AI visual identification runway light state real-time calibration and fault early warning system

Abstract

The invention relates to the technical field of computer vision, and discloses an AI visual identification runway light state real-time calibration and fault early warning system, which comprises an image acquisition module arranged at the periphery of a runway and used for acquiring image information of runway light regularly or in real time, and the image information comprises brightness, color, position, morphological characteristics and the like of the light; the communication module is connected with the image acquisition module and is used for transmitting the acquired image information to the data processing module; and the data processing module is connected with the communication module and used for receiving the image information. A plurality of night-vision and high-resolution cameras are arranged on the periphery of a runway, and multi-dimensional image information such as brightness, color, position and form of lamplight is collected in an omnibearing and multi-angle mode. Advanced AI visual recognition algorithms such as a convolutional neural network trained by a large amount of labeled data, a deep learning algorithm and the like are used for analysis and recognition, and the runway light state monitoring accuracy is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and in particular to a real-time calibration and fault warning system for runway lighting status based on AI visual recognition. Background Art

[0002] In the aviation industry, the importance of runway lighting systems, as key facilities for ensuring safe aircraft takeoff and landing, is self-evident. Existing runway lighting systems typically consist of a series of lights, including edge lights, entrance lights, and end lights. These lights illuminate the runway to provide pilots with information such as the runway's location, outline, and other guidance. This helps pilots accurately assess runway conditions in varying weather conditions and time periods, ensuring safe takeoff and landing.

[0003] Currently, monitoring runway lighting status primarily relies on manual inspections and traditional sensor technologies. Manual inspections have significant limitations. They consume significant manpower and material resources and are subject to numerous factors, including subjective factors, weather conditions, and inspection intervals. This makes it difficult to detect lighting anomalies promptly and accurately. For example, in inclement weather or at night, the efficiency and accuracy of manual inspections are significantly reduced, leading to lighting failures not being detected and addressed promptly, posing a safety hazard to aircraft takeoff and landing.

[0004] While traditional sensor monitoring technology can achieve real-time monitoring of lighting conditions to a certain extent, these sensors typically only monitor limited parameters, such as current and voltage, and cannot fully and accurately reflect the actual lighting conditions, including multi-dimensional information such as brightness, color, position, and shape. Furthermore, the sensors themselves can be affected by environmental factors, leading to failures or measurement errors, which in turn affect the reliability of monitoring results. Furthermore, most existing monitoring systems lack effective fault warning and calibration capabilities. Even if they can detect lighting anomalies, they can often only issue an alarm after the failure occurs, failing to predict and prevent them in advance. Furthermore, it is difficult to accurately calibrate the lighting conditions in real time to ensure that the lighting always meets standard requirements.

[0005] To this end, those skilled in the art have proposed an AI visual recognition runway lighting status real-time calibration and fault warning system to solve the above problems. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the present invention provides an AI visual recognition runway lighting status real-time calibration and fault warning system, which solves the problems raised in the above background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a real-time calibration and fault warning system for runway lighting status based on AI visual recognition, comprising:

[0008] An image acquisition module is provided around the runway to collect image information of the runway lights in a scheduled or real-time manner, including the brightness, color, position, and morphological characteristics of the lights;

[0009] A communication module is connected to the image acquisition module and is used to transmit the acquired image information to the data processing module;

[0010] The data processing module is connected to the communication module and is used to receive image information and use the preset AI visual recognition algorithm to analyze and identify the status of the runway lights to determine whether the lights are working properly and whether there are any potential faults;

[0011] The calibration control module is connected to the data processing module. Based on the analysis results of the data processing module, it calibrates and adjusts the brightness, color and other parameters of the runway lights in real time to ensure that the lighting status meets the preset standards.

[0012] The fault warning module is connected to the data processing module. When the data processing module determines that the runway lights are faulty or at risk of failure, the fault warning module promptly issues a warning message to remind maintenance personnel to handle the problem.

[0013] The storage module is connected to the data processing module and is used to store historical image information collected by the image acquisition module and analysis results of the data processing module, so as to facilitate subsequent query and analysis of the change trend of the runway lighting status.

[0014] Preferably, the image acquisition module includes multiple cameras, which are respectively arranged at different positions and angles of the runway to achieve all-round and multi-angle coverage of the runway lights, ensuring that the collected image information fully and accurately reflects the actual status of the runway lights, and the cameras have night vision function and high resolution, and can clearly capture the details of the light image under different lighting conditions.

[0015] Preferably, the AI ​​visual recognition algorithm includes a convolutional neural network, a deep learning algorithm, etc., which is trained and learned on a large amount of labeled normal and faulty runway lighting image data so as to automatically and accurately identify various status characteristics of the runway lights and determine whether they are normal.

[0016] Preferably, the calibration control module is connected to the drive circuit of the runway lights, and accurate calibration control of the brightness and color of the runway lights is achieved by adjusting parameters such as current and voltage in the drive circuit.

[0017] Preferably, the fault warning module includes a sound alarm unit and a light alarm unit. When a fault occurs, the sound alarm unit emits an alarm sound and the light alarm unit flashes a warning light of a specific color to attract the attention of maintenance personnel. The fault warning module can also send warning information to a remote monitoring center through a communication module. The remote monitoring center can simultaneously receive lighting fault warning information of multiple runways and display and manage it centrally.

[0018] Preferably, a feedback adjustment module is further included, which is connected to the data processing module and the calibration control module respectively, and performs real-time feedback adjustment on the calibration parameters and strategies of the calibration control module based on the re-analysis results of the calibrated runway lighting status by the data processing module.

[0019] Preferably, the communication module adopts a combination of wired communication and wireless communication. The wired communication methods include optical fiber communication, Ethernet communication, etc., which are used to ensure stable and high-speed transmission of large amounts of data between modules within the system. The wireless communication methods include 4G, 5G, etc., which are used to send early warning information to the remote monitoring center and the mobile terminals of relevant maintenance personnel in a timely manner, and to receive instructions and parameter update information issued by the remote monitoring center.

[0020] Preferably, the storage module is also connected to the data processing module and the fault warning module, and can perform in-depth mining and analysis of the stored historical data based on preset data analysis models and algorithms, generate trend prediction reports and maintenance recommendations for the runway lighting status, and provide a scientific basis for the daily maintenance and management of the lights. The trend prediction report includes information such as the time, location, and type of possible lighting failures, and the maintenance recommendations include specific content such as repair methods and replacement cycles for different types of failures.

[0021] Preferably, a remote monitoring module is further included, which is connected to the data processing module and the fault warning module through the communication module. Maintenance personnel can view the current status information, historical data, warning information and system operation status of the runway lights in real time through the remote monitoring module, and can remotely set and adjust the parameters of the calibration control module, thereby realizing remote monitoring and management of the runway lighting system and improving maintenance efficiency and management level.

[0022] The present invention provides a real-time runway lighting status calibration and fault warning system based on AI visual recognition. It has the following beneficial effects:

[0023] 1. This invention deploys multiple high-resolution night vision cameras around the runway to capture multidimensional image information, including brightness, color, position, and shape, from all angles. This information is analyzed and identified using advanced AI visual recognition algorithms, such as convolutional neural networks and deep learning algorithms trained on extensively labeled data. This multi-angle, multi-dimensional image acquisition approach, combined with high-precision AI algorithms, significantly improves the accuracy of runway lighting status monitoring compared to traditional single-angle, limited-parameter monitoring. The system also collects and analyzes data in real time, providing reliable and timely data support for subsequent calibration and fault warnings.

[0024] 2. The system of the present invention utilizes a calibration control module connected to the runway lighting driver circuit. Based on the results of the data processing module, it adjusts the current and voltage to achieve precise calibration of brightness and color. A feedback adjustment module connects the data processing and calibration control modules and adjusts calibration parameters in real time based on the analysis of the calibrated lighting status. This closed-loop mechanism ensures that the lighting always meets standards. The fault warning module includes a local audio and visual alarm unit and also utilizes a communication module to transmit warning information to a remote monitoring center, which can receive and centrally manage multi-runway warnings. These designs enable refined calibration and comprehensive intelligent fault warning, effectively preventing aviation safety accidents and improving maintenance efficiency and quality.

[0025] 3. The system designed in this invention incorporates a storage module connected to the data processing and fault warning modules. This module deeply mines historical data to generate trend predictions and maintenance recommendations, facilitating proactive preventive maintenance. The remote monitoring module enables maintenance personnel to view status in real time and manage the system remotely. These features collectively enable proactive and precise maintenance of runway lighting, optimizing processes, reducing costs, and improving management. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is the overall workflow diagram of the present invention;

[0027] Figure 2 This is a fault warning flow chart of the present invention;

[0028] Figure 3 This is a flow chart of the calibration control and feedback adjustment of the present invention. DETAILED DESCRIPTION

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. 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.

[0030] Example 1

[0031] Please see the attached Figure 1-Attached Figure 3 The embodiment of the present invention provides a real-time calibration and fault warning system for runway lighting status based on AI visual recognition, including:

[0032] The image acquisition module is set up around the runway and is used to collect image information of the runway lights in a scheduled or real-time manner. The image information includes the brightness, color, position and morphological characteristics of the lights. The image acquisition module includes multiple cameras, which are set at different positions and angles of the runway to achieve all-round and multi-angle coverage of the runway lights, ensuring that the collected image information fully and accurately reflects the actual status of the runway lights. The cameras have night vision function and high resolution, and can clearly capture the details of the light images under different lighting conditions.

[0033] Specifically, the image acquisition module is a key component of the system. It consists of multiple cameras positioned at various locations and angles around the runway. This all-encompassing, multi-angle layout ensures comprehensive coverage of the runway lights, accurately capturing information such as their brightness, color, position, and morphological characteristics. The cameras, equipped with night vision and high resolution, can clearly capture detailed images of the lights in all lighting conditions. This ensures image quality, day or night, even in inclement weather, providing a reliable data foundation for subsequent analysis and processing.

[0034] The communication module is connected to the image acquisition module and is used to transmit the collected image information to the data processing module. The communication module adopts a combination of wired communication and wireless communication methods. The wired communication methods include optical fiber communication, Ethernet communication, etc., which are used to ensure the stable and high-speed transmission of large amounts of data between modules within the system. The wireless communication methods include 4G, 5G, etc., which are used to send early warning information to the remote monitoring center and the mobile terminals of relevant maintenance personnel in a timely manner, and to receive instructions and parameter update information issued by the remote monitoring center.

[0035] The data processing module is connected to the communication module and is used to receive image information and use a preset AI visual recognition algorithm to analyze and identify the status of the runway lights to determine whether the lights are working properly and whether there are any potential faults. The AI ​​visual recognition algorithm includes convolutional neural networks, deep learning algorithms, etc., and is trained and learned from a large amount of labeled runway light normal and faulty image data to automatically and accurately identify the various status characteristics of the runway lights and determine whether they are normal.

[0036] Specifically, the communication module is responsible for data transmission between the image acquisition module and the data processing module. It combines wired and wireless communication methods. Wired communication includes fiber optic communication and Ethernet communication, ensuring stable and high-speed transmission of large amounts of data between modules within the system, meeting real-time and accuracy requirements. Wireless communication uses 4G, 5G and other technologies, mainly used to promptly send early warning information to the remote monitoring center and the mobile terminals of relevant maintenance personnel, while receiving instructions and parameter update information issued by the remote monitoring center, realizing two-way information flow and ensuring efficient operation and timely response of the system.

[0037] The calibration control module is connected to the data processing module. Based on the analysis results of the data processing module, it calibrates and adjusts the brightness, color and other parameters of the runway lights in real time to ensure that the lighting status meets the preset standards. The calibration control module is connected to the drive circuit of the runway lights. By adjusting the current, voltage and other parameters in the drive circuit, it achieves precise calibration control of the brightness and color of the runway lights.

[0038] Specifically, when the data processing module determines that the runway lighting brightness or color is deviating, the calibration control module responds quickly, adjusting parameters such as the current and voltage in the driver circuit in real time to restore the lighting to standard conditions. For example, if the light brightness is insufficient, the module increases the current in the driver circuit to boost brightness. If the light color shifts, the module adjusts parameters such as voltage to restore the color to its normal range. This ensures that pilots receive accurate visual guidance, playing an irreplaceable and critical role in maintaining the stable operation of the runway lighting system and preventing aviation accidents.

[0039] The fault warning module is connected to the data processing module. When the data processing module determines that the runway lights have failed or there is a risk of failure, the fault warning module will promptly issue a warning message to remind maintenance personnel to handle the problem. The fault warning module includes a sound alarm unit and a light alarm unit. When a fault occurs, the sound alarm unit will sound an alarm and the light alarm unit will flash a warning light of a specific color to attract the attention of maintenance personnel. The fault warning module can also send the warning information to the remote monitoring center through the communication module. The remote monitoring center can simultaneously receive light fault warning information from multiple runways and display and manage it centrally.

[0040] Specifically, the module includes an audible alarm unit and a light alarm unit. When a fault occurs, the audible alarm unit emits a distinct siren sound, while the light alarm unit flashes a specific color warning light. These warning signals are designed to attract the attention of maintenance personnel, allowing them to quickly recognize the problem. Furthermore, the fault warning module also features information transmission. It transmits warning information to a remote monitoring center via a communication module. This allows the remote monitoring center to simultaneously receive lighting fault warning information from multiple runways and centrally display and manage this information. This helps maintenance personnel gain a comprehensive understanding of the status of each runway's lighting, enabling efficient and unified management and maintenance, ensuring the reliable operation of the runway lighting system and reducing the risk of aviation safety accidents.

[0041] The storage module is connected to the data processing module and is used to store historical image information collected by the image acquisition module and analysis results of the data processing module, so as to facilitate subsequent query and analysis of the change trend of the runway lighting status.

[0042] It also includes a feedback adjustment module, which is connected to the data processing module and the calibration control module respectively. According to the re-analysis results of the runway lighting status after calibration by the data processing module, the calibration parameters and strategies of the calibration control module are adjusted in real time.

[0043] The storage module is also connected to the data processing module and the fault warning module. It can conduct in-depth mining and analysis of the stored historical data based on preset data analysis models and algorithms, and generate trend prediction reports and maintenance recommendations for the runway lighting status, providing a scientific basis for the daily maintenance and management of the lights. The trend prediction report includes information such as the time, location, and type of possible lighting failures. The maintenance recommendations include specific content such as repair methods and replacement cycles for different types of failures.

[0044] It also includes a remote monitoring module, which is connected to the data processing module and the fault warning module through the communication module. Maintenance personnel can use the remote monitoring module to view the current status information, historical data, warning information and system operation status of the runway lights in real time, and can remotely set and adjust the parameters of the calibration control module, thereby realizing remote monitoring and management of the runway lighting system and improving maintenance efficiency and management level.

[0045] Specifically, maintenance personnel, using the remote monitoring module, can access various runway lighting information in real time, regardless of geographic location. Specifically, they can access current runway lighting status information at any time, accurately understanding the real-time status of parameters such as brightness and color; view historical data to trace changes in lighting status and analyze operational trends; obtain early warning information to promptly understand the details of lighting failures or potential risks; and fully understand the system's operating status, including the working status of each module. Real-time access to this information provides maintenance personnel with comprehensive and timely decision-making. Furthermore, the remote monitoring module enables maintenance personnel to remotely control the calibration control module parameters. Through the remote monitoring module, they can precisely set and flexibly adjust calibration control module parameters based on actual conditions. This feature not only reduces the frequency of on-site visits for maintenance personnel, saving time and labor costs, but also improves the timeliness and accuracy of system calibration, ensuring that the runway lighting is always in optimal working condition.

[0046] This AI visual recognition runway lighting status real-time calibration and fault warning system is designed to address the shortcomings of traditional runway lighting monitoring methods. The image acquisition module collects runway lighting image information in all directions and from multiple angles, and transmits it to the data processing module through the communication module. The data processing module uses advanced AI visual recognition algorithms to accurately determine the lighting status, and then the calibration control module realizes real-time calibration of parameters such as light brightness and color. The fault warning module can issue a warning in time before a fault occurs. In addition, the system is also equipped with a storage module for data storage and analysis. The following uses Examples 2, 3, and 4 to specifically explain the application and advantages of this system in different practical scenarios from the perspectives of different module configurations, function expansion, technical details, etc.

[0047] Example 2

[0048] Image acquisition module: Multiple high-resolution cameras with night vision capabilities are installed at different locations and angles around the runway. For example, one camera is installed at regular intervals on both sides of the runway, and one camera is installed at each end of the runway to ensure all-round and multi-angle coverage of the runway lights.

[0049] Communication module: Using optical fiber communication in wired communication mode, the image acquisition module is connected to the data processing module to ensure stable and high-speed transmission of image data.

[0050] Data Processing Module: Utilizing pre-configured AI visual recognition algorithms, such as convolutional neural networks and deep learning algorithms, the collected runway light images are analyzed and identified. These algorithms, trained on a large amount of labeled images of normal and faulty runway lights, can automatically and accurately identify the various status characteristics of runway lights and determine whether they are functioning properly.

[0051] Calibration control module: Connected to the drive circuit of the runway lights, when the data processing module determines that the lights need to be calibrated, it adjusts the current, voltage and other parameters in the drive circuit to achieve precise calibration control of the brightness and color of the runway lights to meet the preset standards.

[0052] The Fault Warning Module includes an audible alarm unit and a light alarm unit. When the data processing module determines that a runway lighting failure or a risk of failure exists, the audible alarm unit sounds an alarm and the light alarm unit flashes a specific color warning light. Simultaneously, the Fault Warning Module transmits warning information to a remote monitoring center via the communication module. The center can simultaneously receive warning information for multiple runway lighting failures and centrally display and manage it.

[0053] Storage module: used to store historical image information collected by the image acquisition module and analysis results of the data processing module, so as to facilitate subsequent query and analysis of the changing trend of the runway lighting status.

[0054] Example 3

[0055] Image acquisition module: Multiple cameras with infrared night vision capabilities and high resolution are installed at key locations at the start, middle, end, and both sides of the runway to ensure that light image details can be clearly captured even at night or in low-light conditions.

[0056] Communication module: Combining Ethernet communication in wired communication mode and 4G communication in wireless communication mode, wired communication is used for stable transmission of large amounts of data between modules within the system, while wireless communication is used to send early warning information to the remote monitoring center and the mobile terminals of relevant maintenance personnel in a timely manner, as well as to receive instructions and parameter update information issued by the remote monitoring center.

[0057] Data processing module: In addition to using common AI visual recognition algorithms, data fusion technology is also introduced to fuse image information collected by multiple cameras to improve the accuracy and reliability of runway lighting status judgment.

[0058] Calibration Control Module: Connected to the runway lighting driver circuit, a feedback adjustment module is added. Based on the data processing module's reanalysis of the calibrated runway lighting status, this module provides real-time feedback to adjust the calibration control module's calibration parameters and strategies, ensuring the lighting always meets standards.

[0059] Fault warning module: In addition to local sound and light alarms, it also has intelligent analysis functions, which can send warning information in different levels according to the severity and urgency of the fault, such as prompt information for minor faults and emergency alarm information for serious faults.

[0060] Storage module: It not only stores historical image information and analysis results, but also conducts in-depth mining and analysis of stored historical data based on preset data analysis models and algorithms, generating trend forecast reports and maintenance recommendations for runway lighting status, providing a scientific basis for daily maintenance and management of the lights.

[0061] Example 4

[0062] Image acquisition module: Use cameras with a wide dynamic range and high frame rate and install them at different positions and angles on the runway to adapt to changes in runway lighting under different weather conditions and light intensities, ensuring that the collected image information can accurately reflect the actual status of the lighting.

[0063] Communication module: Using 5G wireless communication and taking advantage of its high speed and low latency, it can achieve fast and real-time data transmission between the image acquisition module and the data processing module. It also facilitates the timely push of early warning information to the remote monitoring center and the maintenance personnel's mobile terminals.

[0064] Data Processing Module: Utilizing advanced deep learning algorithms, such as generative adversarial networks, the collected runway lighting images are enhanced to further improve image quality and recognition accuracy. Furthermore, combined with big data analytics, large amounts of historical and real-time data are analyzed to uncover potential lighting failure patterns and trends.

[0065] Calibration control module: Through precise current and voltage regulation technology, it can achieve high-precision calibration control of runway lighting brightness and color, and can automatically complete the lighting calibration work without affecting the normal takeoff and landing of aircraft.

[0066] Fault warning module: Integrates multiple warning methods. In addition to local sound and light alarms, it can also send warning information to maintenance personnel via SMS, email, etc., and can include detailed information such as the specific location, type and severity of the fault in the warning information, so that maintenance personnel can respond and handle it quickly.

[0067] Storage module: Using a distributed storage architecture, large amounts of image data and analysis results are stored on multiple storage nodes to improve data reliability and security. At the same time, data mining and machine learning are used.

[0068] Table 1 below provides a quantitative comparison of the operating performance of the AI ​​visual recognition runway lighting status real-time calibration and fault warning system under three different implementations.

[0069]

[0070] Table 1

[0071] Conclusion: From the table data we can see that:

[0072] In terms of the accuracy of lighting status monitoring, after using this system in the three embodiments, the monitoring accuracy increased from 70%, 65%, and 72% to 95%, 92%, and 96%, respectively, with an average increase of approximately 24-26 percentage points, indicating that this system can greatly improve the monitoring accuracy of runway lighting status and reduce misjudgments and missed judgments.

[0073] The improvement in calibration accuracy was 40%, 35%, and 45% in Example 1, Example 2, and Example 3, respectively. This indicates that after the system uses the calibration control module to perform real-time calibration and adjustment of parameters such as the brightness and color of the runway lights, the calibration accuracy of the lighting status has been greatly improved, and it can more accurately ensure that the lights meet the preset standards.

[0074] In terms of fault warning advance time, the three embodiments achieved fault warnings at an average advance of 10 minutes, 8 minutes, and 12 minutes, respectively. Compared with before the use of this system, it can reserve more sufficient time for maintenance personnel to conduct fault investigation and processing, effectively preventing the occurrence of aviation safety accidents.

[0075] Regarding the improvement in operational stability, after using this system, the failure rates of the three embodiments were reduced by 30%, 25%, and 35%, respectively. This reflects that the synergistic effect of the system's real-time monitoring, calibration, and fault warning functions has significantly enhanced the operational stability of the runway lighting system and reduced the frequency of failures.

[0076] 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. AI visual recognition runway lighting status real-time calibration and fault warning system, characterized by: include: An image acquisition module is provided around the runway to collect image information of the runway lights in a scheduled or real-time manner, including the brightness, color, position, and morphological characteristics of the lights; A communication module is connected to the image acquisition module and is used to transmit the acquired image information to the data processing module; The data processing module is connected to the communication module and is used to receive image information and use the preset AI visual recognition algorithm to analyze and identify the status of the runway lights to determine whether the lights are working properly and whether there are any potential faults; The calibration control module is connected to the data processing module. Based on the analysis results of the data processing module, it calibrates and adjusts the brightness, color and other parameters of the runway lights in real time to ensure that the lighting status meets the preset standards. The fault warning module is connected to the data processing module. When the data processing module determines that the runway lights are faulty or at risk of failure, the fault warning module promptly issues a warning message to remind maintenance personnel to handle the problem. The storage module is connected to the data processing module and is used to store historical image information collected by the image acquisition module and analysis results of the data processing module, so as to facilitate subsequent query and analysis of the change trend of the runway lighting status.

2. The AI ​​visual recognition runway lighting status real-time calibration and fault warning system according to claim 1 is characterized in that: The image acquisition module includes multiple cameras, which are set at different positions and angles on the runway to achieve all-round, multi-angle coverage of the runway lights, ensuring that the collected image information fully and accurately reflects the actual status of the runway lights. The cameras have night vision capabilities and high resolution, and can clearly capture light image details under different lighting conditions.

3. The AI ​​visual recognition light state real-time calibration and fault warning system according to claim 1 is characterized in that: The AI ​​visual recognition algorithm includes convolutional neural networks, deep learning algorithms, etc., which are trained and learned from a large amount of labeled runway light normal and faulty image data to automatically and accurately identify the various status characteristics of runway lights and determine whether they are normal.

4. The AI ​​visual recognition runway lighting status real-time calibration and fault warning system according to claim 1 is characterized in that: The calibration control module is connected to the drive circuit of the runway lights, and achieves precise calibration control of the brightness and color of the runway lights by adjusting parameters such as current and voltage in the drive circuit.

5. The AI ​​visual recognition runway lighting status real-time calibration and fault warning system according to claim 1 is characterized in that: The fault warning module includes a sound alarm unit and a light alarm unit. When a fault occurs, the sound alarm unit sounds an alarm and the light alarm unit flashes a warning light of a specific color to attract the attention of maintenance personnel. The fault warning module can also send warning information to a remote monitoring center through a communication module. The remote monitoring center can simultaneously receive lighting fault warning information from multiple runways and centrally display and manage it.

6. The AI ​​visual recognition runway lighting status real-time calibration and fault warning system according to claim 1 is characterized in that: It also includes a feedback adjustment module, which is connected to the data processing module and the calibration control module respectively. According to the re-analysis result of the runway lighting status after calibration by the data processing module, the calibration parameters and strategies of the calibration control module are adjusted in real time.

7. The AI ​​visual recognition runway lighting status real-time calibration and fault warning system according to claim 1 is characterized in that: The communication module adopts a combination of wired communication and wireless communication methods. The wired communication methods include optical fiber communication, Ethernet communication, etc., which are used to ensure the stable and high-speed transmission of large amounts of data between modules within the system. The wireless communication methods include 4G, 5G, etc., which are used to send early warning information to the remote monitoring center and the mobile terminals of relevant maintenance personnel in a timely manner, and to receive instructions and parameter update information issued by the remote monitoring center.

8. The AI ​​visual recognition runway lighting status real-time calibration and fault warning system according to claim 1 is characterized in that: The storage module is also connected to the data processing module and the fault warning module. It can conduct in-depth mining and analysis of stored historical data based on preset data analysis models and algorithms, and generate trend prediction reports and maintenance recommendations for the runway lighting status, providing a scientific basis for the daily maintenance and management of the lights. The trend prediction report includes information such as the time, location, and type of possible lighting failures, and the maintenance recommendations include specific content such as repair methods and replacement cycles for different types of failures.

9. The AI ​​visual recognition runway lighting status real-time calibration and fault warning system according to claim 1 is characterized in that: It also includes a remote monitoring module, which is connected to the data processing module and the fault warning module through the communication module. Maintenance personnel can use the remote monitoring module to view the current status information, historical data, warning information, and system operation status of the runway lights in real time. They can also remotely set and adjust the parameters of the calibration control module, realizing remote monitoring and management of the runway lighting system, improving maintenance efficiency and management level.

Images