CN111795611B - Low-complexity unmanned aerial vehicle modulation mode blind identification and countercheck method and system - Google Patents
Low-complexity unmanned aerial vehicle modulation mode blind identification and countercheck method and system Download PDFInfo
- Publication number
- CN111795611B CN111795611B CN202010433690.5A CN202010433690A CN111795611B CN 111795611 B CN111795611 B CN 111795611B CN 202010433690 A CN202010433690 A CN 202010433690A CN 111795611 B CN111795611 B CN 111795611B
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- signal
- modulation
- modulation mode
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F41—WEAPONS
- F41H—ARMOUR; ARMOURED TURRETS; ARMOURED OR ARMED VEHICLES; MEANS OF ATTACK OR DEFENCE, e.g. CAMOUFLAGE, IN GENERAL
- F41H11/00—Defence installations; Defence devices
- F41H11/02—Anti-aircraft or anti-guided missile or anti-torpedo defence installations or systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The invention discloses a blind identification and countercheck method and a system for a modulation mode of a low-complexity unmanned aerial vehicle, wherein the blind identification and countercheck method specifically comprises the steps of constructing a one-dimensional IQ data vector, inputting the one-dimensional IQ data vector into a trained deep learning model for prediction, identifying the modulation mode used by a communication link layer of the one-dimensional IQ data vector, and finally regenerating and optimizing an interference waveform based on an identification result to perform green, safe and low-power smart interference on a target unmanned aerial vehicle signal. The implementation process reduces the data volume, can acquire the characteristics of the modulation type of the unmanned aerial vehicle communication link layer from the original IQ data with lower complexity, and can perform training and learning on the characteristics by using the constructed neural network model, namely, blindly identify the modulation mode used by the unmanned aerial vehicle communication link; in addition, the network model is designed into a one-dimensional CNN network from the original two-dimensional CNN network, so that the network complexity is reduced, and the identification efficiency is improved under the condition of reducing the implementation complexity.
Description
Technical Field
The invention belongs to the technical field of unmanned aerial vehicle countermeasures, and particularly relates to a low-complexity unmanned aerial vehicle modulation mode blind identification and countermeasures method and system.
Background
In recent years, the unmanned aerial vehicle industry continues to grow rapidly, from 2014 to 2018, the market scale of the global rotor unmanned aerial vehicle increases by about 20% every year, and in each large electric business platform and business yard, people spend about two thousand yuan at least, and can purchase one unmanned aerial vehicle which flies in hand and has functions of aerial photography and the like. However, when the entrance threshold of the unmanned aerial vehicle is lowered continuously, the unmanned aerial vehicle is in a high-emergence situation. When the unmanned aerial vehicle is not allowed to enter airport airspace, public places and sensitive areas, the risk of harming public safety and national safety exists.
At present, high-power electromagnetic suppression interference in an unmanned aerial vehicle counter measure is low in efficiency and serious in secondary disaster, and is not an optimal choice, and instead, a small-power interference signal consistent with a target signal modulation type is generated to carry out purposeful smart interference on the small-power interference signal.
The blind identification of the modulation type of the unmanned aerial vehicle is a key technology, and the traditional modulation mode blind identification method based on mathematical statistics has higher mathematical operation process and higher engineering practice complexity; the modulation type identification based on deep learning mostly adopts a constellation diagram and eye diagram identification method, the essence of the method belongs to an image processing technology, the data volume of images is large, the training parameters of a neural network are increased, and the difficulty of actual engineering deployment is greatly increased.
Disclosure of Invention
The invention aims to solve the technical problem of providing a low-complexity unmanned aerial vehicle modulation mode blind identification and counter-control method and system aiming at the defect that the training parameters of a neural network are increased due to the fact that an image processing technology is adopted in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: a low-complexity unmanned aerial vehicle modulation mode blind identification method is constructed, and the method comprises the following steps:
s1, receiving and monitoring communication signals between the unmanned aerial vehicle and remote control equipment for remotely controlling the unmanned aerial vehicle;
s2, after time domain preprocessing is carried out on the received communication signals, time domain one-dimensional IQ data vectors S are constructed according to a preset vector length k, and normalization processing is carried out on the time domain one-dimensional IQ data vectors; wherein:
s＝{s1,s2,s3,s4,…sk-1,sk}；
sirepresents time domain IQ data, i ═ {1,2, …, k };
s3, building a neural network model for blind recognition of the modulation type result, and building a training data set based on the vector S after normalization processing; inputting the training data set into the neural network model for model training, and obtaining a modulation type blind recognition neural network model when a network loss function is converged; wherein:
the modulation type blind recognition neural network model comprises a CNN network layer formed by a plurality of layers of one-dimensional CNN networks and a full-connection network layer connected to the CNN network layer;
when a training data set is constructed, taking out a real part and an imaginary part of a vector S after normalization processing according to the following formula, and inverting the real part and the imaginary part of the vector S to obtain a matrix S with k rows and 2 columns; and (3) constructing a training data set by taking the matrix S as an object:
and S4, predicting the communication signals monitored by the frequency spectrum detection equipment based on the modulation type blind identification neural network model to obtain a modulation type blind identification result.
The invention discloses a method for realizing counter-control of a target unmanned aerial vehicle based on the low-complexity unmanned aerial vehicle modulation mode blind identification method, which comprises the following steps:
and after a modulation type blind identification result is obtained based on the modulation type blind identification neural network model, generating an interference signal according to the blind identification result, and countering the target unmanned aerial vehicle.
The invention discloses an unmanned aerial vehicle modulation mode blind identification and anti-braking system, which comprises a frequency spectrum detection device, a signal receiving device, a low noise and power amplification device, a radio frequency transceiver, a modulation mode blind identification device and an anti-braking device, wherein:
the frequency spectrum detection device comprises a receiving channel, a frequency spectrum detection unit and a frequency spectrum detection unit, wherein the receiving channel is used for detecting a communication signal between the unmanned aerial vehicle and the remote control equipment;
the signal receiving device comprises a broadband antenna and is used for receiving the detected communication signals, and receiving and processing the currently processed signals by the modulation mode blind identification device after frequency conversion, gain control, filtering and analog-digital conversion processing of the detected signals are finished by the radio frequency transceiver;
the modulation mode blind identification device comprises a first processor and a first memory, wherein a first execution program for carrying out blind identification on the modulation mode of the low-complexity unmanned aerial vehicle is stored in the first memory, and when the first execution program is executed by the first processor, a blind identification result of the modulation type is obtained;
the anti-system device comprises a transmitting channel, a second processor and a second memory, wherein a second execution program for anti-system of the target unmanned aerial vehicle is stored in the second memory, when the second execution program is executed by the second processor, an interference signal is generated according to a blind identification result obtained from the modulation mode blind identification device, and after normalization processing, the generated interference signal is sequentially transmitted through a radio frequency transceiver and a broadband antenna, and after signal frequency conversion, gain control, filtering and analog-to-digital conversion are completed, generation and transmission of an anti-system analog signal are completed.
Compared with the prior image method based on the constellation diagram, the method and the system for implementing the blind identification and the countercheck of the modulation mode of the low-complexity unmanned aerial vehicle have the beneficial effects that the method and the system adopt the original IQ data as the input layer data of the model, and have the following beneficial effects:
1. the input data volume is greatly reduced; the characteristics of the modulation type of the communication link layer of the unmanned aerial vehicle can be acquired from the original IQ data with the most abundant information at lower complexity, and the characteristics are trained and learned by utilizing the constructed neural network model, so that the modulation mode used by the communication link of the unmanned aerial vehicle can be blindly identified;
2. the network model is designed into a one-dimensional CNN network from the original two-dimensional CNN network, thereby greatly reducing the network complexity and effectively improving the identification efficiency under the condition of reducing the implementation complexity;
3. the regenerated interference waveform based on the blind identification result is highly consistent with the real waveform, so that the interference can be falsified, the interference efficiency is improved, the interference power is reduced, and the service life of the device is prolonged.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a block diagram of a low complexity unmanned aerial vehicle modulation mode blind identification and counter-control system thereof;
FIG. 2 is a blind identification and counter-control system of modulation mode of unmanned aerial vehicle in practical application scene;
FIG. 3 is a flow chart of a low complexity unmanned aerial vehicle modulation mode blind identification method;
FIG. 4 is a flow chart of a method for countering a target UAV based on a low complexity UAV modulation scheme;
FIG. 5 is a block diagram of a model of a deep neural network used in the method and system;
fig. 6 is a diagram of identification accuracy in the case of a change in channel transition probability.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
Example 1:
referring to fig. 1-2, which are structural diagrams of a modulation-mode blind identification and counter-control system of an unmanned aerial vehicle, as shown in fig. 1, the system includes a spectrum detection device, a signal receiving device, a low noise and power amplification device, a radio frequency transceiver, a modulation-mode blind identification device, and a counter-control device, and each of the above devices functions as:
a1, the frequency spectrum detection device comprises 2 receiving channels for detecting communication signals between the unmanned aerial vehicle and the remote control equipment;
a2, the signal receiving device includes multiple 75MHz-6GHz broadband antennas, which is used to receive the radio frequency signal received by each receiving channel, and after completing the frequency conversion, gain control, filtering and analog-to-digital conversion processing of the detection signal by the radio frequency transceiver (in the specific implementation, an AD9361 or ADRV9009 or ADRV9008 chip can be adopted), the modulation mode blind identification device receives and processes the currently processed signal;
in practical applications, the apparatuses a1 and a2 may also be integrated into a single apparatus, such as the apparatus shown in fig. 2 that includes a monitoring antenna array, and the apparatus is used to detect a signal between the black-flying drone and the remote control device, and receive the signal based on the monitoring antenna array after detecting the signal, and transmit the signal to the drone communication link modulation type blind identification system shown in fig. 2.
a3, the modulation mode blind identification device (i.e. the unmanned aerial vehicle communication link modulation type blind identification system shown in fig. 2), which is characterized in that:
a first processor and a first memory are arranged;
it is characterized by the following software aspects:
a first execution program for realizing blind identification of the modulation mode of the low-complexity unmanned aerial vehicle is stored in the first memory (the execution step of the first execution program can refer to fig. 3), and when the first execution program is executed by the first processor, a blind identification result of the modulation type is obtained;
a4, the reaction device is in hardware:
the system comprises 2 transmitting channels, a second processor and a second memory; each transmit channel generates a countering digital signal after the processor calls the associated executive program stored in the memory.
In terms of software:
a second execution program for implementing a reverse control on the target unmanned aerial vehicle based on the blind identification result is stored in the second memory (the execution step of the second execution program may refer to fig. 4), and when the second execution program is executed by the second processor, a reverse interference digital signal is generated according to the blind identification result obtained from the modulation mode blind identification device, wherein the generated reverse interference digital signal is processed by a radio frequency transceiver, a broadband antenna in sequence after normalization, and after signal frequency conversion, gain control, filtering and analog-to-digital conversion are completed, generation and transmission of a reverse analog signal are completed.
The interaction process between the devices a3 and a4 can be seen in reference to fig. 2, from which:
after the identification result is obtained based on the modulation type blind identification system, an interference signal can be generated through a reverse device, and the interference of the target unmanned aerial vehicle is realized.
In this embodiment, based on the modulation type blind identification system, processing and identification of a communication waveform signal are implemented to obtain an identification result of a signal modulation type; then, the interference waveform is regenerated based on the recognition result of the signal modulation type, the radio counter-braking of the target unmanned aerial vehicle is realized, the interference efficiency of the target unmanned aerial vehicle is effectively improved, and the interference power is reduced.
Example 2:
in order to improve the identification precision of the modulation mode and generate maximum power output under the condition of a given distortion rate, the unmanned aerial vehicle modulation mode blind identification and anti-modulation system further comprises a low-noise and power amplifier device, and the low-noise and power amplifier device comprises a low-noise amplifier and a power amplifier.
When blind identification of modulation modes is carried out:
the signal received by the signal receiving device is firstly filtered and amplified by a low noise amplifier and then sent to a radio frequency transceiver;
when generating the inverted analog signal:
after signal frequency conversion, gain control, filtering and analog-to-digital conversion are completed through a radio frequency transceiver, a generated anti-modulation analog signal firstly passes through a power amplifier to generate maximum power output under the condition of a given distortion rate; and then the broadband antenna arranged in the signal receiving device receives and transmits the reverse analog signal to realize the reverse of the target unmanned aerial vehicle.
Example 3:
based on embodiment 1 or 2, when the unmanned aerial vehicle modulation mode blind identification system disclosed by the invention is used for realizing a low-complexity unmanned aerial vehicle modulation mode blind identification method, the method comprises the following steps:
s1, receiving the analog communication signal between the unmanned aerial vehicle and the remote control equipment through the frequency spectrum detection device and the signal receiving device;
s2, the received analog communication signal is filtered and amplified by a low noise amplifier, and then is sent to an incident frequency transceiver to complete frequency conversion, gain control, filtering and analog-to-digital conversion, and the conversion from the analog signal to the digital signal is completed;
s3, when the blind recognition result is extracted based on the digital communication signal, the first processor calls the first execution program stored in the first memory, and when the execution is performed, the method includes the following sub-steps:
s31, performing time domain preprocessing on the received communication signal, constructing a time domain one-dimensional IQ data vector S according to a preset vector length k, and performing normalization processing on the time domain one-dimensional IQ data vector; wherein:
s＝{s1,s2,s3,s4,…sk-1,sk}；
sirepresents time domain IQ data, i ═ {1,2, …, k };
currently, the extraction of the original IQ data is finished;
s32, building a neural network model for blind recognition of the modulation type result (the structure of the network model can refer to FIG. 5), and building a training data set based on the vector S after normalization processing; when a training data set is constructed, a real part and an imaginary part of a vector S are taken out according to a formula 1, inversion is carried out on the real part and the imaginary part of the vector S, and a matrix S of k rows and 2 columns is obtained:
over time, a series of vectors … S are obtainedn-2,Sn-1,S…；
S33 at … Sn-2,Sn-1S …, constructing a training data set for the object, and inputting the training data set into the neural network model for model training (specifically, refer to fig. 5, in the training phase, the construction form of the training signal); wherein:
in the training process, firstly, the X is obtained through data preprocessing1,X2,…,Xk，XiRepresents pre-processed data (i ═ 1, …, k) for input to the network input layer for training;
and S34, calculating the network loss, and when the network loss is not converged, performing optimization training on the model by adopting a gradient update-SGD optimization function until the network loss function is converged, and outputting the trained modulation type blind recognition neural network model. Currently, the simulated communication signals monitored by the spectrum detection equipment can be predicted based on the trained modulation type blind recognition neural network model, and a modulation type blind recognition result is obtained.
The modulation type blind recognition neural network model is designed in terms of a network structure and comprises the following steps:
b1) the modulation type blind recognition neural network model in this embodiment includes a CNN network layer formed by a plurality of layers of one-dimensional CNN networks, and a fully connected network layer connected to the CNN network layer; wherein the input of each layer of the one-dimensional CNN network, e.g. the input of the first layer corresponds to X1In this way, inputting the preprocessed data into the CNN network layer, extracting the features through the CNN network layer, and fusing the features with the fully-connected network layer;
b2) in the prediction stage, the neural network model can be identified blindly based on the trained modulation type, the data set collected in real time is input to the input layer of the network model, and the modulation mode information of the unmanned aerial vehicle communication link layer can be automatically extracted from the currently input data through forward prediction iteration of the model, so that the result of model prediction is obtained.
The modulation type blind recognition neural network model comprises the following steps in the aspect of network parameter design:
the parameter design of the network model is shown in table 1, and the hyper-parameter setting is shown in table 2:
table 1CNN network parameter description
TABLE 2 network hyper-parameter settings
According to the setting of the network parameters and the adjustment of the hyper-parameters, the final recognition accuracy of the network is as shown in fig. 6; wherein:
the abscissa of fig. 6 represents the transition probability, and the ordinate represents the recognition accuracy under the corresponding transition probability;
as can be seen from fig. 6, when the channel transition probability is within 10%, the modulation type recognition rate of the network is approximately equal to 91%, and it can be basically determined that, based on the modulation type blind recognition neural network model, when the data set acquired in real time is input to the network model, a better recognition effect can be achieved (the transition probability can be understood as the bit error rate, that is, the recognition rate is tested under the currently set bit error rate condition).
The invention discloses an implementation process of a modulation mode blind identification method of a low-complexity unmanned aerial vehicle, which has the following beneficial effects compared with the prior art:
one aspect is embodied by: the characteristics of the modulation type of the communication link layer of the unmanned aerial vehicle are acquired from the original IQ data with the richest information at lower complexity, so that the input data volume is reduced, and the data processing efficiency is improved;
the other aspect is embodied in: the characteristics are trained and learned by utilizing the constructed neural network model, wherein the used network model is designed into a one-dimensional CNN network from the original two-dimensional CNN network, the network complexity is greatly reduced, and the identification efficiency is effectively improved under the condition of reducing the implementation complexity.
Example 4:
based on the embodiment 1 or 2, when the modulation type of the communication signal is identified by the low-complexity unmanned aerial vehicle modulation mode blind identification method disclosed by the invention, the target unmanned aerial vehicle can be controlled by a control method, so that the unmanned aerial vehicle is prevented from entering an airport airspace, a public place and a sensitive area under the condition of no permission.
The method for countering the target unmanned aerial vehicle comprises the following steps:
firstly, after a modulation type blind identification result is obtained based on a modulation mode blind identification device, a second execution program stored in a second memory is called by a second processor, an interference signal is generated based on the blind identification result, and a target unmanned aerial vehicle is controlled.
Implementation steps for countering the target drone include (refer to fig. 4):
firstly, generating a polynomial and a register initial value according to a pre-loaded pseudo code, and substituting the register initial value into the polynomial to generate a pseudo-random sequence according to an interference bandwidth specified by an instruction;
secondly, acquiring a modulation pattern of a blind identification result based on a modulation mode blind identification device, and modulating the generated pseudo-random sequence to generate an interference signal; wherein:
after signal frequency conversion, gain control, filtering and analog-digital conversion are completed through a radio frequency transceiver, in order to meet the requirement that the amplitude of an analog signal output after the analog-digital conversion reaches the maximum value, normalization processing needs to be carried out on an interference signal, and the maximum value of modulation interference output data is equal to full-scale input of the digital-analog conversion;
and finally, receiving and transmitting a reverse analog signal generated after analog-to-digital conversion through a 75MHz-6GHz broadband antenna arranged on the signal receiving device, so that the reverse signal is transmitted, and the interference target unmanned aerial vehicle enters an airport airspace, a public place and a sensitive area under the condition of unauthorized access.
Compared with the existing image method based on the constellation diagram, on one hand, the blind identification and the countercheck method and system of the modulation mode of the low-complexity unmanned aerial vehicle have the advantages that the input data volume is greatly reduced, the features of the modulation type of the communication link layer of the unmanned aerial vehicle can be obtained from the original IQ data with the richest information at lower complexity, and the features are trained and learned by utilizing the established neural network model, so that the modulation mode used by the communication link of the unmanned aerial vehicle can be identified blindly; on the other hand, the network model is designed into a one-dimensional CNN network from the original two-dimensional CNN network, thereby greatly reducing the network complexity and effectively improving the identification efficiency under the condition of reducing the implementation complexity; and finally, the regenerated interference waveform based on the blind identification result is highly consistent with the real waveform, so that the interference can be falsified, the interference efficiency is improved, the interference power is reduced, and the service life of the device is prolonged.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (4)
1. A counter-braking method for realizing counter-braking of a target unmanned aerial vehicle by adopting a low-complexity unmanned aerial vehicle modulation mode blind identification method is characterized by comprising the following steps of:
s1, receiving and monitoring communication signals between the unmanned aerial vehicle and remote control equipment for remotely controlling the unmanned aerial vehicle;
s2, after time domain preprocessing is carried out on the received communication signals, time domain one-dimensional IQ data vectors S are constructed according to a preset vector length k, and normalization processing is carried out on the time domain one-dimensional IQ data vectors; wherein:
s＝{s1,s2,…si…sk-1,sk}
sirepresents time domain IQ data, i ═ {1,2, …, k };
s3, building a neural network model for blind recognition of the modulation type result, and building a training data set based on the vector S after normalization processing; inputting the training data set into the neural network model for model training, and obtaining a modulation type blind recognition neural network model when a network loss function is converged; wherein:
the modulation type blind recognition neural network model comprises a CNN network layer formed by a plurality of layers of one-dimensional CNN networks and a full-connection network layer connected to the CNN network layer;
when a training data set is constructed, taking out a real part and an imaginary part of a vector S after normalization processing according to the following formula, and inverting the real part and the imaginary part of the vector S to obtain a matrix S with k rows and 2 columns; and (3) constructing a training data set by taking the matrix S as an object:
s4, predicting the communication signals monitored by the frequency spectrum detection device based on the modulation type blind identification neural network model to obtain a modulation type blind identification result;
in step S1, detecting a communication signal between the unmanned aerial vehicle and the remote control device based on the spectrum detection device;
receiving the detected communication signal based on a broadband antenna arranged in the signal receiving device;
in step S3, when the network loss function is not converged, optimizing and training the model by adopting a gradient update-SGD optimization function;
until the network loss function is converged, obtaining a trained network model;
after a modulation type blind identification result is obtained based on the modulation type blind identification neural network model, an interference signal is generated according to the blind identification result, and a target unmanned aerial vehicle is countermarked;
after the modulation type blind identification result is obtained, if the target unmanned aerial vehicle needs to be countermodulated, the implementation steps comprise:
generating a polynomial and a register initial value according to a pre-loaded pseudo code, and bringing the register initial value into the polynomial to generate a pseudo-random sequence according to an interference bandwidth specified by an instruction;
acquiring a modulation pattern of a blind recognition result based on the modulation type blind recognition neural network model, modulating the generated pseudo-random sequence to generate an interference signal, and after signal frequency conversion, gain control, filtering and analog-to-digital conversion are completed through a radio frequency transceiver, wherein in order to meet the requirement that the amplitude of an analog signal output after the analog-to-digital conversion reaches the maximum value, normalization processing needs to be carried out on the interference signal, so that the maximum value of modulation interference output data is equal to full-scale input of the digital-to-analog conversion;
the anti-braking analog signal generated after analog-to-digital conversion is received and transmitted through a broadband antenna arranged on the signal receiving device, so that the anti-braking of the target unmanned aerial vehicle is realized.
2. The utility model provides an unmanned aerial vehicle modulation mode blind discernment and anti-system thereof which characterized in that, includes frequency spectrum detection device, signal receiver, low noise and power amplifier device, radio frequency transceiver, modulation mode blind discernment device and anti-system device, wherein:
the frequency spectrum detection device comprises a receiving channel, a frequency spectrum detection unit and a frequency spectrum detection unit, wherein the receiving channel is used for detecting a communication signal between the unmanned aerial vehicle and the remote control equipment;
the signal receiving device comprises a broadband antenna and is used for receiving the detected communication signals, and receiving and processing the currently processed signals by the modulation mode blind identification device after frequency conversion, gain control, filtering and analog-digital conversion processing of the detected signals are finished by the radio frequency transceiver;
the modulation mode blind identification device comprises a first processor and a first memory, wherein the first memory stores the low-complexity unmanned aerial vehicle modulation mode blind identification method as claimed in claim 1, and when the low-complexity unmanned aerial vehicle modulation mode blind identification method is executed by the first processor, a blind identification result of a modulation type is obtained;
the anti-braking device comprises a transmitting channel, a second processor and a second memory, wherein the anti-braking method for realizing the anti-braking of the target unmanned aerial vehicle by adopting the low-complexity unmanned aerial vehicle modulation mode blind identification method as claimed in claim 1 is stored in the second memory, when the anti-braking method for realizing the anti-braking of the target unmanned aerial vehicle by adopting the low-complexity unmanned aerial vehicle modulation mode blind identification method is executed by the second processor, an interference signal is generated according to a blind identification result obtained from the modulation mode blind identification device, the generated interference signal passes through a radio frequency transceiver and a broadband antenna in sequence after normalization processing, and the generation and the transmission of the anti-braking analog signal are finished after signal frequency conversion, gain control, filtering and analog-to-digital conversion are finished.
3. The unmanned aerial vehicle modulation mode blind identification and counter-control system of claim 2, characterized in that:
when the modulation mode is identified blindly, the signal received by the signal receiving device is firstly filtered and amplified by a low noise amplifier arranged in the low noise and power amplification device and then transmitted to a radio frequency transceiver;
when the anti-modulation analog signal is generated, after signal frequency conversion, gain control, filtering and analog-to-digital conversion are completed through a radio frequency transceiver, the generated anti-modulation analog signal firstly passes through a power amplifier arranged in the low-noise and power amplification device, and the maximum power output is generated under the condition of a given distortion rate; and then the broadband antenna arranged in the signal receiving device receives and transmits the reverse analog signal to realize the reverse of the target unmanned aerial vehicle.
4. The unmanned aerial vehicle modulation mode blind identification and anti-braking system as claimed in claim 3, wherein the radio frequency transceiver adopts AD9361, ADRV9009 or ADRV9008 chip to realize frequency conversion, gain control, filtering and analog-to-digital conversion of signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010433690.5A CN111795611B (en) | 2020-05-20 | 2020-05-20 | Low-complexity unmanned aerial vehicle modulation mode blind identification and countercheck method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010433690.5A CN111795611B (en) | 2020-05-20 | 2020-05-20 | Low-complexity unmanned aerial vehicle modulation mode blind identification and countercheck method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111795611A CN111795611A (en) | 2020-10-20 |
| CN111795611B true CN111795611B (en) | 2021-02-02 |
Family
ID=72806549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010433690.5A Active CN111795611B (en) | 2020-05-20 | 2020-05-20 | Low-complexity unmanned aerial vehicle modulation mode blind identification and countercheck method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111795611B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114866385A (en) * | 2022-04-19 | 2022-08-05 | 安徽省军地创新信息科技有限公司 | Intelligent detection and interference attack method for 5G communication terminal |
| CN117200932A (en) * | 2023-09-28 | 2023-12-08 | 中国南方电网有限责任公司超高压输电公司电力科研院 | Identification method and system of unmanned aerial vehicle frequency emission signal based on neural network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220606A (en) * | 2017-05-22 | 2017-09-29 | 西安电子科技大学 | The recognition methods of radar emitter signal based on one-dimensional convolutional neural networks |
| CN108282426A (en) * | 2017-12-08 | 2018-07-13 | 西安电子科技大学 | Radio signal recognition recognition methods based on lightweight depth network |
| CN108353081A (en) * | 2015-09-28 | 2018-07-31 | 13部门有限公司 | Unmanned plane intrusion detection and confrontation |
| CN108718288A (en) * | 2018-03-30 | 2018-10-30 | 电子科技大学 | Recognition of digital modulation schemes method based on convolutional neural networks |
| CN111083077A (en) * | 2019-12-06 | 2020-04-28 | 成都华日通讯技术有限公司 | Method for realizing modulation recognition of 2ASK signal and AM signal by combining neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10699585B2 (en) * | 2018-08-02 | 2020-06-30 | University Of North Dakota | Unmanned aerial system detection and mitigation |
-
2020
- 2020-05-20 CN CN202010433690.5A patent/CN111795611B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108353081A (en) * | 2015-09-28 | 2018-07-31 | 13部门有限公司 | Unmanned plane intrusion detection and confrontation |
| CN107220606A (en) * | 2017-05-22 | 2017-09-29 | 西安电子科技大学 | The recognition methods of radar emitter signal based on one-dimensional convolutional neural networks |
| CN108282426A (en) * | 2017-12-08 | 2018-07-13 | 西安电子科技大学 | Radio signal recognition recognition methods based on lightweight depth network |
| CN108718288A (en) * | 2018-03-30 | 2018-10-30 | 电子科技大学 | Recognition of digital modulation schemes method based on convolutional neural networks |
| CN111083077A (en) * | 2019-12-06 | 2020-04-28 | 成都华日通讯技术有限公司 | Method for realizing modulation recognition of 2ASK signal and AM signal by combining neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111795611A (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111795611B (en) | Low-complexity unmanned aerial vehicle modulation mode blind identification and countercheck method and system | |
| Yang et al. | Specific emitter identification with limited samples: A model-agnostic meta-learning approach | |
| CN110336594B (en) | Deep learning signal detection method based on conjugate gradient descent method | |
| KR20190113114A (en) | Method and apparatus for controlling transmit power in wireless communication system based on neural network | |
| WO2021103206A1 (en) | Machine learning algorithm-based wireless radio frequency device identity recognition method and system | |
| CN112087774A (en) | Communication radiation source individual identification method based on residual error neural network | |
| CN111800216B (en) | System and method for generating anti-electromagnetic waveform of black-flying unmanned aerial vehicle | |
| CN114189310A (en) | Unmanned aerial vehicle measurement and control signal accurate interference method based on signal reconnaissance and prediction | |
| CN114896887A (en) | Frequency-using equipment radio frequency fingerprint identification method based on deep learning | |
| CN107102305B (en) | Robust cognitive radar transmitting and receiving joint design method in clutter environment | |
| CN114943246A (en) | Semi-supervised specific radiation source identification method based on bispectrum feature extraction | |
| CN111474955A (en) | Unmanned aerial vehicle image signal system identification method, device, equipment and storage medium | |
| CN113205140B (en) | Semi-supervised specific radiation source individual identification method based on generative countermeasure network | |
| CN111683023B (en) | Model-driven large-scale equipment detection method based on deep learning | |
| CN115577305B (en) | Unmanned aerial vehicle signal intelligent recognition method and device | |
| CN108599880B (en) | Civil aviation ground-air intercom system interference early warning method based on convolutional neural network | |
| CN114724245A (en) | CSI-based incremental learning human body action identification method | |
| CN113052080A (en) | Illegal unmanned aerial vehicle detection method based on unsupervised generation countermeasure network | |
| Zhang et al. | DTV radio spectrum anomaly detection based on an improved GAN | |
| Yang et al. | SNR estimation of UAV control signal based on convolutional neural network | |
| CN116955996B (en) | Cloud edge collaborative intelligent reasoning method and system based on cloud wireless access network | |
| CN117852396A (en) | Anti-interference complex signal SEI system template design and optimization method and equipment | |
| CN116647376B (en) | Voiceprint information-based underwater acoustic network node identity authentication method | |
| CN112350791B (en) | Terahertz signal detection method based on deep learning | |
| CN116761179B (en) | Mobile transmitting antenna selection and energy collection TAS-EH system safety communication performance intelligent prediction method based on lightweight MS-Net |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |