Airport navigation aid single lamp monitoring system based on Internet of Things communication technology

Abstract

The invention relates to the technical field of artificial intelligence, and discloses an airport navigation aid single lamp monitoring system based on the Internet of Things communication technology, which comprises a data acquisition module, a matrix generation module, a data classification module, an incidence relation generation module, a target state value generation module and a single lamp control module, the method comprises the following steps: acquiring sensing data of airport navigation aid single lamps, generating an intra-class scatter matrix of the sensing data, generating an inter-class scatter matrix of the sensing data, performing data classification on the sensing data according to the intra-class scatter matrix and the inter-class scatter matrix to obtain classified data of the airport navigation aid single lamps, and generating an association relationship between the classified data. The real-time environment data of the airport navigational aid single lamp is obtained, the target state value of the airport navigational aid single lamp is generated according to the association relationship and the real-time environment data, the airport navigational aid single lamp is controlled by using the preset lamp adjustment algorithm and the target state value, and the monitoring efficiency of the airport navigational aid single lamp is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an airport navigation light monitoring system based on Internet of Things communication technology. Background Art

[0002] Airport navigation lights are key facilities to ensure flight safety at night and in low visibility conditions. Timely detection and repair of lighting failures can avoid aviation accidents caused by insufficient lighting. For example, when navigation lights fail, pilots may not be able to accurately determine the runway location, or mislead the aircraft into entering the wrong runway or take-off and landing path. By improving monitoring efficiency, it is possible to respond quickly to lighting failures, ensuring that pilots can always clearly see the runway, taxiway and related guidance.

[0003] Most airport navigation lights monitoring systems still rely on traditional manual inspections or regular maintenance. This approach not only places high demands on staff, but also fails to achieve real-time monitoring. Especially for larger airports, where there are a large number of lights, manual inspections are time-consuming and lack the ability to detect problems in a timely manner. In addition, traditional monitoring methods cannot remotely adjust the status of lights in real time, resulting in response delays, which leads to low monitoring efficiency for single airport navigation lights. Summary of the invention

[0004] The present invention provides an airport navigation light monitoring system based on Internet of Things communication technology, and its main purpose is to solve the problem of low monitoring efficiency of airport navigation lights.

[0005] To achieve the above-mentioned purpose, the present invention provides an airport navigation light monitoring system based on Internet of Things communication technology, characterized in that the system includes a data acquisition module, a matrix generation module, a data classification module, an association relationship generation module, a target state value generation module and a single light control module, wherein: The data acquisition module is used to collect sensor data of the airport navigation light and generate an intra-class scatter matrix of the sensor data; The matrix generation module is used to generate an inter-class scatter matrix of the sensor data; The data classification module is used to classify the sensor data according to the intra-class scatter matrix and the inter-class scatter matrix to obtain classification data of the airport navigation light, wherein the classification data is single light status data and historical environment data; The association relationship generating module is used to generate an association relationship between the single lamp status data and the historical environment data; The target state value generating module is used to obtain the real-time environmental data of the airport navigation light, and generate the target state value of the airport navigation light according to the association relationship and the real-time environmental data; The single light control module is used to control the airport navigation light by using a preset light adjustment algorithm and the target state value, wherein the preset light adjustment algorithm is: ; in, is the target state value, is the proportional gain, is the difference between the current state value and the target state, is the integral gain, is the integral variable of the integral term, is a time stamp, is the differential gain.

[0006] Optionally, when the data acquisition module generates an intra-class scatter matrix of the sensor data, the data acquisition module includes: Generate an intra-class scatter matrix of the sensor data according to a preset intra-class algorithm, wherein the preset intra-class algorithm is: ; in, is the within-class scatter matrix, is the data category identifier, is the number of categories, It is The number of samples of the class, It is The covariance matrix of the class, It is The mean vector of the class, It is Transpose of the class mean vector.

[0007] Optionally, when the matrix generation module generates the inter-class scatter matrix of the sensor data, the matrix generation module includes: Generate an intra-class scatter matrix of the sensor data according to a preset inter-class algorithm, wherein the preset inter-class algorithm is: ; in, is the between-class scatter matrix, is the data category identifier, is the number of categories, It is The number of samples of the class, is the overall mean vector of all samples, It is The mean vector of the class, is the transpose identity of a vector.

[0008] Optionally, when the data classification module performs data classification on the sensor data according to the intra-class scatter point matrix and the inter-class scatter point matrix to obtain the classification data of the airport navigation light, the data classification module includes: Generate an inverse matrix of the intra-class scatter matrix; generating a discriminant vector of the sensing data according to the inverse matrix and the inter-class scatter matrix; generating a characteristic equation of the sensing data according to the discriminant vector; The sensor data is classified according to the characteristic equation to obtain classification data of the airport navigation light.

[0009] Optionally, when the data classification module generates a discriminant vector of the sensor data according to the inverse matrix and the inter-class scatter matrix, the method includes: The discriminant vector is: ; in, is the discriminant vector of the characteristic equation, is the weight vector to be optimized, is the transpose identity of a vector, is the within-class scatter matrix, is the between-class scatter matrix, is the inverse matrix of the within-class scatter matrix, is the maximum value of the independent variable function.

[0010] Optionally, when executing the characteristic equation for generating the sensing data according to the discriminant vector, the data classification module includes: The characteristic equation is: ; in, is the identity matrix, is the eigenvalue, is the within-class scatter matrix, is the between-class scatter matrix, is the inverse of the within-class scatter matrix.

[0011] Optionally, when the association relationship generating module generates the association relationship between the single lamp state data and the historical environment data, the following steps are performed: Extracting the status timestamp of the single lamp status data; Extracting an environmental timestamp of the historical environmental data; Calculating the similarity between the state timestamp and the environment timestamp; An association relationship between the single lamp status data and the historical environment data is generated according to the similarity.

[0012] Optionally, when the association relationship generation module calculates the similarity between the state timestamp and the environment timestamp, the following steps are performed: Calculating a time difference between the state timestamp and the environment timestamp; The similarity between the state timestamp and the environment timestamp is determined according to the time difference.

[0013] Optionally, when the association relationship generating module generates the association relationship between the single lamp state data and the historical environment data according to the similarity, the module includes: generating the association strength between the single lamp state data and the historical environment data according to the similarity; Determining an association weight between the single lamp state data and the historical environment data according to the association strength; An association relationship between the single lamp status data and the historical environment data is generated according to the association weight.

[0014] Optionally, when the target state value generating module generates the target state value of the airport navigation light according to the association relationship and the real-time environmental data, the target state value generating module includes: Performing data cleaning on the real-time environment data to obtain cleaned data of the real-time environment data; Determining a data weight of the cleansed data according to the association relationship; A target state value of the airport navigation light is generated according to the data weight and the cleaning data.

[0015] The present invention uses the Internet of Things technology to collect various sensor data of airport navigation lights in real time, including but not limited to environmental data such as light intensity, voltage, current, temperature, etc., obtain these data in real time and generate corresponding intra-class and inter-class scatter matrix, which can effectively reflect the current working status of the lamp and environmental changes, ensure the timeliness and accuracy of monitoring data, classify the sensor data using the intra-class scatter matrix and inter-class scatter matrix methods, generate the correlation between the single lamp status data and the historical environmental data, and reveal the dynamic connection between the historical data and the current environment, so as to help the system make more accurate responses when the environment changes. Reaction, through the combination of real-time environmental data and association relationships, the target state value is generated, so that the system can adaptively adjust the state of the lamp, and the preset lamp adjustment algorithm can be used to accurately adjust the state of the airport navigation light. The proportional, integral, and differential gains in the preset lamp adjustment algorithm can be optimized and adjusted according to actual monitoring needs to achieve rapid response and fine adjustment of the lamp. The application of Internet of Things technology enables the monitoring method to have the ability of remote monitoring and control, and can realize automated operation. According to the preset lamp adjustment algorithm and real-time data, the lamp state is automatically optimized, human intervention is reduced, and monitoring efficiency is improved. Therefore, the airport navigation light monitoring system based on Internet of Things communication technology proposed in the present invention can improve the monitoring efficiency of single navigation lights. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a system architecture diagram of an airport navigation light monitoring system based on Internet of Things communication technology provided by one embodiment of the present invention.

[0017] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the embodiments of the present invention are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0020] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0021] In fact, the server-side device deployed by the airport navigation single light monitoring system based on the Internet of Things communication technology may be composed of one or more devices. The above-mentioned airport navigation single light monitoring system based on the Internet of Things communication technology can be implemented as: business instance, virtual machine, hardware device. For example, the airport navigation single light monitoring system based on the Internet of Things communication technology can be implemented as a business instance deployed on one or more devices in the cloud node. In simple terms, the airport navigation single light monitoring system based on the Internet of Things communication technology can be understood as a software deployed on the cloud node, which is used to provide the airport navigation single light monitoring system based on the Internet of Things communication technology for each user terminal. Alternatively, the airport navigation single light monitoring system based on the Internet of Things communication technology can also be implemented as a virtual machine deployed on one or more devices in the cloud node. The virtual machine is installed with application software for managing each user terminal. Alternatively, the airport navigation single light monitoring system based on the Internet of Things communication technology can also be implemented as a server consisting of many hardware devices of the same or different types, and one or more hardware devices are set to provide the airport navigation single light monitoring system based on the Internet of Things communication technology for each user terminal.

[0022] In terms of implementation, the airport navigation light monitoring system based on the Internet of Things communication technology and the user end are adapted to each other. That is, the airport navigation light monitoring system based on the Internet of Things communication technology is an application installed on the cloud service platform, and the user end is a client that establishes a communication connection with the application; or the airport navigation light monitoring system based on the Internet of Things communication technology is implemented as a website, and the user end is implemented as a web page; or the airport navigation light monitoring system based on the Internet of Things communication technology is implemented as a cloud service platform, and the user end is implemented as a small program in the instant messaging application.

[0023] like Figure 1 , which is a system architecture diagram of an airport navigation light monitoring system based on Internet of Things communication technology provided by an embodiment of the present invention.

[0024] The airport navigation light monitoring system 100 based on the Internet of Things communication technology of the present invention can be set in a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed on the cloud (such as a server of a mobile service operator, a server cluster, etc.), or it can also be developed as a website. According to the functions implemented, the airport navigation light monitoring system 100 based on the Internet of Things communication technology may include a data acquisition module 101, a matrix generation module 102, a data classification module 103, an association relationship generation module 104, a target state value generation module 105 and a single light control module 106. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0025] In the embodiment of the present invention, in the airport navigation light monitoring system based on the Internet of Things communication technology, each of the above modules can be independently implemented and called with other modules. The call here can be understood as a module that can connect to multiple modules of another type and provide corresponding services to the multiple modules connected to it. For example, the sharing evaluation module can call the same information collection module to obtain the information collected by the information collection module. Based on the above characteristics, in the airport navigation light monitoring system based on the Internet of Things communication technology provided by the embodiment of the present invention, the scope of application of the airport navigation light monitoring system architecture based on the Internet of Things communication technology can be adjusted by adding modules and directly calling them without modifying the program code, so as to achieve cluster-type horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the airport navigation light monitoring system based on the Internet of Things communication technology. In actual applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in cloud servers.

[0026] In the following, in combination with specific embodiments, each component and specific workflow of the airport navigation light monitoring system based on the Internet of Things communication technology are described respectively: The data collection module 101 is used to collect sensor data of the airport navigation light and generate an intra-class scatter matrix of the sensor data.

[0027] In the embodiment of the present invention, when the data acquisition module 101 executes the collection of sensor data of the airport navigation light, it includes: the following types of sensors can be used to collect data; photoelectric sensors, current sensors, temperature and humidity sensors, voltage sensors and vibration sensors, among which the photoelectric sensors are used to detect the brightness, flickering frequency and working status of the lights; the current sensors are used to monitor the current consumption of the lamps and detect whether there are circuit problems, such as short circuit or overload; the temperature and humidity sensors monitor the temperature and humidity of the environment; the voltage sensors monitor the voltage of the navigation lights; in some cases, there may be vibrations at the installation position of the lamps, which may affect the stability of the lamps. These problems can be discovered in time by monitoring with vibration sensors.

[0028] In detail, in the IoT application of airport navigation lights, the choice of communication protocol is crucial, which determines the response speed, stability and reliability of the system.

[0029] Furthermore, the following communication technologies and protocols can be used: Wi-Fi / LTE (4G / 5G), LoRaWAN (long-distance low-power network), NB-IoT (narrowband Internet of Things), Zigbee, and Bluetooth Mesh. In large areas such as airports, Wi-Fi or high-bandwidth networks such as LTE / 5G are used for data transmission. Wi-Fi is suitable for use in environments with smaller areas, and 5G can provide lower latency and higher bandwidth, which is suitable for real-time monitoring and control. LoRaWAN (long-distance low-power network) is suitable for application scenarios with wide coverage and low power consumption. LoRa technology can achieve low-power and long-distance communication in a wide area, which is very suitable for remote monitoring of airport navigation lights distributed in different areas. NB-IoT (narrowband Internet of Things) is a low-power wide-area network technology suitable for devices deployed over a large area and without frequent data exchange. NB-IoT has strong signal penetration and is very suitable for equipment deployment in large buildings such as airports. Zigbee and Bluetooth Mesh are suitable for low-power communication in local areas, especially when controlling the intelligent adjustment of lamps, and can be used for short-range device-to-device communication.

[0030] Furthermore, the sensor transmits the collected data to the central monitoring system through wireless networks (such as Wi-Fi, LoRa, NB-IoT, etc.). The data transmission adopts IoT communication protocols such as MQTT, CoAP, etc. to ensure the reliability and low latency of data transmission. The central monitoring system receives and analyzes the data from each navigation light.

[0031] In the embodiment of the present invention, when the data acquisition module 101 generates the intra-class scatter matrix of the sensor data, it includes: Generate an intra-class scatter matrix of the sensor data according to a preset intra-class algorithm, wherein the preset intra-class algorithm is: ; in, is the within-class scatter matrix, is the data category identifier, is the number of categories, It is The number of samples of the class, It is The covariance matrix of the class, It is The mean vector of the class, It is Transpose of the class mean vector.

[0032] In detail, it is assumed that the collected sensor data can be divided into two categories: Category 1 (single light state data) contains multiple samples, each sample represents a different state of the light (e.g., on, off, etc.); Category 2 (historical environmental data) contains multiple samples, each sample represents a different environmental factor (e.g., temperature, humidity, etc.).

[0033] Furthermore, each data point may have multiple features. For example, single lamp status data may include features such as brightness and frequency, and historical environmental data may include temperature, humidity, etc.

[0034] In detail, the intra-class scatter matrix measures the distribution of samples within each class.

[0035] In detail, Class 1 (single lamp status data) has samples, with a mean of , the covariance matrix is ; Category 2 (historical environmental data) has samples, with a mean of , the covariance matrix is .

[0036] In detail, the intra-class scatter matrix The calculation formula is: ; For class 1: ; The contribution of class 1 is: ; For class 2: ; The contribution of class 2 is: ; Therefore, the within-class scatter matrix for: ; The matrix generation module 102 is used to generate an inter-class scatter matrix of the sensor data.

[0037] In the embodiment of the present invention, when the matrix generation module 102 generates the inter-class scatter matrix of the sensor data, it includes: Generate an intra-class scatter matrix of the sensor data according to a preset inter-class algorithm, wherein the preset inter-class algorithm is: ; in, is the between-class scatter matrix, is the data category identifier, is the number of categories, It is The number of samples of the class, is the overall mean vector of all samples, It is The mean vector of the class, is the transpose identity of a vector.

[0038] In detail, the between-class scatter matrix measures the dispersion between different classes.

[0039] In detail, assuming that the overall mean .

[0040] For class 1: ; The contribution of class 1 is: ; For class 2: ; The contribution of class 2 is: ; Therefore, the between-class scatter matrix for: ; The data classification module 103 is used to classify the sensor data according to the intra-class scatter matrix and the inter-class scatter matrix to obtain classification data of the airport navigation light, wherein the classification data is single light status data and historical environment data.

[0041] In the embodiment of the present invention, when the data classification module 103 performs data classification on the sensor data according to the intra-class scatter matrix and the inter-class scatter matrix to obtain the classification data of the airport navigation light, it includes: Generate an inverse matrix of the intra-class scatter matrix; generating a discriminant vector of the sensing data according to the inverse matrix and the inter-class scatter matrix; generating a characteristic equation of the sensing data according to the discriminant vector; The sensor data is classified according to the characteristic equation to obtain classification data of the airport navigation light.

[0042] In detail, the within-class scatter matrix is ​​inverted and multiplied with the between-class scatter matrix to obtain the eigenvalues ​​and eigenvectors.

[0043] Specifically, the inverse matrix of the intra-class scatter matrix is ​​calculated. The inverse matrix exists only if the matrix is ​​invertible. By calculating the inverse matrix, it can be ensured that the scatter of the data points within the class is properly handled when the projection is performed. The calculation process of the inverse matrix usually requires standard linear algebra methods, such as Gaussian elimination or using determinants to solve.

[0044] In detail, the discriminant vector is the key to classification. It is used to project the data into a low-dimensional space so that the difference between different categories is maximized and the variance within the class is minimized. The discriminant vector is obtained by optimizing the objective function, which is defined based on the product of the inverse matrix of the intra-class scatter matrix and the inter-class scatter matrix.

[0045] Furthermore, the goal is to find the optimal weight vector that maximizes the difference between classes and minimizes the variation within classes.

[0046] In detail, the characteristic equation is the process used to solve the discriminant vector. The solution of the characteristic equation corresponds to the eigenvalue and eigenvector, where: the eigenvalue, which represents the "importance" or "superiority" of the data projection direction. By solving the characteristic equation, the eigenvector corresponding to the eigenvalue obtained is the discriminant vector, which is the optimal direction after the data is projected into the low-dimensional space.

[0047] Furthermore, after obtaining the discriminant vector, the original data is projected into this new low-dimensional space, after which common classification algorithms (such as nearest neighbor, support vector machine, etc.) can be used to classify the data.

[0048] In detail, when the data classification module 103 generates the discriminant vector of the sensor data according to the inverse matrix and the inter-class scatter matrix, it includes: The discriminant vector is: ; in, is the discriminant vector of the characteristic equation, is the weight vector to be optimized, is the transpose identity of a vector, is the within-class scatter matrix, is the between-class scatter matrix, is the inverse matrix of the within-class scatter matrix, is the maximum value of the independent variable function.

[0049] In detail, the optimization goal is to find a weight vector , so that the ratio of the difference between categories (between-class scatter matrix) to the difference within the class (within-class scatter matrix) is maximized. The solution to this optimization problem is the so-called discriminant vector.

[0050] In detail, by solving the above optimization problem, the discriminant vector obtained is the final , which is the optimal direction for data projection. This discriminant vector can help project the data into a new space to maximize the separability between different categories.

[0051] In detail, when the data classification module 103 executes the characteristic equation for generating the sensor data according to the discriminant vector, it includes: The characteristic equation is: ; in, is the identity matrix, is the eigenvalue, is the within-class scatter matrix, is the between-class scatter matrix, is the inverse of the within-class scatter matrix.

[0052] In detail, the discriminant vector is used to generate a characteristic equation of the sensing data, and the characteristic equation is used to project the original data into a new low-dimensional space so that data of the same type are clustered together and data of different types are separated.

[0053] In detail, the inverse of the intra-class scatter matrix can enhance the separability between categories by standardizing the intra-class scatter. The inter-class scatter matrix represents the degree of separation between categories. The product of the two calculates the ratio of the differences between each category to the intra-class differences.

[0054] In detail, the eigenvalue reflects the "importance" of the discriminant direction. The size of the eigenvalue indicates how effective the separation is in that direction. The larger the eigenvalue, the stronger the separability between categories in that direction.

[0055] In detail, the identity matrix is ​​used to ensure that the eigenvalue decomposition is performed effectively when solving the eigenvalue problem. Its role is to "balance" The relationship between and eigenvalues.

[0056] In detail, is the standard form of the characteristic equation of a matrix. According to the eigenvalue theory in linear algebra, the eigenvalues ​​of a matrix appear when the determinant is zero. In other words, the solution to this equation gives the matrix The eigenvalues ​​and eigenvectors of are the discriminant vectors, which indicate the best direction of data projection.

[0057] In detail, solving the equation is actually solving the matrix The eigenvalue and eigenvector of , the eigenvector corresponds to the optimal discrimination direction, and the eigenvalue indicates the degree of category separation in that direction.

[0058] The association relationship generating module 104 is used to generate an association relationship between the single lamp status data and the historical environment data.

[0059] In the embodiment of the present invention, when the association relationship generating module 104 generates the association relationship between the single lamp state data and the historical environment data, the following steps are performed: Extracting the status timestamp of the single lamp status data; Extracting an environmental timestamp of the historical environmental data; Calculating the similarity between the state timestamp and the environment timestamp; An association relationship between the single lamp status data and the historical environment data is generated according to the similarity.

[0060] In detail, the status data of a single lamp usually includes multiple information points, such as the working status, current, voltage, brightness, etc. of the lamp. Each data record should contain a timestamp (status timestamp) to identify the specific time when the data was collected. Extracting these timestamps is the basis for establishing data association.

[0061] Furthermore, the timestamp of each data record is extracted from the real-time data of a single lamp. Assume that each timestamp is , represents the status data of the lamp at a certain moment (such as brightness, fault, working status, etc.).

[0062] In detail, the historical environmental data includes multiple environmental variables, such as temperature, humidity, wind speed, etc. Each piece of historical environmental data also has a timestamp (environmental timestamp), indicating the time corresponding to the data record.

[0063] Furthermore, the timestamp of each data record is extracted from the historical environmental data. Assume that each environmental timestamp is , representing environmental data at a certain moment (such as temperature, humidity, etc.).

[0064] In detail, when the association relationship generation module 104 calculates the similarity between the state timestamp and the environment timestamp, it includes: Calculating a time difference between the state timestamp and the environment timestamp; The similarity between the state timestamp and the environment timestamp is determined according to the time difference.

[0065] In detail, in order to associate the single light status data with the environmental data, it is necessary to calculate the similarity between their timestamps. This similarity mainly measures the proximity between time points.

[0066] In detail, if you want to accurately calculate the similarity of timestamps, you can use the time difference as a similarity measure. For example, the smaller the time difference, the higher the similarity of the timestamps.

[0067] Furthermore, the state timestamp is calculated and historical environment timestamps The time difference between ,The smaller the time difference, the higher the similarity between the state data and the environment data.

[0068] In detail, when the association relationship generating module 104 generates the association relationship between the single lamp state data and the historical environment data according to the similarity, it includes: generating the association strength between the single lamp state data and the historical environment data according to the similarity; Determining an association weight between the single lamp state data and the historical environment data according to the association strength; An association relationship between the single lamp status data and the historical environment data is generated according to the association weight.

[0069] Specifically, the weighted time difference method can be used to weight the association relationship according to the similarity (weight). For example, the smaller the time difference, the greater the weight, and the final association data set can be generated in a weighted manner.

[0070] Furthermore, we assume an incidence matrix where each element of the matrix Indicates The status data of a single lamp is the same as that of the The correlation strength of historical environmental data. Calculate each pair ( , ) and fill in the association matrix.

[0071] Furthermore, the association results can be output in various formats, for example: an association table can show the degree of association between each single lamp status data and the corresponding environmental data; a chart can be used to show the trend of the associated data, such as the relationship between temperature and light brightness; and single lamp status data and environmental data can be integrated in chronological order to form a multidimensional time series data set.

[0072] In detail, the key to generating the association between single lamp status data and historical environmental data lies in how to match data through timestamp similarity.

[0073] The target state value generating module 105 is used to obtain the real-time environmental data of the airport navigation light, and generate the target state value of the airport navigation light according to the association relationship and the real-time environmental data.

[0074] In an embodiment of the present invention, when the target state value generating module 105 executes to obtain the real-time environmental data of the airport navigation light, it includes: the real-time environmental data is meteorological data, lighting data and power data, wherein the meteorological data is temperature, humidity, wind speed and direction, air pressure, precipitation and visibility; the lighting data is light intensity, pollution data, air pollutants; the power data is voltage and current.

[0075] In the embodiment of the present invention, when the target state value generating module 105 generates the target state value of the airport navigation light according to the association relationship and the real-time environmental data, it includes: Performing data cleaning on the real-time environment data to obtain cleaned data of the real-time environment data; Determining a data weight of the cleansed data according to the association relationship; A target state value of the airport navigation light is generated according to the data weight and the cleaning data.

[0076] In detail, before generating the target state value, it is necessary to first collect and preprocess various environmental data, such as meteorological data (temperature, humidity, wind speed, etc.), light intensity, power data, etc., including: removing noise data, filling missing values, processing outliers and other data cleaning steps.

[0077] In detail, the target state value usually refers to the ideal working state of the airport navigation light after adjustment according to environmental data, which may include the following parameters: brightness value, switch state, power consumption and working mode. Among them, the brightness value is the working brightness of the lamp, which usually depends on the ambient light intensity. When the ambient light is strong, the brightness of the lamp can be reduced, otherwise the brightness needs to be increased to ensure visibility; the switch state is based on visibility (such as light intensity, weather conditions, etc.) and preset safety standards to decide whether to turn on the light; power consumption refers to minimizing the energy consumption of the lamp while meeting visibility requirements; working mode refers to selecting different working modes (for example, low power consumption mode, high brightness mode, etc.) according to changes in weather or time (such as day and night changes or excessive wind speed).

[0078] For example, the specific form of the target state value may be: brightness value: 0 (off) to 100% (maximum brightness); switch state: 1 (on), 0 (off); power consumption: unit power (such as watts); working mode: according to preset conditions (such as night mode, storm mode, etc.).

[0079] In detail, after obtaining the cleaned data, the next step is to determine the weight of each data item based on the association relationship (the influence relationship between environmental data and the status of the airport navigation light). Different environmental factors have different degrees of influence on the status of the lights, so different weights need to be assigned to different data.

[0080] In detail, a preliminary weight is assigned to each environmental factor (such as light intensity, temperature, wind speed, etc.) based on engineering experience and prior knowledge. For example, light intensity and visibility have a greater impact on the brightness of the lamp, while temperature may have a more important impact on power consumption.

[0081] The single light control module 106 is used to control the airport navigation light by using a preset light adjustment algorithm and the target state value.

[0082] In the embodiment of the present invention, when the single light control module 106 controls the airport navigation light by using a preset light adjustment algorithm and the target state value, the single light control module 106 includes: In detail, the preset lamp adjustment algorithm is: ; in, is the target state value, is the proportional gain, is the difference between the current state value and the target state, is the integral gain, is the integral variable of the integral term, is a time stamp, is the differential gain.

[0083] In detail, It is the final value to be adjusted, such as adjusting the brightness, temperature or voltage of the lamp; the proportional gain determines the direct response of the control system to the error. The larger the proportion, the stronger the system response will be when the error is larger. The larger the value, the more sensitive the system is to errors. The integral gain determines the system's response to long-term accumulated errors. In particular, when the error is small but lasts for a long time, the integral term can accelerate the correction of the deviation. The larger the gain, the faster the system will respond to long-term accumulated errors. The differential gain determines the system's response to the rate of error change. When the error changes rapidly, the differential term will respond in advance to reduce system oscillation and overreaction. The larger the value, the more sensitive the system is to changes in error; It is the integral variable of the integral term, usually an auxiliary variable of time, used to represent the time from time 0 to the current moment The error accumulation situation; It represents the rate of change of error over time, reflects the changing trend of the error, and is used to suppress the excessive response of the system.

[0084] In detail, if the target brightness is lower than the actual brightness (the error is negative), the proportional term This causes the controller to reduce output and brightness. If small errors exist for a long time (the effect of the integral term), the integral term will gradually increase, pushing the controller to adjust to eliminate these small deviations. If the brightness changes too quickly (the effect of the differential term), the differential term will make predictions and slow down adjustments to prevent excessive brightness changes. In this way, the brightness of the lamp can be adjusted to reach the target brightness as quickly and smoothly as possible through the combined effect of these three methods (proportional, integral, and differential).

[0085] In detail, assume that during the day (or when there is sufficient light), the brightness of the navigation lights should be low; at night or in low visibility conditions, the brightness of the lights should be increased. The state target value is the desired brightness value, which may be dynamically adjusted according to external environmental conditions (for example, darkness or weather changes) and can be calculated. The current brightness is the light brightness measured in real time by the sensor. This is usually the light intensity monitored by a photoelectric sensor.

[0086] Furthermore, if the sensor detects that the ambient brightness is very high (for example, strong sunlight), the target brightness will be set to a lower value (for example, 30% brightness). At this time, the current brightness may be close to the target value, and the output is reduced through the proportional term to maintain a lower brightness. If the ambient brightness does not change much, the integral term will not play a big role. If the weather gets darker, the target brightness will be set to a higher value (for example, 100% brightness). If the actual brightness of the light is lower than the target brightness, the brightness will be increased through the proportional term, and if the system is at low brightness for a long time, the integral term will gradually increase the output until the system reaches the set target brightness.

[0087] In short, the brightness of the airport navigation lights can be automatically adjusted under different environmental conditions to ensure flight safety. According to the error between the target brightness and the current brightness, the output is continuously adjusted to balance the response speed and stability so that the light brightness is always kept within a suitable range.

[0088] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0089] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is a theory, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An airport navigation light monitoring system based on Internet of Things communication technology, characterized in that: The system includes a data acquisition module, a matrix generation module, a data classification module, an association relationship generation module, a target state value generation module and a single lamp control module, wherein: The data acquisition module is used to collect sensor data of the airport navigation light, and generate an intra-class scatter matrix of the sensor data according to a preset intra-class algorithm, wherein the preset intra-class algorithm is: ; in, is the within-class scatter matrix, is the data category identifier, is the number of categories, It is The number of samples of the class, It is The covariance matrix of the class, It is The mean vector of the class, It is Transpose of the class mean vector; The matrix generation module is used to generate an intra-class scatter matrix of the sensor data according to a preset inter-class algorithm, wherein the preset inter-class algorithm is: ; in, is the between-class scatter matrix, is the data category identifier, is the number of categories, It is The number of samples of the class, is the overall mean vector of all samples, It is The mean vector of the class, is the transpose identity of a vector; The data classification module is used to classify the sensor data according to the intra-class scatter matrix and the inter-class scatter matrix to obtain classification data of the airport navigation light, wherein the classification data is single light status data and historical environment data; The association relationship generating module is used to generate an association relationship between the single lamp status data and the historical environment data; The target state value generating module is used to obtain the real-time environmental data of the airport navigation light, and generate the target state value of the airport navigation light according to the association relationship and the real-time environmental data; The single light control module is used to control the airport navigation light by using a preset light adjustment algorithm and the target state value, wherein the preset light adjustment algorithm is: ; in, is the target state value, is the proportional gain, is the difference between the current state value and the target state, is the integral gain, is the integral variable of the integral term, is a time stamp, is the differential gain.

2. The airport navigation light monitoring system based on Internet of Things communication technology as claimed in claim 1, characterized in that: When the data classification module performs data classification on the sensor data according to the intra-class scatter point matrix and the inter-class scatter point matrix to obtain the classification data of the airport navigation light, the data classification module includes: Generate an inverse matrix of the intra-class scatter matrix; generating a discriminant vector of the sensing data according to the inverse matrix and the inter-class scatter matrix; generating a characteristic equation of the sensing data according to the discriminant vector; The sensor data is classified according to the characteristic equation to obtain classification data of the airport navigation light.

3. The airport navigation light monitoring system based on Internet of Things communication technology as claimed in claim 2, characterized in that: When the data classification module generates a discriminant vector of the sensor data according to the inverse matrix and the inter-class scatter matrix, the data classification module includes: The discriminant vector is: ; in, is the discriminant vector of the characteristic equation, is the weight vector to be optimized, is the transpose identity of a vector, is the within-class scatter matrix, is the between-class scatter matrix, is the inverse matrix of the within-class scatter matrix, is the maximum value of the independent variable function.

4. The airport navigation light monitoring system based on Internet of Things communication technology as claimed in claim 2, characterized in that: When the data classification module executes the characteristic equation for generating the sensing data according to the discriminant vector, it includes: The characteristic equation is: ; in, is the identity matrix, is the eigenvalue, is the within-class scatter matrix, is the between-class scatter matrix, is the inverse of the within-class scatter matrix.

5. The airport navigation light monitoring system based on Internet of Things communication technology as claimed in claim 1, characterized in that: When the association relationship generating module generates the association relationship between the single lamp status data and the historical environment data, the module includes: Extracting the status timestamp of the single lamp status data; Extracting an environmental timestamp of the historical environmental data; Calculating the similarity between the state timestamp and the environment timestamp; An association relationship between the single lamp status data and the historical environment data is generated according to the similarity.

6. The airport navigation light monitoring system based on Internet of Things communication technology as claimed in claim 5, characterized in that: When the association relationship generation module calculates the similarity between the state timestamp and the environment timestamp, the association relationship generation module includes: Calculating a time difference between the state timestamp and the environment timestamp; The similarity between the state timestamp and the environment timestamp is determined according to the time difference.

7. The airport navigation light monitoring system based on Internet of Things communication technology as claimed in claim 5, characterized in that: When the association relationship generating module generates the association relationship between the single lamp state data and the historical environment data according to the similarity, the module includes: generating, according to the similarity, the correlation strength between the single lamp state data and the historical environment data; Determining an association weight between the single lamp state data and the historical environment data according to the association strength; An association relationship between the single lamp status data and the historical environment data is generated according to the association weight.

8. The airport navigation light monitoring system based on Internet of Things communication technology as claimed in claim 1, characterized in that: When the target state value generating module generates the target state value of the airport navigation light according to the association relationship and the real-time environmental data, the target state value generating module includes: Performing data cleaning on the real-time environment data to obtain cleaned data of the real-time environment data; Determining a data weight of the cleansed data according to the association relationship; A target state value of the airport navigation light is generated according to the data weight and the cleaning data.

Images