports according to the present invention; Figure 2 A flow chart for integrating risk factor calculation and warning level classification; Figure 3 Workflow diagram for calculating abnormal scores and updating thresholds for chicken flocks; Figure 4 A diagram showing how airport bird strike and drone incursion prevention measures are adjusted based on feedback. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] See also Figures 1-4 The present invention provides a technical solution: a method for integrating the prevention of bird strikes and UAV intrusion at airports, the method comprising: Data Acquisition and Feature Parameter Generation: Dynamic image data and radar monitoring data from the airport's surrounding area are continuously collected according to a pre-set monitoring cycle. The acquired dynamic image data is fed into a pre-trained bird flock recognition model, which analyzes and processes the images to generate characteristic parameters for bird flock activity. Simultaneously, the radar monitoring data is fed into a pre-set drone recognition model, which generates characteristic parameters for drone activity.

[0023] Multi-source data fusion and warning level classification: The generated bird flock activity characteristic parameters and drone activity characteristic parameters are fused to obtain a fusion risk coefficient. Based on the different numerical ranges of the fusion risk coefficient, different warning levels are classified to facilitate the subsequent implementation of different preventive measures.

[0024] Dynamic prevention strategy generation: Also based on a pre-set monitoring cycle, airport runway usage data is collected. Combining the current warning level and runway usage data, a dynamic prevention strategy is generated, ensuring that preventive measures can be flexibly adjusted based on actual conditions.

[0025] Equipment control: Based on the generated dynamic prevention strategy, the preset bird-repellent device activation mode and the response intensity of the drone countermeasure equipment are precisely controlled to effectively respond to the risks of bird strikes and drone intrusions.

[0026] Feedback Adjustment: Real-time feedback data from bird repellent and drone countermeasures devices is collected during operation. This data is combined with the current fusion risk factor to update the warning level. Simultaneously, prevention strategies are dynamically adjusted based on the updated warning level, enabling the entire prevention system to continuously adapt to changes in actual conditions and maintain effective prevention capabilities.

[0027] The present invention will be further described below in conjunction with Examples 1 to 5:

[0028] Example 1

[0029] In actual application scenarios, in order to effectively prevent bird strikes and drone intrusions at airports, it is necessary to elaborate on the various data processing and prevention strategy generation processes. Specifically, it includes: Dynamic image data is collected using high-definition visible light cameras and infrared thermal imagers installed at key locations around the airport, collecting data at a preset monitoring interval (e.g., every 30 seconds). Visible light images contain various types of noise. An adaptive filtering algorithm is used to model the dynamic background and separate the moving targets (bird flocks) from the static background noise. Specifically, the algorithm automatically adjusts the filter parameters based on the statistical characteristics of local image regions, allowing the filter to better adapt to background changes. The separated moving targets are then subjected to morphological processing, such as erosion and dilation operations to eliminate isolated noise points and extract clear bird flock outline features, thereby generating pre-processed dynamic image data.

[0030] Infrared thermal imaging data processing uses temperature threshold segmentation based on the temperature difference between the bird's body temperature and the surrounding environment. By setting an appropriate temperature threshold, the bird target is separated from the background, and pre-processed infrared thermal imaging data is also obtained.

[0031] Radar monitoring data contains the drone's reflected signal strength and trajectory parameters, but it is subject to clutter interference and requires signal filtering. Using the Kalman filter algorithm, the current state of the drone is predicted using the previous state and corrected based on the current measurement value, effectively extracting the accurate drone's reflected signal strength and trajectory parameters.

[0032] The pre-processed dynamic image data is fed into a flock recognition model, which analyzes and calculates image features to derive flock density, flight altitude, and movement direction. For example, flock density is estimated by analyzing the number of bird silhouettes and pixel percentage; flight altitude is calculated by comparing the flock in the image with a reference object of known altitude or using multi-camera parallax; and movement direction is determined based on the changes in the flock's position in successive images.

[0033] Parameters extracted from radar monitoring data are fed into a drone identification model. The model analyzes signal characteristics and motion parameters to calculate characteristic parameters of drone activity, such as drone type, flight speed, and intrusion distance. For example, the model identifies drone type based on the spectral characteristics of the radar reflection signal; calculates flight speed by measuring the change in the drone's position at different times; and determines intrusion distance based on the distance between the drone and the airport boundary or runway.

[0034] When calculating the fusion risk coefficient, we first normalize the bird density, flight altitude, movement direction, drone type, flight speed, and intrusion distance, and map these parameters to the [0, 1] interval to eliminate the dimension effect. Calculate the bird density risk value separately. and drone invasion risk value , using the weighted fusion formula Calculate fusion risk coefficient .in, represents the fusion risk coefficient, reflecting the comprehensive risk level of bird strikes and drone intrusions at the airport; is the bird flock density risk value, which represents the risk degree caused by bird flock density to airport safety; is the drone intrusion risk value, reflecting the risk of drone intrusion to airport safety; and In order to dynamically adjust the weight coefficient, it is adjusted according to the correlation between the bird flock density risk value and the drone invasion risk value under different meteorological conditions to balance the proportion of bird flock risk and drone risk in the comprehensive risk. The numerical range is divided into warning levels, such as A low-risk warning. It is a medium risk warning. A high-risk warning.

[0035] Example 2

[0036] When obtaining airport runway usage status data, the airport flight dispatch system is used to obtain real-time information such as flight take-off and landing times, runway occupancy status, etc., and meteorological monitoring equipment is connected to obtain meteorological condition data.

[0037] According to the preset prevention strategy template matched with the warning level, during low-risk warning, the bird-repellent device maintains the normal activation frequency and the drone counter-measure equipment keeps running at low power; during medium-risk warning, the activation frequency of the bird-repellent device is increased and the power of the drone counter-measure equipment is increased; during high-risk warning, the bird-repellent device is activated at the maximum frequency and the drone counter-measure equipment is operated at maximum power.

[0038] The deployment area of ​​bird-repellent devices is adjusted according to the runway occupancy status. When there are flights taking off and landing on the runway, bird-repellent devices are deployed mainly at both ends of the runway and within a certain range on both sides; when the runway is idle, the coverage of the bird-repellent devices is expanded to a larger area around the airport.

[0039] Adjust the signal coverage range of the drone countermeasure equipment according to meteorological conditions. In clear weather, the signal coverage range can be appropriately expanded; in severe weather such as rain and fog, due to signal attenuation, the signal coverage range should be reduced and the transmission power should be increased to ensure signal strength.

[0040] When generating a dynamic prevention strategy, the activation frequency of the bird repellent device, the power level of the drone countermeasures, and the response priority are determined. For example, the bird repellent device activation frequency is set to every 10 minutes for low risk, every 5 minutes for medium risk, and every 2 minutes for high risk. The drone countermeasures power levels are divided into low, medium, and high levels, corresponding to different transmission powers. The response priority is determined by the distance and speed of the drone intrusion, with priority given to countering close and fast drones.

[0041] The output frequency of the sound wave generator and the coverage angle of the directional speaker are controlled according to the starting frequency of the bird repellent device. When the starting frequency is low, the output frequency of the sound wave generator is fixed in the bird-sensitive frequency range (such as 2000-5000Hz), and the coverage angle of the directional speaker is larger (such as 120°); when the starting frequency is high, variable frequency sound waves are used (such as 2000-8000Hz variable frequency), and the coverage angle of the directional speaker is reduced (such as 60°), thereby enhancing the bird repellent effect.

[0042] The electromagnetic interference signal transmission intensity is adjusted based on the power level of the drone countermeasure equipment. At low power, the transmission intensity is 5W; at medium power, the transmission intensity is 10W; and at high power, the transmission intensity is 20W. The order of countermeasures against different intruding drones is determined based on the response priority, with priority given to transmitting jamming signals to drones that are close to the airport runway and flying at high speeds.

[0043] Example 3

[0044] During actual operation, real-time data collection from the bird repellent and drone countermeasures is crucial for achieving dynamic system optimization. This data is collected using a sensor network. Infrared sensors, sound sensors, and other devices are installed within the coverage area of ​​the bird repellent. The infrared sensors detect the entry and exit of birds. When a bird enters the area, the sensor is triggered, recording a bird appearance event. When a bird leaves, another departure event is recorded. The difference between these two values ​​accurately calculates the number of effective bird repellent events. Meanwhile, sound sensors monitor the frequency and intensity of the sound emitted by the bird repellent, determining whether the device is functioning properly and whether the sound is within the effective repellent range, thereby capturing data on changes in the coverage area.

[0045] For drone countermeasures, a monitoring system connected to the equipment can record the number of successful interceptions in real time. Based on the characteristics of the received drone signal, the monitoring system can determine whether the drone's flight control signal has been successfully interfered with. If the detected drone's flight trajectory shows an anomaly that matches the characteristics of an interfered drone, it is considered a successful interception. Furthermore, using signal strength detection equipment, the signal interference range of the drone countermeasures can be obtained in real time, indicating the coverage of the interference effect.

[0046] After obtaining the effective number of expulsions and successful interceptions Then, according to the formula Calculating the prevention efficiency coefficient Here Represents the statistical time period, which is a manually set length of time used to measure the effectiveness of the defense device during that period. For 1 hour, during this 1 hour, the bird repellent device effectively drives away birds 50 times, and the drone countermeasure equipment successfully intercepts drones 10 times, then the prevention efficiency coefficient is This coefficient intuitively reflects the effectiveness of the entire prevention system against bird strikes and drone intrusions during the statistical period.

[0047] Combined with the current fusion risk factor To update the warning level. Assuming the current warning level is medium risk, the fusion risk coefficient is 0.5, the prevention efficiency coefficient It is relatively high, reaching 80 (hypothesis). This indicates that under the current risk situation, the prevention equipment works well and the system is capable of dealing with the current threat. At this time, the warning level can be appropriately lowered to low risk. On the contrary, if the prevention efficiency coefficient is Lower, only 30 (hypothetical), even if the fusion risk coefficient In the low-risk warning range, such as , it may also be necessary to raise the warning level because current preventive measures may not be able to effectively deal with potential risks.

[0048] Recalculate the dynamic adjustment weight coefficient based on the updated warning level and prevention efficiency coefficient and When the warning level increases and the prevention efficiency coefficient is low, it means that the current drone intrusion risk may pose a greater threat to airport safety. For example, when the warning level increases from medium risk to high risk, the prevention efficiency coefficient is Only 20, you can increase it appropriately value, increase the weight of drone invasion risk in the fusion risk coefficient. , , which can be adjusted to , On the contrary, when the warning level is reduced and the prevention efficiency coefficient is high, such as the warning level is reduced from high risk to medium risk, the prevention efficiency coefficient is Reach 70, you can improve value, highlighting the proportion of flock risk in the fusion risk coefficient, Adjust to 0.5, Adjusted to 0.5. This adjustment allows for iterative optimization of dynamic prevention strategies. For example, the activation frequency of bird repellent devices, the power level of drone countermeasures, and response priority can be readjusted based on the new weight coefficients, making the prevention strategy more tailored to actual conditions and improving airport safety.

[0049] Example 4

[0050] In order to dynamically adjust the weight coefficient and To more accurately reflect the overall risk level in real-time, in-depth analysis of historical data is required. Data on bird flock activity and drone intrusions over a period of time, such as the past year, should be collected. This data includes information such as bird flock density, flight altitude, and movement direction at different times and weather conditions, as well as drone type, flight speed, and intrusion distance.

[0051] Calculate the bird density risk value according to different meteorological conditions, such as sunny, cloudy, rainy, windy, etc. and drone invasion risk value Taking strong winds as an example, in strong winds, the flight behavior of birds will be significantly affected. The flocks may be more dispersed, and the flight height and direction will be unstable, which will lead to the risk value of the bird density. At the same time, strong winds will also affect the flight of drones, which may make it difficult to control the flight speed and trajectory of drones, thereby affecting the drone invasion risk value. By analyzing a large amount of historical data on strong winds, we can calculate the and The correlation coefficient of . Assume that after calculation, in strong winds, and The correlation coefficient is 0.8, which indicates that in windy weather, there is a strong positive correlation between the bird density risk value and the drone invasion risk value.

[0052] Establish a meteorological condition and 、 The correlation database stores data such as correlation coefficients under different meteorological conditions in the database. When the system obtains the current meteorological conditions, it queries the corresponding correlation parameters from the database. For example, the current meteorological condition is strong wind weather, and the correlation coefficient under strong wind weather is 0.8. Based on this correlation parameter, the system dynamically adjusts the and Since the risk correlation between bird flocks and drones is strong in windy weather, in order to make the fusion risk coefficient It can more accurately reflect the comprehensive risk level in the real-time environment and can be appropriately improved. and The coefficient with the larger value. Assuming that under normal meteorological conditions, , After querying the correlation parameters of strong wind weather, considering that the risk of drone invasion may be more threatening in strong wind weather, Adjust to 0.4, Adjusted to 0.7. In this way, when calculating the fusion risk coefficient When this is done, we can better balance the proportion of bird flock risk and drone risk in the overall risk, so that the prevention strategy can allocate resources more reasonably according to the actual risk situation and effectively respond to the threats of bird strikes and drone intrusions.

[0053] Example 5

[0054] When adjusting the electromagnetic interference signal's transmission intensity, the first step is to match the communication frequency band and modulation method to the drone type, generating a targeted electromagnetic interference signal. Different drone types utilize different communication frequency bands and modulation methods. For example, most common consumer drones operate in the 2.4 GHz band, using either direct sequence spread spectrum (DSSS) or orthogonal frequency division multiplexing (OFDM) as their modulation methods. To effectively generate an interference signal for drones using the 2.4 GHz band and DSSS modulation, a signal with the same frequency band but opposite modulation method must be selected. An electromagnetic interference signal with a center frequency of 2.4 GHz and frequency hopping spread spectrum (FHSS) modulation can be generated. FHSS operates differently from DSSS. When a drone receives this interference signal, its communication system is disrupted, preventing it from properly demodulating the signal, thereby blocking the drone's communications.

[0055] After determining the frequency band and modulation mode of the interference signal, the signal transmission power is adjusted based on the UAV intrusion distance to ensure that the interference signal reaches the preset intensity threshold in the target area. Assuming a preset intensity threshold 15dBm, signal propagation environment factor In an open environment, the value is 2. When the UAV invasion distance is According to the signal propagation attenuation formula Calculate the required transmit power .in, Indicates the signal power reaching the drone, is the transmit power, is the drone invasion distance. For example, when the drone invasion distance When m, we can get In order to make the signal power reaching the drone reach the preset strength threshold dBm, then , the solution is If the current transmit power level of the drone countermeasure device corresponds to less than 35dBm, the transmit power needs to be increased to ensure the interference signal is strong enough to block drone communications. If the current transmit power is greater than or equal to 35dBm, the current power is maintained. This approach allows precise adjustment of the electromagnetic interference signal's transmit strength based on the actual drone intrusion situation, effectively countering intruding drones and ensuring safe airport operations.

[0056] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0057] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for integrated fusion of bird strike and drone intrusion prevention at airports, characterized in that: include: Acquire dynamic image data and radar monitoring data of the area surrounding the airport based on a preset monitoring period, input the dynamic image data into a preset bird flock recognition model, and input the radar monitoring data into a preset drone recognition model to generate bird flock activity characteristic parameters and drone activity characteristic parameters, respectively; Performing multi-source data fusion processing on the bird flock activity characteristic parameters and the drone activity characteristic parameters to generate a fusion risk coefficient, and dividing the warning level according to the fusion risk coefficient; Based on the preset monitoring cycle, the airport runway usage status data is obtained, and a dynamic prevention strategy is generated by combining the current warning level and runway usage status data; Control the preset bird repellent device activation mode and the response intensity of the drone countermeasure equipment according to the dynamic prevention strategy; Collect operational feedback data from bird-repellent devices and drone countermeasure equipment in real time, update the warning level based on the current fusion risk factor, and dynamically adjust the prevention strategy.

2. The method for integrated airport bird strike and drone intrusion prevention according to claim 1 is characterized by: The dynamic image data includes visible light images and infrared thermal imaging data, the radar monitoring data includes the drone reflection signal intensity and motion trajectory parameters; the fusion risk coefficient includes the bird flock density risk value and the drone intrusion risk value; Obtaining visible light images, infrared thermal imaging data, and radar monitoring data based on a preset monitoring period, performing background noise removal processing on the visible light images, and performing temperature threshold segmentation processing on the infrared thermal imaging data to generate pre-processed dynamic image data; The pre-processed dynamic image data is input into the bird flock recognition model to calculate the density, flight height and movement direction of the bird flock and generate the characteristic parameters of the bird flock activity; The radar monitoring data is subjected to signal filtering processing to extract the drone's reflected signal strength and motion trajectory parameters, which are input into the drone identification model to calculate the drone type, flight speed and intrusion distance, and generate drone activity characteristic parameters.

3. The integrated method for preventing bird strikes and drone intrusions at airports according to claim 1 is characterized by: The multi-source data fusion processing of the bird flock activity characteristic parameters and the drone activity characteristic parameters to generate a fusion risk coefficient, and the early warning level is divided according to the fusion risk coefficient, including: Normalize the bird flock density, flight altitude, movement direction, drone type, flight speed, and invasion distance to calculate the bird flock density risk value. and drone invasion risk value ; Risk value based on bird population density and drone invasion risk value , calculate the fusion risk coefficient through the weighted fusion formula ,in: , and To dynamically adjust the weight coefficient; According to the fusion risk factor The warning level is divided into numerical ranges.

4. The method for integrated airport bird strike and drone intrusion prevention according to claim 1 is characterized by: The method of acquiring airport runway usage status data based on a preset monitoring cycle and generating a dynamic prevention strategy by combining the current warning level and the runway usage status data includes: Obtain current runway usage status data, including flight take-off and landing times, runway occupancy status, and weather conditions; Match the preset prevention strategy template according to the warning level, adjust the deployment area of ​​the bird repellent device based on the runway occupancy status, and adjust the signal coverage of the drone countermeasure equipment based on the weather conditions; Generate a dynamic prevention strategy that includes the activation frequency of bird repellent devices, the power level of drone countermeasure equipment, and the response priority.

5. The method for integrated airport bird strike and drone intrusion prevention according to claim 4 is characterized by: The method of controlling the preset bird-repelling device activation mode and the response strength of the drone countermeasure device according to the dynamic prevention strategy includes: Control the output frequency of the sound wave generator and the coverage angle of the directional speaker according to the activation frequency of the bird repellent device; Adjust the emission intensity of the electromagnetic interference signal according to the power level of the drone countermeasure equipment, and determine the countermeasure order of different invading drones based on the response priority.

6. The integrated method for preventing bird strikes and drone intrusions at airports according to claim 1 is characterized by: The real-time collection of operational feedback data from bird repellent devices and drone countermeasure equipment, combined with the current fusion risk factor to update the warning level and dynamically adjust the prevention strategy, includes: Collect data on the number of effective bird repellents and changes in coverage areas by bird repellent devices, as well as the number of successful interceptions and signal interference range by drone countermeasures. Calculate the prevention efficiency coefficient based on the number of effective expulsions and successful interceptions, combined with the current fusion risk coefficient Update alert levels; Recalculate the dynamic adjustment weight coefficient based on the updated warning level and prevention efficiency coefficient and , and iteratively optimize dynamic prevention strategies.

7. The integrated method for preventing bird strikes and drone intrusions at airports according to claim 3 is characterized by: The fusion risk coefficient is calculated by the weighted fusion formula , wherein the method for determining the sum of the dynamically adjusted weight coefficients includes: Based on historical bird flock activity data and drone intrusion event data, the bird flock density risk value under different meteorological conditions is calculated. and drone invasion risk value relevance; Match correlation parameters according to current meteorological conditions and dynamically adjust and The value of the fusion risk coefficient Reflects the comprehensive risk level in a real-time environment.

8. The integrated method for preventing bird strikes and drone intrusions at airports according to claim 2 is characterized by: The background noise removal process for the visible light image includes: Adaptive filtering algorithm is used to model the dynamic background in visible light images and separate moving targets from static background noise. Morphological processing is performed on the separated moving targets to eliminate isolated noise points in the image and extract the outline features of the bird flock.

9. The integrated method for preventing bird strikes and drone intrusions at airports according to claim 5 is characterized by: The adjusting the emission intensity of the electromagnetic interference signal includes: Match the corresponding communication frequency band and modulation mode according to the drone type to generate targeted electromagnetic interference signals; Adjust the signal transmission power based on the drone intrusion distance to ensure that the interference signal reaches the preset strength threshold in the target area.

10. An integrated system for preventing bird strikes and drone intrusions at airports, characterized by: The system comprises: Data acquisition module: used to obtain dynamic image data, radar monitoring data and airport runway usage status data of the airport surrounding area based on a preset monitoring cycle; Identification and analysis module: inputs the dynamic image data into a preset bird flock identification model, inputs the radar monitoring data into a preset drone identification model, generates bird flock activity characteristic parameters and drone activity characteristic parameters respectively, performs multi-source data fusion processing on the bird flock activity characteristic parameters and drone activity characteristic parameters, generates a fusion risk coefficient, and divides the warning level according to the fusion risk coefficient; Strategy generation module: Generates dynamic prevention strategies based on airport runway usage data obtained during a preset monitoring period and the current warning level; Equipment control module: controls the preset bird repellent device activation mode and the response intensity of the drone countermeasure device according to the dynamic prevention strategy; Feedback adjustment module: collects operational feedback data from bird-repellent devices and drone countermeasure equipment in real time, updates the warning level based on the current fusion risk factor, and dynamically adjusts prevention strategies.

Images