Unmanned aerial vehicle electromagnetic signal management and modulation mode identification method

By establishing a drone electromagnetic signal management and modulation pattern identification platform, and utilizing IoT, big data, and machine learning technologies, combined with optical communication and spectrum analysis, the accuracy problem of drone electromagnetic signal management and modulation identification was solved, achieving efficient identification and data management under electromagnetic interference.

CN119025997AInactive Publication Date: 2024-11-26YULIN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411286528.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-13
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The accuracy of electromagnetic signal management and modulation identification for drones is greatly affected by interference, making effective identification difficult.

Method used

A drone electromagnetic signal management and modulation pattern identification platform based on IoT and big data technologies is established. A recognition model is built through machine learning methods, and recognition is performed using optical communication and intelligent information processing technologies. Feature extraction and classification are then performed by combining spectrum analysis and 5G communication sensing integrated technologies.

Benefits of technology

It achieves accurate identification of UAV electromagnetic signals under electromagnetic interference, improves the accuracy and reliability of identification, can generate identification views and reports, and supports data storage and remote management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119025997A_ABST
    Figure CN119025997A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of unmanned aerial vehicle identification, in particular to an unmanned aerial vehicle electromagnetic signal management and modulation mode identification method, which comprises the following steps of: 1, determining an unmanned aerial vehicle electromagnetic signal management and modulation mode identification target based on an internet of things technology; step 2, based on a big data technology, establishing an unmanned aerial vehicle electromagnetic signal identification platform of an unmanned aerial vehicle electromagnetic signal management and modulation mode; 3, collecting and sorting unmanned aerial vehicle electromagnetic signal management and modulation mode identification data, establishing an unmanned aerial vehicle electromagnetic signal management and modulation mode identification database, and recording feature items contained in each sample; the unmanned aerial vehicle electromagnetic signal management and modulation mode identification model is established and applied to the unmanned aerial vehicle electromagnetic signal identification platform, the unmanned aerial vehicle electromagnetic signal management and modulation mode identification data are obtained, the unmanned aerial vehicle electromagnetic signal management and modulation mode identification view and report are generated, and identification is convenient and accurate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle identification, and in particular to a method for managing and modulating electromagnetic signals of unmanned aerial vehicles. Background Art

[0002] Drones have been widely used in many fields, including national defense, emergency firefighting, water conservancy, forestry, electricity, oil and gas, and civil services. With the development of science and technology, the performance of drones has been continuously improved. With the advancement of technology and the reduction of costs, the civilian consumer drone market will continue to grow rapidly. The development of lightweight composite materials, communication systems, and the maturity of flight control technology have made multi-rotor drones more flexible and convenient to operate.

[0003] At present, the electromagnetic signal management and modulation data of drones are complex and highly susceptible to interference. Therefore, the identification data has a large amount of null value data, which interferes with the accuracy of the electromagnetic signal management and modulation identification of drones. In addition, the electromagnetic signal management and modulation identification of drones are difficult. In order to solve the above-mentioned problems, the present invention proposes a method for electromagnetic signal management and modulation mode identification of drones. Summary of the invention

[0004] In view of the problems in the prior art, the present invention provides a method for managing electromagnetic signals of unmanned aerial vehicles and identifying modulation modes.

[0005] The technical solution adopted by the present invention to solve the technical problem is: a method for managing and modulating electromagnetic signals of unmanned aerial vehicles, the method comprising the following steps: Step 1: Based on the Internet of Things technology, determine the management and modulation method of drone electromagnetic signals to identify targets; Step 2: Based on big data technology, establish a drone electromagnetic signal recognition platform for drone electromagnetic signal management and modulation; Step 3: Collect and organize the UAV electromagnetic signal management and modulation mode identification data, establish a UAV electromagnetic signal management and modulation mode identification database, and record the feature items contained in each sample; Step 4: In order to build an accurate UAV electromagnetic signal management and modulation mode recognition model, the data containing null values ​​is processed before training the network, and the null values ​​are represented by NaN to preprocess the missing data; Step 5: Determine the training set, validation set, and test set, select attributes, and define neurons to obtain training set data, validation set data, and test set data; Step 6: Establish a UAV electromagnetic signal management and modulation mode recognition model, and train the model with the above training set data; Step 7: Input the validation set data into the UAV electromagnetic signal management and modulation mode recognition model to evaluate the performance of the model during the training process, and perform parameter adjustment and model selection; Step 8: Input the test set data into the UAV electromagnetic signal management and modulation mode recognition model to evaluate the final performance and generalization ability of the model and test the sensitivity and specificity of the model; Step 9, Identification: Apply the UAV electromagnetic signal management and modulation mode identification model to the UAV electromagnetic signal identification platform, obtain the UAV electromagnetic signal management and modulation mode identification data, and generate the UAV electromagnetic signal management and modulation mode identification view and report; Step 10: Storage: Based on database technology, the identification data, identification views and reports of the UAV electromagnetic signal management and modulation mode are stored to build a UAV electromagnetic signal management and modulation mode identification data center; The UAV electromagnetic signal management and modulation mode identification utilizes optical communication and intelligent information processing technology to enable UAV electromagnetic signal transmission under electromagnetic interference; The UAV electromagnetic signal management and modulation mode identification is performed based on a UAV electromagnetic signal management and modulation mode identification system.

[0006] Specifically, the UAV electromagnetic signal management and modulation mode identification system includes an acquisition module, a normalization module, a processing module, an identification module, a storage module, a server and a user terminal; The acquisition module is used to acquire the electromagnetic signal management and modulation mode identification data of the UAV; The normalization module is used to divide the recognition data into a training set, a validation set and a test set, and perform data normalization; The processing module is used to process the collected data containing null values; The identification module is used to perform UAV electromagnetic signal management and modulation mode identification through a UAV electromagnetic signal management and modulation mode identification model; The storage module is used to store the UAV electromagnetic signal management and modulation mode identification system data; The server is used to provide shared resources, network access control, data storage and backup, application hosting, and remote management and monitoring support for the UAV electromagnetic signal management and modulation mode identification system.

[0007] Specifically, in the construction of the UAV electromagnetic signal management and modulation mode identification model, machine learning methods are used, including k-nearest neighbor kNN, support vector machine SVM, decision tree DT, and neural network NN, to extract features and classify and identify UAV electromagnetic signals. The management and modulation mode identification of UAV electromagnetic signals rely on frequency planning, bandwidth filters, broadband spectrum feature detectors, and electromagnetic signal modeling and modulation identification methods based on deep learning. The frequency plan involves monitoring frequency bands, working channels, and independent frequency points. The image transmission signal detection method based on power spectrum calculates the cancellation ratio between the average power spectrum of the signal and the original power spectrum, and uses the feature of the image transmission signal with relatively large cancellation to determine whether the received signal is an image transmission signal.

[0008] Specifically, the UAV electromagnetic signal management and modulation mode identification utilizes optical communication and intelligent information processing technology to emit optical signals through the lighting equipment on the UAV, and uses photoelectric sensors to capture these optical signals for intelligent analysis, thereby achieving short-distance anti-interference transmission of the UAV electromagnetic signal. Since the transmission of optical signals is not affected by the electromagnetic environment, intermodulation and mutual interference will not occur.

[0009] Specifically, in step 4, the identification data of the UAV electromagnetic signal management and modulation mode is preprocessed to obtain the characteristic parameters for identifying the UAV electromagnetic signal management and modulation mode, and a correlation analysis is performed on the characteristic parameters for identifying the UAV electromagnetic signal management and modulation mode and the UAV electromagnetic signal data to obtain the target characteristic data for constructing a UAV electromagnetic signal management and modulation mode identification model.

[0010] Specifically, the UAV electromagnetic signal management and modulation mode recognition model uses random forest to construct a bagging ensemble based on a decision tree as the base learner, and further introduces random attribute selection in the training of the decision tree, so that the generalization performance of the final ensemble can be further improved by increasing the difference between individual learners. The correlation coefficient method and the integrated feature selection method based on the intelligent optimization algorithm are used for feature selection, and the random forest model is optimized using a genetic algorithm.

[0011] Specifically, the feature extraction of the UAV electromagnetic signal management and modulation mode identification includes waveform feature extraction and wavelet domain transform feature extraction. The waveform feature extraction is to obtain the corresponding waveform feature by taking the absolute value of the signal sample, which is used to extract key information that can represent the signal characteristics from the signal sample. The wavelet domain transform feature extraction is to extract features by obtaining the approximation coefficients obtained by discrete wavelet transform of the signal sample.

[0012] Specifically, the method for obtaining UAV electromagnetic signals by managing UAV electromagnetic signals and identifying modulation mode data includes a spectrum analyzer and a spectrum analyzer, as well as utilizing 5G communication perception integrated technology and intelligent reflective surface technology.

[0013] Beneficial effects of the present invention: (1) A method for managing and modulating the electromagnetic signals of unmanned aerial vehicles described in the present invention. The present invention establishes a model for managing and modulating the electromagnetic signals of unmanned aerial vehicles and applies it to an electromagnetic signal recognition platform of unmanned aerial vehicles to obtain electromagnetic signal management and modulation recognition data of unmanned aerial vehicles and generate electromagnetic signal management and modulation recognition views and reports of unmanned aerial vehicles, so that the electromagnetic signal management and modulation recognition of unmanned aerial vehicles is convenient and accurate. (2) A method for managing and identifying electromagnetic signals of unmanned aerial vehicles (UAVs) according to the present invention. The method adopts a machine learning method to extract features and classify the electromagnetic signals of UAVs, pre-process the missing data, reconstruct the data containing the missing items and analyze them, and adopts a method for electromagnetic signal modeling and modulation identification based on deep learning. The method uses a random forest to construct a bagging ensemble based on a decision tree as the base learner, adopts a correlation coefficient method and an integrated feature selection method based on an intelligent optimization algorithm to select features, and adopts a genetic algorithm to optimize the random forest model. The method is self-learning. Through future use and the increase in sample size, the execution efficiency and sensitivity of the network of the UAV electromagnetic signal management and modulation mode identification model are improved, thereby achieving long-term accuracy and reliability of the electromagnetic signal management and modulation mode identification of UAVs. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0015] Figure 1 A flow chart of an identification method for a method for managing and identifying modulation modes of electromagnetic signals of unmanned aerial vehicles provided by the present invention; Figure 2 A working principle diagram of an identification system for a method for managing electromagnetic signals and identifying modulation modes of unmanned aerial vehicles provided by the present invention. DETAILED DESCRIPTION

[0016] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0017] like Figure 1 and Figure 2 As shown, a method for managing and modulating a UAV electromagnetic signal of the present invention comprises the following steps: Step 1: Based on the Internet of Things technology, determine the management and modulation method of drone electromagnetic signals to identify targets; Step 2: Based on big data technology, establish a drone electromagnetic signal recognition platform for drone electromagnetic signal management and modulation; Step 3: Collect and organize the UAV electromagnetic signal management and modulation mode identification data, establish a UAV electromagnetic signal management and modulation mode identification database, and record the feature items contained in each sample; Step 4: In order to build an accurate UAV electromagnetic signal management and modulation mode recognition model, the data containing null values ​​is processed before training the network, and the null values ​​are represented by NaN to preprocess the missing data; Step 5: Determine the training set, validation set, and test set, select attributes, and define neurons to obtain training set data, validation set data, and test set data; Step 6: Establish a UAV electromagnetic signal management and modulation mode recognition model, and train the model with the above training set data; Step 7: Input the validation set data into the UAV electromagnetic signal management and modulation mode recognition model to evaluate the performance of the model during the training process, and perform parameter adjustment and model selection; Step 8: Input the test set data into the UAV electromagnetic signal management and modulation mode recognition model to evaluate the final performance and generalization ability of the model and test the sensitivity and specificity of the model; Step 9, Identification: Apply the UAV electromagnetic signal management and modulation mode identification model to the UAV electromagnetic signal identification platform, obtain the UAV electromagnetic signal management and modulation mode identification data, and generate the UAV electromagnetic signal management and modulation mode identification view and report; Step 10: Storage: Based on database technology, the identification data, identification views and reports of the UAV electromagnetic signal management and modulation mode are stored to build a UAV electromagnetic signal management and modulation mode identification data center; The UAV electromagnetic signal management and modulation mode identification utilizes optical communication and intelligent information processing technology to enable UAV electromagnetic signal transmission under electromagnetic interference; The UAV electromagnetic signal management and modulation mode identification is performed based on a UAV electromagnetic signal management and modulation mode identification system.

[0018] Specifically, the UAV electromagnetic signal management and modulation mode identification system includes an acquisition module, a normalization module, a processing module, an identification module, a storage module, a server and a user terminal; The acquisition module is used to acquire the electromagnetic signal management and modulation mode identification data of the UAV; The normalization module is used to divide the recognition data into a training set, a validation set and a test set, and perform data normalization; The processing module is used to process the collected data containing null values; The identification module is used to perform UAV electromagnetic signal management and modulation mode identification through a UAV electromagnetic signal management and modulation mode identification model; The storage module is used to store the UAV electromagnetic signal management and modulation mode identification system data; The server is used to provide shared resources, network access control, data storage and backup, application hosting, and remote management and monitoring support for the UAV electromagnetic signal management and modulation mode identification system.

[0019] Specifically, in the construction of the UAV electromagnetic signal management and modulation mode identification model, machine learning methods are used, including k-nearest neighbor kNN, support vector machine SVM, decision tree DT, and neural network NN, to extract features and classify and identify UAV electromagnetic signals. The management and modulation mode identification of UAV electromagnetic signals rely on frequency planning, bandwidth filters, broadband spectrum feature detectors, and electromagnetic signal modeling and modulation identification methods based on deep learning. The frequency plan involves monitoring frequency bands, working channels, and independent frequency points. The image transmission signal detection method based on power spectrum calculates the cancellation ratio between the average power spectrum of the signal and the original power spectrum, and uses the feature of the image transmission signal with relatively large cancellation to determine whether the received signal is an image transmission signal.

[0020] Specifically, the UAV electromagnetic signal management and modulation mode identification utilizes optical communication and intelligent information processing technology to emit optical signals through the lighting equipment on the UAV, and uses photoelectric sensors to capture these optical signals for intelligent analysis, thereby achieving short-distance interference-resistant transmission of UAV electromagnetic signals. Since the transmission of optical signals is not affected by the electromagnetic environment, no intermodulation and mutual interference will occur, which can better cope with electromagnetic interference problems and ensure the accuracy of information.

[0021] Specifically, in step 4, the identification data of the UAV electromagnetic signal management and modulation mode is preprocessed to obtain the characteristic parameters for identifying the UAV electromagnetic signal management and modulation mode, and a correlation analysis is performed on the characteristic parameters for identifying the UAV electromagnetic signal management and modulation mode and the UAV electromagnetic signal data to obtain the target characteristic data for constructing a UAV electromagnetic signal management and modulation mode identification model.

[0022] Specifically, the UAV electromagnetic signal management and modulation mode recognition model uses random forest to construct a bagging ensemble based on a decision tree as the base learner, and further introduces random attribute selection in the training of the decision tree, so that the generalization performance of the final ensemble can be further improved by increasing the difference between individual learners. The correlation coefficient method and the integrated feature selection method based on the intelligent optimization algorithm are used for feature selection, and the random forest model is optimized by a genetic algorithm. Compared with the unimproved random forest model, the optimized model has a stronger fitting ability.

[0023] Specifically, the feature extraction for the management and modulation mode identification of the UAV electromagnetic signal includes waveform feature extraction and wavelet domain transform feature extraction. The waveform feature extraction is to obtain the corresponding waveform feature by taking the absolute value of the signal sample, and is used to extract key information that can represent the signal characteristics from the signal sample. The wavelet domain transform feature extraction is to extract features by obtaining the approximation coefficients obtained by the discrete wavelet transform of the signal sample, so that the identification of the UAV electromagnetic signal becomes more accurate and efficient. By extracting and analyzing these features, the type, status and behavior pattern of the UAV can be effectively identified.

[0024] Specifically, the method for acquiring the electromagnetic signal of the drone for the management and modulation mode identification data includes a spectrum analyzer and a spectrum analyzer, as well as the use of 5G communication perception integrated technology and intelligent reflective surface technology. The acquisition of the electromagnetic signal of the drone mainly depends on the spectrum detection technology and the signal acquisition and processing technology. The spectrum detection technology identifies, measures and locates the radio signal by analyzing the distribution and characteristics of the signal in the frequency domain. In the signal acquisition stage, the device receives the radio signal in the air through a high-sensitivity receiver and converts it into a digital signal for subsequent processing. In the signal processing stage, the device uses advanced digital signal processing algorithms to filter, amplify, demodulate and other operations on the collected signals to extract useful information. At the same time, the device can also perform statistical analysis and feature extraction on the signal to further improve the accuracy and reliability of drone detection.

[0025] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for managing and modulating UAV electromagnetic signals, characterized in that: The identification method comprises the following steps: Step 1: Based on the Internet of Things technology, determine the management and modulation method of drone electromagnetic signals to identify targets; Step 2: Based on big data technology, establish a drone electromagnetic signal recognition platform for drone electromagnetic signal management and modulation; Step 3: Collect and organize the UAV electromagnetic signal management and modulation mode identification data, establish a UAV electromagnetic signal management and modulation mode identification database, and record the feature items contained in each sample; Step 4: In order to build an accurate UAV electromagnetic signal management and modulation mode recognition model, the data containing null values ​​is processed before training the network, and the null values ​​are represented by NaN to preprocess the missing data; Step 5: Determine the training set, validation set, and test set, select attributes, and define neurons to obtain training set data, validation set data, and test set data; Step 6: Establish a UAV electromagnetic signal management and modulation mode recognition model, and train the model with the above training set data; Step 7: Input the validation set data into the UAV electromagnetic signal management and modulation mode recognition model to evaluate the performance of the model during the training process, and perform parameter adjustment and model selection; Step 8: Input the test set data into the UAV electromagnetic signal management and modulation mode recognition model to evaluate the final performance and generalization ability of the model and test the sensitivity and specificity of the model; Step 9, Identification: Apply the UAV electromagnetic signal management and modulation mode identification model to the UAV electromagnetic signal identification platform, obtain the UAV electromagnetic signal management and modulation mode identification data, and generate the UAV electromagnetic signal management and modulation mode identification view and report; Step 10: Storage: Based on database technology, the identification data, identification views and reports of the UAV electromagnetic signal management and modulation mode are stored to build a UAV electromagnetic signal management and modulation mode identification data center; The UAV electromagnetic signal management and modulation mode identification utilizes optical communication and intelligent information processing technology to enable UAV electromagnetic signal transmission under electromagnetic interference; The UAV electromagnetic signal management and modulation mode identification is performed based on a UAV electromagnetic signal management and modulation mode identification system.

2. The method for managing and identifying electromagnetic signals of unmanned aerial vehicles according to claim 1, characterized in that: The UAV electromagnetic signal management and modulation mode identification system includes a collection module, a normalization module, a processing module, an identification module, a storage module, a server and a user terminal; The acquisition module is used to acquire the electromagnetic signal management and modulation mode identification data of the UAV; The normalization module is used to divide the recognition data into a training set, a validation set and a test set, and perform data normalization; The processing module is used to process the collected data containing null values; The identification module is used to perform UAV electromagnetic signal management and modulation mode identification through a UAV electromagnetic signal management and modulation mode identification model; The storage module is used to store the UAV electromagnetic signal management and modulation mode identification system data; The server is used to provide shared resources, network access control, data storage and backup, application hosting, and remote management and monitoring support for the UAV electromagnetic signal management and modulation mode identification system.

3. The method for managing and modulating UAV electromagnetic signals according to claim 1, characterized in that: In the construction of the UAV electromagnetic signal management and modulation mode identification model, machine learning methods are used, including k-nearest neighbor kNN, support vector machine SVM, decision tree DT, neural network NN, to extract features and classify and identify UAV electromagnetic signals. The management of UAV electromagnetic signals and the identification of modulation modes rely on frequency plans, bandwidth filters, broadband spectrum feature detectors, and electromagnetic signal modeling and modulation identification methods based on deep learning. The frequency plan involves monitoring frequency bands, working channels and independent frequency points. The image transmission signal detection method based on power spectrum calculates the cancellation ratio between the average power spectrum of the signal and the original power spectrum, and uses the feature of the image transmission signal with a relatively large cancellation ratio to determine whether the received signal is an image transmission signal.

4. The method for managing and identifying electromagnetic signals of unmanned aerial vehicles according to claim 1, characterized in that: The drone electromagnetic signal management and modulation mode identification utilizes optical communication and intelligent information processing technology to emit optical signals through the lighting equipment on the drone, and uses photoelectric sensors to capture these optical signals for intelligent analysis, thereby achieving short-distance anti-interference transmission of the drone electromagnetic signal. Since the transmission of optical signals is not affected by the electromagnetic environment, intermodulation and mutual interference will not occur.

5. The method for managing and modulating UAV electromagnetic signals according to claim 1, characterized in that: In the step 4, the identification data of the UAV electromagnetic signal management and modulation mode is preprocessed to obtain the characteristic parameters for identifying the UAV electromagnetic signal management and modulation mode, and a correlation analysis is performed between the characteristic parameters for identifying the UAV electromagnetic signal management and modulation mode and the UAV electromagnetic signal data to obtain the target characteristic data for constructing the UAV electromagnetic signal management and modulation mode identification model.

6. The method for managing and modulating UAV electromagnetic signals according to claim 1, characterized in that: The UAV electromagnetic signal management and modulation mode recognition model uses random forest to build a bagging ensemble based on a decision tree as the base learner, and further introduces random attribute selection in the training of the decision tree, so that the generalization performance of the final ensemble can be further improved by increasing the difference between individual learners. The correlation coefficient method and the integrated feature selection method based on the intelligent optimization algorithm are used for feature selection, and the random forest model is optimized by a genetic algorithm.

7. The method for managing and modulating UAV electromagnetic signals according to claim 1, characterized in that: The feature extraction of the UAV electromagnetic signal management and modulation mode identification includes waveform feature extraction and wavelet domain transformation feature extraction. The waveform feature extraction is to obtain the corresponding waveform feature by taking the absolute value of the signal sample, and is used to extract key information that can represent the signal characteristics from the signal sample. The wavelet domain transformation feature extraction is to extract features by obtaining the approximation coefficients obtained by discrete wavelet transformation of the signal sample.

8. The method for managing and modulating UAV electromagnetic signals according to claim 1, characterized in that: The method for obtaining drone electromagnetic signals by managing and modulating the identification data of drone electromagnetic signals includes a spectrum analyzer and a spectrum analyzer, as well as utilizing 5G communication perception integration technology and intelligent reflective surface technology.