An unmanned aerial vehicle based radar beacon status patrol system and method

Abstract

This application discloses a radar beacon status inspection system and method based on unmanned aerial vehicles (UAVs), relating to the field of maritime navigation aid equipment inspection technology. The system includes a UAV, a dual-band radar transceiver, a radio frequency spectrum analysis module, an AI visual inspection unit, a positioning module, a signal processing module, and a cloud management platform. The UAV carries the dual-band radar transceiver, radio frequency spectrum analysis module, AI visual inspection unit, signal processing module, and positioning module to the target area. The cloud management platform generates a radar beacon health status report, triggers fault alarms, or generates maintenance suggestions based on the data transmitted back by the UAV, dual-band radar transceiver, radio frequency spectrum analysis module, AI visual inspection unit, positioning module, and signal processing module. This application solves the problems of high cost, low efficiency, and inaccurate detection in traditional manual inspections by combining UAVs with multimodal sensing.

Description

Technical Field

[0001] This application relates to the field of marine navigation aids testing technology, and in particular to a highly efficient and automated system and method for radar beacon status inspection, status detection and fault diagnosis based on unmanned aerial vehicles (UAVs). Background Technology

[0002] Existing technical issues: 1. Traditional radar beacon inspection methods rely on personnel on board ships using shipborne radar and telescopes for manual inspection, which is basically a subjective assessment by personnel (assessing visibility and clarity). Traditional methods require the use of medium to large-sized ships and professional personnel, resulting in high costs, low efficiency, lack of objective data quantification, no automated detection system, and difficulty in execution under adverse weather and sea conditions.

[0003] 2. Radar beacon signals traditionally rely on marine radar for triggering. Their operational status cannot be directly verified using existing UAV onboard equipment. Therefore, a dedicated UAV onboard system needs to be designed to complete the corresponding radar beacon triggering, radar signal echo reception, signal processing, and analysis and judgment of the received beacon echoes.

[0004] 3. Lack of intelligent analysis methods makes it impossible to determine in real time whether radar beacon signals are normal or whether coverage meets the standards.

[0005] Shortcomings of existing solutions: 1. Some patents propose using drones to inspect buoys (navigation marks), but do not cover radar beacon detection. 2. Existing radar beacon detection equipment is mostly fixed or shipborne, which cannot flexibly adapt to the rapid patrol needs of different sea areas. Summary of the Invention

[0006] The main objective of this application is to propose a radar beacon status inspection system and method based on unmanned aerial vehicles (UAVs). The system consists of a UAV, an airborne detection module, a signal processing module, and a cloud management platform. The modules have clearly defined roles (the UAV serves as the mobile carrier, dual-band radar is the core detection unit, AI vision and RF spectrum are used for auxiliary detection, RTK-GPS and BeiDou are used for positioning, and the cloud platform is the data processing and management center). The multi-sensor fusion design aligns with the dual requirements of radar beacon detection—signal and physical status—solving the problems of low efficiency and inability to operate in harsh environments associated with traditional manual inspection. Simultaneously, it enables modeling from discrete sampling points to continuous signal coverage, providing intuitive output of coverage radius and blind spots, filling the gap in traditional inspection methods that "can only measure single-point signals and cannot assess overall coverage."

[0007] To achieve the above objectives, one aspect of this application proposes a radar beacon status inspection system based on unmanned aerial vehicles (UAVs). The system includes: a UAV, a dual-band radar transceiver, a radio frequency spectrum analysis module, an AI visual inspection unit, a positioning module, a signal processing module, and a cloud management platform. The drone is used to carry the dual-band radar transceiver, the radio frequency spectrum analysis module, the AI ​​visual detection unit, and the positioning module to the target area. The dual-band radar transceiver is used to transmit a detection signal in a preset frequency band to the radar beacon in the target area, triggering the radar beacon to operate, and simultaneously receiving radar beacon signals. The signal processing module is used to preprocess and decode the radar echo signal; The radio frequency spectrum analysis module is used to synchronously monitor the radar beacon signal and collect the signal strength, frequency and signal-to-noise ratio of the radar beacon signal in real time. The AI ​​visual detection unit is used to acquire image data of the radar beacon and detect the appearance of the radar beacon and its surrounding environment; The positioning module is used to acquire positioning information; The cloud management platform is used to generate a health status report for the radar beacon, trigger fault alarms, or generate maintenance suggestions based on the data transmitted back from the drone, the dual-band radar transceiver, the radio frequency spectrum analysis module, the AI ​​visual inspection unit, the positioning module, and the signal processing module.

[0008] In some embodiments, the dual-band radar transceiver includes a transmitting unit, a receiving unit, and the signal processing module; The transmitting unit is used for: The dual-band signal generation specifically includes: adopting a software-defined radio architecture, integrating X-band and S-band dual-channel voltage-controlled oscillator and phase-locked loop, dynamic frequency band switching, and frequency resolution ≤1 MHz; The adjustable output power includes: a gallium nitride power amplifier with a dynamic output power range of 10 mW to 2 W, which is based on existing size and weight limitations and is adapted to different detection distances and testing requirements through a digitally controlled attenuator.

[0009] The receiving unit includes a duplex filter bank and a low-noise amplifier; The duplex filter bank is used to achieve X / S band signal separation, with insertion loss <1.5 dB and out-of-band rejection >40 dB; The low-noise amplifier has a noise figure of <1.5 dB, a gain of >20 dB, and supports full-band signal amplification. The receiving unit is used for zero-IF downconversion, specifically including: directly converting the received signal into a baseband I / Q signal through a mirror rejection mixer to reduce the complexity of the intermediate frequency circuit; The signal processing module is used for: Adaptive filtering and sampling specifically include: using a variable bandwidth FIR filter to dynamically suppress out-of-band noise, and combining it with a dual-channel 14-bit ADC to digitize the signal; Real-time pulse decoding specifically includes: an FPGA-based symbol classification algorithm to parse the Morse code in the radar echo signal, supporting dynamic threshold detection and noise suppression.

[0010] To achieve the above objectives, another aspect of this application proposes a method for radar beacon status inspection based on unmanned aerial vehicles (UAVs). This method is applied to a UAV-based radar beacon status inspection system as described above, and includes the following steps: Preprocess the radar echo signal; The preprocessed radar echo signal is decoded; The radar beacon signal is monitored synchronously through the radio frequency spectrum analysis module, and the signal strength, frequency and signal-to-noise ratio of the radar beacon signal are collected in real time. Image data of radar beacons is acquired using an AI visual inspection unit; Based on the positioning information and timestamp, the decoded radar echo signal, the spectrum obtained by the radio frequency spectrum analysis module, and the image data are spatiotemporally aligned to obtain spatiotemporal data; The fault diagnosis engine is used to diagnose the faults of the radar beacon based on the spatiotemporal data.

[0011] In some embodiments, the preprocessing of the radar echo signal includes the following steps: A variable bandwidth finite impulse response filter is used to bandpass filter the radar echo signal, and the center frequency dynamically tracks the nominal frequency of the radar beacon. The bandwidth of the variable bandwidth finite impulse response filter is set to a multiple of the code rate according to the code rate of the radar beacon; The radar echo signal is subjected to wavelet filtering based on an improved wavelet threshold denoising algorithm. The pulse characteristics of the radar echo signal are enhanced by applying the Tiger Kaiser energy operator to generate a signal energy envelope; An ordered statistical constant false alarm rate algorithm is adopted to dynamically set the detection threshold based on the background noise of the radar echo signal, thereby filtering the background noise.

[0012] In some embodiments, decoding the preprocessed radar echo signal includes the following steps: The radar echo signal after preprocessing is used to distinguish between short pulses, long pulses, and intervals based on the pulse duration. The short pulses and the long pulses are combined into corresponding letters or numbers according to the Morse code standard.

[0013] In some embodiments, the fault diagnosis of the radar beacon using the fault diagnosis engine based on the spatiotemporal data includes the following steps: Extracting fault features from the spatiotemporal data specifically includes: If the radar echo signal decoding fails or the signal is lost, the extracted feature is no signal fault; The detection signal is checked to see if the transmission frequency offset exceeds the standard range. If so, the feature is extracted as a frequency drift fault. Detect whether the signal strength of the probe signal is lower than a standard threshold; if so, extract the feature as a signal attenuation fault. AI image analysis is performed on the image data to identify whether the radar beacon has physical damage or obstructions; if so, the feature is extracted as an antenna physical fault. The fault diagnosis engine employs DS evidence theory or Bayesian network to output the fault type and confidence level of the radar beacon based on each fault characteristic.

[0014] In some embodiments, the method further includes the following steps: A heatmap of the effective detection range of the radar beacon is drawn based on the flight trajectory of the UAV, specifically including: The drone flies along the preset flight path, and the signal strength, frequency stability and signal-to-noise ratio of the radar beacon are dynamically collected by the airborne radio frequency spectrum analysis module. The location and flight timestamp of the drone are recorded using a positioning module. Based on the free space path loss model and the actual environment correction factor, the signal strength of the radar beacon is compensated. The expression for the compensation calculation is: P 校正 =P 接收 +20log10(d)+K 环境 ; Where d is the distance between the UAV and the radar beacon, and K 环境 This is an environmental correction factor; The Kriging interpolation algorithm is used to interpolate discrete UAV sampling point data into a continuous spatial signal distribution; A signal strength heatmap is generated by combining geographic information systems, with color gradients representing coverage intensity. Define an effective coverage threshold, extract the boundary of the qualified area in the heat map, and generate the polygon of the effective detection range of the radar beacon; Output the coverage radius and blind zone location of the effective detection range polygon.

[0015] To achieve the above objectives, another aspect of this application proposes a radar beacon status inspection device based on an unmanned aerial vehicle (UAV). The device is applied to a UAV-based radar beacon status inspection system as described above, and includes: The signal preprocessing unit is used to preprocess radar echo signals; A signal decoding unit is used to decode the preprocessed radar echo signal; The spectrum analysis unit is used to synchronously monitor radar beacon signals through the radio frequency spectrum analysis module and to collect the signal strength, frequency and signal-to-noise ratio of the radar beacon signals in real time. An image detection unit is used to acquire image data of radar beacons using an AI vision detection unit. The data alignment unit is used to perform spatiotemporal alignment of the decoded radar echo signal, the spectrum analyzed by the radio frequency spectrum analysis module, and the image data according to the positioning information and timestamp to obtain spatiotemporal data. The fault diagnosis unit is used to perform fault diagnosis on the radar beacon based on the spatiotemporal data using the fault diagnosis engine.

[0016] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0017] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0018] To achieve the above objectives, another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0019] The embodiments of this application include at least the following beneficial effects: This application provides a radar beacon status inspection system and method based on unmanned aerial vehicles (UAVs). The system includes a UAV, a dual-band radar transceiver, a radio frequency spectrum analysis module, an AI vision inspection unit, a positioning module, a signal processing module, and a cloud management platform. By combining UAVs with multimodal sensing, the system solves the problems of low efficiency and inaccurate detection in traditional manual inspections. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a radar beacon status inspection method based on an unmanned aerial vehicle (UAV) provided in this application embodiment; Figure 2 An example diagram of a radar beacon status inspection system based on an unmanned aerial vehicle (UAV) provided in this application embodiment; Figure 3 The signal strength heatmap provided in the embodiments of this application; Figure 4 Example diagram of system workflow provided for embodiments of this application; Figure 5 A schematic diagram of a radar beacon status inspection device based on an unmanned aerial vehicle (UAV) provided in this application embodiment; Figure 6 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0024] This application provides a method for radar beacon status inspection based on unmanned aerial vehicles (UAVs), relating to the field of maritime navigation aid equipment detection technology. The UAV-based radar beacon status inspection method provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle-mounted terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster consisting of multiple physical servers, or a distributed system. It can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing a UAV-based radar beacon status inspection method, but is not limited to the above forms.

[0025] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0026] This application provides a radar beacon status inspection system based on a drone. The system includes: a drone, a dual-band radar transceiver, a radio frequency spectrum analysis module, an AI visual inspection unit, a positioning module, a signal processing module, and a cloud management platform. The drone is used to carry the dual-band radar transceiver, the radio frequency spectrum analysis module, the AI ​​visual detection unit, and the positioning module to the target area. The dual-band radar transceiver is used to transmit a detection signal in a preset frequency band to the radar beacon in the target area, triggering the radar beacon to operate, and simultaneously receiving radar beacon signals. The signal processing module is used to preprocess and decode the radar echo signal; The radio frequency spectrum analysis module is used to synchronously monitor the radar beacon signal and collect the signal strength, frequency and signal-to-noise ratio of the radar beacon signal in real time. The AI ​​visual detection unit is used to acquire image data of the radar beacon and detect the appearance of the radar beacon and its surrounding environment; The positioning module is used to acquire positioning information; The cloud management platform is used to generate a health status report for the radar beacon, trigger fault alarms, or generate maintenance suggestions based on the data transmitted back from the drone, the dual-band radar transceiver, the radio frequency spectrum analysis module, the AI ​​visual inspection unit, the positioning module, and the signal processing module.

[0027] Optionally, the dual-band radar transceiver includes a transmitting unit, a receiving unit, and the signal processing module; The transmitting unit is used for: The dual-band signal generation specifically includes: adopting a software-defined radio architecture, integrating X-band and S-band dual-channel voltage-controlled oscillator and phase-locked loop, dynamic frequency band switching, and frequency resolution ≤1 MHz; The output power is adjustable, specifically including: based on a gallium nitride power amplifier, the output power dynamic range is 10 mW to 2W, and it can be adapted to different detection distance requirements through a digitally controlled attenuator.

[0028] The receiving unit includes a duplex filter bank and a low-noise amplifier; The duplex filter bank is used to achieve X / S band signal separation, with insertion loss <1.5 dB and out-of-band rejection >40 dB; The low-noise amplifier has a noise figure of <1.5 dB, a gain of >20 dB, and supports full-band signal amplification. The receiving unit is used for zero-IF downconversion, specifically including: directly converting the received signal into a baseband I / Q signal through a mirror rejection mixer to reduce the complexity of the intermediate frequency circuit; The signal processing module is used for: Adaptive filtering and sampling specifically include: using a variable bandwidth FIR filter to dynamically suppress out-of-band noise, and combining it with a dual-channel 14-bit ADC to digitize the signal; Real-time pulse decoding specifically includes: an FPGA-based symbol classification algorithm to parse the Morse code in the radar echo signal, supporting dynamic threshold detection and noise suppression.

[0029] Reference Figure 1Another aspect of this application proposes a method for radar beacon status inspection based on unmanned aerial vehicles (UAVs). This method is applied to a UAV-based radar beacon status inspection system as described above, and includes the following steps S100-S150: S100: Preprocess radar echo signals; S110: Decode the preprocessed radar echo signal; S120: Simultaneously monitors radar beacon signals through the radio frequency spectrum analysis module, and collects the signal strength, frequency and signal-to-noise ratio of radar beacon signals in real time; S130: Acquires image data of radar beacons using an AI vision inspection unit; S140: Based on the positioning information and timestamp, the decoded radar echo signal, the spectrum obtained by the radio frequency spectrum analysis module, and the image data are spatiotemporally aligned to obtain spatiotemporal data; S150: Use the fault diagnosis engine to perform fault diagnosis on the radar beacon based on the spatiotemporal data.

[0030] Optionally, the preprocessing of the radar echo signal includes the following steps: A variable bandwidth finite impulse response filter is used to bandpass filter the radar echo signal, and the center frequency dynamically tracks the nominal frequency of the radar beacon. The bandwidth of the variable bandwidth finite impulse response filter is set to a multiple of the code rate according to the code rate of the radar beacon; The radar echo signal is subjected to wavelet filtering based on an improved wavelet threshold denoising algorithm. The pulse characteristics of the radar echo signal are enhanced by applying the Tiger Kaiser energy operator to generate a signal energy envelope; An ordered statistical constant false alarm rate algorithm is adopted to dynamically set the detection threshold based on the background noise of the radar echo signal, thereby filtering the background noise.

[0031] Optionally, decoding the preprocessed radar echo signal includes the following steps: The radar echo signal after preprocessing is used to distinguish between short pulses, long pulses, and intervals based on the pulse duration. The short pulses and the long pulses are combined into corresponding letters or numbers according to the Morse code standard.

[0032] Optionally, the step of using a fault diagnosis engine to perform fault diagnosis on the radar beacon based on the spatiotemporal data includes the following steps: Extracting fault features from the spatiotemporal data specifically includes: If the radar echo signal decoding fails or the signal is lost, the extracted feature is no signal fault; The detection signal is checked to see if the transmission frequency offset exceeds the standard range. If so, the feature is extracted as a frequency drift fault. Detect whether the signal strength of the probe signal is lower than a standard threshold; if so, extract the feature as a signal attenuation fault. AI image analysis is performed on the image data to identify whether the radar beacon has physical damage or obstructions; if so, the feature is extracted as an antenna physical fault. The fault diagnosis engine employs DS evidence theory or Bayesian network to output the fault type and confidence level of the radar beacon based on each fault characteristic.

[0033] Optionally, the method further includes the following steps: A heatmap of the effective detection range of the radar beacon is drawn based on the flight trajectory of the UAV, specifically including: The drone flies along the preset flight path, and the signal strength, frequency stability and signal-to-noise ratio of the radar beacon are dynamically collected by the airborne radio frequency spectrum analysis module. The location and flight timestamp of the drone are recorded using a positioning module. Based on the free space path loss model and the actual environment correction factor, the signal strength of the radar beacon is compensated. The expression for the compensation calculation is: P 校正 =P 接收 +20log10(d)+K 环境 ; Where d is the distance between the UAV and the radar beacon, and K 环境 This is an environmental correction factor; The Kriging interpolation algorithm is used to interpolate discrete UAV sampling point data into a continuous spatial signal distribution; A signal strength heatmap is generated by combining geographic information systems, with color gradients representing coverage intensity. Define an effective coverage threshold, extract the boundary of the qualified area in the heat map, and generate the polygon of the effective detection range of the radar beacon; Output the coverage radius and blind zone location of the effective detection range polygon.

[0034] The following sections will provide a detailed description and explanation of some optional embodiments of this application, using specific application examples.

[0035] 1. This embodiment proposes a radar beacon status inspection system based on unmanned aerial vehicles (UAVs). Through multi-sensor fusion (radar, RF spectrum analysis, computer vision), it achieves automatic detection, signal quality assessment, and fault alarm for radar beacons (see reference). Figure 2 ).

[0036] 2. The objective of this embodiment is achieved through the following technical solution: 2.1 UAV airborne detection system.

[0037] This system includes a miniaturized radar transceiver, a radio frequency (RF) spectrum analysis module, an AI vision inspection unit, and an RTK-GPS positioning module. It achieves comprehensive status detection of radar beacons through multi-sensor fusion. The miniaturized X / S dual-band radar transceiver is the core component, and its specific technical solution is as follows: 2.1.1 Design of dual-band radar transceiver.

[0038] 1. Transmission unit.

[0039] Dual-band signal generation: It adopts a software-defined radio (SDR) architecture, integrating a dual-channel voltage-controlled oscillator (VCO) and phase-locked loop (PLL) for X-band (9300-9500MHz) and S-band (2900-3100MHz), supporting dynamic frequency band switching, with a frequency resolution ≤1MHz.

[0040] Adjustable power output: Based on gallium nitride (GaN) power amplifier (PA), the output power dynamic range is 10mW-2W, and it can be adapted to different detection distance requirements through digitally controlled attenuator (0-30dB step adjustment).

[0041] Antenna design: A 4×4 microstrip antenna array is adopted, with a radiation efficiency of >70% and an adjustable beamwidth (15°-60°); a waveguide slot antenna is optional, with a beamwidth selectable according to the physical length of the antenna (5°-30°) and a radiation efficiency of >90%, ensuring stable signal coverage when the UAV changes its flight attitude.

[0042] 2. Receiving unit.

[0043] Broadband low-noise receiver chain: Duplex filter bank: Enables X / S band signal separation with insertion loss <1.5dB and out-of-band rejection >40dB.

[0044] Low-noise amplifier (LNA): Noise figure < 1.5dB, gain > 20dB, supports full-band signal amplification.

[0045] Zero-IF downconversion: The received signal is directly converted into a baseband I / Q signal through a mirror rejection mixer, reducing the complexity of the intermediate frequency circuit.

[0046] 3. Signal processing module.

[0047] Adaptive filtering and sampling: A variable bandwidth FIR filter (e.g., Hamming window, order 64) is used to dynamically suppress out-of-band noise, and combined with a dual-channel 14-bit ADC (sampling rate 100MSPS) to digitize the signal.

[0048] Real-time pulse decoding: Based on FPGA symbol classification algorithm, it parses Morse code in radar echo and supports dynamic threshold detection (OS-CFAR algorithm) and noise suppression (wavelet denoising).

[0049] 2.1.2 Technical Collaboration and Functional Implementation.

[0050] Dual-band compatibility: The main control unit dynamically switches between X and S bands to adapt to the frequency band requirements of different radar beacon equipment (such as X band for international waterways and S band for nearshore waters), thereby expanding the detection coverage.

[0051] Signal strength calibration: By combining the free space path loss model (FSPL) with environmental correction factors (such as sea surface reflection +3dB), the received signal strength (RSSI) is dynamically compensated to ensure data accuracy.

[0052] Linked with the RF spectrum module: After the transceiver triggers the radar beacon response, the RF module synchronously monitors the stability of the transmission frequency (such as frequency deviation < ±50kHz) and the signal-to-noise ratio (SNR≥15dB) to assist in fault diagnosis.

[0053] 2.1.3 Technical effects.

[0054] Lightweight integration: Transceiver size ≤150×100×30mm, weight <500g, power consumption <15W (standby <5W), with sufficient redundancy in weight and power to adapt to the payload limitations of existing general drones. For example, the DJI M300 drone can provide an effective payload of about 2.7kg and a power consumption of 96W.

[0055] Highly efficient detection: The dual-band design allows for the detection of multi-band radar beacon equipment in a single flight, directly doubling the detection results (detection content) without requiring extensive ship maneuvering tests. Actual work efficiency has been calculated to increase by 3-5 times. For example, a navigation aid inspection plan at a navigation aid station in the Pearl River Estuary previously required 8-10 working days to complete a certain inspection plan using ships and manual inspections. Using this inspection plan, only 2 working days are needed. Each UAV flight takes 30 minutes (plus 1 hour of take-off and landing preparation time) to complete at least half a working day's worth of ship inspection work (4 hours). Moreover, it can operate at night, compared to ships, which cannot effectively observe fishing nets and buoys at night, cannot maneuver effectively, and cannot complete inspection tasks.

[0056] Accurate decoding: Based on FPGA real-time processing algorithm, Morse code decoding success rate >98%, bit error rate <0.1%. In actual work, due to the large number of repeated detection mechanisms at fixed points for a period of time, the above decoding success rate >98% and bit error rate <0.1% can be regarded as 100% confidence in the presence / absence and data quality.

[0057] 2.2. Intelligent analysis algorithm.

[0058] 2.2.1 Radar echo decoding algorithm.

[0059] The automatic parsing of radar beacon Morse code and verification of signal integrity are achieved through a multi-step process. The specific technical solution is as follows: Step 1: Signal preprocessing.

[0060] Adaptive filtering: A variable bandwidth finite impulse response (FIR) filter (Hamming window, order 64) is used to perform bandpass filtering on the received signal, and the center frequency dynamically tracks the nominal frequency of the radar beacon (such as the baseband frequency after downconversion from 9340MHz).

[0061] Dynamic bandwidth adjustment: Automatically sets the filter bandwidth to twice the code rate (200Hz) based on the radar beacon code rate (e.g., 100Hz) to ensure signal integrity.

[0062] Noise suppression: Based on an improved wavelet threshold denoising algorithm (using a soft threshold as the threshold function and a decomposition level of 5), the signal-to-noise ratio is effectively improved (compared to no denoising algorithm, the SNR can be improved by ≥20dB).

[0063] Step 2: Pulse detection.

[0064] Energy envelope extraction: The Tiger-Kaiser Energy Operator (TKEO) is applied to enhance pulse characteristics and generate the signal energy envelope.

[0065] Dynamic threshold determination: The ordered statistical constant false alarm rate (OS-CFAR) algorithm is adopted to dynamically set the detection threshold based on the background noise, so as to avoid false detection or missed detection caused by fixed threshold.

[0066] Step 3: Morse code decoding.

[0067] Code element classification: Based on pulse duration, distinguish between "dot" (short pulse, ≤150ms), "dash" (long pulse, ≥300ms), and interval (inter-character interval ≥3 times the dot length).

[0068] Character assembly: Based on the international Morse code standard, "dots" and "dashes" are combined to form corresponding letters or numbers (such as "·"). "Decoded as the letter A".

[0069] Step 4: Signal integrity verification.

[0070] The decoding result is compared with the preset radar beacon identification code. If the match fails (e.g., the decoding result is "B" instead of the preset "A"), it is determined to be a signal abnormality and a fault marker is triggered. Given that pulse loss / distortion is prone to occur in the sea surface environment, leading to symbol errors, the system employs a mechanism of repeated detection and decoding at fixed points for a continuous period of time. Reasonable thresholds can be set according to different objective conditions to achieve integrity fault tolerance.

[0071] Step 5: Output Results and Alarms.

[0072] The decoding results and signal status (normal / abnormal) are uploaded to the cloud management platform. Utilizing multi-source data from radar, RF spectrum, and AI vision, the system outputs the fault type and confidence level. If an anomaly is detected (such as signal loss, frequency shift, or symbol error), a fault alarm is triggered and a report is generated.

[0073] 2.2.2 Signal coverage modeling.

[0074] Based on the flight trajectory of the UAV, a heat map of the effective detection range of the radar beacon is drawn, realizing the modeling from discrete sampling points to continuous signal coverage. It can intuitively output the coverage radius and blind zone, filling the gap of traditional detection that "can only measure single-point signals and cannot evaluate the overall coverage".

[0075] The specific process is as follows: Step 1: Data acquisition and preprocessing.

[0076] The drone flies along a preset route and collects radar beacon signal strength (RSSI), frequency stability, and signal-to-noise ratio (SNR) data in real time through its onboard RF spectrum analysis module.

[0077] Combine RTK-GPS (BeiDou) to record the precise location (latitude, longitude, and altitude) and flight timestamp of the UAV, ensuring data spatiotemporal alignment. (System time synchronization can be achieved using PTP precision clock synchronization or GPS time synchronization).

[0078] Step 2: Propagation loss compensation.

[0079] Based on the free space path loss model (FSPL) and actual environmental correction factors (such as sea surface reflection and atmospheric attenuation), the signal strength is compensated and the influence of distance on RSSI is eliminated.

[0080] The expression for compensation calculation is: P 校正 =P 接收 +20log10(d)+K 环境 ; Where d is the distance between the UAV and the radar beacon, and K 环境This is an environmental correction factor (e.g., +3dB for wet sea surfaces).

[0081] Step 3: Dynamic modeling of signal coverage.

[0082] The Kriging interpolation algorithm is used to interpolate discrete UAV sampling point data into a continuous spatial signal distribution.

[0083] Generate a signal strength heatmap using a Geographic Information System (GIS) (see reference) Figure 3 The color gradient represents the coverage intensity (e.g., red for strong signal, blue for weak signal).

[0084] Step 4: Coverage boundary calibration.

[0085] Define an effective coverage threshold (based on a combination of base noise and receiver sensitivity, such as RSSI≥-90dBm), extract the boundary of the qualified area in the heat map, and generate a polygon of the effective detection range of the radar beacon.

[0086] Output key parameters such as coverage radius and blind spot location.

[0087] 2.2.3 Multi-sensor fusion fault diagnosis engine.

[0088] By combining radar, RF, and visual data, determine whether the radar beacon is malfunctioning (e.g., no signal, frequency shift, antenna damage).

[0089] The technical solution is as follows: Step 1: Multi-source data synchronization.

[0090] Time alignment: Align radar echoes, RF spectrum, and visual inspection data using UTC timestamps.

[0091] Spatial alignment: Based on the UAV's GPS coordinates, sensor data is mapped to the same radar beacon device coordinate system.

[0092] Step 2: Fault feature extraction.

[0093] 1) Detection of radar echo anomalies.

[0094] If Morse code decoding fails or the signal is lost, it is judged as "no signal fault".

[0095] 2) RF spectrum analysis.

[0096] If the transmission frequency is detected to be off (e.g., exceeding the standard range of 9300-9500MHz), it is determined to be a "frequency drift fault".

[0097] When the signal strength is below a threshold (e.g., <-100dBm), it is marked as "signal attenuation fault".

[0098] 3) Visual inspection.

[0099] AI image analysis identifies physical damage (such as rust or breakage) and obstructions (such as bird nests or snow) to radar beacon antennas, classifying them as "antenna physical faults".

[0100] Step 3: Multimodal decision fusion.

[0101] Using Dempster-Shafer (DS) evidence theory or Bayesian networks, the failure probabilities of radar, RF, and vision are combined to output the final failure type and confidence level.

[0102] Example: If the radar has no signal (confidence level 80%) and visual detection shows that the antenna is damaged (confidence level 90%), then it is determined to be an "antenna physical failure".

[0103] Step 4: Output the diagnostic results.

[0104] Generate structured fault reports, including fault type, location, time, and repair recommendations (such as "replace antenna" or "adjust transmission frequency").

[0105] Alarm information is pushed to the maritime administration department through a cloud platform.

[0106] 2.2.4 Cloud management platform.

[0107] It receives data transmitted back from drones in real time and generates radar beacon health status reports.

[0108] It supports historical data comparison and predicts radar beacon maintenance cycles.

[0109] 2.3 System Workflow Example (Refer to) Figure 4 ).

[0110] Step 1: Frequency band initialization and signal transmission.

[0111] After the UAV arrives at the target area, the main control unit configures the transceiver parameters according to the preset radar beacon frequency band (such as X-band 9340MHz), setting the transmission power to 1W and the pulse repetition frequency to 1kHz.

[0112] The microstrip antenna array radiates a detection signal, triggering a radar beacon response.

[0113] Step 2: Signal reception and processing.

[0114] The receiving unit captures the radar beacon echo signal, which is then amplified and mixed by an LNA to output the baseband I / Q signal.

[0115] FPGA performs real-time Morse code parsing. If the decoding result is a preset identifier (such as "A"), If decoding fails, the signal is determined to be normal; if decoding fails, the RF module is triggered to perform a secondary frequency band scan.

[0116] Step 3: Multi-source data fusion.

[0117] The RSSI and frequency stability data output by the transceiver are synchronized with the AI ​​visual inspection results (antenna physical state) to the fault diagnosis engine, and the comprehensive fault probability is calculated through DS evidence theory.

[0118] (3) This embodiment has the following advantages and effects compared with the prior art.

[0119] 1. This paper proposes a radar beacon detection scheme that combines UAVs and multimodal sensors for the first time, which solves the problem of low efficiency in traditional manual and ship patrols.

[0120] 2. The miniaturized radar + RF spectrum analysis fusion technology enables UAVs to have professional-grade radar beacon signal detection capabilities.

[0121] 3. AI-driven fault diagnosis algorithms enable automatic assessment of radar beacon status and transform subjective evaluations into objective standard data indicators, reducing misjudgments.

[0122] 4. Dynamic signal coverage modeling enables modeling from discrete sampling points to continuous signal coverage, providing intuitive output of coverage radius and blind spots. This fills the gap in traditional detection methods, which "can only measure single-point signals and cannot assess overall coverage," and provides accurate data support for maritime safety.

[0123] 5. Improve patrol efficiency: A single flight can detect multiple radar beacons, which is 4-5 times faster than manual patrols plus ships.

[0124] 6. Reduce maintenance costs: Reduce manpower and ship time at sea, and cover more radar beacon inspection plans with less cost.

[0125] 7. Enhance maritime safety: A more effective and comprehensive understanding of radar beacon status can further improve the availability of radar beacon equipment and enhance the support effectiveness of navigation equipment and facilities.

[0126] 8. Compared with CN114217279A, a portable radar transponder tester and test method, the innovations of this embodiment are mainly reflected in the following aspects: (1) Innovation in detection methods and platforms.

[0127] Mobile drone detection platform: Unlike the portable ground testing instrument in CN114217279A, this embodiment uses a drone (UAV) as a mobile detection carrier, which can cover a wide sea area and realize rapid inspection of multiple radar beacon devices. It is especially suitable for harsh sea conditions or remote areas, significantly improving detection efficiency (multiple radar beacons can be detected in a single flight, with an efficiency 4-5 times higher than that of manual vessels).

[0128] In comparison, CN114217279A requires manual testing with equipment at close range (0.5-2 meters), which is limited by geographical environment and operating range.

[0129] Dynamic signal coverage analysis: By collecting signal strength (RSSI) and GPS coordinates in real time through the drone's flight trajectory, and combining this with the Kriging interpolation algorithm to generate a signal coverage heatmap, the effective response range and blind spots of the radar beacon can be intuitively displayed.

[0130] In comparison, CN114217279A can only perform static testing of single-point signal parameters and cannot evaluate overall coverage performance.

[0131] (2) Multi-sensor fusion and intelligent analysis.

[0132] Multimodal sensing integration: It integrates miniaturized X / S band radar, RF spectrum analysis module, AI visual inspection and RTK-GPS to achieve multi-dimensional detection such as radar beacon signal decoding, physical status inspection and precise positioning.

[0133] In comparison, the CN114217279A relies on a single RF transceiver unit and can only test basic parameters such as signal frequency, power, and Morse code.

[0134] AI-driven fault diagnosis: By employing DS evidence theory or Bayesian networks to fuse radar, RF, and visual data, fault type determination (such as antenna damage or frequency shift) and confidence calculation can be achieved, reducing human error.

[0135] In comparison, CN114217279A judges sensitivity or frequency response through simple thresholds and lacks the ability to conduct collaborative analysis of multi-source data.

[0136] (3) Innovation in algorithms and data processing.

[0137] Adaptive signal decoding technology: A dynamic impulse detection algorithm based on the Teager-Kaiser Energy Operator (TKEO) and OS-CFAR is proposed, which is combined with improved wavelet denoising (e.g., the wavelet denoising decomposition layer can be designed to be 5) to improve the decoding accuracy of Morse code.

[0138] In comparison, CN114217279A obtains Morse code through envelope demodulation, without involving complex noise suppression or dynamic threshold optimization.

[0139] Real-time propagation loss compensation model: Free space path loss (FSPL) and environmental correction factors (such as sea surface reflection) are introduced to dynamically compensate signal strength data and ensure the accuracy of coverage analysis.

[0140] In comparison, CN114217279A does not involve signal propagation environment modeling.

[0141] (4) System functional scalability.

[0142] Cloud management platform: It supports real-time data transmission, historical comparison analysis, and maintenance cycle prediction, forming a closed-loop management system.

[0143] In comparison, CN114217279A only provides local test results and lacks cloud data integration or long-term tracking capabilities.

[0144] Multi-device compatibility potential: The system design can be extended to the detection of other maritime navigation aids (such as AIS base stations), while CN114217279A is specifically designed for radar transponder testing.

[0145] (5) Application scenarios and cost advantages.

[0146] High-efficiency and low-cost inspection: The drone solution reduces the frequency of manual sea patrols and lowers maintenance costs; CN114217279A still requires manual on-site operation and cannot replace ship patrols.

[0147] Adaptability to harsh environments: Unmanned aerial vehicles (UAVs) can perform missions in high sea states, while CN114217279A relies on human operation in a safe environment.

[0148] The specific implementation method will be described below.

[0149] Example 1: Complete process of UAV inspection of radar beacon operation status.

[0150] Step 1: System initialization and route planning.

[0151] By inputting the coordinates of the target radar beacon (e.g., longitude 123.45°E, latitude 32.10°N) into the cloud management platform, the UAV automatically generates the optimal patrol route according to the predetermined detection rules, planning the route, setting the radius of the spiral route, and the density of sampling points to avoid blind spots. The flight altitude is generally set to 50-100 meters according to the actual ship and radar beacon settings, and the UAV patrols within a range of 0.1-30km from the radar beacon.

[0152] Airborne system self-test: Check whether the radar (X / S band), RF spectrum analysis module (frequency band 9300-9500MHz), high-definition camera (20 million pixels), RTK-GPS, Beidou positioning, and timing status are normal.

[0153] Step 2: Signal detection and data acquisition.

[0154] 1. Triggered by radar signal.

[0155] The drone flies to a distance of 3km from the radar beacon, and its onboard radar emits a detection signal (X-band, 9.34GHz) to receive the Morse code echo from the radar beacon (e.g., the identification code "A"). ).

[0156] 2. RF spectrum analysis.

[0157] The RF module monitors the radar beacon's transmission frequency (e.g., 9340MHz) in real time and records the signal strength (e.g., RSSI=-85dBm and SNR=15dB).

[0158] 3. Visual inspection.

[0159] The camera captures high-definition images of the radar beacon antenna at a 30° downward angle, and the AI ​​algorithm detects the antenna's physical condition (such as no rust or obstructions).

[0160] 4. Location synchronization.

[0161] RTK-GPS records the current drone coordinates (123.44°E, 32.09°N) and timestamp (UTC10:00:00).

[0162] Step 3: Data processing and fault diagnosis.

[0163] 1. Radar echo decoding.

[0164] Signal preprocessing: Noise is filtered out by Hamming window FIR filter (center frequency 9340MHz, bandwidth 200Hz), and wavelet denoising improves the signal-to-noise ratio to 20dB.

[0165] Morse code decoding: Identifying the echo as "·" (The letter A) matches the preset identifier, indicating that the signal is normal.

[0166] 2. RF anomaly detection.

[0167] The frequency detection value is 9340MHz (standard range 9300-9500MHz), the signal strength is -85dBm (≥-90dBm threshold), and it is determined that there is no frequency shift or attenuation.

[0168] 3. Visual analysis.

[0169] AI identified that the antenna image was undamaged (95% confidence level) and unobstructed (98% confidence level).

[0170] Step 4: Upload results and issue an alarm.

[0171] After receiving the data, the cloud platform generates a report. If a fault is detected (such as a frequency offset to 9480MHz), the platform triggers an alarm to the backend (or the maritime management center).

[0172] Example 2: Radar beacon signal coverage modeling and heat map generation.

[0173] Step 1: Multi-angle data acquisition.

[0174] The UAV flies along a spiral path centered on the radar beacon (radius 0.1-30km, altitude 100m), collecting RF signal strength (RSSI) and GPS coordinates once.

[0175] Example data points are shown in Table 1: Table 1

[0176] Step 2: Propagation loss compensation.

[0177] Applying the Free Space Path Loss (FSPL) model to compensate for sea surface reflection (correction factor +3dB): P-correction = P-received + 20log10(d) + 3dB.

[0178] Example: The measured value at 20km is -95dBm, and after compensation it is -95+26+3=-66dBm.

[0179] Step 3: Heatmap generation.

[0180] The Kriging interpolation algorithm is used to convert discrete data into a continuous signal distribution, and a heat map is rendered using a GIS platform. Figure 3 The red area (RSSI≥-80dBm) represents the effective coverage area, while the blue area (RSSI≤-100dBm) represents the blind zone.

[0181] Output coverage radius: 25km (with RSSI=-90dBm as the threshold).

[0182] Step 4: Coverage anomaly analysis.

[0183] Compare with historical data (e.g., the coverage radius was 28km last month). If the current radius shrinks by 10%, it is marked as "signal attenuation warning". It is recommended to check the radar beacon signal transmission power.

[0184] Example 3: Fault diagnosis of multi-sensor fusion.

[0185] Scenario: Comprehensive diagnosis of radar beacon signal loss.

[0186] 1. Data synchronization.

[0187] Radar: Detected Morse code decoding failure at 10:05:00 (confidence level 85%).

[0188] RF module: No signal detected at 10:05:00 (90% confidence level).

[0189] Visual: 10:05:02 Antenna breakage detected (confidence level 95%).

[0190] 2. Fault fusion judgment.

[0191] Calculate the joint probability using DS evidence theory: Antenna physical failure probability = radar (85%) × vision (95%) ≈ 81%.

[0192] Frequency offset probability = RF (90%) × radar (85%) ≈ 76%.

[0193] Final determination: Antenna physical failure (highest probability), confidence level 81%.

[0194] 3. Maintenance suggestions are generated.

[0195] The report is as follows: Fault type: Antenna physical damage (breakage).

[0196] Location: Radar beacon-002 (123.50°E, 32.15°N).

[0197] Recommendation: Replace the antenna immediately. Estimated repair time: 2 hours.

[0198] Reference Figure 5 This application also provides a UAV-based radar beacon status inspection device, which can implement the above-described UAV-based radar beacon status inspection method. The device includes: The signal preprocessing unit is used to preprocess radar echo signals; A signal decoding unit is used to decode the preprocessed radar echo signal; The spectrum analysis unit is used to synchronously monitor radar beacon signals through the radio frequency spectrum analysis module, and to collect the signal strength, frequency and signal-to-noise ratio of radar beacon signals in real time. An image detection unit is used to acquire image data of radar beacons using an AI vision detection unit. The data alignment unit is used to perform spatiotemporal alignment of the decoded radar echo signal, the spectrum analyzed by the radio frequency spectrum analysis module, and the image data according to the positioning information and timestamp to obtain spatiotemporal data. The fault diagnosis unit is used to perform fault diagnosis on the radar beacon based on the spatiotemporal data using the fault diagnosis engine.

[0199] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0200] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method of this application. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0201] It is understood that the content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the methods of this application, and the beneficial effects achieved are the same as those achieved by the methods of this application.

[0202] Please see Figure 6 , Figure 6 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 601 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 602 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 602 and is called and executed by the processor 601. The input / output interface 603 is used to implement information input and output; The communication interface 604 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 605 transmits information between various components of the device (e.g., processor 601, memory 602, input / output interface 603, and communication interface 604); The processor 601, memory 602, input / output interface 603, and communication interface 604 are connected to each other within the device via bus 605.

[0203] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of this application.

[0204] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0205] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0206] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0207] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0208] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0209] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0210] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0211] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0212] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0213] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0214] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0215] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0216] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0217] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A radar beacon status inspection system based on unmanned aerial vehicles (UAVs), characterized in that, The system includes: a drone, a dual-band radar transceiver, a radio frequency spectrum analysis module, an AI visual inspection unit, a positioning module using RTK-GPS and BeiDou, a signal processing module, and a cloud management platform; The drone is used to carry the dual-band radar transceiver, the radio frequency spectrum analysis module, the AI ​​visual detection unit, and the positioning module to the target area. The dual-band radar transceiver is used to transmit a detection signal in a preset frequency band to the radar beacon in the target area, triggering the radar beacon to operate, and simultaneously receiving radar beacon signals. The signal processing module is used to preprocess and decode the radar echo signal; The radio frequency spectrum analysis module is used to synchronously monitor the radar beacon signal and collect the signal strength, frequency and signal-to-noise ratio of the radar beacon signal in real time. The AI ​​visual detection unit is used to acquire image data of the radar beacon and detect the appearance of the radar beacon and its surrounding environment; The positioning module is used to acquire positioning information; The cloud management platform is used to generate a health status report for the radar beacon, trigger fault alarms, or generate maintenance suggestions based on the data transmitted back from the drone, the dual-band radar transceiver, the radio frequency spectrum analysis module, the AI ​​visual inspection unit, the positioning module, and the signal processing module.

2. The radar beacon status inspection system based on unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, The dual-band radar transceiver includes a transmitting unit, a receiving unit, and the signal processing module; The transmitting unit is used for: The dual-band signal generation specifically includes: adopting a software-defined radio architecture, integrating X-band and S-band dual-channel voltage-controlled oscillator and phase-locked loop, dynamic frequency band switching, and frequency resolution ≤1 MHz; The output power is adjustable, specifically including: a gallium nitride power amplifier with a dynamic range of output power from 10 mW to 2 W based on existing size and weight limitations, while adapting to different detection distances through a digitally controlled attenuator to meet test requirements. The receiving unit includes a duplex filter bank and a low-noise amplifier; The duplex filter bank is used to achieve X / S band signal separation, with insertion loss <1.5 dB and out-of-band rejection >40 dB; The low-noise amplifier has a noise figure of <1.5 dB, a gain of >20 dB, and supports full-band signal amplification. The receiving unit is used for zero-IF downconversion, specifically including: directly converting the received signal into a baseband I / Q signal through a mirror rejection mixer to reduce the complexity of the intermediate frequency circuit; The signal processing module is used for: Adaptive filtering and sampling specifically include: using a variable bandwidth FIR filter to dynamically suppress out-of-band noise, combined with a dual-channel 14-bit ADC to digitize the signal; Real-time pulse decoding specifically includes: an FPGA-based symbol classification algorithm to parse the Morse code in the radar echo signal, supporting dynamic threshold detection and noise suppression.

3. A method for radar beacon status inspection based on unmanned aerial vehicles (UAVs), characterized in that, The method is applied to a UAV-based radar beacon status inspection system as described in claim 1, and the method includes the following steps: Preprocess the radar echo signal; The preprocessed radar echo signal is decoded; The radar beacon signal is monitored synchronously through the radio frequency spectrum analysis module, and the signal strength, frequency and signal-to-noise ratio of the radar beacon signal are collected in real time. Image data of radar beacons is acquired using an AI visual inspection unit; Based on the positioning information and timestamp, the decoded radar echo signal, the spectrum obtained by the radio frequency spectrum analysis module and the image data are spatiotemporally aligned, and spatiotemporal data is obtained based on the timestamp and spatial coordinates obtained by clock calibration and trusted RTK system. The fault diagnosis engine is used to perform fault assessment and diagnosis on various indicators of the radar beacon based on the spatiotemporal data.

4. The method for radar beacon status inspection based on unmanned aerial vehicles (UAVs) according to claim 3, characterized in that, The preprocessing of the radar echo signal includes the following steps: A variable bandwidth finite impulse response filter is used to bandpass filter the radar echo signal, and the center frequency dynamically tracks the nominal frequency of the radar beacon. The bandwidth of the variable bandwidth finite impulse response filter is set to a multiple of the code rate according to the code rate of the radar beacon; The radar echo signal is subjected to wavelet filtering based on an improved wavelet threshold denoising algorithm. The pulse characteristics of the radar echo signal are enhanced by applying the Tiger Kaiser energy operator to generate a signal energy envelope; An ordered statistical constant false alarm rate algorithm is adopted to dynamically set the detection threshold based on the background noise of the radar echo signal, thereby filtering the background noise.

5. The method for radar beacon status inspection based on unmanned aerial vehicles (UAVs) according to claim 3, characterized in that, Decoding the preprocessed radar echo signal includes the following steps: The radar echo signal after preprocessing is used to distinguish between short pulses, long pulses, and intervals based on the pulse duration. The short pulses and the long pulses are combined into corresponding letters or numbers according to the Morse code standard.

6. The method for radar beacon status inspection based on unmanned aerial vehicles (UAVs) according to claim 3, characterized in that, The method of using a fault diagnosis engine to diagnose faults in the radar beacon based on the spatiotemporal data includes the following steps: Extracting fault features from the spatiotemporal data specifically includes: If the radar echo signal decoding fails or the signal is lost, the extracted feature is no signal fault; The detection signal is checked to see if the transmission frequency offset exceeds the standard range. If so, the feature is extracted as a frequency drift fault. Detect whether the signal strength of the probe signal is lower than a standard threshold; if so, extract the feature as a signal attenuation fault. AI image analysis is performed on the image data to identify whether the radar beacon has physical damage or obstructions; if so, the feature is extracted as an antenna physical fault. The fault diagnosis engine employs DS evidence theory or Bayesian network to output the fault type and confidence level of the radar beacon based on each fault characteristic.

7. A method for radar beacon status inspection based on unmanned aerial vehicles (UAVs) according to any one of claims 3 to 6, characterized in that, The method further includes the following steps: A heatmap of the effective detection range of the radar beacon is drawn based on the flight trajectory of the UAV, specifically including: The drone flies along the preset flight path, and the signal strength, frequency stability and signal-to-noise ratio of the radar beacon are dynamically collected by the airborne radio frequency spectrum analysis module. The location and flight timestamp of the drone are recorded using a positioning module. Based on the free space path loss model and the actual environment correction factor, the signal strength of the radar beacon is compensated. The expression for the compensation calculation is: P 校正 =P 接收 +20log10(d)+K 环境 ; Where d is the distance between the UAV and the radar beacon, and K 环境 This is an environmental correction factor; The Kriging interpolation algorithm is used to interpolate discrete UAV sampling point data into a continuous spatial signal distribution; A signal strength heatmap is generated by combining geographic information systems, with color gradients representing coverage intensity. Define an effective coverage threshold, extract the boundary of the qualified area in the heat map, and generate the polygon of the effective detection range of the radar beacon; Output the coverage radius and blind zone location of the effective detection range polygon.

8. A radar beacon status inspection device based on unmanned aerial vehicles (UAVs), characterized in that, The device is applied to a UAV-based radar beacon status inspection system as described in claim 1, the device comprising: The signal preprocessing unit is used to preprocess radar echo signals; A signal decoding unit is used to decode the preprocessed radar echo signal; The spectrum analysis unit is used to synchronously monitor radar beacon signals through the radio frequency spectrum analysis module and to collect the signal strength, frequency and signal-to-noise ratio of the radar beacon signals in real time. An image detection unit is used to acquire image data of radar beacons using an AI vision detection unit. The data alignment unit is used to perform spatiotemporal alignment of the decoded radar echo signal, the spectrum analyzed by the radio frequency spectrum analysis module, and the image data according to the positioning information and timestamp to obtain spatiotemporal data. The fault diagnosis unit is used to perform fault diagnosis on the radar beacon based on the spatiotemporal data using the fault diagnosis engine.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 3 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 3 to 7.

Images