Intelligent monitoring method for state of single navigational light lamp

Abstract

The invention relates to the technical field of navigation-aid light monitoring, in particular to an intelligent monitoring method for the state of a single navigation-aid light lamp. The method comprises the following steps: acquiring basic information of all lighting equipment of an airport, and performing model construction according to the basic information of the lighting equipment to obtain a lighting equipment model; a light loop primary cable is used as a communication carrier, carrier communication parameters are set, it is ensured that digital signals can be transmitted at a high speed between a light equipment end and a preset monitoring end, and light equipment communication state data are generated; according to the unique identifier of the light equipment end and the communication state data of the light equipment, collecting real-time operation parameters of a single lamp through carrier communication to obtain state data of the single lamp; and according to the light equipment model, the light equipment communication state data and the single-lamp state data, performing single-lamp state intelligent analysis to obtain navigation-aid light single-lamp state data. According to the invention, the management efficiency and safety of the airport lighting equipment can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of navigation light monitoring, and in particular to a method for intelligently monitoring the state of a single navigation light. Background Art

[0002] The airport navigation lighting system is one of the core infrastructures in the field of aviation transportation. Its main function is to provide clear ground navigation guidance for aircraft to ensure that the aircraft can complete operations safely and accurately during takeoff, taxiing and landing. Especially at night or in bad weather conditions (such as dense fog, heavy rain or snow), the role of the navigation lighting system is particularly critical. It not only provides intuitive visual guidance for pilots, but also significantly improves the safety and efficiency of aviation ground transportation. With the rapid development of modern aviation industry, the scale of airports and the number of flights are constantly expanding, and the complexity and operation intensity of airport ground lighting systems are also increasing accordingly. Due to technical limitations, traditional navigation lighting systems have obvious deficiencies in real-time, accuracy and intelligence, and can no longer meet the current needs of airport management. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a method for intelligently monitoring the status of a single light of a navigation light, so as to solve at least one of the above technical problems.

[0004] The present application provides a method for intelligently monitoring the status of a single light of a navigation light, comprising the following steps: Step S1: Obtain basic information of all lighting equipment of the airport, and construct a model based on the basic information of the lighting equipment to obtain a lighting equipment model, wherein the basic information of the lighting equipment includes a unique identifier, geographical location, circuit number and function type of the lighting equipment; Step S2: using the primary cable of the lighting circuit as a communication carrier, setting carrier communication parameters, ensuring that the digital signal can be transmitted at high speed between the lighting device end and the preset monitoring end, and generating lighting device communication status data; Step S3: According to the unique identification of the lighting equipment end and the communication status data of the lighting equipment, the real-time operating parameters of the single lamp are collected through carrier communication to obtain the single lamp status data, wherein the single lamp status data includes current, voltage, luminous color and light intensity; Step S4: performing intelligent analysis of the status of a single light according to the lighting equipment model, the lighting equipment communication status data and the status data of a single light, and obtaining the status data of a single light of the navigation light.

[0005] In the present invention, by acquiring and integrating the basic information of lighting equipment (such as unique identification, geographical location, loop number and function type), a digital model of lighting equipment is constructed, so that the monitoring system can clearly understand the physical location and function of each lamp, avoiding management blind spots caused by incomplete or inaccurate equipment information. Through accurate communication status data collection, it can ensure that the data transmission between the lighting equipment and the monitoring end is always stable. Communication failures can be discovered in time through the real-time feedback mechanism, so that maintenance responses can be made in advance to avoid major failures. Through intelligent analysis methods, the system can automatically detect abnormal conditions of equipment and issue early warning signals. For example, if the light intensity or current value of the lighting equipment exceeds the normal range, the system will automatically remind maintenance personnel to check and repair, which not only reduces the downtime caused by equipment failure, but also avoids the high maintenance costs caused by sudden failures.

[0006] Preferably, step S1 specifically includes: Step S11: using the IoT-based sensor network to collect basic data from various lighting devices on the airport ground, including the unique device identifier, geographic location (GPS coordinates), loop number and function type, to obtain the original data of the lighting devices; Step S12: coordinate projection is performed on the original data of the lighting equipment to obtain the coordinate projection data of the lighting equipment; Step S13: classifying functional equipment according to the lighting equipment coordinate projection data to obtain lighting equipment functional classification data; Step S14: performing device position mapping according to the lighting device classification data to obtain lighting device position mapping data; Step S15: performing spatial analysis on the lighting equipment position mapping data to obtain lighting equipment spatial data; Step S16: Associating equipment attributes according to lighting equipment spatial data to obtain lighting equipment attribute assignment data; Step S17: Perform three-dimensional modeling and virtual reality integration according to the lighting equipment attribute assignment data to obtain a lighting equipment model.

[0007] In the present invention, basic data (equipment unique identification, geographic location, loop number and functional type) is collected from airport ground lighting equipment in real time through technology based on the Internet of Things sensor network. By coordinate projection of the original data and equipment functional classification and position mapping, the accurate spatial positioning of each lighting equipment is ensured. By functional classification of lighting equipment, the system can automatically identify the functional requirements of different types of lighting equipment and classify and manage them according to the functional type of the equipment. Through spatial analysis of the lighting equipment location mapping data, the layout effect of the equipment can be analyzed according to the actual geographical environment, and the distribution of the equipment can be optimized, thereby improving system efficiency and reducing redundant configuration. Through the integration of three-dimensional models and virtual reality, the system can provide real-time feedback on the operating status, fault information, maintenance requirements, etc. of the lighting equipment, greatly improving the intelligence and precision of equipment management.

[0008] Preferably, the coordinate projection is specifically: Performing local coordinate projection and global geographic coordinate projection on the original data of the lighting equipment to obtain first coordinate projection data and second coordinate projection data respectively; Obtain airport physical environment data; A coordinate accuracy environment adaptability model is constructed based on the airport physical environment data to obtain a coordinate environment adaptability model; Correcting the first coordinate projection data and the second coordinate projection data by using the coordinate environment adaptability model to obtain first coordinate projection corrected data and second coordinate projection corrected data; Performing coordinate projection accuracy error calculation on the first coordinate projection correction data and the second coordinate projection correction data to obtain coordinate projection accuracy error data; The first coordinate projection correction data and the second coordinate projection correction data are projected and fused according to the coordinate projection accuracy error data to obtain the lighting equipment coordinate projection data.

[0009] In the present invention, the original data of the lighting equipment is projected with local coordinates and global geographic coordinates to obtain the first and second coordinate projection data respectively, ensuring that high-precision positioning information can be obtained at different scales (such as local and global). Through this dual projection, it can be ensured that no matter where the equipment is located in the airport, the system can obtain accurate geographic location information. By obtaining the physical environment data of the airport, the coordinate projection errors in different areas can be corrected for environmental adaptability. The coordinate projection accuracy error calculation can evaluate and quantify the errors generated in the coordinate correction process and provide quantitative error data. By using the coordinate environmental adaptability model for correction and projection fusion, the system can automatically adjust the correction parameters of the coordinate data according to the actual environment, enhancing the adaptability and flexibility of the system.

[0010] Preferably, step S2 specifically includes: Step S21: using the primary cable of the lighting circuit as a communication carrier, determining a carrier frequency range suitable for lighting equipment communication, and obtaining carrier frequency planning data; Step S22: performing signal modulation according to the carrier frequency planning data to obtain modulated signal data; Step S23: performing signal transmission setting according to the modulated signal data to obtain signal transmission setting data; Step S24: performing carrier signal synchronization according to the signal transmission setting data to obtain carrier synchronization deviation data; Step S25: performing signal demodulation according to the carrier synchronization deviation data to obtain signal demodulation data; Step S26: Perform signal quality detection based on the signal demodulation data to obtain lighting equipment communication status data.

[0011] In the present invention, by accurately planning the carrier frequency suitable for lighting equipment communication, interference with other equipment signals can be avoided and the signal transmission efficiency can be maximized. By synchronizing the carrier signal, the signal synchronization between different lighting equipment can be ensured to avoid signal misalignment or loss. The generation of carrier synchronization deviation data can monitor the signal deviation in real time and make timely corrections, thereby effectively reducing signal interference. After signal demodulation, signal quality detection is performed, and by monitoring and analyzing the noise, bit error rate, etc. during the transmission process, the transmission parameters can be timely identified and adjusted, further enhancing the system's anti-interference ability and the accuracy of information.

[0012] Preferably, step S3 specifically includes: Step S31: according to the unique identification of the lighting device and the communication status data of the lighting device, a request signal is sent through a preset monitoring terminal, requiring all lighting devices to feedback the current real-time operation status data according to their unique identification; Step S32: Control the lighting device end to receive the request signal, and transmit the current operating parameters of the device to the preset monitoring end through the carrier signal to obtain the original lighting operating data; Step S33: decoding the received signal at the monitoring end, and extracting the real-time operating parameters of the lighting equipment from it to obtain the lighting operation decoding data; Step S34: performing single lamp status identification according to the light operation decoding data to obtain single lamp status data, wherein the single lamp status data includes current, voltage, luminous color and light intensity.

[0013] In the present invention, a request signal is sent out through the monitoring end, and all lighting equipment is required to feedback the real-time operating status according to its unique identification, which can ensure that the system can obtain the operating parameters of each lighting equipment in real time, avoid the lag caused by the traditional periodic collection method, and improve the timeliness of the data. By identifying the status of a single lamp based on the lighting operation decoding data, the system can accurately identify the status of each lamp's current, voltage, light intensity and other parameters, and generate single lamp status data. The acquired real-time operating data of the lighting equipment can be automatically diagnosed through subsequent intelligent analysis algorithms, and potential equipment failures or performance degradations can be discovered in advance, so as to avoid sudden failures affecting work efficiency and reduce manual inspection costs.

[0014] Preferably, step S4 is specifically: Step S41: performing data association according to the lighting equipment model, the lighting equipment communication status data and the single lamp status data to obtain lighting-related multi-dimensional data; Step S42: extracting operation stability characteristics and electrical imbalance characteristics according to the light-related multi-dimensional data, and obtaining light operation stability characteristic data and electrical imbalance characteristic data respectively; Step S43: Perform intelligent status evaluation based on the light operation stability characteristic data and the electrical imbalance characteristic data to obtain single light status data of the navigation light.

[0015] The associated lighting equipment data in the present invention not only includes basic electrical parameters, but also involves multi-dimensional information such as geographic location, equipment status, historical performance, etc., so that the system can have a deeper insight into the equipment operation status and conduct multi-dimensional and multi-level analysis. By extracting the lighting operation stability characteristics and electrical imbalance characteristics based on the lighting-associated multi-dimensional data, the system can comprehensively evaluate the working status of each lighting equipment, including key parameters such as the equipment's operating stability, electrical load, and environmental factors, which helps to gain a deeper understanding of the reliability and performance of the equipment's operation. By performing intelligent analysis on the lighting operation stability and electrical imbalance characteristics, the system can automatically identify potential faults or abnormalities of the equipment. Based on the lighting equipment's operating stability characteristics and electrical imbalance characteristics, the possibility of a fault and its specific location can be accurately identified, thereby improving the accuracy of equipment maintenance.

[0016] Preferably, the operation stability feature extraction is specifically: Perform sliding average calculation based on multi-dimensional data associated with lighting to obtain segmented characteristic data of lighting operation; Performing frequency domain feature extraction on the segmented feature data of the lighting operation to obtain first frequency domain feature data of the lighting operation; Performing generalized autoregressive conditional heteroscedasticity on the frequency domain characteristic data of the first light operation to obtain the first light operation stability characteristic data; Perform correlation analysis based on the multi-dimensional data associated with lighting to obtain preliminary feature correlation data; Perform canonical correlation analysis on the preliminary feature correlation data to obtain secondary feature correlation data; Extract features from the light-related multidimensional data according to the secondary feature correlation data to obtain light-related feature data; Perform frequency domain feature extraction based on the light-related feature data to obtain second light operation frequency domain feature data; Performing anomaly detection based on the frequency domain characteristic data of the second light operation to obtain the second light operation stability characteristic data; The first lighting operation stability characteristic data and the second lighting operation stability characteristic data are integrated to obtain the lighting operation stability characteristic data.

[0017] In the present invention, by performing sliding average calculation according to the multi-dimensional data associated with the light (step S4.1), the segmented feature extraction of the light operation state is performed, which not only helps to remove noise, but also can refine the time series data, so that the trend change of the device operation state can be captured more smoothly. Frequency domain feature extraction enables the system to evaluate the operation state of the device from different angles, especially in identifying periodic fluctuations, frequent current and voltage changes, and device oscillations. It can capture the nonlinear characteristics and risks of fluctuations in the operation of the device, especially the impact of high-frequency fluctuations. The introduction of the model enhances the understanding of the stability of the device operation, and can identify the nonlinear behavior and electrical instability of the lighting device under high load or abnormal conditions, thereby improving the ability to predict the health status of the device. By analyzing the correlation between features, it helps to dig out important factors affecting the stability of the device. Through preliminary feature correlation analysis, redundant features that contribute little to the analysis or are irrelevant to the target can be effectively eliminated, thereby simplifying the complexity of subsequent analysis. For example, if the correlation between current and voltage is extremely high, a feature that has a greater impact on the target can be selected. Canonical correlation analysis (CCA) is a high-order statistical analysis method used to mine complex nonlinear relationships between multiple groups of variables. In the multi-dimensional data of lighting, different features have a synergistic impact on the status of lighting equipment. Canonical correlation analysis can transform the joint relationship of multiple variables into the relationship between simple canonical variables, and extract the most explanatory variable combination. Preliminary correlation analysis is often based on simple linear relationships in a single dimension, while canonical correlation analysis can capture the joint relationship between multiple dimensions. For example, voltage, current, and light intensity jointly reflect the electrical imbalance characteristics of the equipment. Canonical correlation analysis can extract this implicit relationship and provide more representative input features for intelligent analysis. The processing of the second lighting operation frequency domain feature data enables the system to automatically identify abnormal fluctuations in equipment operation. Combining the first lighting operation stability feature data with the second lighting operation stability feature data, the equipment status can be evaluated from multiple dimensions and levels.

[0018] Preferably, the electrical imbalance feature extraction is specifically as follows: Perform simple electrical anomaly detection based on the multi-dimensional data associated with lighting to obtain preliminary electrical anomaly data; Perform high-dimensional feature extraction on the preliminary electrical anomaly data to obtain electrical high-dimensional anomaly feature data; Perform isolation forest recognition on the electrical high-dimensional anomaly feature data to obtain secondary electrical anomaly data; Perform instantaneous imbalance ratio on the secondary electrical abnormality data to obtain imbalance ratio data; Asymmetric quantification is performed on the secondary electrical anomaly data to obtain electrical anomaly asymmetric data; According to the imbalance ratio data and the electrical abnormality asymmetry data, a multi-dimensional graph is constructed for the lighting-related multi-dimensional data to obtain lighting abnormality-related graph data; Perform graph convolution calculation based on the lighting anomaly correlation graph data to obtain the electrical imbalance fluctuation characteristic data; Graph attention calculation is performed on the electrical imbalance fluctuation characteristic data to obtain the electrical imbalance characteristic data.

[0019] The present invention uses simple electrical anomaly detection to quickly identify potential electrical anomalies in lighting equipment, can effectively filter out noise data, and reduce the complexity of subsequent analysis. By extracting high-dimensional features from preliminary electrical anomaly data, it is possible to capture patterns of electrical changes from multiple dimensions, including key electrical features such as current and voltage fluctuations, thereby improving the accuracy of anomaly detection. The isolation forest algorithm can automatically identify secondary electrical anomalies that do not conform to normal operating modes. This method is particularly suitable for processing large-scale and diversified equipment data, can effectively discover equipment anomalies that are not easily detected, improve the accuracy of electrical anomaly identification, and avoid missed reports and false reports. By calculating the instantaneous imbalance ratio of secondary electrical anomaly data, the degree of electrical imbalance of the equipment can be accurately quantified. Asymmetric quantification of secondary electrical anomaly data can capture subtle differences in electrical imbalance, especially for the voltage and current asymmetry phenomenon of the equipment. By constructing a graph of the multidimensional data of the lighting equipment through the imbalance ratio data and the electrical anomaly asymmetry data, the system can establish a multidimensional graph based on the electrical correlation between different devices. Through this graph construction, the system can further enhance its ability to analyze electrical imbalance, especially in complex equipment environments. Graph construction enables the system to identify the correlation and influence between devices, providing a more comprehensive analysis perspective. By performing graph convolution calculations on the light anomaly association graph data, the electrical mutual influence and fluctuation characteristics between devices can be efficiently captured. Graph convolution enables the system to capture the spatiotemporal characteristics of electrical imbalance in a multi-dimensional graph structure, thereby providing a more accurate device status assessment. Graph attention calculations are performed on electrical imbalance fluctuation feature data to further optimize the calculation process of electrical imbalance features. By paying attention to the importance of different nodes (devices), the graph attention mechanism can adaptively adjust the weight of each node in the graph, focusing on devices that have a greater impact on anomalies, thereby improving the sensitivity of the system's anomaly detection and status assessment.

[0020] Preferably, the multi-dimensional graph is constructed as follows: The feature space is constructed according to the imbalance ratio data and the electrical abnormal asymmetry data to obtain the abnormal feature space data; Construct a device relationship diagram based on the multi-dimensional data related to lighting, and obtain lighting relationship diagram data; The edge relationship of the light association graph data is adjusted according to the abnormal feature space data to obtain the light abnormality association graph data.

[0021] In the present invention, by integrating the imbalance ratio data and the electrical abnormal asymmetry data in the feature space for construction, the details and patterns of electrical imbalance can be captured more comprehensively. The multidimensionality of the feature space data enables the graph structure to not only consider the spatial position relationship of the equipment, but also add the spatiotemporal variation characteristics of the electrical imbalance, thereby improving the recognition accuracy of electrical anomalies, especially in a multi-device and complex environment, and better identifying the hidden anomalies between devices. According to the associated multidimensional data of the lighting equipment, the equipment relationship graph (lighting association graph data) is constructed. The graph construction can clearly express the electrical dependency relationship between the equipment. In a large-scale and complex lighting equipment network, the graph structure can effectively present the information such as electrical interaction and mutual dependence between the equipment. By adjusting the edge relationship of the graph according to the abnormal feature space data, the electrical changes between the equipment can be dynamically reflected. By combining the abnormal feature space and the equipment relationship graph, the spatiotemporal characteristics of the electrical anomaly can be captured simultaneously in the multidimensional space of the equipment network. The system can identify the spatial distribution and time evolution of electrical imbalance fluctuations in real time, thereby improving the recognition ability of electrical abnormal fluctuations. Through graph construction and edge relationship adjustment, the system can not only model the direct electrical relationship between devices, but also form a multi-level relationship structure in the graph according to the intensity and nature of electrical anomalies. The system can analyze electrical imbalances at different levels, thereby identifying deep-seated anomaly sources and indirect impacts between devices.

[0022] Preferably, the asymmetric quantization is specifically: Obtain historical equipment electrical data; Deviation measurement is performed based on historical equipment electrical data and secondary electrical abnormality data to obtain electrical deviation data; Asymmetry is defined based on electrical deviation data to obtain electrical abnormal asymmetry measurement data; Extract the electrical fluctuation range based on the historical equipment electrical data to obtain the electrical fluctuation range data; Perform clustering calculation based on secondary electrical anomaly data and historical equipment electrical data to obtain historical electrical anomaly clustering data; The electrical property fluctuation range data is thresholded according to the historical electrical property anomaly clustering data to obtain electrical property threshold data; The electrical abnormality asymmetry measurement data is quantified at multiple levels according to the electrical threshold data to obtain the electrical abnormality asymmetry data.

[0023] In the present invention, by comparing the historical equipment electrical data with the secondary electrical anomaly data, the electrical deviation can be accurately quantified. Extracting the electrical fluctuation range from the historical equipment electrical data can help the system identify the electrical fluctuation range of the equipment during normal operation. By clustering the historical electrical anomalies, different modes and types of electrical anomalies can be identified. Based on these clustering data, the system can set corresponding electrical thresholds for each device or device group to adapt to the electrical characteristics of different devices. By performing multi-level quantization on the electrical anomaly asymmetry measurement data, the degree of electrical imbalance can be expressed more delicately, especially the imbalance in extreme cases. Through multi-level quantization, subtle changes in electrical anomalies can be captured, especially when the equipment load changes are small or the electrical fluctuation amplitude is low, the electrical imbalance can be detected more sensitively, thereby improving the sensitivity of anomaly detection. Through the electrical anomaly data after multi-level quantization, the system can discover the potential trend of electrical imbalance earlier, providing a more accurate basis for equipment early warning and fault maintenance.

[0024] The beneficial effects of the present invention are as follows: by obtaining the unique identification, geographic location (GPS coordinates), loop number and function type of the lighting equipment, and constructing a lighting equipment model based on this information, the standardization and digital management of the equipment status is achieved. The primary cable of the lighting loop is used as a communication carrier, combined with precise carrier communication parameter configuration, to ensure that the digital signal can be transmitted at high speed between the lighting equipment end and the preset monitoring end. By collecting the real-time operating parameters of a single lamp (including current, voltage, luminous color, light intensity, etc.) through carrier communication, the operating status of each lighting device can be accurately monitored and equipment data in multiple dimensions can be obtained. Combining the lighting equipment model, communication status data and single lamp status data, the operating status of the lighting equipment is evaluated in real time through an intelligent analysis method, which can effectively identify the operating abnormalities of the equipment, determine whether the equipment is in a healthy state, and predict future faults based on historical data and current status. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting implementations made with reference to the following drawings: Figure 1 A flowchart showing a method for intelligently monitoring the state of a single light of a navigation light according to an embodiment is shown; Figure 2 A flowchart showing a method for constructing a lighting equipment model according to an embodiment of the present invention is provided; Figure 3 A flowchart showing the steps of a method for acquiring the communication status of a lighting device according to an embodiment is shown; Figure 4 A flowchart showing a method for collecting data on a single lamp status according to an embodiment is shown; Figure 5 A flowchart of the steps of a single lamp status intelligent analysis method according to an embodiment is shown. DETAILED DESCRIPTION

[0026] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0028] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0029] Using the IoT sensor network, basic information is collected from various lighting equipment on the airport ground. The information includes the unique identification (such as ID) of the lighting equipment, geographic location (GPS coordinates), loop number and functional type (such as runway lights, navigation lights, etc.). The basic information of a lighting equipment is such as unique identification: ID_001, geographic location: GPS coordinates (38.8810° N, 77.0316° W), loop number: LC_01, functional type: runway light. Based on these basic data, a lighting equipment model is constructed. The model is a virtual digital twin that records the operating parameters, physical characteristics and performance of each lighting equipment. The equipment model contains information such as the spatial distribution of lighting equipment, historical operating data, functional requirements, etc., and obtains the lighting equipment model (for example, the equipment model of ID_001).

[0030] Determine the carrier frequency range suitable for lighting equipment communication, such as selecting 2MHz as the carrier frequency range. According to the set carrier frequency, QAM is used for signal modulation to generate modulated signal data. Through synchronization technology, the signal synchronization between devices is ensured, and carrier synchronization deviation data is generated, and the synchronization error is 0.01 ms. After signal demodulation, the communication status data of the lighting equipment is generated through error detection and signal quality detection algorithms. The signal demodulation result is error-free and the signal strength is 100%, and the communication status data of the lighting equipment is obtained.

[0031] A request signal is sent through the preset monitoring terminal, requesting the lighting device to return real-time operating parameters. Each device feedbacks the current status according to its unique identification (such as ID_001). The lighting device returns the operating parameters (current, voltage, luminous color, light intensity) through the carrier signal. These parameters are decoded and extracted at the monitoring terminal. The received lighting operating data is current: 5.2A, voltage: 230 V, luminous color: white, light intensity: 85%, and the single lamp status data is obtained: current, voltage, luminous color, light intensity.

[0032] According to the lighting equipment model, lighting equipment communication status data and single lamp status data, a multidimensional data set of lighting equipment is constructed. The lighting equipment multidimensional data set is such as current: 5.2 A, voltage: 230 V, luminous color: white, light intensity: 85%. According to the fluctuation of current and light intensity, the lighting equipment is judged whether it is stable. The extracted current change range is ±0.2 A, and the light intensity change is ±5%. The operating stability characteristics are current fluctuation rate = ±0.2 A, and light intensity fluctuation rate = ±5%. By calculating the relationship between current, voltage and light intensity, the electrical imbalance characteristics are extracted. For example, the electrical imbalance threshold is an imbalance when the voltage deviation is greater than ±10V. Voltage deviation: 0V (within the normal range), electrical imbalance characteristic data: no electrical imbalance. According to the extracted operating stability and electrical imbalance characteristics, an intelligent status evaluation is performed to output the lighting equipment status. Status evaluation result: normal.

[0033] There is a lighting device ID_001 at a certain airport. The real-time data collected is as follows: current: 5.2 A, voltage: 230V, luminous color: white, light intensity: 85%. According to the electrical anomaly detection, the voltage deviation is ±5V, which is within the normal range. The current fluctuation is ±0.2 A, and the light intensity fluctuation is ±5%, both of which are within the normal fluctuation range. After feature extraction and intelligent analysis, the system evaluates the lighting equipment status as "normal" and there is no electrical imbalance. The system found that the current, voltage and other parameters did not fluctuate significantly, and there was no electrical imbalance in the lighting equipment during operation. The operating status is stable, and the light intensity remains within the standard range.

[0034] See also Figures 1 to 5The present application provides a method for intelligently monitoring the state of a single light of a navigation light, comprising the following steps: Step S1: Obtain basic information of all lighting equipment of the airport, and construct a model based on the basic information of the lighting equipment to obtain a lighting equipment model, wherein the basic information of the lighting equipment includes a unique identifier, geographical location, circuit number and function type of the lighting equipment; Specifically, first extract the basic information of all lighting equipment from the airport equipment management system. This basic information includes the unique identification (ID) of the lighting equipment, the geographical location (GPS coordinates or relative position coordinates), the loop number (used to distinguish the circuit loop to which the lighting equipment belongs), and the functional type (such as runway lights, taxiway lights, etc.). Using the above data, build a lighting equipment model based on a tree or graph data structure. Specifically, define nodes, each lighting equipment is a node, and the node contains the basic information of the lighting equipment. Define the connection relationship, and connect the lighting equipment nodes belonging to the same loop according to the loop number to form a hierarchical relationship diagram.

[0035] Step S2: using the primary cable of the lighting circuit as a communication carrier, setting carrier communication parameters, ensuring that the digital signal can be transmitted at high speed between the lighting device end and the preset monitoring end, and generating lighting device communication status data; Specifically, the primary cable of the lighting circuit is selected as the communication carrier. The primary cable transmits power signals and digital signals at the same time. Ensure that the carrier does not affect the power supply of the lighting equipment. Set key communication parameters, including the carrier frequency. Generally, a frequency band that avoids interference from the power frequency (50Hz) and its harmonics is selected, such as 90kHz to 490kHz. Modulation mode, using a coding method (such as ASK modulation) to map digital signals to high and low levels. Signal bandwidth, determined according to the data transmission rate requirements, for example, the bandwidth corresponding to 100bps can be set to 20kHz. Add a synchronization header before the digital signal to ensure that the data frame can be correctly aligned when the signal is received. Add a CRC checksum to ensure data integrity.

[0036] Step S3: According to the unique identification of the lighting equipment end and the communication status data of the lighting equipment, the real-time operating parameters of the single lamp are collected through carrier communication to obtain the single lamp status data, wherein the single lamp status data includes current, voltage, luminous color and light intensity; Specifically, carrier communication is used to transmit the unique identification of the lighting device (such as the ID number). During each communication process, the device ID is first sent to confirm its address to ensure that the data matches the target device. The real-time parameters of a single lamp are measured and collected based on the device ID, including detection by Hall sensor and measurement by voltage divider circuit. Photoelectric sensor detection is used to match the detected light wavelength with the color mapping table, and the light intensity is calculated by the resistance change of the photoresistor.

[0037] Step S4: performing intelligent analysis of the status of a single light according to the lighting equipment model, the lighting equipment communication status data and the status data of a single light, and obtaining the status data of a single light of the navigation light.

[0038] Specifically, the status of a single lamp is judged according to the set thresholds and rules: the current and voltage abnormalities are judged as normal values ​​within the threshold range, and values ​​that do not meet the threshold range are abnormal. The minimum light intensity threshold is set. If the light intensity is less than the minimum light intensity threshold, it is judged as aging or failure of the light source. The abnormal light color is detected by whether the wavelength is within the preset range.

[0039] Preferably, step S1 specifically includes: Step S11: using the IoT-based sensor network to collect basic data from various lighting devices on the airport ground, including the unique device identifier, geographic location (GPS coordinates), loop number and function type, to obtain the original data of the lighting devices; Specifically, through the IoT sensor network, the lighting equipment sensor nodes deployed on the airport ground collect basic information about the equipment, including the equipment unique identification (ID): a unique code for each lighting equipment, automatically uploaded by the sensor. Geographic location: GPS sensor obtains the longitude and latitude coordinates of the equipment. Loop number: obtains the circuit number of the equipment from the equipment control loop sensor. Function type: uses the internal identification of the equipment to resolve the functional classification, such as runway lights, taxiway lights, etc.

[0040] Step S12: coordinate projection is performed on the original data of the lighting equipment to obtain the coordinate projection data of the lighting equipment; Specifically, the Gauss projection formula is used to convert the GPS longitude and latitude of the lighting equipment into plane rectangular coordinates.

[0041] Step S13: classifying functional equipment according to the lighting equipment coordinate projection data to obtain lighting equipment functional classification data; Specifically, according to the function type field, the lighting equipment is classified by function to form a functional group. The classification rule is based on logical conditions: if the function type is "runway light", it is classified into the runway light group. If the function type is "taxiway light", it is classified into the taxiway light group.

[0042] Step S14: performing device position mapping according to the lighting device classification data to obtain lighting device position mapping data; Specifically, based on the coordinate projection data, a spatial indexing algorithm is used to construct a geographical location mapping table for lighting equipment. The indexing algorithm steps are as follows: Use a quadtree structure to divide the spatial area into hierarchical grids. Recursively insert the (x, y) coordinates of the equipment into the corresponding nodes of the quadtree. Construct a mapping table to record the corresponding relationship between each node and the equipment.

[0043] Step S15: performing spatial analysis on the lighting equipment position mapping data to obtain lighting equipment spatial data; Specifically, the location mapping data is analyzed for proximity, and the nearest neighbor distance of each lighting device is calculated. At the same time, the layout characteristics of the lighting devices are determined based on the spatial relationship, such as whether the devices in the group meet the uniformity of spacing and the spatial distribution characteristics between different groups.

[0044] Step S16: performing device attribute association according to the lighting device spatial data to obtain lighting device attribute assignment data; Specifically, more attribute information (such as maintenance cycle and light intensity standard value) is obtained by associating the device ID with the airport database.

[0045] Step S17: Perform three-dimensional modeling and virtual reality integration according to the lighting equipment attribute assignment data to obtain a lighting equipment model.

[0046] Specifically, use 3D modeling tools to merge device spatial data and attribute assignment data to generate a 3D model. Define the geometric features of lighting equipment (such as lamp post height and light source size). Set the 3D coordinates (x, y, z) of each device according to the position mapping data. Import the 3D model into the virtual reality engine and integrate texture and interactive functions.

[0047] Preferably, the coordinate projection is specifically: Performing local coordinate projection and global geographic coordinate projection on the original data of the lighting equipment to obtain first coordinate projection data and second coordinate projection data respectively; Specifically, the original data of lighting equipment is collected, which includes the geographical location of the equipment (GPS coordinates) and other necessary equipment information. For the location data of each device, two coordinate projections are first performed, the local coordinate projection, which converts the geographical location of the device into the local coordinate system of the airport. The airport will have a local coordinate system, which is suitable for the precise positioning of the entire airport area. Through this projection, the location information of the lighting equipment can be accurately connected with other facilities and areas in the airport. At the same time, the geographical location data of the lighting equipment is converted into a global standard coordinate system (such as WGS84), which is suitable for global positioning to ensure the global compatibility of the equipment location information. Through this projection, the geographical location of the equipment can be identified and shared globally. The result of this process is two sets of projection data, the first coordinate projection data (local coordinate projection) and the second coordinate projection data (global geographic coordinate projection).

[0048] Obtain airport physical environment data; Specifically, after completing the preliminary projection of the lighting equipment position, the physical environment data of the airport is obtained, including terrain data such as the airport ground flatness, elevation and other information; meteorological data such as wind speed, temperature, humidity and other factors; building data such as the height and position of surrounding buildings.

[0049] A coordinate accuracy environment adaptability model is constructed based on the airport physical environment data to obtain a coordinate environment adaptability model; Specifically, a coordinate accuracy environmental adaptability model is constructed based on the physical environment data of the airport. The model takes into account the impact of environmental factors on the accuracy of the coordinate system. For example, buildings can cause multipath effects on GPS signals, and meteorological conditions (such as rain and snow) can affect the transmission stability of satellite signals. The model analyzes these environmental factors and corrects the accuracy of the projection data. The construction of this model is mainly based on historical data and real-time monitoring data to form an adaptive correction mechanism that can adapt to environmental changes.

[0050] Correcting the first coordinate projection data and the second coordinate projection data by using the coordinate environment adaptability model to obtain first coordinate projection corrected data and second coordinate projection corrected data; Specifically, once the adaptive model is built, it is applied to the first coordinate projection data (local coordinates) and the second coordinate projection data (global coordinates) obtained previously. The model analyzes the impact of physical environmental factors on the coordinate data and corrects the two projection data separately. The corrected data will be more accurate and can eliminate coordinate errors caused by environmental factors. For example, in some areas, GPS signal reception is unstable due to building obstruction. After correction by this model, the accuracy of the coordinate data can be improved.

[0051] Performing coordinate projection accuracy error calculation on the first coordinate projection correction data and the second coordinate projection correction data to obtain coordinate projection accuracy error data; Specifically, coordinate projection accuracy error calculation is performed on the corrected first coordinate projection data and the second coordinate projection data. The goal of this step is to evaluate the accuracy and reliability of the corrected coordinate projection. By comparing the original data with the corrected data, the error value is calculated. For example, the projection error can be obtained by comparing the difference between the corrected data and the existing precise reference coordinate system. The error data provides a reference for projection fusion.

[0052] The first coordinate projection correction data and the second coordinate projection correction data are projected and fused according to the coordinate projection accuracy error data to obtain the lighting equipment coordinate projection data.

[0053] Specifically, according to the obtained coordinate projection accuracy error data, the corrected first coordinate projection data (local coordinates) and the second coordinate projection data (global coordinates) are projected and fused. The purpose of projection fusion is to combine the advantages of the two projection data to obtain a more accurate and reliable coordinate data. The local coordinates provide a close fit with the internal environment of the airport and can reflect a more precise equipment positioning. The global coordinates ensure the global compatibility of the coordinate system and facilitate cross-regional data sharing and coordination. By integrating the advantages of the two, the final lighting equipment coordinate projection data can be obtained, which can take into account both local accuracy and global applicability and meet the needs of lighting equipment monitoring and management.

[0054] Preferably, step S2 specifically includes: Step S21: using the primary cable of the lighting circuit as a communication carrier, determining a carrier frequency range suitable for lighting equipment communication, and obtaining carrier frequency planning data; Specifically, the primary cable of the lighting circuit is used as a communication carrier, and a communication carrier frequency range suitable for the lighting equipment is selected. The cable system is used for power supply and communication data transmission in the lighting equipment. To ensure the effective transmission of data in the cable, the carrier signal needs to be transmitted within an appropriate frequency range to avoid interference between the signal and the power supply frequency. According to the working environment of the lighting equipment (such as power frequency, signal transmission distance, bandwidth requirements, etc.), the optimal frequency range of the carrier is determined through experimental measurement. This frequency range needs to ensure the stability of data transmission and the availability of bandwidth, and avoid electromagnetic interference with the surrounding electrical system. The obtained carrier frequency planning data is used for subsequent signal modulation and transmission.

[0055] Step S22: performing signal modulation according to the carrier frequency planning data to obtain modulated signal data; Specifically, the signal is modulated according to the obtained carrier frequency planning data. The modulation process embeds the communication data into the carrier signal so that it can be transmitted through the cable. Frequency modulation (FM) or amplitude modulation (AM) is used to select the appropriate modulation method according to the communication requirements and transmission environment of the lighting equipment. In the modulation process, the original data of the communication signal (such as the status information of the lighting equipment) is appropriately encoded and modulated with the carrier signal to generate the modulated signal data. Ensure that the data can be transmitted stably in the cable and effectively avoid signal attenuation or interference.

[0056] Step S23: performing signal transmission setting according to the modulated signal data to obtain signal transmission setting data; Specifically, after the modulation signal is generated, signal transmission settings are performed. Transmission settings refer to determining the transmission mode and parameters of the signal in the lighting circuit cable, mainly including parameters such as transmission power, signal frequency, and transmission delay. At this time, factors such as the length, impedance, and signal attenuation of the cable need to be considered to ensure efficient and stable signal transmission. According to the transmission characteristics of the cable and the modulation mode of the signal, appropriate signal transmission setting data is formulated to optimize the quality and stability of signal transmission.

[0057] Step S24: Perform carrier signal synchronization based on the signal transmission setting data to obtain carrier synchronization deviation data; Specifically, during signal transmission, the synchronization of the carrier signal is crucial. Due to the influence of factors such as multipath effects, signal attenuation, and time delay in cable communication, the synchronization of the carrier signal will deviate. To ensure the accuracy of signal transmission, carrier signal synchronization is required. According to the set data of signal transmission, by comparing the signals at the sending end and the receiving end, the time deviation and frequency deviation of the signal are measured and corresponding adjustments are made. Carrier synchronization deviation data is obtained to describe the error in the signal synchronization process. Through synchronization adjustment, it is ensured that the received signal is consistent with the transmitted signal, avoiding data errors caused by time delay or frequency drift.

[0058] Step S25: Demodulate the signal based on the carrier synchronization deviation data to obtain signal demodulation data; Specifically, once the carrier signal synchronization is completed, the receiving end starts to demodulate the signal. Demodulation is the process of extracting the original data from the received modulated signal, which is achieved through a demodulation algorithm matching the modulation method. The main goal of signal demodulation is to restore the original lighting device status data, such as current, voltage, light intensity, and other information. During the demodulation process, the carrier signal undergoes an inverse modulation process to restore the status information of the lighting device. The obtained signal demodulation data contains the real-time operating status of the lighting device.

[0059] Step S26: Perform signal quality detection based on the signal demodulation data to obtain lighting device communication status data.

[0060] Specifically, after signal demodulation, to ensure the reliability and accuracy of the data, signal quality detection is also required. Signal quality detection includes the detection of parameters such as signal-to-noise ratio (SNR), bit error rate (BER), and signal attenuation. The detection indicators can evaluate the quality problems in the signal transmission process to ensure that the signal is not overly interfered. By performing quality assessment on the demodulated signal, the communication status data of the lighting device is obtained, which is used to monitor whether the communication status of the device is normal and whether there are problems such as signal loss and interference.

[0061] Preferably, step S3 is specifically as follows: Step S31: according to the unique identification of the lighting device and the communication status data of the lighting device, a request signal is sent through a preset monitoring terminal, requiring all lighting devices to feedback the current real-time operation status data according to their unique identification; Specifically, the preset monitoring end sends a request signal based on the unique identification and communication status data of the lighting device. This signal is used to request all lighting devices to feedback the current real-time operating status based on their unique identification. The unique identification of each lighting device can uniquely identify each device, ensuring that the monitoring end can identify and request the real-time data of each lighting device. The monitoring end sends a request to each lighting device through a wireless or wired communication network, requiring the device to feedback the corresponding operating parameters based on its unique identification. The sending cycle of this request signal can be set to a timed trigger to ensure that the system can monitor the operating status of each lighting device in real time.

[0062] Step S32: Control the lighting device end to receive the request signal, and transmit the current operating parameters of the device to the preset monitoring end through the carrier signal to obtain the original lighting operating data; Specifically, after the lighting device receives the request signal sent by the monitoring end, it confirms and identifies the corresponding device identity according to the unique identifier in the request. The lighting device then feeds back its current real-time operating parameters to the monitoring end through a carrier signal. These operating parameters include but are not limited to current, voltage, luminous color, light intensity, etc. After obtaining these operating parameters, the lighting device will encode the information and transmit it to the monitoring end through a previously set communication channel (such as through a lighting loop cable). Ensure the real-time and accuracy of the device status data, and reduce the impact of signal interference and attenuation during the communication process. During the transmission process, the lighting device embeds its status information into the carrier signal through a modulated signal, and then transmits it to the monitoring end. Through appropriate modulation and demodulation methods, ensure that the data can be accurately transmitted.

[0063] Step S33: decoding the received signal at the monitoring end, and extracting the real-time operating parameters of the lighting equipment from it to obtain lighting operation decoding data; Specifically, after receiving the signal from the lighting equipment, the monitoring end first extracts the original operating parameter data through the demodulation process. It is necessary to perform decoding processing according to the communication protocol and signal format of the lighting equipment to restore the electrical and optical parameters of the equipment. The signal decoding process includes demodulating the carrier signal, that is, extracting the data transmitted by the lighting equipment end into clear and usable digital information through the inverse modulation process. From the decoded data, the monitoring end can extract key operating parameters such as current, voltage, luminous color and light intensity.

[0064] Step S34: performing single lamp status identification according to the light operation decoding data to obtain single lamp status data, wherein the single lamp status data includes current, voltage, luminous color and light intensity.

[0065] Specifically, after obtaining the real-time operating parameters of the lighting equipment (such as current, voltage, etc.), the monitoring end performs single lamp status identification. The purpose of this step is to determine whether the lighting equipment is in normal working condition by analyzing the real-time operating data. The basis for judging the status of a single lamp includes changes in light brightness, abnormal current or voltage fluctuations, and light color deviations from the normal range. Based on the known working standards and normal operating range, the monitoring end compares the data fed back by the equipment to analyze whether there are deviations or faults. Through this analysis, the monitoring end can determine the status of the lighting equipment in real time and obtain complete single lamp status data. After status identification and analysis, single lamp status data is generated. Single lamp status data includes the current value, voltage value, luminous color (such as red, green or white) and light intensity value (i.e. light brightness) of the equipment. These data will serve as the basis for subsequent monitoring and decision support.

[0066] Preferably, step S4 is specifically: Step S41: performing data association according to the lighting equipment model, the lighting equipment communication status data and the single lamp status data to obtain lighting-related multi-dimensional data; Specifically, the lighting equipment model, the communication status data of the lighting equipment, and the status data of a single lamp are data-associated. The purpose of this process is to integrate the information of each data source into a unified framework for further analysis. The lighting equipment model contains information such as the structure, function type, and location of each device, while the communication status data provides parameters such as the communication quality, communication delay, and signal strength of the device. The single lamp status data includes the real-time current, voltage, light intensity, and luminous color of each lamp. The data is matched with each other through the set association rules (such as based on unique identification, geographic location, etc.) to generate associated multi-dimensional data of the lighting equipment. This data can display the multi-dimensional operation information of each lighting device, including the values ​​of multiple time periods and multiple parameter dimensions, forming a multi-dimensional information set.

[0067] Step S42: extracting operation stability characteristics and electrical imbalance characteristics according to the light-related multi-dimensional data, and obtaining light operation stability characteristic data and electrical imbalance characteristic data respectively; Specifically, after obtaining the associated multi-dimensional data of the lighting equipment, the next step of feature extraction is performed. Useful stability features and electrical imbalance features are extracted from these multi-dimensional data. The operational stability features of the lighting equipment are identified by statistically analyzing the operating data of the lighting equipment (such as current, voltage, light intensity, etc.). For example, the current and voltage fluctuation range, light intensity change frequency, etc. of the light are analyzed, and stability feature data are extracted through sliding average or other statistical methods. The data reflects the stability performance of the lighting system in different time periods and helps to identify whether the lighting equipment is in normal operation. Electrical imbalance refers to the imbalance or abnormal fluctuation in the electrical aspects of the lighting equipment. By analyzing the electrical data of the lighting equipment such as current, voltage and power, the electrical imbalance feature data of the equipment can be extracted, including abnormal fluctuations in current or voltage, power imbalance, etc., which can reflect whether the electrical state of the equipment is normal.

[0068] Step S43: Perform intelligent status evaluation based on the light operation stability characteristic data and the electrical imbalance characteristic data to obtain single light status data of the navigation light.

[0069] Specifically, after obtaining the operational stability characteristic data and electrical imbalance characteristic data of the lighting equipment, an intelligent status assessment is performed. By comprehensively considering the stability performance and electrical status of the equipment, it is determined whether the equipment is in normal working condition. The intelligent status assessment mainly analyzes various characteristics through set thresholds and rules. For example, if the current and voltage fluctuations of the lighting equipment exceed the preset range, or the electrical imbalance characteristic index exceeds the standard, it indicates that the equipment has potential failure or unstable operation risk. The output result of the assessment is the status data of the single light of the navigation light, including the comprehensive status assessment result of the lighting equipment. The result provides a comprehensive analysis of the current status of each lighting device, covering the electrical health of the equipment, operational stability, and recommendations on whether maintenance or overhaul is required.

[0070] Preferably, the operation stability feature extraction is specifically: Perform sliding average calculation based on multi-dimensional data associated with lighting to obtain segmented characteristic data of lighting operation; Specifically, sliding average calculation is performed based on the multi-dimensional data associated with the lighting. Smoothing the data reduces the impact of instantaneous fluctuations so as to more accurately capture the stable operation of the equipment. The sliding average obtains new data points by averaging the data at each moment with the data in a certain time window before and after it, forming segmented characteristic data of lighting operation. A certain time window (such as 1 minute, 5 minutes, etc.) is set, and the average value of the current, voltage and other parameters of the lighting equipment is calculated in each time window. The noise caused by instantaneous fluctuations is removed, so that the stability of the equipment over a longer period of time can be more clearly observed.

[0071] Performing frequency domain feature extraction on the segmented feature data of the lighting operation to obtain first frequency domain feature data of the lighting operation; Specifically, after obtaining the segmented characteristic data of the lighting operation, frequency domain feature extraction is performed. Through frequency analysis, the periodic changes or abnormal frequency components existing in the operation of the lighting equipment are identified. By performing fast Fourier transform (FFT) on the lighting operation data, the time domain signal is converted into a frequency domain signal, thereby extracting the features in the frequency domain. For example, through Fourier transform, it is possible to detect whether there are periodic fluctuations in the operation of the lighting equipment, and identify the low-frequency and high-frequency components in the current or voltage signal, which represent the normal or abnormal frequency mode in the operation of the equipment. The result obtained by the frequency domain feature extraction is the first lighting operation frequency domain characteristic data, which provides important information for stability analysis.

[0072] Performing generalized autoregressive conditional heteroscedasticity on the frequency domain characteristic data of the first light operation to obtain the first light operation stability characteristic data; Specifically, based on the frequency domain characteristic data of the first lighting operation, the generalized autoregressive conditional heteroskedasticity (GARCH) model is used to conduct an in-depth analysis of the operating stability of the lighting equipment. The GARCH model is used to analyze the volatility of time series data. It is used to evaluate whether there are abnormalities in the volatility of lighting equipment in different time periods and predict future fluctuation trends. The focus of the GARCH model analysis is whether the voltage and current fluctuations of the equipment have high volatility, which is a precursor to equipment failure or unstable operation. Through the GARCH model, the first lighting operation stability characteristic data is obtained, which reveals the fluctuation characteristics of the lighting equipment during operation and whether its fluctuations have a trend of increasing or stabilizing.

[0073] Specifically, the first frequency domain characteristic data (such as frequency intensity, frequency amplitude, etc.) of the light operation is used. The volatility of the characteristic sequence is calculated to identify whether there is conditional heteroskedasticity (volatility changes dynamically over time). The characteristic of conditional heteroskedasticity is that the peaks and troughs of volatility appear alternately, that is, the volatility clusters appear. The generalized autoregressive conditional heteroskedasticity (GARCH) model is selected. The basic structure of the model is as follows, the characteristic sequence value: , It is a characteristic value at a certain moment in time, representing a sequence of current, voltage or other operating characteristic values ​​of the lighting equipment. is the mean of the sequence, which represents the long-term average level of the eigenvalues. is the residual, indicating that the eigenvalue is The deviation of a moment from the mean, is the distribution of the residual, which has a mean of 0 and a variance of The normal distribution of is the conditional variance, which means The volatility of the characteristic value at each moment is the core of the GARCH model analysis. Volatility (conditional variance): ,in is the conditional variance, which indicates the volatility at the current moment, is a constant term, which represents the basic volatility level of the model, and the minimum level of conditional variance even when there is no historical volatility and shock. To represent the index of the historical residual square term, is the number of autoregressive terms, indicating the number of historical residual square terms involved in the model. is the coefficient of the residual square term, which reflects the influence of the historical residual square on the current volatility. For the The residual at the lag time, the square of the residual (the square of the shock term) represents the impact of historical shocks on current fluctuations. is the index of the historical conditional variance term, is the number of moving average terms, indicating the number of historical conditional variance terms involved in the model. is the coefficient of conditional variance, which reflects the impact of historical conditional variance on current volatility. is the condition at the lag time, and the conditional variance represents the impact of historical fluctuations on current fluctuations. By fitting the model using the maximum likelihood estimation (MLE), we get , , Parameters such as . Parameter estimation requires iterative optimization to minimize the error function. Use residual analysis to check the model fit. The residual series should appear as white noise (mean 0, variance constant, no significant correlation). Check the conditional variance series Whether it can accurately capture the volatility of the original series. The conditional variance of the time series is calculated by the model. , that is, the volatility at each moment. The conditional variance sequence reflects the dynamic stability of the operating state of the lighting equipment. By statistically analyzing the conditional variance sequence, the following features are extracted, such as the average volatility, which indicates the overall stability of the lighting equipment operation; the extreme values ​​of volatility, the peak values ​​and the valley values, which reflect the extreme fluctuations of the equipment operating state; and the volatility distribution, which analyzes the distribution characteristics of the volatility sequence and determines whether there is an abnormality in the equipment operating state.

[0074] Perform correlation analysis based on the multi-dimensional data associated with lighting to obtain preliminary feature correlation data; Specifically, feature correlation analysis based on lighting-related multidimensional data aims to understand the relationship between various types of equipment data. For example, there is a certain linear or nonlinear relationship between the current and voltage of lighting equipment, which helps to identify the stability of the equipment and whether there are abnormalities. By calculating the correlation between various data (such as relative distance calculation), preliminary feature correlation data is obtained, which represents the interdependence and influence between different data sources.

[0075] Perform canonical correlation analysis on the preliminary feature correlation data to obtain secondary feature correlation data; Specifically, preliminary feature correlation data of lighting equipment is collected and divided into two groups. Input data includes operating parameters of lighting equipment, such as real-time features such as current, voltage, and light intensity. Output data includes stability indicators of lighting equipment, such as volatility, abnormal ratio, etc. Each data is standardized, and the mean value of the data is adjusted to zero and the standard deviation is adjusted to one. The internal correlation of input data is analyzed, and the relationship between the internal features of input data is calculated to determine whether these features have high similarity or redundancy. The internal correlation of output data is analyzed, and similar analysis is performed on the indicators in output data to determine whether they have high correlation. The correlation between input and output data is analyzed, and the input data is compared with the output data to find the correlation between the two groups of data. Typical variables are constructed, and the variables that best represent their characteristics are extracted from the input data and output data respectively according to the correlation between the two groups of data. The representative variable of input data is a linear combination of multiple features, reflecting the key features of the operating status. The representative variable of output data is a linear combination of multiple indicators, reflecting the key features of stability. The correlation between variables is optimized, and the representative variables of input data and output data are adjusted to maximize the correlation between the two. Obtain key associations and extract the most important association features from input and output data. These features reflect the core connection between the operating status and stability of lighting equipment. Retain significant features, only retain features that have a significant impact on the operating status and stability, reduce redundant data, and optimize data structure. Integrate the extracted features to form secondary feature correlation data, which only contains the most important associations between the operating status and stability of lighting equipment. Perform canonical correlation analysis on the preliminary feature correlation data to optimize and refine the correlation structure between data. Canonical correlation analysis can more accurately identify the key factors that affect the stability and operating status of lighting equipment through multivariate statistical methods. The preliminary feature correlation data is subjected to canonical correlation analysis to obtain secondary feature correlation data.

[0076] Extract features from the light-related multidimensional data according to the secondary feature correlation data to obtain light-related feature data; Specifically, based on the secondary feature correlation data, feature extraction is further performed on the associated multidimensional data of the lighting equipment. The features that have the greatest impact on the stability of the lighting equipment are extracted from a large amount of data. For example, sharp fluctuations in current and temperature changes are key factors affecting the stability of the equipment. Through analysis, the lighting-related feature data obtained contains features that play a decisive role in the change of the equipment status.

[0077] Perform frequency domain feature extraction based on the light-related feature data to obtain second light operation frequency domain feature data; Specifically, the second round of frequency domain feature extraction is performed based on the light-related feature data. Unlike the first round of frequency domain feature extraction, this frequency domain analysis is based on more refined and targeted feature data, thereby more accurately capturing abnormal periodic changes in equipment operation. By performing Fourier transform and frequency domain analysis again, potential problems in equipment operation can be revealed, such as abnormal fluctuation frequencies of equipment current or voltage, which are early signals of equipment failure or performance degradation. The result is the second light operation frequency domain feature data.

[0078] Performing anomaly detection based on the frequency domain characteristic data of the second light operation to obtain the second light operation stability characteristic data; Specifically, the second light operation frequency domain characteristic data is used for anomaly detection. By analyzing the frequency domain data, abnormal fluctuations in the operation of the equipment can be identified in a timely manner. Abnormalities include sudden changes in frequency components, drastic fluctuations in frequency amplitude, etc., which indicate that the equipment has faults, aging or other problems. The results of the anomaly detection form the second light operation stability characteristic data, which helps identify whether the lighting equipment has potential safety hazards.

[0079] The first lighting operation stability characteristic data and the second lighting operation stability characteristic data are integrated to obtain the lighting operation stability characteristic data.

[0080] Specifically, the first lighting operation stability characteristic data and the second lighting operation stability characteristic data are integrated to obtain lighting operation stability characteristic data. By integrating stability analysis results from different angles, the operating status and stability of the lighting equipment can be comprehensively and accurately evaluated.

[0081] Preferably, the electrical imbalance feature extraction is specifically as follows: Perform simple electrical anomaly detection based on the multi-dimensional data associated with lighting to obtain preliminary electrical anomaly data; Specifically, simple electrical anomaly detection is performed based on the multi-dimensional data associated with the lighting. The electrical anomalies in the lighting equipment can be quickly identified through basic statistical methods or threshold detection technology. For example, the normal range of parameters such as current and voltage can be set. If the electrical parameters at a certain moment exceed the set normal range, it is considered that an electrical anomaly has occurred at that moment.

[0082] Perform high-dimensional feature extraction on the preliminary electrical anomaly data to obtain electrical high-dimensional anomaly feature data; Specifically, high-dimensional feature extraction is performed on the preliminary electrical anomaly data. Deeper features are mined from the anomaly data, and the original electrical data is mapped to a higher-dimensional space. In the high-dimensional space, the pattern and potential change trend of electrical anomalies can be captured more effectively. The feature extraction process includes time domain features (such as instantaneous values ​​of current and voltage), statistical features (such as mean and variance), and other multi-dimensional features to obtain electrical high-dimensional anomaly feature data. Perform isolation forest recognition on the electrical high-dimensional anomaly feature data to obtain secondary electrical anomaly data; Specifically, the electrical high-dimensional abnormal feature data of lighting equipment is organized into a high-dimensional feature matrix, which contains multiple electrical features (such as current, voltage, power, etc.). Each row represents an abnormal feature sample of a device, and each column represents a feature. Row: electrical abnormal sample of lighting equipment. Column: electrical features, such as current, voltage fluctuation, etc. Each eigenvalue is mapped to the range of [0,1] so that the eigenvalues ​​have the same dimension and eliminate the influence of different features. Abnormal data is smoothed by moving average or filtering method to remove short-term fluctuation noise. 256 or less samples are randomly selected for the construction of each segmentation tree. The number of trees in the isolated forest is set to 100 to increase the robustness of the model. The depth of the segmentation tree is set to control the maximum number of segmentations for each tree. Electrical features (such as current or voltage) and a segmentation point are randomly selected to divide the sample data into two parts, such as left subtree: samples with eigenvalues ​​less than the segmentation point. Right subtree: samples with eigenvalues ​​greater than the segmentation point. Repeat the segmentation for each subset until the number of samples is 1 or the maximum segmentation depth is reached. For each sample point, calculate its average path length in all segmentation trees. The path length of anomaly points is shorter because they are more easily randomly segmented. Normalize the path length to anomaly score, and the anomaly score range is [0,1]: anomaly scores close to 1 indicate that the sample is an anomaly point. Anomaly scores close to 0 indicate that the sample is a normal point. Set a threshold (such as 0.6) based on the calculated anomaly score, and mark samples with scores higher than the threshold as anomalies. Normal points are those with anomaly scores less than or equal to the threshold. Anomaly points are those with anomaly scores higher than the threshold. Extract the feature data and corresponding anomaly scores of all anomaly points to generate secondary electrical anomaly data.

[0083] Perform instantaneous imbalance ratio on the secondary electrical abnormality data to obtain imbalance ratio data; Specifically, the real-time electrical data of the equipment (such as current, voltage, light intensity, etc.) is extracted from the secondary electrical anomaly data set that has been isolated forest identified. For each lighting device, the normal working parameter value of the device is pre-set based on the preset or historical data. The standard value is the electrical performance of the device under ideal conditions, obtained through the device manual, historical measurements or statistical analysis. By calculating: imbalance ratio , Real-time electrical data of the device (such as current, voltage, light intensity, etc.), It is the normal working parameter value of the device.

[0084] Specifically, more importantly, the time domain imbalance ratio is calculated according to the secondary electrical abnormality data to obtain the first imbalance ratio data; the frequency domain imbalance ratio is calculated according to the secondary electrical abnormality data to obtain the second imbalance ratio data; the weighted instantaneous imbalance ratio is calculated according to the first imbalance ratio data and the second imbalance ratio data to obtain the imbalance ratio data; The time domain imbalance ratio calculation is specifically as follows: performing time series division according to the secondary electrical abnormality data to obtain the secondary electrical abnormality time series division data; performing standard deviation calculation on the secondary electrical abnormality time series division data to obtain the time series division standard deviation data; performing standard deviation imbalance ratio calculation according to the time series division standard deviation data to obtain the first imbalance ratio data; The frequency domain imbalance ratio is calculated specifically as follows: Fourier transform is performed on the secondary electrical abnormality data to obtain secondary electrical abnormality frequency domain data; and frequency domain imbalance ratio is performed on the secondary electrical abnormality frequency domain data to obtain second imbalance ratio data.

[0085] Generate a time window length (such as 1 second, 5 seconds, 10 seconds, etc.) according to preset parameters, and divide it according to the operating characteristics of the equipment and the frequency of abnormal fluctuations. Use the sliding window method to move the starting point of the window each time and calculate the data in the window. Perform segmented processing on the secondary electrical abnormality data, such as dividing it into multiple time segments or window segments with equal time intervals. Obtain multiple time segment data, each of which represents the secondary electrical abnormality value within a time window. Calculate the standard deviation of the electrical data for each time segment, and the standard deviation reflects the degree of fluctuation of the data. Set a normal fluctuation range (such as 0.2A current deviation, 0.5V voltage deviation, etc.). When the standard deviation of the electrical parameter exceeds the normal range, it is considered that there is an imbalance. By calculating the formula: the first imbalance ratio data = time series division standard deviation data / standard deviation corresponding to the parameter when the device is operating normally.

[0086] The secondary electrical anomaly data is subjected to fast Fourier transform (FFT) to obtain the amplitude of each frequency component. The imbalance ratio in the frequency domain is calculated by comparing the amplitude of different frequency components with the amplitude under normal conditions. ,in is the imbalance ratio in the frequency domain, is the amplitude of the frequency component corresponding to the secondary electrical anomaly data, It is the amplitude of the frequency component corresponding to the normal electrical data. According to the characteristics of the equipment or the operation requirements, the weight coefficients of the time domain and frequency domain imbalance ratios are set, such as setting the weight of the time domain to 0.7 and the weight of the frequency domain to 0.3.

[0087] Asymmetric quantification is performed on the secondary electrical anomaly data to obtain electrical anomaly asymmetric data; Specifically, the reference values ​​of electrical parameters of the device when it is working normally (such as reference current and reference voltage). Calculate the current and voltage deviations of each sampling point. Calculate the average deviation and standard deviation of current and voltage. Electrical asymmetry refers to the asymmetric distribution of electrical parameters, such as the directionality of the deviation (the distribution of positive deviation and negative deviation is different). To quantify this asymmetry, calculate the asymmetry metric. The deviation is divided into positive deviation and negative deviation by calculation. For current and voltage, calculate the average value of positive deviation and negative deviation. Compare the average values ​​of positive and negative deviations to obtain the electrical asymmetry metric, such as comparing the average values ​​of positive and negative deviations of current and voltage to obtain the electrical asymmetry metric of current and voltage respectively. According to the asymmetry metric data, quantize the asymmetry metric of each electrical parameter (such as current and voltage) to obtain electrical abnormal asymmetry data. Use a quantization model to convert the deviation metric into a discrete quantization value. For example, define a quantization level (such as 1 to 5) and map the asymmetry metric to the level. If the asymmetry metric value is less than a certain threshold, it is quantized to 1 (normal state). If the asymmetry metric value is between the two thresholds, it is quantified as 2 or 3 (mild abnormality). If the asymmetry metric value is greater than the maximum threshold, it is quantified as 4 or 5 (serious abnormality). The electrical abnormal asymmetry data is obtained through the quantized asymmetry metric data. For example, assuming that the electrical asymmetry metrics of the current and voltage of the device are 3.2 and 2.5 respectively, after quantization, they are mapped to quantization levels 3 and 2 respectively, and the electrical abnormal asymmetry data is {3,2}.

[0088] According to the imbalance ratio data and the electrical abnormality asymmetry data, a multi-dimensional graph is constructed for the lighting-related multi-dimensional data to obtain lighting abnormality-related graph data; Specifically, a multi-dimensional graph of lighting equipment is constructed based on the imbalance ratio data and electrical abnormality asymmetry data. The purpose of this process is to visualize the electrical relationship between devices and perform data association. According to the electrical imbalance and asymmetry, an association graph between each lighting device and other devices is constructed. The nodes in the graph represent lighting devices, and the edges represent the electrical relationship between them. The weight of the edge is determined by the imbalance ratio and electrical abnormality asymmetry measurement. The lighting abnormality association graph data is constructed, which can effectively show the spatial distribution and mutual influence relationship of electrical imbalance between devices.

[0089] Perform graph convolution calculation based on the lighting anomaly correlation graph data to obtain the electrical imbalance fluctuation characteristic data; Specifically, graph convolution calculations are performed using the light anomaly association graph data. Graph convolution network (GCN) is a neural network that can process graph structure data. It extracts local features between nodes (lighting devices) and their relationship with the global structure by performing convolution operations on the graph. In the detection of electrical imbalance, graph convolution can help capture the electrical fluctuation patterns between devices, thereby revealing the hidden electrical imbalance patterns in the system. Calculated through graph convolution: , For the The node feature matrix of the layer, is the activation function, for , that is, the normalized adjacency matrix, is the degree matrix of the node, the diagonal elements , is the degree of the node, is a vertex in the graph, is another vertex in the graph, is an element in the adjacency matrix of the graph, representing the node and nodes Is there an edge between them? If so, then =1, otherwise = 0 (for undirected graphs, the adjacency matrix is ​​symmetric), is the adjacency matrix of the graph (i.e., the light anomaly association graph data), For the The node feature matrix of the layer, For the The learned weight matrix of the layer (i.e., the convolution kernel).

[0090] Graph attention calculation is performed on the electrical imbalance fluctuation characteristic data to obtain the electrical imbalance characteristic data.

[0091] Specifically, for each node, it aggregates the features of its neighbors by calculating the attention weights based on the electrical imbalance fluctuation characteristics between it and its neighboring nodes. In this way, the network can capture the heterogeneity of electrical fluctuations, and the impact of different nodes on electrical imbalance is represented by different weights. The calculated attention weights need to be normalized to ensure that the sum of the weights of each node is 1. The feature vector of each node is the weighted sum of its original features and the features of its neighboring nodes. After the graph attention calculation, the updated features of each node are obtained. The features contain information about the node itself and its neighboring nodes, and the output is the electrical imbalance feature data of each lighting device. Graph attention calculation is performed on the electrical imbalance fluctuation feature data. The graph attention network (GAT) is used to optimize the calculation process of graph convolution. Through the graph attention mechanism, the network can adaptively assign different weights to different nodes and edges in the graph, so as to more accurately capture the key features of electrical imbalance. Through the attention mechanism, the model can focus on the most important electrical imbalance fluctuations and ignore minor and less influential data.

[0092] Preferably, the multi-dimensional graph is constructed as follows: The feature space is constructed according to the imbalance ratio data and the electrical abnormal asymmetry data to obtain the abnormal feature space data; Specifically, a feature space is constructed based on the imbalance ratio data and electrical abnormality asymmetry data. The purpose of feature space construction is to map different indicators of electrical imbalance into a new space in order to more intuitively display the electrical abnormality relationship between devices. During the construction process, the imbalance ratio data and asymmetry quantification data are used as input, and they are converted into points in the feature space using certain mathematical mapping and transformation methods. Each electrical abnormality feature of a lighting device will occupy a position in the feature space, indicating its electrical relationship and differences and similarities with other devices. The constructed abnormal feature space data contains the differences between the electrical states of different devices, helping to identify which devices have more significant electrical imbalance or asymmetry.

[0093] Construct a device relationship diagram based on the multi-dimensional data related to lighting, and obtain lighting relationship diagram data; Specifically, a device relationship graph is constructed based on the association data between lighting devices. Each node in the device relationship graph represents a lighting device, and the connection relationship between the devices reflects their electrical relationship and interaction. Based on the geographical location, circuit number and electrical data of the lighting devices, it is determined whether there is a direct association or influence between the devices. The edges in the device relationship graph represent the relationship between these devices, and the weight of the edges can be set based on factors such as electrical differences between devices, geographical proximity, and functional type.

[0094] The edge relationship of the light association graph data is adjusted according to the abnormal feature space data to obtain the light abnormality association graph data.

[0095] Specifically, the edge relationships in the light association graph data are adjusted based on the previously constructed abnormal feature space data. Since the abnormal feature space data reflects the strength of the electrical differences between devices, the edge weights should be corrected according to these differences when constructing the relationship graph. Specifically, for those devices with more serious electrical imbalance, the edge weights should be increased, indicating that the electrical relationship between them is closer; while for devices with normal electrical performance or small fluctuations, the edge weights can be appropriately reduced. By adjusting the connection strength between devices, the edges in the relationship graph can more realistically reflect the degree of electrical imbalance of the devices, thereby forming the light abnormality association graph data. These adjusted edge relationships more accurately describe the electrical imbalance fluctuations between devices, which is helpful for further evaluation of device status and anomaly detection.

[0096] Preferably, the asymmetric quantization is specifically: Obtain historical equipment electrical data; Specifically, the IoT sensor network collects historical electrical data from the airport's lighting equipment. These data include electrical parameters such as current, voltage, power factor, and light intensity of the lighting equipment, and record the operating status of the equipment in different time periods. Obtaining these historical data is the basis for asymmetric quantification.

[0097] Deviation measurement is performed based on historical equipment electrical data and secondary electrical abnormality data to obtain electrical deviation data; Specifically, the electrical property deviation data of the equipment is measured by using the historical electrical property data and the secondary electrical property abnormality data. The electrical property deviation refers to the difference between the actual electrical property parameters of the equipment and the standard or expected value. By comparing the deviation between the historical data and the theoretical value or the normal operating value, the electrical property deviation of each equipment can be calculated. These deviations can help identify which equipment has a large deviation in electrical performance.

[0098] Asymmetry is defined based on electrical deviation data to obtain electrical abnormal asymmetry measurement data; Specifically, based on the electrical deviation data, an asymmetry metric is defined to obtain electrical abnormal asymmetry metric data. Asymmetry refers to the degree to which the electrical parameters of a device deviate from the expected value, especially in variables such as current, voltage or light intensity. If there is a significant difference between the positive and negative deviations of the device, it means that the asymmetry is strong. Asymmetry can be quantified by calculating the absolute value of the deviation (i.e., the result of subtracting the negative deviation from the positive deviation divided by the sum of the positive and negative deviations) and combining the positive and negative changes in the electrical parameters.

[0099] Extract the electrical fluctuation range based on the historical equipment electrical data to obtain the electrical fluctuation range data; Specifically, the electrical fluctuation range is extracted from the historical equipment electrical data to obtain the electrical fluctuation range data. The fluctuation range reflects the degree of fluctuation of the equipment electrical parameters. The fluctuation range of the electrical parameters is calculated by analyzing the minimum and maximum values ​​of the equipment in the historical data. The fluctuation range is very important for evaluating the stability of the equipment.

[0100] Perform clustering calculation based on secondary electrical anomaly data and historical equipment electrical data to obtain historical electrical anomaly clustering data; Specifically, clustering calculation is performed based on the secondary electrical anomaly data and the historical equipment electrical data to obtain the historical electrical anomaly clustering data. Clustering algorithms (such as K-means or DBSCAN) classify the electrical anomaly data of the equipment into different categories and identify groups of equipment that exhibit abnormal performance. By clustering the equipment electrical data, different types of electrical anomalies can be identified. For example, using the K-means clustering algorithm, the equipment is grouped according to the electrical anomaly data to obtain various types of electrical anomaly equipment. Each cluster represents the abnormal performance of the equipment under a certain electrical parameter.

[0101] The electrical property fluctuation range data is thresholded according to the historical electrical property anomaly clustering data to obtain electrical property threshold data; Specifically, based on the historical electrical anomaly clustering data, the threshold of the electrical fluctuation range data is set to obtain the electrical threshold data. The threshold setting is based on the clustering analysis results and is used to determine whether the device has electrical anomalies. By analyzing the clustered electrical data, the upper and lower limits of the normal fluctuation range are determined, and the threshold is set. If the electrical data of the device exceeds the threshold, it is considered that the device has electrical anomalies.

[0102] The electrical abnormality asymmetry measurement data is quantified at multiple levels according to the electrical threshold data to obtain the electrical abnormality asymmetry data.

[0103] Specifically, based on the electrical threshold data, the electrical abnormality asymmetry measurement data is quantified at multiple levels to obtain electrical abnormality asymmetry data. The purpose of multi-level quantification is to divide the asymmetry measurement into different levels, such as low, medium, and high levels, and to assess the device status according to the degree of electrical abnormality of the device. Based on the set threshold, the asymmetry measurement data is divided into multiple levels. For example, if the measurement value is less than a certain threshold, the device status is "normal"; if the measurement value is between two thresholds, the device status is "slightly abnormal"; if the measurement value is greater than a certain threshold, the device status is "severely abnormal". The electrical abnormality asymmetry of the equipment can be quantified and classified, which is helpful for monitoring and management.

[0104] Therefore, from any point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the attached application documents rather than the above description, and it is intended that all changes falling within the meaning and scope of equivalent elements of the application documents are included in the present invention.

[0105] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for intelligently monitoring the status of a single light of a navigation light, characterized in that: The following steps are involved: Step S1: Obtain basic information of all lighting equipment of the airport, and construct a model based on the basic information of the lighting equipment to obtain a lighting equipment model, wherein the basic information of the lighting equipment includes a unique identifier, geographical location, circuit number and function type of the lighting equipment; Step S2: using the primary cable of the lighting circuit as a communication carrier, setting carrier communication parameters, ensuring that the digital signal can be transmitted at high speed between the lighting device end and the preset monitoring end, and generating lighting device communication status data; Step S3: According to the unique identification of the lighting equipment end and the communication status data of the lighting equipment, the real-time operating parameters of the single lamp are collected through carrier communication to obtain the single lamp status data, wherein the single lamp status data includes current, voltage, luminous color and light intensity; Step S4: performing intelligent analysis of the status of a single light according to the lighting equipment model, the lighting equipment communication status data and the status data of a single light, and obtaining the status data of a single light of the navigation light.

2. The method according to claim 1, characterized in that: Step S1 is specifically as follows: Using the IoT-based sensor network, basic data is collected from various lighting devices on the airport ground, including the unique device identification, geographic location (GPS coordinates), loop number and function type, to obtain the original data of the lighting devices; Perform coordinate projection on the original data of the lighting equipment to obtain the coordinate projection data of the lighting equipment; Functional equipment classification is performed according to the lighting equipment coordinate projection data to obtain lighting equipment functional classification data; Perform equipment position mapping according to the lighting equipment classification data to obtain lighting equipment position mapping data; Perform spatial analysis on the lighting equipment position mapping data to obtain the lighting equipment spatial data; According to the lighting equipment spatial data, equipment attributes are associated to obtain lighting equipment attribute assignment data; According to the attribute assignment data of the lighting equipment, three-dimensional modeling is performed and virtual reality integration is performed to obtain a lighting equipment model.

3. The method according to claim 2, characterized in that The coordinate projection is as follows: Performing local coordinate projection and global geographic coordinate projection on the original data of the lighting equipment to obtain first coordinate projection data and second coordinate projection data respectively; Obtain airport physical environment data; A coordinate accuracy environment adaptability model is constructed based on the airport physical environment data to obtain a coordinate environment adaptability model; Correcting the first coordinate projection data and the second coordinate projection data by using the coordinate environment adaptability model to obtain first coordinate projection corrected data and second coordinate projection corrected data; Performing coordinate projection accuracy error calculation on the first coordinate projection correction data and the second coordinate projection correction data to obtain coordinate projection accuracy error data; The first coordinate projection correction data and the second coordinate projection correction data are projected and fused according to the coordinate projection accuracy error data to obtain the lighting equipment coordinate projection data.

4. The method according to claim 1, characterized in that: Step S2 is specifically as follows: Using the primary cable of the lighting circuit as a communication carrier, determine the carrier frequency range suitable for lighting equipment communication and obtain carrier frequency planning data; Perform signal modulation according to carrier frequency planning data to obtain modulated signal data; Perform signal transmission setting according to the modulated signal data to obtain signal transmission setting data; Carrier signal synchronization is performed according to signal transmission setting data to obtain carrier synchronization deviation data; Perform signal demodulation according to the carrier synchronization deviation data to obtain signal demodulation data; The signal quality is detected based on the signal demodulation data to obtain the communication status data of the lighting equipment.

5. The method according to claim 1, characterized in that Step S3 is specifically as follows: According to the unique identification of the lighting equipment and the communication status data of the lighting equipment, a request signal is sent through the preset monitoring terminal, requiring all lighting equipment to feedback the current real-time operation status data according to its unique identification; The control lighting device receives the request signal and transmits the current operating parameters of the device to the preset monitoring terminal through the carrier signal to obtain the original lighting operation data; Decode the received signal at the monitoring end, and extract the real-time operating parameters of the lighting equipment from it to obtain the lighting operation decoding data; The single lamp status is identified according to the light operation decoding data to obtain the single lamp status data, wherein the single lamp status data includes current, voltage, luminous color and light intensity.

6. The method according to claim 1, characterized in that Step S4 is specifically as follows: Data association is performed based on the lighting equipment model, lighting equipment communication status data and single light status data to obtain lighting-related multi-dimensional data; According to the multi-dimensional data associated with lighting, operation stability feature extraction and electrical imbalance feature extraction are performed to obtain lighting operation stability feature data and electrical imbalance feature data respectively; Intelligent status assessment is performed based on the light operation stability characteristic data and electrical imbalance characteristic data to obtain the single light status data of the navigation light.

7. The method according to claim 6, characterized in that The specific operation stability feature extraction is as follows: Perform sliding average calculation based on multi-dimensional data associated with lighting to obtain segmented characteristic data of lighting operation; Performing frequency domain feature extraction on the segmented feature data of the lighting operation to obtain first frequency domain feature data of the lighting operation; Performing generalized autoregressive conditional heteroscedasticity on the frequency domain characteristic data of the first light operation to obtain the first light operation stability characteristic data; Perform correlation analysis based on the multi-dimensional data associated with lighting to obtain preliminary feature correlation data; Perform canonical correlation analysis on the preliminary feature correlation data to obtain secondary feature correlation data; Extract features from the light-related multidimensional data according to the secondary feature correlation data to obtain light-related feature data; Perform frequency domain feature extraction based on the light-related feature data to obtain second light operation frequency domain feature data; Performing anomaly detection based on the frequency domain characteristic data of the second light operation to obtain the second light operation stability characteristic data; The first lighting operation stability characteristic data and the second lighting operation stability characteristic data are integrated to obtain the lighting operation stability characteristic data.

8. The method according to claim 6, characterized in that The electrical imbalance feature extraction is specifically as follows: Perform simple electrical anomaly detection based on the multi-dimensional data associated with lighting to obtain preliminary electrical anomaly data; Perform high-dimensional feature extraction on the preliminary electrical anomaly data to obtain electrical high-dimensional anomaly feature data; Perform isolation forest recognition on the electrical high-dimensional anomaly feature data to obtain secondary electrical anomaly data; Perform instantaneous imbalance ratio on the secondary electrical abnormality data to obtain imbalance ratio data; Asymmetric quantification is performed on the secondary electrical anomaly data to obtain electrical anomaly asymmetric data; According to the imbalance ratio data and the electrical abnormality asymmetry data, a multi-dimensional graph is constructed for the lighting-related multi-dimensional data to obtain lighting abnormality-related graph data; Perform graph convolution calculation based on the lighting anomaly correlation graph data to obtain the electrical imbalance fluctuation characteristic data; Graph attention calculation is performed on the electrical imbalance fluctuation characteristic data to obtain the electrical imbalance characteristic data.

9. The method according to claim 8, characterized in that The multi-dimensional graph construction is as follows: The feature space is constructed according to the imbalance ratio data and the electrical abnormal asymmetry data to obtain the abnormal feature space data; Construct a device relationship diagram based on the multi-dimensional data related to lighting, and obtain lighting relationship diagram data; The edge relationship of the light association graph data is adjusted according to the abnormal feature space data to obtain the light abnormality association graph data.

10. The method according to claim 8, characterized in that The specific asymmetric quantization is: Obtain historical equipment electrical data; Deviation measurement is performed based on historical equipment electrical data and secondary electrical abnormality data to obtain electrical deviation data; Asymmetry is defined based on electrical deviation data to obtain electrical abnormal asymmetry measurement data; Extract the electrical fluctuation range based on the historical equipment electrical data to obtain the electrical fluctuation range data; Perform clustering calculation based on secondary electrical anomaly data and historical equipment electrical data to obtain historical electrical anomaly clustering data; The electrical property fluctuation range data is thresholded according to the historical electrical property anomaly clustering data to obtain electrical property threshold data; The electrical abnormality asymmetry measurement data is quantified at multiple levels according to the electrical threshold data to obtain the electrical abnormality asymmetry data.

Images