CN117320236A

CN117320236A - Lighting control method and system of unmanned aerial vehicle

Info

Publication number: CN117320236A
Application number: CN202311609379.1A
Authority: CN
Inventors: 曹广阔; 冯磊磊; 孔令中; 简亚东
Original assignee: Shenzhen Guangmingding Technology Co ltd
Current assignee: Shenzhen Guangmingding Technology Co ltd
Priority date: 2023-11-29
Filing date: 2023-11-29
Publication date: 2023-12-29
Anticipated expiration: 2043-11-29
Also published as: CN117320236B

Abstract

The application relates to the technical field of unmanned aerial vehicle control, and discloses an unmanned aerial vehicle illumination control method and system. The method comprises the following steps: performing flight state monitoring on the target unmanned aerial vehicle to obtain target flight state data, performing power detection and temperature detection to obtain target illumination power data and target equipment temperature data; performing state identification to obtain a flight state feature set and performing feature extraction to obtain an illumination power feature set and a device temperature feature set; performing feature code conversion to generate a power state influence vector and a temperature state influence vector; performing flight illumination analysis through a flight illumination analysis model to generate a flight illumination operation scheme; performing flight heat dissipation control analysis through a flight heat dissipation control model to obtain a flight heat dissipation control scheme; and the cooperative illumination control is performed, the abnormal state monitoring is performed, and the abnormal state processing scheme is output.

Description

Lighting control method and system of unmanned aerial vehicle

Technical Field

The application relates to the field of unmanned aerial vehicle control, in particular to an unmanned aerial vehicle illumination control method and system.

Background

The wide application of unmanned aerial vehicles promotes the requirements on the flight efficiency and safety of the unmanned aerial vehicles. With the rapid development of unmanned aerial vehicle technology, they are widely used in various fields such as geographical mapping, agricultural monitoring, disaster relief and the like. In these applications, the drone is often required to perform tasks in complex environments, such as night flights, operation in severe weather conditions, and the like. Therefore, an efficient illumination control method is developed, so that the operation efficiency of the unmanned aerial vehicle in the night or low-light environment can be improved, and the safety of the unmanned aerial vehicle in the task execution process can be greatly enhanced.

The development of intelligent control technology provides new possibilities for unmanned aerial vehicle illumination control. Along with the rapid progress of technologies such as big data, cloud computing, artificial intelligence and the like, the level of the intelligence of unmanned aerial vehicles is continuously improved. By integrating advanced sensors, data processing algorithms and control systems, the unmanned aerial vehicle can achieve more accurate and automated lighting control. The intelligent control not only can automatically adjust the lighting equipment according to the environment and the flight state, but also can monitor and respond to the potential abnormal state in real time, thereby improving the flexibility and reliability of the whole operation.

Along with the continuous expansion of the application field of unmanned aerial vehicles, the requirements on the functions of the unmanned aerial vehicles are increasing. The unmanned aerial vehicle is especially important in the task such as executing night photography, emergency rescue, efficient lighting control. The illumination control method can ensure that the unmanned aerial vehicle maintains good visual effect in a complex environment, and is beneficial to reducing energy consumption and prolonging equipment service life. Therefore, the technology not only improves the practicability of the unmanned aerial vehicle, but also lays a foundation for the application of the unmanned aerial vehicle in more fields.

Disclosure of Invention

The application provides an unmanned aerial vehicle's illumination control method and system for the intelligence of unmanned aerial vehicle's radiating efficiency and illumination operation has been improved.

In a first aspect, the present application provides an illumination control method of an unmanned aerial vehicle, where the illumination control method of the unmanned aerial vehicle includes:

performing flight state monitoring on a target unmanned aerial vehicle to obtain target flight state data, and performing power detection and temperature detection on lighting equipment of the target unmanned aerial vehicle to obtain target lighting power data and target equipment temperature data;

performing state identification on the target flight state data to obtain a flight state feature set, and performing feature extraction on the target illumination power data and the target equipment temperature data to obtain an illumination power feature set and an equipment temperature feature set;

performing feature code conversion on the illumination power feature set and the flight state feature set to generate corresponding power state influence vectors, and performing feature code conversion on the equipment temperature feature set and the flight state feature set to generate corresponding temperature state influence vectors;

inputting the power state influence vector into a preset flight illumination analysis model to carry out flight illumination analysis, and generating a flight illumination operation scheme;

Inputting the temperature state influence vector into a preset flight heat dissipation control model for flight heat dissipation control analysis to obtain a flight heat dissipation control scheme;

and carrying out cooperative illumination control on the target unmanned aerial vehicle according to the flight illumination operation scheme and the flight heat dissipation control scheme, monitoring abnormal states of illumination equipment of the target unmanned aerial vehicle, and outputting an abnormal state processing scheme.

In a second aspect, the present application provides a lighting control system of an unmanned aerial vehicle, the lighting control system of an unmanned aerial vehicle comprising:

the monitoring module is used for monitoring the flight state of the target unmanned aerial vehicle to obtain target flight state data, and carrying out power detection and temperature detection on the lighting equipment of the target unmanned aerial vehicle to obtain target lighting power data and target equipment temperature data;

the identification module is used for carrying out state identification on the target flight state data to obtain a flight state feature set, and carrying out feature extraction on the target illumination power data and the target equipment temperature data to obtain an illumination power feature set and an equipment temperature feature set;

the coding module is used for carrying out feature coding conversion on the illumination power feature set and the flight state feature set to generate corresponding power state influence vectors, and carrying out feature coding conversion on the equipment temperature feature set and the flight state feature set to generate corresponding temperature state influence vectors;

The illumination analysis module is used for inputting the power state influence vector into a preset flight illumination analysis model to carry out flight illumination analysis and generate a flight illumination operation scheme;

the heat dissipation analysis module is used for inputting the temperature state influence vector into a preset flight heat dissipation control model to carry out flight heat dissipation control analysis, so as to obtain a flight heat dissipation control scheme;

and the cooperative control module is used for carrying out cooperative lighting control on the target unmanned aerial vehicle according to the flight lighting operation scheme and the flight heat dissipation control scheme, carrying out abnormal state monitoring on lighting equipment of the target unmanned aerial vehicle and outputting an abnormal state processing scheme.

According to the technical scheme, the method can accurately adjust the illumination intensity and the mode by monitoring the flight state data of the unmanned aerial vehicle and the power and temperature data of the illumination equipment in real time so as to adapt to different flight conditions and environment requirements. This not only improves the energy efficiency of the illumination, but also ensures an optimal illumination effect in various environments. According to the method, the flight state of the unmanned aerial vehicle and the running state of the lighting equipment are monitored and analyzed in real time, and the lighting strategy and the heat dissipation control are timely adjusted, so that the safe flight of the unmanned aerial vehicle in a complex environment is ensured. Meanwhile, the abnormal state of the lighting equipment is monitored and processed in real time, so that the reliability of the unmanned aerial vehicle is further improved. By utilizing advanced data processing and analysis technology, the method can automatically identify and respond to the change of the flight state, and the intellectualization of illumination and heat dissipation control is realized. This reduces the need for manual intervention and improves operating efficiency and accuracy. By optimizing the illumination power and the heat dissipation control, the method is beneficial to reducing the energy consumption, thereby reducing the battery burden and prolonging the flight time and the equipment life of the unmanned aerial vehicle. In the long term, this is not only beneficial to environmental protection, but also reduces the operation and maintenance costs. The control method is flexible in design and easy to adjust and optimize according to unmanned aerial vehicles of different types and specifications. In addition, the core technology and principle of the unmanned aerial vehicle system can be applied to other unmanned aerial vehicle systems, and the unmanned aerial vehicle system has good expansibility, so that the heat dissipation efficiency of the unmanned aerial vehicle and the intelligence of lighting operation are improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained based on these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic view of an embodiment of a method for controlling illumination of a drone according to an embodiment of the present application;

fig. 2 is a schematic view of an embodiment of a lighting control system of a drone in an embodiment of the present application.

Detailed Description

The embodiment of the application provides an illumination control method and system of an unmanned aerial vehicle. The terms "first," "second," "third," "fourth" and the like in the description and in the claims of this application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

For ease of understanding, the following describes a specific flow of an embodiment of the present application, referring to fig. 1, and one embodiment of a method for controlling illumination of a drone in an embodiment of the present application includes:

step S101, performing flight state monitoring on a target unmanned aerial vehicle to obtain target flight state data, and performing power detection and temperature detection on lighting equipment of the target unmanned aerial vehicle to obtain target lighting power data and target equipment temperature data;

it may be understood that the execution body of the present application may be a lighting control system of an unmanned aerial vehicle, and may also be a terminal or a server, which is not limited herein. The embodiment of the present application will be described by taking a server as an execution body.

Specifically, first, the flight state of the target unmanned aerial vehicle is monitored through a preset Inertial Measurement Unit (IMU) sensor array, which includes real-time collection of flight parameters such as speed, altitude, attitude and the like, so as to obtain initial flight state data. Meanwhile, power detection is carried out on the lighting equipment through a power sensor array arranged on the unmanned aerial vehicle, and temperature detection is carried out on the lighting equipment through a temperature sensor array, so that initial lighting power data and initial equipment temperature data are respectively obtained. These sensor arrays are not only capable of providing accurate real-time data, but also capable of ensuring accuracy and reliability of data through their high sensitivity. These initial data are then transmitted to a preset central control system, respectively. The system is responsible for carrying out data filtering and denoising processing on the collected initial flight state data, so that more accurate and clean target flight state data are obtained. In the data filtering and denoising process, advanced algorithms such as a Kalman filter are adopted to remove noise introduced by factors such as sensor errors, environmental interference and the like, so that the data quality is ensured. The central control system then performs standard deviation threshold calculations on the initial lighting power data and the initial device temperature data. Through this calculation, the system determines the normal fluctuation range of the data, and sets the first standard deviation threshold value and the second standard deviation threshold value accordingly. Then, the central control system performs an outlier removal process on the initial illumination power data and the initial device temperature data by these standard deviation thresholds. And data anomalies caused by abnormal factors such as equipment faults, environmental changes and the like are eliminated, so that the accuracy and reliability of the obtained target illumination power data and the target equipment temperature data are ensured. Finally, the processed target illumination power data and target equipment temperature data are used in a subsequent unmanned aerial vehicle illumination control flow so as to realize efficient and accurate control of an unmanned aerial vehicle illumination system.

Step S102, carrying out state identification on target flight state data to obtain a flight state feature set, and respectively carrying out feature extraction on target illumination power data and target equipment temperature data to obtain an illumination power feature set and an equipment temperature feature set;

specifically, first, a plurality of state parameter labels of a target unmanned aerial vehicle are acquired, wherein the state parameter labels comprise key parameters such as position, speed, height and gesture. These parameter tags provide the necessary dimensions for status recognition, making analysis of flight status more comprehensive and accurate. Next, a plurality of status parameter cluster centers for the target flight status data are determined based on the plurality of status parameter tags. Similar status data are grouped by a cluster analysis method, such as K-means clustering, to identify representative flight status patterns. And then, mapping the characteristic value of the target state parameter clustering result of each state parameter clustering center, and further obtaining a flight state characteristic set. In this process, the function of the eigenvalue mapping is to convert the raw flight status data into a more abstract and generalized representation of the characteristics, facilitating subsequent data processing and analysis. In order to further analyze the variation characteristics of the illumination power and the device temperature, the system also needs to acquire first time stamp data of the target illumination power data and second time stamp data of the target device temperature data. Next, curve fitting is performed on the target illumination power data and the first timestamp data to generate an illumination power variation curve. In this process, curve fitting can not only reveal the trend of power data over time, but also help identify key change nodes or feature points. By identifying and extracting these feature points, a set of illumination power features can be derived that assist in understanding and predicting the performance of the unmanned lighting system. The same method is also used for processing the target equipment temperature data and the second timestamp data, obtaining an equipment temperature change curve through curve fitting, further identifying and extracting characteristic points, and finally obtaining an equipment temperature characteristic set. Through the steps, the system not only can accurately capture and analyze the flight state of the unmanned aerial vehicle, but also can deeply understand the change rule of the illumination power and the equipment temperature. These analysis results provide a data basis for subsequent lighting control.

Step S103, performing feature code conversion on the illumination power feature set and the flight state feature set to generate corresponding power state influence vectors, and performing feature code conversion on the equipment temperature feature set and the flight state feature set to generate corresponding temperature state influence vectors;

specifically, firstly, the mean value and standard deviation of the flight state feature set are calculated, and the statistical characteristics of the flight state features, including the average level and the variation degree, are obtained, so that a basis is provided for subsequent feature weight distribution. The same calculations are also applied to the illumination power feature set and the device temperature feature set to obtain the mean and standard deviation of these features. Next, calculation of the difference coefficient is performed based on these statistical results. The difference coefficient is an important index describing the variation degree of the features relative to the mean value, and can reflect the relative importance of different features. The first coefficient of difference may be obtained by calculating a state characteristic mean, a state characteristic standard deviation, a power characteristic mean, and a coefficient of difference of the power characteristic standard deviation. The calculation of the first coefficient of difference is used to generate first feature weight data reflecting the relative importance of the different features throughout the lighting control system. And then, performing feature code conversion on the illumination power feature set and the flight state feature set according to the first feature weight data to generate corresponding power state influence vectors. The raw feature data is transformed by encoding into a form usable by the model, i.e. an influence vector. These impact vectors not only contain critical information of the original data, but also fuse the relative importance between features, thereby providing more accurate and efficient inputs for subsequent control decisions. And then, calculating a second difference coefficient by carrying out difference coefficient calculation on the state characteristic mean value, the state characteristic standard deviation, the temperature characteristic mean value and the temperature characteristic standard deviation. The second coefficient of difference is also used to generate second feature weight data that is then used to feature code the device temperature feature set and the flight state feature set to generate corresponding temperature state impact vectors.

Step S104, inputting the power state influence vector into a preset flight illumination analysis model for flight illumination analysis, and generating a flight illumination operation scheme;

specifically, first, a power state influence vector is input into a preset flight illumination analysis model. The model is a multi-level neural network structure, and comprises an input layer, a plurality of strategy analysis network layers and an output layer. The input layer then receives the power state impact vector and normalizes it to generate a normalized power state vector. The purpose of standardization is to unify the scales of different data sources and ensure the accuracy and consistency of model analysis. This normalized power state vector is then distributed to a plurality of policy analysis networks in the model. Each policy analysis network contains a random forest network, which is an efficient integrated learning method, and complex data analysis and pattern recognition are performed by constructing a plurality of decision trees. Each random forest network is responsible for detailed illumination intensity and illumination pattern analysis of the standard power state vector, generating an initial illumination strategy for each case. The advantage of a random forest network is that it can handle a large number of input features and has a strong resistance to data noise, which makes it suitable for illumination analysis in complex and diverse flight environments. These different random forest network generated initial lighting policies are then summarized to the output layer. At the output level, these strategies are subjected to a comprehensive fusion process to produce the final flight lighting operation scheme. The strategy fusion considers a plurality of initial lighting strategies generated by each strategy analysis network, integrates the advantages of the strategies, and eliminates redundant or contradictory parts to obtain a comprehensive and efficient flight lighting operation scheme. The operation scheme not only considers the optimization of illumination intensity and mode, but also considers the current flight state and energy efficiency of the unmanned aerial vehicle, ensures that the energy efficiency and flight safety of the unmanned aerial vehicle are ensured while the illumination requirement is met.

Step S105, inputting the temperature state influence vector into a preset flight heat dissipation control model for flight heat dissipation control analysis to obtain a flight heat dissipation control scheme;

specifically, firstly, a temperature state influence vector is input into a preset flight heat dissipation control model, wherein the model is a complex neural network and comprises three main parts of a double-layer threshold circulation unit, a single-layer threshold circulation unit and a fully-connected network. In the first part of the model, namely a double-layer threshold circulation unit, 256 threshold circulation units are used for carrying out deep feature analysis on the input temperature state influence vector, so that a temperature hidden feature vector is extracted. These threshold cycle units perform well in processing time series data and are capable of effectively capturing the time-varying dynamics of temperature data. And then, carrying out feature decoding on the temperature hidden feature vectors through 128 threshold circulating units in the single-layer threshold circulating unit, and further carrying out decoding processing on the hidden feature vectors, so as to obtain a target decoded feature sequence, and converting the complex temperature features into a more specific and operable form, thereby providing a foundation for the final heat dissipation control parameters. Finally, the target decoding feature sequence is operated through ReLU (Rectified Linear Unit) functions in the fully connected network of the model to generate a flight heat dissipation control parameter set. The ReLU function has remarkable effect in dealing with the nonlinear problem, and can effectively enhance the learning capacity and the expression capacity of the model. By using the control parameters, the finally formed flight heat dissipation control scheme not only can accurately adjust the heat dissipation system of the unmanned aerial vehicle, but also can make corresponding adjustment according to different flight conditions and environmental changes. Through the series of processing and conversion, the flight heat dissipation control model can convert complex temperature state data into a practical heat dissipation control scheme, so that the temperature of the unmanned aerial vehicle when the unmanned aerial vehicle executes tasks is always kept within a safe range. The intelligent temperature management strategy not only improves the reliability and safety of the unmanned aerial vehicle, but also prolongs the service life of the unmanned aerial vehicle, and provides powerful guarantee for the efficient operation of the unmanned aerial vehicle.

And S106, performing cooperative illumination control on the target unmanned aerial vehicle according to the flight illumination operation scheme and the flight heat dissipation control scheme, performing abnormal state monitoring on illumination equipment of the target unmanned aerial vehicle, and outputting an abnormal state processing scheme.

Specifically, first, the flight lighting operation scheme and the flight heat dissipation control scheme are integrated comprehensively to form a unified unmanned aerial vehicle lighting control scheme. This integration process not only requires optimization of the illumination intensity and pattern, but also the heat dissipation requirements and the overall performance of the drone. By integrating the two schemes, the unmanned aerial vehicle can ensure that the unmanned aerial vehicle can keep good lighting effect and effectively control the temperature of equipment when executing tasks, thereby avoiding damage caused by overheating. And then, carrying out cooperative illumination control on the target unmanned aerial vehicle according to an unmanned aerial vehicle illumination control scheme through a preset multivariable cooperative control algorithm. The algorithm dynamically adjusts the power of the lighting device and the running state of the heat dissipation system based on the actual flight condition and environmental changes of the unmanned aerial vehicle. The key to a multivariable cooperative control algorithm is that it is capable of processing multiple input variables simultaneously and making fast and accurate control decisions based on real-time changes in these variables. The application of the algorithm ensures that the illumination and heat dissipation systems of the unmanned aerial vehicle can work cooperatively and efficiently in various flight environments. And then, monitoring the abnormal state of the lighting equipment of the target unmanned aerial vehicle to obtain abnormal state monitoring data. By continuously collecting operational data of the lighting device, such as power consumption, temperature variations, etc., the system is able to discover any abnormal conditions in time. The abnormal state monitoring data are then used to perform abnormal state processing matching, identify the cause of the fault by analyzing the monitoring data, and output a corresponding abnormal state processing scheme according to the information. For example, if the monitored data indicates an abnormal rise in the temperature of the lighting device, the system may present a treatment regimen that reduces power consumption or enhances heat dissipation.

According to the method, the illumination intensity and the mode can be accurately adjusted by monitoring the flight state data of the unmanned aerial vehicle and the power and temperature data of the illumination equipment in real time so as to adapt to different flight conditions and environment requirements. This not only improves the energy efficiency of the illumination, but also ensures an optimal illumination effect in various environments. According to the method, the flight state of the unmanned aerial vehicle and the running state of the lighting equipment are monitored and analyzed in real time, and the lighting strategy and the heat dissipation control are timely adjusted, so that the safe flight of the unmanned aerial vehicle in a complex environment is ensured. Meanwhile, the abnormal state of the lighting equipment is monitored and processed in real time, so that the reliability of the unmanned aerial vehicle is further improved. By utilizing advanced data processing and analysis technology, the method can automatically identify and respond to the change of the flight state, and the intellectualization of illumination and heat dissipation control is realized. This reduces the need for manual intervention and improves operating efficiency and accuracy. By optimizing the illumination power and the heat dissipation control, the method is beneficial to reducing the energy consumption, thereby reducing the battery burden and prolonging the flight time and the equipment life of the unmanned aerial vehicle. In the long term, this is not only beneficial to environmental protection, but also reduces the operation and maintenance costs. The control method is flexible in design and easy to adjust and optimize according to unmanned aerial vehicles of different types and specifications. In addition, the core technology and principle of the unmanned aerial vehicle system can be applied to other unmanned aerial vehicle systems, and the unmanned aerial vehicle system has good expansibility, so that the heat dissipation efficiency of the unmanned aerial vehicle and the intelligence of lighting operation are improved.

In a specific embodiment, the process of executing step S101 may specifically include the following steps:

(1) Carrying out flight state monitoring on the target unmanned aerial vehicle through a preset IMU sensor array to obtain initial flight state data;

(2) Performing power detection on the lighting equipment of the target unmanned aerial vehicle through a preset power sensor array to obtain initial lighting power data, and performing temperature detection on the lighting equipment of the target unmanned aerial vehicle through a preset temperature sensor array to obtain initial equipment temperature data;

(3) Transmitting initial flight state data, initial illumination power data and initial equipment temperature data to a preset central control system respectively;

(4) The method comprises the steps of performing data filtering and data denoising on initial flight state data through a central control system to obtain target flight state data;

(5) Respectively carrying out standard deviation threshold calculation on the initial illumination power data and the initial equipment temperature data through a central control system to obtain a first standard deviation threshold of the initial illumination power data and a second standard deviation threshold of the initial equipment temperature data;

(6) And performing outlier removal on the initial illumination power data through a first standard deviation threshold to obtain target illumination power data, and performing outlier removal on the initial equipment temperature data through a second standard deviation threshold to obtain target equipment temperature data.

Specifically, first, the unmanned aerial vehicle is subjected to flight state monitoring through a preset IMU (inertial measurement unit) sensor array. The IMU sensor array is capable of accurately measuring acceleration, rotational rate and direction of the drone, thereby providing initial flight state data regarding the drone's position, speed and attitude. For example, when the unmanned aerial vehicle performs a flight mission in the air, the IMU sensor array may capture key flight parameters such as its inclination angle, altitude variation, and acceleration in real time. To ensure efficient operation of the lighting system, the drone is also equipped with a power sensor array and a temperature sensor array. The power sensor array monitors the power consumption of the unmanned aerial vehicle lighting device, and initial lighting power data are obtained. For example, if the drone is flying at night, the power sensor may record the amount of power consumed by the light fixtures to facilitate monitoring and control of energy consumption. At the same time, the temperature sensor array monitors the temperature of the lighting device to obtain initial device temperature data. For example, when performing tasks in a high temperature environment, the temperature sensor can detect the temperature rise of the lighting device in time so as to take corresponding measures. These initial flight status data, initial illumination power data and initial equipment temperature data are then transmitted to a preset central control system, respectively. The central control system is the brain of the unmanned lighting control, which is responsible for processing and analyzing the data collected from the various sensors. When processing the initial flight state data, the central control system performs data filtering and denoising operations to ensure that accurate target flight state data is obtained. For example, by using a Kalman filter or other advanced filtering algorithm, noise due to sensor errors or external environmental disturbances may be removed, thereby obtaining more accurate flight status information. And meanwhile, the central control system calculates standard deviation threshold values of the initial illumination power data and the initial equipment temperature data, identifies and eliminates abnormal values, and ensures the reliability and the effectiveness of the data. For example, by calculating the standard deviation of the initial illumination power data, the system determines the normal fluctuation range of the power data beyond which data is caused by equipment failure or other abnormal conditions, should be regarded as abnormal values and rejected. The same method is also used to process the initial device temperature data, and by calculating a second standard deviation threshold, the system is able to identify abnormal fluctuations in the temperature data. After determining the first and second standard deviation thresholds, the central control system performs outlier removal on the initial illumination power data and the initial device temperature data, respectively. For example, if the illumination power data at a certain moment is well above the average level and exceeds the first standard deviation threshold, this data point will be considered abnormal and rejected. Similarly, if the detected device temperature suddenly rises to an abnormal range, this temperature reading is also excluded.

In a specific embodiment, the process of executing step S102 may specifically include the following steps:

(1) Acquiring a plurality of state parameter tags of the target unmanned aerial vehicle, wherein the plurality of state parameter tags comprise: position parameter labels, speed parameter labels, altitude parameter labels and attitude parameter labels;

(2) Determining a plurality of state parameter clustering centers of the target flight state data according to the plurality of state parameter labels, and performing feature clustering on the target flight state data through the plurality of state parameter clustering centers to obtain a target state parameter clustering result of each state parameter clustering center;

(3) Respectively mapping the characteristic values of the target state parameter clustering results to obtain a flight state characteristic set;

(4) Acquiring first time stamp data of target illumination power data and second time stamp data of target equipment temperature data;

(5) Performing curve fitting on the target illumination power data and the first timestamp data to obtain an illumination power change curve, and performing feature point identification and extraction on the illumination power change curve to obtain an illumination power feature set;

(6) And performing curve fitting on the target equipment temperature data and the second timestamp data to obtain an equipment temperature change curve, and performing characteristic point identification and extraction on the equipment temperature change curve to obtain an equipment temperature characteristic set.

Specifically, first, a plurality of state parameter tags of the target unmanned aerial vehicle are acquired. These status parameters include position parameters, speed parameters, altitude parameters and attitude parameters, each of which provides critical information for the unmanned aerial vehicle under certain flight conditions. For example, the position parameter can tell the system the exact position of the drone in space, the speed parameter shows how fast it is moving, the altitude parameter shows the vertical distance of the drone from the ground, and the attitude parameter describes the degree of tilt of the drone from the horizontal. Next, based on these status parameters, the system determines a plurality of status parameter cluster centers for the target flight status data. The flight status data is divided into several categories, each category representing a particular flight status, by using a clustering algorithm, such as a K-means algorithm. For example, one set of data represents a low speed flight condition, while another set of data represents a high speed flight condition. The classification method is helpful for more clearly understanding the behavior patterns of the unmanned aerial vehicle under different flight conditions. And then, mapping the characteristic value of the target state parameter clustering result of each state parameter clustering center to obtain a flight state characteristic set. Eigenvalue mapping is a process that converts raw data into a form that is easier to analyze and process. For example, complex raw data can be converted into a simpler form by dimension reduction or transformation of the clustering results, thereby facilitating further data analysis and application. Then, the system obtains first time stamp data of the target illumination power data and second time stamp data of the target device temperature data. These time stamp data provide key information on the illumination power and device temperature over time, which is the basis for effective control. For example, the first timestamp data shows that during night-time tasks, the illumination power gradually increases over time. Next, the system curve fits the target illumination power data and the first timestamp data to obtain an illumination power variation curve. Curve fitting is a statistical method for finding the best matching curve between data points. For example, by fitting using a polynomial or exponential function, it is possible to describe exactly how the illumination power varies with time. Once the curve fitting is completed, the system identifies and extracts feature points of the illumination power variation curve to obtain an illumination power feature set. Feature point extraction is a process of identifying important change points in data, such as power peaks or abrupt changes. Similarly, the system also curve fits the target device temperature data and the second time stamp data to obtain a device temperature profile. This may help the system understand the trend of temperature change of the lighting device during operation. For example, if the temperature profile shows a sharp rise in temperature over a certain period of time, this indicates that the device is overheating and that measures need to be taken for cooling. By identifying and extracting feature points from these curves, the system is able to obtain a set of device temperature features that facilitate the implementation of an effective heat dissipation control strategy.

In a specific embodiment, the process of executing step S103 may specifically include the following steps:

(1) Calculating the mean value and standard deviation of the flight state feature set to obtain a state feature mean value and a state feature standard deviation;

(2) Calculating the mean value and standard deviation of the illumination power feature set to obtain a power feature mean value and a power feature standard deviation, and calculating the mean value and standard deviation of the equipment temperature feature set to obtain a temperature feature mean value and a temperature feature standard deviation;

(3) Calculating a difference coefficient of the state characteristic mean value, the state characteristic standard deviation, the power characteristic mean value and the power characteristic standard deviation to obtain a first difference coefficient, and generating first characteristic weight data according to the first difference coefficient;

(4) Performing feature code conversion on the illumination power feature set and the flight state feature set according to the first feature weight data to generate corresponding power state influence vectors;

(5) Calculating a difference coefficient of the state characteristic mean value, the state characteristic standard deviation, the temperature characteristic mean value and the temperature characteristic standard deviation to obtain a second difference coefficient, and generating second characteristic weight data according to the second difference coefficient;

(6) And performing feature code conversion on the equipment temperature feature set and the flight state feature set according to the second feature weight data to generate corresponding temperature state influence vectors.

Specifically, firstly, the system calculates the mean value and standard deviation of the flight state feature set, and comprehensively analyzes a plurality of flight parameters such as the position, speed, height and attitude of the unmanned aerial vehicle. The mean and standard deviation are calculated to obtain the average level for each flight state and its range of variation. For example, by calculating the average speed and standard deviation of the speed change of the drone over a period of time, important information about the speed stability of the drone may be obtained. The same calculation method is also applicable to the illumination power feature set and the device temperature feature set. The mean value and standard deviation calculation of the illumination power feature set can reveal the average energy consumption of the unmanned aerial vehicle illumination system and the fluctuation condition of the unmanned aerial vehicle illumination system under different flight conditions. For example, if the average value of the illumination power is relatively high and the standard deviation is small during night flight tasks, this indicates that the illumination system is high in energy consumption but relatively stable during night operation. For a device temperature feature set, calculating its mean and standard deviation can help monitor and control the temperature of the lighting device, preventing overheating. For example, if the standard deviation of the temperature signature is large, this means that the device is prone to overheating under certain flight conditions. Further, the system performs coefficient of difference calculations on the mean and standard deviation of these features. The difference coefficient is an index describing the variation degree of the data relative to the average value, and can reflect the relative importance of different characteristics. For example, if the coefficient of variation of the illumination power characteristics is relatively large, this means that the energy consumption of the illumination system varies widely in different flight conditions, which requires special attention. The first difference coefficient obtained through calculation is used for generating first characteristic weight data, and the data can reflect the relative importance of each characteristic in unmanned aerial vehicle illumination control. Next, based on the first feature weight data, the system performs feature code conversion on the illumination power feature set and the flight state feature set, thereby generating corresponding power state impact vectors. The raw feature data is transformed by encoding into a form usable by the model, i.e. an influence vector. These impact vectors contain key information of the original data, and combine the relative importance between features to provide a more accurate and efficient input for subsequent control decisions. And finally, calculating a second difference coefficient by carrying out difference coefficient calculation on the state characteristic mean value, the state characteristic standard deviation, the temperature characteristic mean value and the temperature characteristic standard deviation. This second coefficient of difference is used to generate second feature weight data that is then used to feature code the device temperature feature set and the flight state feature set to generate corresponding temperature state impact vectors.

In a specific embodiment, the process of executing step S104 may specifically include the following steps:

(1) Inputting the power state influence vector into a preset flight illumination analysis model, wherein the flight illumination analysis model comprises an input layer, a plurality of strategy analysis networks and an output layer;

(2) Receiving a power state influence vector through an input layer, and carrying out standardization processing on the power state influence vector to obtain a standard power state vector;

(3) Distributing the standard power state vector to a plurality of strategy analysis networks, and analyzing the illumination intensity and the illumination mode of the standard power state vector through a random forest network in each strategy analysis network to obtain an initial illumination strategy corresponding to each strategy analysis network;

(4) And carrying out strategy fusion on the initial lighting strategy corresponding to each strategy analysis network through the output layer to obtain a flight lighting operation scheme.

Specifically, firstly, a flight illumination analysis model is constructed, and the model mainly comprises three parts: an input layer, a plurality of policy analysis networks, and an output layer. The input layer is responsible for receiving the power state impact vector. The power state impact vector contains comprehensive information about the power usage and flight status of the drone lighting system. And carrying out standardization processing on the power state influence vector. The purpose of the normalization process is to convert the data into a format with a uniform standard, which helps to reduce the impact of different data scales and distributions, ensuring accuracy and consistency of model analysis. For example, if the raw power data ranges between 0 and 1000 watts, the system converts these data to values in the range of 0 to 1 by a normalization process. Next, the normalized power state vector is distributed to a plurality of policy analysis networks in the model. These policy analysis networks are the core of the model, each comprising a random forest network, which is an integrated learning method based on multiple decision trees. Random forest networks perform well in processing complex data and finding patterns in data, particularly in non-linear and highly dimensional data analysis tasks. Each random forest network is used to perform detailed illumination intensity and illumination pattern analysis on the standard power state vector. For example, one network focuses on analyzing lighting requirements at low flight speeds, while another network analyzes lighting requirements at high flight speeds. In this way, each policy analysis network is able to generate an initial lighting policy for a particular flight condition. And finally, carrying out strategy fusion on the initial lighting strategy corresponding to each strategy analysis network through an output layer to obtain a flight lighting operation scheme. Policy fusion takes into account policies that are analyzed from multiple perspectives and combines the advantages of these policies, excluding redundant or contradictory parts. For example, if two strategic analysis networks recommend higher and lower illumination intensities, respectively, the output layer needs to determine an equilibrium illumination intensity based on factors such as flight status and energy efficiency.

In a specific embodiment, the process of executing step S105 may specifically include the following steps:

(1) Inputting a temperature state influence vector into a preset flight heat dissipation control model, wherein the flight heat dissipation control model comprises a double-layer threshold circulation unit, a single-layer threshold circulation unit and a fully-connected network;

(2) Carrying out temperature hiding feature extraction on the temperature state influence vector through 256 threshold circulating units in the double-layer threshold circulating units to obtain a temperature hiding feature vector;

(3) Performing feature decoding on the temperature hidden feature vector through 128 threshold circulating units in the single-layer threshold circulating units to obtain a target decoding feature sequence;

(4) Performing flight heat dissipation control parameter operation on the target decoding feature sequence through a ReLU function in the fully connected network, and outputting a flight heat dissipation control parameter set;

(5) And carrying out scheme integration on the flight heat dissipation control parameter set to obtain a flight heat dissipation control scheme.

Specifically, firstly, a temperature state influence vector is input into a preset flight heat dissipation control model, and the model comprises three key parts: a double-layer threshold circulation unit, a single-layer threshold circulation unit and a fully connected network. And carrying out temperature hiding feature extraction on the temperature state influence vector through 256 threshold circulating units in the double-layer threshold circulating unit to obtain a temperature hiding feature vector. The threshold cycling unit is capable of effectively capturing the time-varying dynamics of the temperature data. For example, if the drone is performing a long flight mission, the dual threshold cycle unit may capture a tendency for temperature to gradually rise due to continuous operation. And then, performing feature decoding on the temperature hidden feature vector through 128 threshold circulating units in the single-layer threshold circulating unit to obtain a target decoding feature sequence. Converting complex temperature characteristics into a more specific and operational form provides a basis for final heat dissipation control parameters. For example, by means of these threshold cycling units, the system identifies key points of change in the device temperature during a particular flight phase, which information is helpful for achieving effective temperature control. And finally, carrying out flight heat dissipation control parameter operation on the target decoding characteristic sequence through a ReLU function in the fully connected network, and outputting a flight heat dissipation control parameter set. The ReLU function can effectively enhance the learning ability and the expression ability of the model. Through the operation of the fully connected network, the system can extract the flight heat dissipation control parameter set from the target decoding characteristic sequence. These parameter sets are the core of the heat dissipation control strategy, which provide specific control instructions for the unmanned aerial vehicle heat dissipation system based on key features extracted from the temperature state data. Next, the system performs comprehensive analysis and scheme integration on these flight heat dissipation control parameter sets to form the final flight heat dissipation control scheme. The process of this solution integration involves evaluating and integrating the interactions and effects of the different heat dissipation parameters to ensure optimal heat dissipation in actual flight.

In a specific embodiment, the process of executing step S106 may specifically include the following steps:

(1) Carrying out scheme integration on the flight lighting operation scheme and the flight heat dissipation control scheme to obtain an unmanned aerial vehicle lighting control scheme;

(2) Carrying out cooperative illumination control on the target unmanned aerial vehicle according to an unmanned aerial vehicle illumination control scheme by a preset multivariable cooperative control algorithm;

(3) Abnormal state monitoring is carried out on the lighting equipment of the target unmanned aerial vehicle, and abnormal state monitoring data are obtained;

(4) And carrying out abnormal state processing matching on the abnormal state monitoring data, and outputting an abnormal state processing scheme.

Specifically, first, a flight lighting operation scheme and a flight heat dissipation control scheme are subjected to scheme integration to obtain an unmanned aerial vehicle lighting control scheme. While flying lighting operation schemes typically include control strategies for the light intensity, light pattern, and run time of the unmanned lighting system, flying heat dissipation control schemes focus on how to efficiently manage the unmanned heat dissipation system to avoid overheating and maintain the device in an optimal operating state. The key to solution integration is to find the best balance point between these two solutions to ensure that the device temperature is effectively controlled while providing adequate illumination. And then, carrying out cooperative illumination control on the target unmanned aerial vehicle according to the comprehensive unmanned aerial vehicle illumination control scheme by a preset multivariable cooperative control algorithm. A multivariable cooperative control algorithm is an advanced control method capable of processing data and control requirements from a plurality of different sources and making optimal control decisions accordingly. The algorithm may analyze the flight status, environmental conditions, and operational data of the lighting system and the heat dissipation system of the unmanned aerial vehicle in real time, and then adjust the lighting intensity, pattern, and heat dissipation strategy to adapt to the changing flight conditions. For example, when the drone enters a dark environment, the cooperative control algorithm increases the illumination intensity, and when the temperature sensor detects an increase in the device temperature, the heat dissipation efficiency is enhanced. And then, monitoring the abnormal state of the lighting equipment of the target unmanned aerial vehicle to obtain abnormal state monitoring data. Abnormal state monitoring is mainly to track the operation states of the unmanned aerial vehicle lighting system and related equipment, such as power consumption, temperature change, light intensity and the like, in real time through various sensors so as to discover any abnormal signs in time. For example, if a certain sensor suddenly detects an abnormal rise in the temperature of the lighting device, which is a signal of overload or device failure, immediate measures need to be taken. Finally, the system analyzes the collected abnormal state monitoring data to determine an appropriate abnormal state handling scheme. This includes classifying the anomaly data, analyzing the cause and effect, and formulating corresponding emergency measures. For example, if the temperature increase of the lighting device is found to be due to an increase in the external ambient temperature, the treatment regimen is to temporarily decrease the lighting intensity or adjust the flight path to avoid overheating. If the anomaly is caused by a device failure, the system needs to activate the backup lighting device while sending a failure report for repair or replacement.

The method for controlling the illumination of the unmanned aerial vehicle in the embodiment of the present application is described above, and the following describes the system for controlling the illumination of the unmanned aerial vehicle in the embodiment of the present application, referring to fig. 2, an embodiment of the system for controlling the illumination of the unmanned aerial vehicle in the embodiment of the present application includes:

the monitoring module 201 is configured to monitor a flight state of a target unmanned aerial vehicle to obtain target flight state data, and perform power detection and temperature detection on a lighting device of the target unmanned aerial vehicle to obtain target lighting power data and target device temperature data;

the identifying module 202 is configured to perform state identification on the target flight state data to obtain a flight state feature set, and perform feature extraction on the target illumination power data and the target equipment temperature data to obtain an illumination power feature set and an equipment temperature feature set;

the encoding module 203 is configured to perform feature encoding conversion on the illumination power feature set and the flight state feature set to generate corresponding power state influence vectors, and perform feature encoding conversion on the equipment temperature feature set and the flight state feature set to generate corresponding temperature state influence vectors;

The illumination analysis module 204 is configured to input the power state impact vector into a preset flight illumination analysis model to perform flight illumination analysis, and generate a flight illumination operation scheme;

the heat dissipation analysis module 205 is configured to input the temperature state influence vector into a preset flight heat dissipation control model to perform flight heat dissipation control analysis, so as to obtain a flight heat dissipation control scheme;

and the cooperative control module 206 is configured to perform cooperative lighting control on the target unmanned aerial vehicle according to the flight lighting operation scheme and the flight heat dissipation control scheme, perform abnormal state monitoring on lighting equipment of the target unmanned aerial vehicle, and output an abnormal state processing scheme.

Through the cooperation of the components, the method can accurately adjust the illumination intensity and the mode by monitoring the flight state data of the unmanned aerial vehicle and the power and temperature data of the illumination equipment in real time so as to adapt to different flight conditions and environmental requirements. This not only improves the energy efficiency of the illumination, but also ensures an optimal illumination effect in various environments. According to the method, the flight state of the unmanned aerial vehicle and the running state of the lighting equipment are monitored and analyzed in real time, and the lighting strategy and the heat dissipation control are timely adjusted, so that the safe flight of the unmanned aerial vehicle in a complex environment is ensured. Meanwhile, the abnormal state of the lighting equipment is monitored and processed in real time, so that the reliability of the unmanned aerial vehicle is further improved. By utilizing advanced data processing and analysis technology, the method can automatically identify and respond to the change of the flight state, and the intellectualization of illumination and heat dissipation control is realized. This reduces the need for manual intervention and improves operating efficiency and accuracy. By optimizing the illumination power and the heat dissipation control, the method is beneficial to reducing the energy consumption, thereby reducing the battery burden and prolonging the flight time and the equipment life of the unmanned aerial vehicle. In the long term, this is not only beneficial to environmental protection, but also reduces the operation and maintenance costs. The control method is flexible in design and easy to adjust and optimize according to unmanned aerial vehicles of different types and specifications. In addition, the core technology and principle of the unmanned aerial vehicle system can be applied to other unmanned aerial vehicle systems, and the unmanned aerial vehicle system has good expansibility, so that the heat dissipation efficiency of the unmanned aerial vehicle and the intelligence of lighting operation are improved.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, systems and units may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random acceS memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are merely for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims

1. The unmanned aerial vehicle illumination control method is characterized by comprising the following steps:

2. The method for controlling illumination of an unmanned aerial vehicle according to claim 1, wherein the step of performing flight status monitoring on the target unmanned aerial vehicle to obtain target flight status data, and performing power detection and temperature detection on an illumination device of the target unmanned aerial vehicle to obtain target illumination power data and target device temperature data comprises:

Carrying out flight state monitoring on the target unmanned aerial vehicle through a preset IMU sensor array to obtain initial flight state data;

performing power detection on the lighting equipment of the target unmanned aerial vehicle through a preset power sensor array to obtain initial lighting power data, and performing temperature detection on the lighting equipment of the target unmanned aerial vehicle through a preset temperature sensor array to obtain initial equipment temperature data;

transmitting the initial flight state data, the initial lighting power data and the initial equipment temperature data to a preset central control system respectively;

performing data filtering and data denoising on the initial flight state data through the central control system to obtain target flight state data;

calculating standard deviation threshold values of the initial lighting power data and the initial equipment temperature data through the central control system respectively to obtain a first standard deviation threshold value of the initial lighting power data and a second standard deviation threshold value of the initial equipment temperature data;

and performing outlier removal on the initial illumination power data through the first standard deviation threshold to obtain target illumination power data, and performing outlier removal on the initial equipment temperature data through the second standard deviation threshold to obtain target equipment temperature data.

3. The method for controlling illumination of an unmanned aerial vehicle according to claim 1, wherein the performing state recognition on the target flight state data to obtain a flight state feature set, and performing feature extraction on the target illumination power data and the target equipment temperature data to obtain an illumination power feature set and an equipment temperature feature set respectively, includes:

acquiring a plurality of state parameter labels of the target unmanned aerial vehicle, wherein the plurality of state parameter labels comprise: position parameter labels, speed parameter labels, altitude parameter labels and attitude parameter labels;

determining a plurality of state parameter clustering centers of the target flight state data according to the plurality of state parameter labels, and performing feature clustering on the target flight state data through the plurality of state parameter clustering centers to obtain a target state parameter clustering result of each state parameter clustering center;

respectively mapping the characteristic values of the target state parameter clustering results to obtain a flight state characteristic set;

acquiring first timestamp data of the target illumination power data and second timestamp data of the target equipment temperature data;

Performing curve fitting on the target illumination power data and the first timestamp data to obtain an illumination power change curve, and performing feature point identification and extraction on the illumination power change curve to obtain an illumination power feature set;

and performing curve fitting on the target equipment temperature data and the second timestamp data to obtain an equipment temperature change curve, and performing characteristic point identification and extraction on the equipment temperature change curve to obtain an equipment temperature characteristic set.

4. The method of claim 1, wherein performing feature code conversion on the illumination power feature set and the flight state feature set to generate corresponding power state influence vectors, and performing feature code conversion on the equipment temperature feature set and the flight state feature set to generate corresponding temperature state influence vectors, comprises:

calculating the mean value and standard deviation of the flight state feature set to obtain a state feature mean value and a state feature standard deviation;

calculating the mean value and standard deviation of the illumination power feature set to obtain a power feature mean value and a power feature standard deviation, and calculating the mean value and standard deviation of the equipment temperature feature set to obtain a temperature feature mean value and a temperature feature standard deviation;

Calculating a difference coefficient of the state characteristic mean value, the state characteristic standard deviation, the power characteristic mean value and the power characteristic standard deviation to obtain a first difference coefficient, and generating first characteristic weight data according to the first difference coefficient;

performing feature code conversion on the illumination power feature set and the flight state feature set according to the first feature weight data to generate corresponding power state influence vectors;

calculating a difference coefficient of the state characteristic mean value, the state characteristic standard deviation, the temperature characteristic mean value and the temperature characteristic standard deviation to obtain a second difference coefficient, and generating second characteristic weight data according to the second difference coefficient;

and performing feature code conversion on the equipment temperature feature set and the flight state feature set according to the second feature weight data to generate corresponding temperature state influence vectors.

5. The method for controlling lighting of an unmanned aerial vehicle according to claim 1, wherein inputting the power state impact vector into a preset flight lighting analysis model for flight lighting analysis, generating a flight lighting operation scheme, comprises:

Inputting the power state influence vector into a preset flight lighting analysis model, wherein the flight lighting analysis model comprises an input layer, a plurality of strategy analysis networks and an output layer;

receiving the power state influence vector through the input layer, and carrying out standardization processing on the power state influence vector to obtain a standard power state vector;

distributing the standard power state vector to the plurality of strategy analysis networks, and analyzing the illumination intensity and the illumination pattern of the standard power state vector through a random forest network in each strategy analysis network to obtain an initial illumination strategy corresponding to each strategy analysis network;

and carrying out strategy fusion on the initial lighting strategy corresponding to each strategy analysis network through the output layer to obtain a flight lighting operation scheme.

6. The method for controlling illumination of an unmanned aerial vehicle according to claim 1, wherein the step of inputting the temperature state influence vector into a preset flight heat dissipation control model for flight heat dissipation control analysis to obtain a flight heat dissipation control scheme comprises the steps of:

inputting the temperature state influence vector into a preset flight heat dissipation control model, wherein the flight heat dissipation control model comprises a double-layer threshold circulation unit, a single-layer threshold circulation unit and a fully-connected network;

Carrying out temperature hiding feature extraction on the temperature state influence vector through 256 threshold circulating units in the double-layer threshold circulating unit to obtain a temperature hiding feature vector;

performing feature decoding on the temperature hidden feature vector through 128 threshold circulating units in the single-layer threshold circulating unit to obtain a target decoding feature sequence;

performing flight heat dissipation control parameter operation on the target decoding feature sequence through a ReLU function in the fully connected network, and outputting a flight heat dissipation control parameter set;

and carrying out scheme integration on the flight heat dissipation control parameter set to obtain a flight heat dissipation control scheme.

7. The method according to claim 1, wherein the performing cooperative lighting control on the target unmanned aerial vehicle according to the flying lighting operation scheme and the flying heat dissipation control scheme, performing abnormal state monitoring on lighting equipment of the target unmanned aerial vehicle, and outputting an abnormal state processing scheme includes:

carrying out scheme integration on the flying illumination operation scheme and the flying heat dissipation control scheme to obtain an unmanned aerial vehicle illumination control scheme;

carrying out cooperative illumination control on the target unmanned aerial vehicle according to the unmanned aerial vehicle illumination control scheme by a preset multivariable cooperative control algorithm;

Abnormal state monitoring is carried out on the lighting equipment of the target unmanned aerial vehicle, and abnormal state monitoring data are obtained;

and carrying out abnormal state processing matching on the abnormal state monitoring data, and outputting an abnormal state processing scheme.

8. An unmanned aerial vehicle's lighting control system, characterized in that the unmanned aerial vehicle's lighting control system includes: