CN115664906B - Method and device for unsupervised clustering of TDMA signal protocol - Google Patents
Method and device for unsupervised clustering of TDMA signal protocol Download PDFInfo
- Publication number
- CN115664906B CN115664906B CN202211276019.XA CN202211276019A CN115664906B CN 115664906 B CN115664906 B CN 115664906B CN 202211276019 A CN202211276019 A CN 202211276019A CN 115664906 B CN115664906 B CN 115664906B
- Authority
- CN
- China
- Prior art keywords
- training
- signal
- clustering
- tdma
- tdma signal
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Time-Division Multiplex Systems (AREA)
Abstract
The invention discloses an unsupervised clustering method and device for a TDMA signal protocol, wherein the method comprises the following steps: acquiring a receiving instruction; receiving a target frequency band signal by utilizing the receiving instruction, and acquiring a TDMA signal data set; processing the TDMA signal data set to obtain IQ data; preprocessing the IQ data to obtain a TDMA signal clustering algorithm training set; performing signal protocol unsupervised algorithm training by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model; and clustering the received TDMA signals by using the target signal clustering algorithm model to obtain the protocol type of the TDMA signals, thereby realizing the unsupervised clustering of the TDMA signal protocol based on deep learning. The method adopts a clustering technology based on deep learning to realize the unsupervised clustering of the TDMA signal protocol through signal receiving, cutting-off and time-frequency conversion.
Description
Technical Field
The invention relates to the field of signal protocol unsupervised clustering, in particular to a TDMA signal protocol unsupervised clustering method and device.
Background
The traditional protocol analysis needs to perform parameter estimation layer by layer on the communication protocol, and can perform bit stream analysis on the protocol words on the premise of solving the problems of modulation pattern recognition and demodulation, interleaving and scrambling parameter estimation and de-interleaving and de-scrambling and channel decoding parameter estimation and decoding. This analytical method has the following disadvantages: the analysis period is long, the expert dependence is strong, the algorithm complexity is high, and the real-time analysis of unknown and swift electromagnetic signals is difficult to solve.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an unsupervised clustering method and device for TDMA signal protocol, which can acquire a receiving instruction; receiving a target frequency band signal by utilizing the receiving instruction, and acquiring a TDMA signal data set; processing the TDMA signal data set to obtain IQ data; preprocessing the IQ data to obtain a TDMA signal clustering algorithm training set; performing signal protocol unsupervised algorithm training by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model; and clustering the received TDMA signals by using the target signal clustering algorithm model to obtain the protocol type of the TDMA signals, thereby realizing the unsupervised clustering of the TDMA signal protocol based on deep learning. The signal protocol is clustered rapidly by a deep learning method, and the method can be applied to an electronic information system, such as communication signal processing and the like, and lays a technical foundation for intelligent protocol analysis.
In order to solve the technical problem, a first aspect of the embodiment of the present invention discloses an unsupervised clustering method for TDMA signal protocols, where the method includes:
s1, acquiring a receiving instruction; the receiving instruction comprises a working frequency band and a line gain parameter;
s2, receiving a target frequency band signal by utilizing the receiving instruction, and acquiring a TDMA signal data set; the TDMA signal data set comprises service burst TB data, reference burst AB data and synchronous burst RB data;
s3, processing the TDMA signal data set to obtain IQ data; the IQ data are in-phase and quadrature signal data, I is in-phase, and Q is quadrature which is different from the phase of I by 90 degrees;
s4, preprocessing the IQ data to obtain a TDMA signal clustering algorithm training set;
s5, training the TDMA signal clustering algorithm model by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model;
and S6, clustering the received TDMA signals by using the target signal clustering algorithm model to obtain the protocol types of the TDMA signals.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the preprocessing is performed on the IQ data to obtain a TDMA signal clustering algorithm training set, and the method includes:
S41, measuring the IQ data to obtain the length value of each TDMA signal data in the TDMA signal data set, and taking the maximum value as L max ；
S42, for any one of the TDMA signal data, starting from the starting position of the TDMTATIMA signal data, the length is
I is the length of the TDMA signal data;
s43, judging whether l is equal to 128, and obtaining a judging result;
when the judging result is negative, supplementing from 0 to 128 to obtain second communication signal data with the shape of [2,128 ];
when the judgment result is yes, directly obtaining second communication signal data with the shape of [2,128 ];
s44, performing WVD time-frequency conversion on the second communication signal data to obtain a time-frequency spectrogram with the shape of [128,128 ]:
in the method, in the process of the invention,
an instantaneous autocorrelation function R (t, τ) for the signal x (t), t being the time shift, τ being the integral variable, f being the frequency, S (t, f) being the time-frequency transformation function;
the WVD time-frequency transformation is Wigner-Ville distribution, is the Fourier transformation of a signal instantaneous correlation function, and reflects the signal instantaneous time-frequency relation;
s45, constructing training data with the shape of 128,128 by using the time-frequency spectrogram;
s46, marking the signal protocol type of the time-frequency spectrogram by using the signal protocol type of the time-frequency spectrogram to obtain training data labels with the shapes of 128 and 128;
The signal protocol types include: a traffic burst TB, a reference burst AB, and a synchronization burst RB;
s47, integrating the training data and the training data label to obtain the training data of the signal clustering algorithm;
s48, fusing all the signal clustering algorithm training data to obtain a TDMA signal clustering algorithm training set.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the TDMA signal clustering algorithm model is composed of a pre-training module and a clustering training module; training the TDMA signal clustering algorithm model by utilizing the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model, wherein the method comprises the following steps of;
s51, pre-training the pre-training module by utilizing the TDMA signal training data set to obtain adjacent sample data and a feature extraction encoder of the TDMA signal training data set;
the characteristic extraction encoder is used for carrying out characteristic extraction on the frequency domain information of the TDMA communication signal to obtain a characteristic expression vector;
s52, training the feature extraction encoder and the clustering training module by utilizing the TDMA signal training data set and the adjacent sample data to obtain a target signal clustering algorithm model;
And the clustering training module trains the feature expression vectors to form a feature library.
In a first aspect of the embodiment of the present invention, the pre-training module is pre-trained by using the TDMA signal training data set to obtain the adjacent sample data and the feature extraction encoder of the TDMA signal training data set, and the method includes:
s511, inputting the TDMA signal training data set after WVD pretreatment into a standard contrast learning BYOL network;
the contrast learning BYOL network consists of a target network with a parameter of theta and an online network with a parameter of epsilon; the online network is formed by an encoder f θ () Predictor g θ () Sum mapper q θ () A composition, the target network comprising an encoder f θ () And predictor g θ ()；
The predictor is used for the structural asymmetry of the target network and the online network;
s512, training the TDMA signal training data set by utilizing the contrast learning BYOL network to obtain a feature expression vector;
the TDMA signal training data set is respectively input into an online network and a target network of the contrast learning BYOL network to obtain q θ (Z θ ) And Z ε Using q θ (Z θ ) And Z ε Design loss function L B ：
Wherein q is θ (Z θ ) Q for output of on-line network θ () Predictor, Z θ To output vector for on-line network mapper, Z ε Outputting for a target network;
by L B The gradient descent updating online network parameter theta and the updating method of the target network parameter epsilon comprises the following steps: :
ε←τε+(1-τ)θ
wherein epsilon is an online network parameter, theta is a target network parameter, and tau=0.5 is a super parameter;
s513, measuring the adjacent sample data of the feature expression vector by using the similarity function to obtain the position information of the adjacent sample in the TDMA signal training data set;
the cosine similarity function expression is:
wherein a, b are feature vectors, respectively, and C (a, b) is the similarity between a, b;
s514, inputting the position information into an encoder for encoding and storing to obtain adjacent sample data information of the TDMA signal training data set, and using the encoder f of the online network θ () And saving to obtain the feature extraction encoder.
In a first aspect of the embodiment of the present invention, the training the feature extraction encoder and the clustering training module by using the TDMA signal training data set and the adjacent sample data to obtain a target signal clustering algorithm model, the method includes:
S521, connecting the characteristic output extracted by the characteristic extraction encoder with the clustering module to obtain a clustering network phi (); the clustering module consists of a full-connection layer;
the clustering training module is used for classifying the extracted characteristic parameters by using a classification model to obtain a classification result;
s522, inputting the TDMA signal training data set and the contiguous sample data information into the clustering network Φ ();
s523, regarding the clustering loss function L c And probability entropy L e Calculating to obtain a cluster loss function L c Value and probability entropy L e A value;
the cluster loss function L c The expression is:
L c ＝λL n +L a
wherein:
wherein L is n For contiguous loss, L a To distribute losses, x i Is an element in the second communication signal training data set X, n xi Is the nearest neighbor information N of each second communication signal training data set X is calculated x Phi () is the clustering network, M is the number of all elements in the second communication signal training data set X, k=3, λ and γ are super parameters, λ is used for balancing L n And L a ，q i Training the second communication signal training data set X through the clustering network phi () to obtain an allocation probability matrix P N Elements of each column vector after transformation into column vectors; 
Training the nearest neighbor information N through the clustering network phi () x Obtaining an allocation probability matrix P N Elements of each column vector after transformation into column vectors;
the probability entropy L e The expression is:
wherein H is an entropy function, M is the number of all elements in the second communication signal training data set X, k=3, q i Training the second communication signal training data set X through the clustering network phi () to obtain an allocation probability matrix P N The element of each column vector after transformation into column vector, j is q i Elements in vectorsSubscript;
s524, utilizing the cluster loss function L c And probability entropy L e Iterative training is carried out on the clustering network phi () to obtain training accuracy and standard mutual information of each time;
and S525, optimizing the loss function by using a batch gradient descent optimization algorithm based on the training accuracy and the standard mutual information, and completing training of the TDMA signal clustering algorithm model to obtain the target signal clustering algorithm model.
As an optional implementation manner, in a first aspect of the embodiment of the present invention, the processing the TDMA signal data set to obtain IQ data includes:
performing low-noise power amplification, filtering, A/D conversion and digital down-conversion on the TDMA signal data set to obtain IQ data;
S31, carrying out low-noise power amplification on the TDMA signal data set by using a low-noise power amplifier to obtain a first TDMA signal data set;
s32, processing the low-noise TDMA signal data set by using a band-pass filter to obtain a second TDMA signal data set;
s33, carrying out A/D conversion on the second TDMA signal data set by utilizing an A/D converter to obtain a third TDMA signal data set;
and S34, performing digital down-conversion on the third TDMA signal data set by using a digital down-converter to obtain the IQ data.
The second aspect of the embodiment of the invention discloses a TDMA signal protocol unsupervised clustering device, which comprises:
the instruction receiving module is used for acquiring a receiving instruction; the receiving instruction comprises a working frequency band and a line gain parameter;
the first processing module is used for receiving the target frequency band signal by utilizing the receiving instruction and acquiring a TDMA signal data set; the TDMA signal data set comprises service burst TB data, reference burst AB data and synchronous burst RB data;
the second processing module is used for processing the TDMA signal data set to obtain IQ data; the IQ data are in-phase and quadrature signal data, I is in-phase, and Q is quadrature which is different from the phase of I by 90 degrees;
The IQ data preprocessing module is used for preprocessing the IQ data to obtain a TDMA signal clustering algorithm training set;
the unsupervised clustering algorithm training module is used for training the TDMA signal clustering algorithm model by utilizing the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model;
and the unsupervised clustering module is used for clustering the received TDMA signals by using the target signal clustering algorithm model to obtain the protocol types of the TDMA signals.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the IQ data preprocessing module performs preprocessing on the IQ data to obtain a TDMA signal clustering algorithm training set:
measuring the IQ data to obtain the length value of each TDMA signal data in the TDMA signal data set, and taking the maximum value as L max ；
For any one of the TDMA signal data, the length of the time stamp pad is taken from the starting position of the TDMATDMA signal data
I is the length of the TDMA signal data;
judging whether l is equal to 128 or not to obtain a judging result;
when the judging result is negative, supplementing from 0 to 128 to obtain second communication signal data with the shape of [2,128 ];
When the judgment result is yes, directly obtaining second communication signal data with the shape of [2,128 ];
performing WVD time-frequency conversion on the second communication signal data to obtain a time-frequency spectrogram with the shape of [128,128 ]:
in the method, in the process of the invention,
an instantaneous autocorrelation function R (t, τ) for the signal x (t), t being the time shift, τ being the integral variable, f being the frequency, S (t, f) being the time-frequency transformation function;
constructing training data with the shape of 128,128 by utilizing the time-frequency spectrogram;
labeling the signal protocol type of the time-frequency spectrogram by using the signal protocol type of the time-frequency spectrogram to obtain a training data label with the shape of 128, 128;
the signal protocol types include: a traffic burst TB, a reference burst AB, and a synchronization burst RB;
integrating the training data and the training data label to obtain the training data of the signal clustering algorithm;
and fusing all the signal clustering algorithm training data to obtain a TDMA signal clustering algorithm training set.
In a second aspect of the embodiment of the present invention, the unsupervised clustering algorithm training module trains the TDMA signal clustering algorithm model by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model:
The TDMA signal clustering algorithm model consists of a pre-training module and a clustering training module;
pre-training the pre-training module by utilizing the TDMA signal training data set to obtain adjacent sample data and a feature extraction encoder of the TDMA signal training data set;
the characteristic extraction encoder is used for carrying out characteristic extraction on the frequency domain information of the TDMA communication signal to obtain a characteristic expression vector;
training the feature extraction encoder and the clustering training module by utilizing the TDMA signal training data set and the adjacent sample data to obtain a target signal clustering algorithm model;
and the clustering training module trains the feature expression vectors to form a feature library.
In a second aspect of the present invention, the method further includes the step of pre-training the pre-training module by using the TDMA signal training data set to obtain adjacent sample data and a feature extraction encoder of the TDMA signal training data set, where the adjacent sample data and feature extraction encoder include:
inputting the TDMA signal training data set after WVD pretreatment into a standard contrast learning BYOL network;
the contrast learning BYOL network consists of a target network with a parameter of theta and an online network with a parameter of epsilon; the online network is formed by an encoder f θ () Predictor g θ () Sum mapper q θ () A composition, the target network comprising an encoder f θ () And predictor g θ ()；
The predictor is used for the structural asymmetry of the target network and the online network;
training the TDMA signal training data set by utilizing the contrast learning BYOL network to obtain a feature expression vector;
the TDMA signal training data set is respectively input into an online network and a target network of the contrast learning BYOL network to obtain q θ (Z θ ) And Z ε Using q θ (Z θ ) And Z ε Design loss function L B ：
Wherein q is θ (Z θ ) Q for output of on-line network θ () Predictor, Z θ To output vector for on-line network mapper, Z ε Outputting for a target network;
by L B The gradient descent updating online network parameter theta and the updating method of the target network parameter epsilon comprises the following steps:
ε←τε+(1-τ)θ
wherein epsilon is an online network parameter, theta is a target network parameter, and tau=0.5 is a super parameter;
measuring adjacent sample data of the feature expression vector by utilizing the similarity function to obtain position information of the adjacent sample in the TDMA signal training data set;
the cosine similarity function expression is:
wherein a, b are feature vectors, respectively, and C (a, b) is the similarity between a, b;
inputting the position information into an encoder for encoding and storing to obtain adjacent sample data information of the TDMA signal training data set, and using the encoder f of the online network θ () And saving to obtain the feature extraction encoder.
In a second aspect of the embodiment of the present invention, the unsupervised clustering algorithm training module trains the feature extraction encoder and the clustering training module to obtain a target signal clustering algorithm model by using the TDMA signal training data set and the adjacent sample data, and the method includes:
connecting the feature output extracted by the feature extraction encoder with the clustering module to obtain a clustering network phi (); the clustering module consists of a full-connection layer;
the clustering training module is used for classifying the extracted characteristic parameters by using a classification model to obtain a classification result;
inputting the TDMA signal training data set and the contiguous sample data information to the clustering network Φ ();
for the cluster loss function L c And probability entropy L e Calculating to obtain a cluster loss function L c Value and probability entropy L e A value;
the cluster loss function L c The expression is:
L c ＝λL n +L a
wherein:
wherein L is n For contiguous loss, L a To distribute losses, x i Is an element in the second communication signal training data set X, n xi Is the nearest neighbor information N of each second communication signal training data set X is calculated x Phi () is the clustering network, M is the number of all elements in the second communication signal training data set X, k=3, λ and γ are super parameters, λ is used for balancing L n And L a ，q i Training the second communication signal training data set X through the clustering network phi () to obtain an allocation probability matrix P N Elements of each column vector after transformation into column vectors;
training the nearest neighbor information N through the clustering network phi () x Obtaining an allocation probability matrix P N Elements of each column vector after transformation into column vectors;
the probability entropy L e The expression is:
wherein H is an entropy function, M is the number of all elements in the second communication signal training data set X, k=3, q i Training the second communication signal training data set X through the clustering network phi () to obtain an allocation probability matrix P N The element of each column vector after transformation into column vector, j is q i Element subscripts in the vectors;
using the cluster loss function L c And probability entropy L e Iterative training is carried out on the clustering network phi () to obtain training accuracy and standard mutual information of each time;
and optimizing the loss function by utilizing a batch gradient descent optimization algorithm based on the training accuracy and the standard mutual information, and completing training of the TDMA signal clustering algorithm model to obtain the target signal clustering algorithm model.
In a second aspect of the embodiment of the present invention, the second processing module processes the TDMA communication signal data set to obtain IQ data, and the method includes:
performing low-noise power amplification, filtering, A/D conversion and digital down-conversion on the TDMA communication signal data set to obtain IQ data;
amplifying the TDMA signal data set with low noise power by using a low noise power amplifier to obtain a first TDMA signal data set;
processing the low noise TDMA signal data set by using a band-pass filter to obtain a second TDMA signal data set;
performing A/D conversion on the second TDMA signal data set by using an A/D converter to obtain a third TDMA signal data set;
and carrying out digital down-conversion on the third TDMA signal data set by utilizing a digital down-converter to obtain the IQ data.
In a third aspect, the present invention discloses another TDMA signal protocol unsupervised clustering apparatus, said apparatus comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform some or all of the steps in the TDMA signal protocol unsupervised clustering method disclosed in the first aspect of the embodiment of the present invention.
In a fourth aspect, the present invention discloses a computer storage medium, where computer instructions are stored, where the computer instructions, when called, are used to perform part or all of the steps in the TDMA signal protocol unsupervised clustering method disclosed in the first aspect of the present invention.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, the receiving instruction can be acquired; receiving a target frequency band signal by utilizing the receiving instruction, and acquiring a TDMA signal data set; processing the TDMA signal data set to obtain IQ data; preprocessing the IQ data to obtain a TDMA signal clustering algorithm training set; performing signal protocol unsupervised algorithm training by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model; and clustering the received TDMA signals by using the target signal clustering algorithm model to obtain the protocol types of the TDMA signals. The fast clustering of the TDMA signal protocol is realized by the deep learning method without depending on expert, the analysis period is short, the algorithm is simple and efficient, and the requirement of real-time analysis of unknown and agile electromagnetic signals is met.
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 apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a TDMA signal protocol unsupervised clustering method disclosed in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a TDMA signal protocol unsupervised clustering apparatus according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a TDMA signal clustering algorithm model used by a TDMA signal protocol unsupervised clustering device according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a bandpass filter employed by another TDMA signal protocol unsupervised clustering apparatus in accordance with an embodiment of the present invention;
FIG. 5 is a schematic diagram of digital down conversion employed by another TDMA signal protocol unsupervised clustering apparatus in accordance with an embodiment of the present invention;
fig. 6 is a schematic structural diagram of another TDMA signal protocol unsupervised clustering apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the present invention better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or device that comprises a list of steps or elements is not limited to the list of steps or elements but may, in the alternative, include other steps or elements not expressly listed or inherent to such process, method, article, or device.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention discloses an unsupervised clustering method and device for a TDMA signal protocol, which can acquire a receiving instruction; receiving a target frequency band signal by utilizing the receiving instruction, and acquiring a TDMA signal data set; processing the TDMA signal data set to obtain IQ data; preprocessing the IQ data to obtain a TDMA signal clustering algorithm training set; training a TDMA signal protocol unsupervised algorithm by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model; and clustering the received TDMA signals by using the target signal clustering algorithm model to obtain the protocol types of the TDMA signals. And the TDMA signal protocol is clustered rapidly in a physical layer by a deep learning method, so that a technical foundation is laid for intelligent protocol analysis. The following will describe in detail.
Example 1
Referring to fig. 1, fig. 1 is a schematic flow chart of a TDMA signal protocol unsupervised clustering method according to an embodiment of the present invention. The method for unsupervised clustering of TDMA signaling protocol described in fig. 1 is applied to an electronic information system, such as a local server or cloud server for unsupervised clustering management of TDMA signaling protocol, which is not limited in the embodiments of the present invention. As shown in fig. 1, the unsupervised clustering method for TDMA signal protocol may include the following operations:
s1, acquiring a receiving instruction; the receiving instruction comprises a working frequency band and a line gain parameter;
s2, receiving a target frequency band signal by utilizing the receiving instruction, and acquiring a TDMA signal data set; the TDMA signal data set comprises service burst TB data, reference burst AB data and synchronous burst RB data;
s3, processing the TDMA signal data set to obtain IQ data; the IQ data are in-phase and quadrature signal data, I is in-phase, and Q is quadrature which is different from the phase of I by 90 degrees;
performing low-noise power amplification, filtering, A/D conversion and digital down-conversion on the TDMA communication signal data set to obtain IQ data;
s31, carrying out low-noise power amplification on the TDMA signal data set by using a low-noise power amplifier to obtain a first TDMA signal data set;
S32, processing the low-noise TDMA signal data set by using a band-pass filter to obtain a second TDMA signal data set;
optionally, a bandpass filter is used to filter the received signal, fig. 4 is a basic schematic diagram of the bandpass filter, vi is an input voltage, vo is an output voltage, L is an inductance, and C is a capacitance;
optionally, filtering the received signal by adopting an extended Kalman filtering algorithm of a multidimensional variable, wherein the expression is;
wherein x is a variable, x k As a state vector of the state vector,
is a jacobian matrix, o n The method is characterized by being infinitely small in higher order, n is the order, and f (x) is a one-dimensional Taylor expansion function;
in the method, in the process of the invention,
is a jacobian matrix, f (x k ) For an m-dimensional taylor expansion function, f (x) is a function with an n-th derivative, x is a variable, x k Is a state vector, m is a vector dimension, +.>
S33, carrying out A/D conversion on the second TDMA signal data set by utilizing an A/D converter to obtain a third TDMA signal data set;
s34, performing digital down-conversion on the third TDMA signal data set by using a digital down-converter to obtain the IQ data;
alternatively, the received signal is down-converted using digital down-conversion, as shown in fig. 5.
S4, preprocessing the IQ data to obtain a TDMA signal clustering algorithm training set, wherein the training set comprises;
S41, measuring the IQ data to obtain the length value of each TDMA signal data in the TDMA signal data set, and taking the maximum value as L max ；
S42, for any one of the TDMA signal data, starting from the starting position of the TDMTATIMA signal data, the length is
I is the length of the TDMA signal data;
s43, judging whether l is equal to 128, and obtaining a judging result;
when the judging result is negative, supplementing from 0 to 128 to obtain second communication signal data with the shape of [2,128 ];
when the judgment result is yes, directly obtaining second communication signal data with the shape of [2,128 ];
s44, performing WVD time-frequency conversion on the second communication signal data to obtain a time-frequency spectrogram with the shape of [128,128 ]:
in the method, in the process of the invention,
an instantaneous autocorrelation function R (t, τ) for the signal x (t), t being the time shift, τ being the integral variable, f being the frequency, S (t, f) being the time-frequency transformation function;
s45, constructing training data with the shape of 128,128 by using the time-frequency spectrogram;
s46, marking the signal protocol type of the time-frequency spectrogram by using the signal protocol type of the time-frequency spectrogram to obtain training data labels with the shapes of 128 and 128;
the signal protocol types include: a traffic burst TB, a reference burst AB, and a synchronization burst RB;
S47, integrating the training data and the training data label to obtain the training data of the signal clustering algorithm;
s48, fusing all the signal clustering algorithm training data to obtain a TDMA signal clustering algorithm training set.
S5, training the TDMA signal clustering algorithm model by utilizing the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model, wherein the training step comprises the following steps:
the TDMA signal clustering algorithm model is shown in fig. 3, in which Aug1 and Aug2 are two different enhancement modes, and Anchor and Neighbor are Anchor samples and their adjacent samples, respectively;
s51, pre-training the pre-training module by utilizing the TDMA signal training data set to obtain adjacent sample data and a feature extraction encoder of the TDMA signal training data set, wherein the adjacent sample data and the feature extraction encoder comprise;
s511, inputting the TDMA signal training data set after WVD pretreatment into a standard contrast learning BYOL network;
the contrast learning BYOL network consists of a target network with a parameter of theta and an online network with a parameter of epsilon; the online network is formed by an encoder f θ () Predictor g θ () Sum mapper q θ () A composition, the target network comprising an encoder f θ () And predictor g θ ()；
The predictor is used for the structural asymmetry of the target network and the online network;
S512, training the TDMA signal training data set by utilizing the contrast learning BYOL network to obtain a feature expression vector;
the TDMA signal training data set is respectively input into an online network and a target network of the contrast learning BYOL network to obtain q θ (Z θ ) And Z ε Using q θ (Z θ ) And Z ε Design loss function L B ：
Wherein q is θ (Z θ ) Q for output of on-line network θ () Predictor, Z θ To output vector for on-line network mapper, Z ε Outputting for a target network;
by L B The gradient descent updating online network parameter theta and the updating method of the target network parameter epsilon comprises the following steps:
ε←τε+(1-τ)θ
wherein epsilon is an online network parameter, theta is a target network parameter, and tau=0.5 is a super parameter;
s513, measuring the adjacent sample data of the feature expression vector by using the similarity function to obtain the position information of the adjacent sample in the TDMA signal training data set;
the cosine similarity function expression is:
wherein a, b are feature vectors, respectively, and C (a, b) is the similarity between a, b;
s514, inputting the position information into an encoder for encoding and storing to obtain adjacent sample data information of the TDMA signal training data set, and using the encoder f of the online network θ () And saving to obtain the feature extraction encoder.
S52, training the feature extraction encoder and the clustering training module by using the TDMA signal training data set and the adjacent sample data to obtain a target signal clustering algorithm model, wherein the method comprises the following steps:
s521, connecting the characteristic output extracted by the characteristic extraction encoder with the clustering module to obtain a clustering network phi (); the clustering module consists of a full-connection layer;
the clustering training module is used for classifying the extracted characteristic parameters by using a classification model to obtain a classification result;
s522, inputting the TDMA signal training data set and the contiguous sample data information into the clustering network Φ ();
s523, regarding the clustering loss function L c And probability entropy L e Calculating to obtain a cluster loss function L c Value and probability entropy L e A value;
the cluster loss function L c The expression is:
L c ＝λL n +L a
wherein:
wherein L is n For contiguous loss, L a To distribute losses, x i Is an element in the second communication signal training data set X, n xi Is the nearest neighbor information N of each second communication signal training data set X is calculated x Phi () is the clustering network, M is the number of all elements in the second communication signal training data set X, k=3, λ and γ are super parameters, λ is used for balancing L n And L a ，q i Training the second communication signal training data set X through the clustering network phi () to obtain an allocation probability matrix P N Elements of each column vector after transformation into column vectors;
training the nearest neighbor information N through the clustering network phi () x Obtaining an allocation probability matrix P N Elements of each column vector after transformation into column vectors;
the probability entropy L e The expression is:
wherein H is an entropy function, M is the number of all elements in the second communication signal training data set X, k=3, q i Training the second communication signal training data set X through the clustering network phi () to obtain an allocation probability matrix P N The element of each column vector after transformation into column vector, j is q i Element subscripts in the vectors;
s524, utilizing the cluster loss function L c And probability entropy L e Iterative training is carried out on the clustering network phi () to obtain training accuracy and standard mutual information of each time;
and S525, optimizing the loss function by using a batch gradient descent optimization algorithm based on the training accuracy and the standard mutual information, and completing training of the TDMA signal clustering algorithm model to obtain the target signal clustering algorithm model.
S6, clustering the received TDMA signals by using the target signal clustering algorithm model to obtain the protocol types of the TDMA signals;
Optionally, a batch gradient descent algorithm is adopted for iterative optimization, and the parameter updating mode is as follows:
where Θ is a parameter of the clustered network, a=0.001 is the learning rate,
in order to reduce the direction of the fastest drop of the loss function, the method is obtained by deflecting the theta parameter in the loss function.
Therefore, by implementing the method for unsupervised clustering of the TDMA signal protocol described in the embodiment of the invention, a receiving instruction can be obtained; receiving a target frequency band signal by utilizing the receiving instruction, and acquiring a TDMA signal data set; processing the TDMA signal data set to obtain IQ data; preprocessing the IQ data to obtain a TDMA signal clustering algorithm training set; performing signal protocol unsupervised algorithm training by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model; and clustering the received TDMA signals by using the target signal clustering algorithm model to obtain the protocol types of the TDMA signals. The signal protocol is clustered quickly by a deep learning method without depending on expert, so that a technical foundation is laid for intelligent protocol analysis.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of an unsupervised clustering device for TDMA signal protocol according to an embodiment of the present invention. The apparatus described in fig. 2 can be applied to a TDMA signal processing system, such as a local server or a cloud server for TDMA signal processing, and the embodiment of the invention is not limited. As shown in fig. 2, the apparatus may include:
An instruction receiving module 201, configured to obtain a received instruction; the receiving instruction comprises a working frequency band and a line gain parameter;
a first processing module 202, configured to receive a target frequency band signal by using the receiving instruction, and obtain a TDMA signal data set; the TDMA signal data set comprises service burst TB data, reference burst AB data and synchronous burst RB data;
a second processing module 203, configured to process the TDMA signal data set to obtain IQ data; the IQ data are in-phase and quadrature signal data, I is in-phase, and Q is quadrature which is different from the phase of I by 90 degrees;
the IQ data preprocessing module 204 is configured to preprocess the IQ data to obtain a TDMA signal clustering algorithm training set;
the unsupervised clustering algorithm training module 205 is configured to train the TDMA signal clustering algorithm model by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model;
and the unsupervised clustering module 206 is configured to perform clustering processing on the received TDMA signals by using the target signal clustering algorithm model, so as to obtain protocol types of the TDMA signals.
It can be seen that implementing the apparatus for unsupervised clustering of TDMA signal protocols described in fig. 2, a TDMA signal dataset can be obtained by obtaining a reception instruction, receiving a target frequency band signal; processing the TDMA signal data set to obtain IQ data; preprocessing the IQ data to obtain a TDMA signal clustering algorithm training set; performing signal protocol unsupervised algorithm training by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model; and clustering the received TDMA signals by using the target signal clustering algorithm model to obtain the protocol types of the TDMA signals. The TDMA signal protocol is clustered quickly by a deep learning method without depending on expert, so that a technical foundation is laid for intelligent protocol analysis.
In another alternative embodiment, as shown in fig. 2, the IQ data preprocessing module 204 performs preprocessing on IQ data to obtain a TDMA signal protocol unsupervised clustering algorithm training set, including:
measuring the IQ data to obtain the length value of each TDMA signal data in the TDMA signal data set, and taking the maximum value as L max ；
For any one of the TDMA signal data, the length of the time stamp pad is taken from the starting position of the TDMATDMA signal data
I is the length of the TDMA signal data;
judging whether l is equal to 128 or not to obtain a judging result;
when the judging result is negative, supplementing from 0 to 128 to obtain second communication signal data with the shape of [2,128 ];
when the judgment result is yes, directly obtaining second communication signal data with the shape of [2,128 ];
performing WVD time-frequency conversion on the second communication signal data to obtain a time-frequency spectrogram with the shape of [128,128 ]:
in the method, in the process of the invention,
an instantaneous autocorrelation function R (t, τ) for the signal x (t), t being the time shift, τ being the integral variable, f being the frequency, S (t, f) being the time-frequency transformation function;
constructing training data with the shape of 128,128 by utilizing the time-frequency spectrogram;
labeling the signal protocol type of the time-frequency spectrogram by using the signal protocol type of the time-frequency spectrogram to obtain a training data label with the shape of 128, 128;
The signal protocol types include: a traffic burst TB, a reference burst AB, and a synchronization burst RB;
integrating the training data and the training data label to obtain the training data of the signal clustering algorithm;
and fusing all the signal clustering algorithm training data to obtain a TDMA signal clustering algorithm training set.
Therefore, the reinforcement learning-based TDMA signal protocol unsupervised clustering device for TDMA signal protocol unsupervised clustering described in fig. 2 can preprocess IQ data to obtain a TDMA signal protocol unsupervised clustering algorithm training set, and perform TDMA signal protocol unsupervised clustering algorithm training, thereby facilitating rapid clustering of TDMA signal protocols independent of experts and laying a technical foundation for intelligent protocol analysis.
In yet another alternative embodiment, as shown in fig. 2, the unsupervised clustering algorithm training module 205 trains the TDMA signal clustering algorithm model to obtain a target signal clustering algorithm model by using the TDMA signal clustering algorithm training set, and the method includes;
s51, pre-training the pre-training module by utilizing the TDMA signal training data set to obtain adjacent sample data and a feature extraction encoder of the TDMA signal training data set;
The characteristic extraction encoder is used for carrying out characteristic extraction on the frequency domain information of the TDMA communication signal to obtain a characteristic expression vector;
s52, training the feature extraction encoder and the clustering training module by utilizing the TDMA signal training data set and the adjacent sample data to obtain a target signal clustering algorithm model;
and the clustering training module trains the feature expression vectors to form a feature library.
Therefore, the implementation of the TDMA signal protocol unsupervised clustering device for TDMA signal protocol unsupervised clustering described in fig. 2 can utilize the TDMA signal clustering algorithm model to process the received signals, thereby being beneficial to fast clustering the TDMA signal protocol independent of experts and laying a technical foundation for intelligent protocol analysis.
In yet another alternative embodiment, as shown in fig. 2, an unsupervised clustering algorithm training module 205 uses the TDMA signal training dataset to pretrain the pretraining module to obtain contiguous sample data of the TDMA signal training dataset and a feature extraction encoder, comprising;
inputting the TDMA signal training data set after WVD pretreatment into a standard contrast learning BYOL network;
The contrast learning BYOL network consists of a target network with a parameter of theta and an online network with a parameter of epsilon; the online network is formed by an encoder f θ () Predictor g θ () Sum mapper q θ () A composition, the target network comprising an encoder f θ () And predictor g θ ()；
The predictor is used for the structural asymmetry of the target network and the online network;
training the TDMA signal training data set by utilizing the contrast learning BYOL network to obtain a feature expression vector;
the TDMA signal training data set is respectively input into an online network and a target network of the contrast learning BYOL network to obtain q θ (Z θ ) And Z ε Using q θ (Z θ ) And Z ε Design loss function L B ：
Wherein q is θ (Z θ ) Q for output of on-line network θ () Predictor, Z θ To output vector for on-line network mapper, Z ε Outputting for a target network;
by L B The gradient descent updating online network parameter theta and the updating method of the target network parameter epsilon comprises the following steps:
ε←τε+(1-τ)θ
wherein epsilon is an online network parameter, theta is a target network parameter, and tau=0.5 is a super parameter;
measuring adjacent sample data of the feature expression vector by utilizing the similarity function to obtain position information of the adjacent sample in the TDMA signal training data set;
The cosine similarity function expression is:
wherein a, b are feature vectors, respectively, and C (a, b) is the similarity between a, b;
inputting the position information into an encoder for encoding and storing to obtain adjacent sample data information of the TDMA signal training data set, and using the encoder f of the online network θ () And saving to obtain the feature extraction encoder.
Therefore, the implementation of the TDMA signal protocol unsupervised clustering device for TDMA signal protocol unsupervised clustering described in fig. 2 can pretrain the TDMA signal training data set to obtain the adjacent sample data and the feature extraction encoder of the TDMA signal training data set, which is favorable for realizing rapid clustering of the TDMA signal protocol independent of experts and lays a technical foundation for intelligent protocol analysis.
In yet another alternative embodiment, as shown in fig. 2, an unsupervised clustering algorithm training module 205 trains the feature extraction encoder and the clustering training module using the TDMA signal training dataset and the contiguous sample data to obtain a target signal clustering algorithm model, comprising:
connecting the feature output extracted by the feature extraction encoder with the clustering module to obtain a clustering network phi (); the clustering module consists of a full-connection layer;
The clustering training module is used for classifying the extracted characteristic parameters by using a classification model to obtain a classification result;
inputting the TDMA signal training data set and the contiguous sample data information to the clustering network Φ ();
for the cluster loss function L c And probability entropy L e Calculating to obtain a cluster loss function L c Value and probability entropy L e A value;
the cluster loss function L c The expression is:
L c ＝λL n +L a
wherein:
wherein L is n For contiguous loss, L a To distribute losses, x i Is an element in the second communication signal training data set X, n xi Is the nearest neighbor information N of each second communication signal training data set X is calculated x Phi () is the clustering network, M is the number of all elements in the second communication signal training data set X, k=3, λ and γ are super parameters, λ is used for balancing L n And L a ，q i Training the second communication signal training data set X through the clustering network phi () to obtain an allocation probability matrix P N Elements of each column vector after transformation into column vectors;
training the nearest neighbor information N through the clustering network phi () x Obtaining an allocation probability matrix P N Elements of each column vector after transformation into column vectors;
The probability entropy L e The expression is:
wherein H is an entropy function, M is the number of all elements in the second communication signal training data set X, k=3, q i Training the second communication signal training data set X through the clustering network phi () to obtain an allocation probability matrix P N The element of each column vector after transformation into column vector, j is q i Element subscripts in the vectors;
using the cluster loss function L c And probability entropy L e Iterative training is carried out on the clustering network phi () to obtain training accuracy and standard mutual information of each time;
and optimizing the loss function by utilizing a batch gradient descent optimization algorithm based on the training accuracy and the standard mutual information, and completing training of the TDMA signal clustering algorithm model to obtain the target signal clustering algorithm model.
Therefore, the implementation of the TDMA signal protocol unsupervised clustering device for TDMA signal protocol unsupervised clustering described in fig. 2 can process the TDMA signal training data set and the adjacent sample data to obtain a signal protocol unsupervised clustering model, which is favorable for implementing fast clustering of TDMA signal protocols independent of experts and lays a technical foundation for intelligent protocol analysis.
Example III
Referring to fig. 6, fig. 6 is a schematic structural diagram of another TDMA signal protocol unsupervised clustering apparatus according to an embodiment of the present invention. The apparatus described in fig. 6 can be applied to an electronic information system, such as a local server or a cloud server for non-supervised cluster management of TDMA signal protocol, which is not limited by the embodiment of the present invention. As shown in fig. 6, the apparatus may include:
a memory 301 storing executable program code;
a processor 302 coupled with the memory 301;
Example IV
The embodiment of the invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps in the TDMA signal protocol unsupervised clustering method described in the embodiment one.
Example five
The present invention discloses a computer program product comprising a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the TDMA signal protocol unsupervised clustering method described in embodiment one.
The apparatus embodiments described above are merely illustrative, in which the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Finally, it should be noted that: the embodiment of the invention discloses a reinforcement learning-based TDMA signal protocol unsupervised clustering method and device, which are disclosed as preferred embodiments of the invention, and are only used for illustrating the technical scheme of the invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (4)
1. A method for unsupervised clustering of TDMA signal protocols, the method comprising:
s1, acquiring a receiving instruction; the receiving instruction comprises a working frequency band and a line gain parameter;
s2, receiving a target frequency band signal by utilizing the receiving instruction, and acquiring a TDMA signal data set; the TDMA signal data set comprises service burst TB data, reference burst AB data and synchronous burst RB data;
s3, processing the TDMA signal data set to obtain IQ data; the IQ data are in-phase and quadrature signal data, I is in-phase, and Q is quadrature which is different from the phase of I by 90 degrees;
S4, preprocessing the IQ data to obtain a TDMA signal clustering algorithm training set;
the IQ data is preprocessed to obtain a TDMA signal clustering algorithm training set, and the method comprises the following steps:
s41, measuring the IQ data to obtain the length value of each TDMA signal data in the TDMA signal data set, and taking the maximum value as L max ；
S42, for any one of the TDMA signal data, the length of the starting position of the TDMA signal data is as follows
I is the length of the TDMA signal data;
s43, judging whether l is equal to 128, and obtaining a judging result;
when the judging result is negative, supplementing from 0 to 128 to obtain second communication signal data with the shape of [2,128 ];
when the judgment result is yes, directly obtaining second communication signal data with the shape of [2,128 ];
s44, performing WVD time-frequency conversion on the second communication signal data to obtain a time-frequency spectrogram with the shape of [128,128 ]:
in the method, in the process of the invention,
as an instantaneous autocorrelation function of the signal x (t)
R (t, τ), t is the time shift, τ is the integral variable, f is the frequency, S (t, f) is the time-frequency transform function;
s45, constructing training data with the shape of 128,128 by using the time-frequency spectrogram;
S46, marking the signal protocol type of the time-frequency spectrogram by using the signal protocol type of the time-frequency spectrogram to obtain training data labels with the shapes of 128 and 128;
the signal protocol types include: a traffic burst TB, a reference burst AB, and a synchronization burst RB;
s47, integrating the training data and the training data label to obtain the training data of the signal clustering algorithm;
s48, fusing all the signal clustering algorithm training data to obtain a TDMA signal clustering algorithm training set;
s5, training the TDMA signal clustering algorithm model by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model;
the TDMA signal clustering algorithm model consists of a pre-training module and a clustering training module;
training the TDMA signal clustering algorithm model by using the TDMA signal clustering algorithm training set to obtain a target signal clustering algorithm model, wherein the method comprises the following steps of;
s51, pre-training the pre-training module by utilizing the TDMA signal training data set to obtain adjacent sample data and a feature extraction encoder of the TDMA signal training data set;
the method includes the steps of pre-training the pre-training module by using the TDMA signal training data set to obtain adjacent sample data and a feature extraction encoder of the TDMA signal training data set, and the method includes the steps of:
S511, inputting the TDMA signal training data set after WVD pretreatment into a standard contrast learning BYOL network;
the contrast learning BYOL network consists of a target network with a parameter of theta and an online network with a parameter of epsilon; the online network is formed by an encoder f θ () Predictor g θ () Sum mapper q θ () A composition, the target network comprising an encoder f θ () And predictor g θ ()；
The predictor is used for the structural asymmetry of the target network and the online network;
s512, training the TDMA signal training data set by utilizing the contrast learning BYOL network to obtain a feature expression vector;
the TDMA signal trainingThe training data set is respectively input into an online network and a target network of the contrast learning BYOL network to obtain q θ (Z θ ) And Z ε Using q θ (Z θ ) And Z ε Design loss function L B ：
Wherein q is θ (Z θ ) Q for output of on-line network θ () For mapper, Z θ To output vector for on-line network mapper, Z ε Outputting for a target network;
by L B The gradient descent updating target network parameter theta and the online network parameter epsilon updating method comprises the following steps:
ε←τε+(1-τ)θ
wherein epsilon is an online network parameter, theta is a target network parameter, and tau=0.5 is a super parameter;
s513, measuring adjacent sample data of the feature expression vector by using a cosine similarity function to obtain position information of the adjacent sample in the TDMA signal training data set;
The cosine similarity function expression is:
wherein a, b are feature vectors, respectively, and C (a, b) is the similarity between a, b;
s514, inputting the position information into an encoder for encoding and storing to obtain adjacent sample data information of the TDMA signal training data set, and using the encoder f of the online network θ () Saving to obtain the feature extraction encoder;
the characteristic extraction encoder is used for carrying out characteristic extraction on the frequency domain information of the TDMA communication signal to obtain a characteristic expression vector;
s52, training the feature extraction encoder and the clustering training module by utilizing the TDMA signal training data set and the adjacent sample data to obtain a target signal clustering algorithm model;
the training of the feature extraction encoder and the clustering training module by using the TDMA signal training data set and the adjacent sample data is performed to obtain a target signal clustering algorithm model, and the method comprises the following steps:
s521, connecting the characteristic output extracted by the characteristic extraction encoder with the clustering training module to obtain a clustering network phi (); the clustering training module consists of a full-connection layer;
the clustering training module is used for classifying the extracted characteristic parameters by using a classification model to obtain a classification result;
S522, inputting the TDMA signal training data set and the contiguous sample data information into the clustering network Φ ();
s523, regarding the clustering loss function L c And probability entropy L e Calculating to obtain a cluster loss function L c Value and probability entropy L e A value;
the cluster loss function L c The expression is:
L c ＝λL n +L a
wherein:
wherein L is n For contiguous loss, L a To distribute losses, x i Is an element of the training data set X of the second communication signal data, n xi Is the nearest neighbor information N of the training data set X of each second communication signal data obtained by calculation x Phi () is the clustering network, M isThe number of all elements in the training data set X of the second communication signal data, k=3, λ and γ are super-parameters, λ is used for balancing L n And L a ，q i Training a training data set X of the second communication signal data through the clustering network phi (), and obtaining elements of each column vector after the distribution probability matrix is transformed into the column vector;
training the nearest neighbor information N through the clustering network phi () x Obtaining the elements of each column vector after the distribution probability matrix is transformed into the column vector;
the probability entropy L e The expression is:
wherein H is an entropy function, M is the number of all elements in the training data set X of the second communication signal data, k=3, j is q i Element subscripts in the vectors;
s524, utilizing the cluster loss function L c And probability entropy L e Iterative training is carried out on the clustering network phi () to obtain training accuracy and standard mutual information of each time;
s525, optimizing a loss function by using a batch gradient descent optimization algorithm based on the training accuracy and the standard mutual information, and completing training of the TDMA signal clustering algorithm model to obtain a target signal clustering algorithm model;
the clustering training module trains the feature expression vectors to form a feature library;
and S6, clustering the received TDMA signals by using the target signal clustering algorithm model to obtain the protocol types of the TDMA signals.
2. The method of unsupervised clustering of TDMA signal protocols according to claim 1, wherein said processing said TDMA signal data sets to obtain IQ data comprises:
performing low-noise power amplification, filtering, A/D conversion and digital down-conversion on the TDMA signal data set to obtain IQ data;
s31, carrying out low-noise power amplification on the TDMA signal data set by using a low-noise power amplifier to obtain a first TDMA signal data set;
S32, processing the low-noise TDMA signal data set by using a band-pass filter to obtain a second TDMA signal data set;
s33, carrying out A/D conversion on the second TDMA signal data set by utilizing an A/D converter to obtain a third TDMA signal data set;
and S34, performing digital down-conversion on the third TDMA signal data set by using a digital down-converter to obtain the IQ data.
3. An apparatus for unsupervised clustering of TDMA signal protocols, said apparatus comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the TDMA signal protocol unsupervised clustering method of any one of claims 1-2.
4. A computer storage medium storing computer instructions which, when invoked, are operable to perform the TDMA signal protocol unsupervised clustering method of any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211276019.XA CN115664906B (en) | 2022-10-18 | 2022-10-18 | Method and device for unsupervised clustering of TDMA signal protocol |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211276019.XA CN115664906B (en) | 2022-10-18 | 2022-10-18 | Method and device for unsupervised clustering of TDMA signal protocol |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115664906A CN115664906A (en) | 2023-01-31 |
| CN115664906B true CN115664906B (en) | 2023-05-02 |
Family
ID=84989300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211276019.XA Active CN115664906B (en) | 2022-10-18 | 2022-10-18 | Method and device for unsupervised clustering of TDMA signal protocol |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115664906B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116578874B (en) * | 2023-07-10 | 2023-11-21 | 武汉能钠智能装备技术股份有限公司四川省成都市分公司 | Satellite signal attribute appraising method and device based on network protocol |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107682216A (en) * | 2017-09-01 | 2018-02-09 | 南京南瑞集团公司 | A kind of network traffics protocol recognition method based on deep learning |
| CN108256488A (en) * | 2018-01-19 | 2018-07-06 | 中国人民解放军陆军装甲兵学院 | A kind of radar target identification method based on micro-Doppler feature extraction and deep learning |
| CN110071885A (en) * | 2019-04-17 | 2019-07-30 | 成都华日通讯技术有限公司 | A kind of deep learning method of discrimination of PSK digital signal subclass Modulation Identification |
| CN113971440A (en) * | 2021-10-21 | 2022-01-25 | 中国人民解放军空军航空大学 | Unsupervised radar signal sorting method based on deep clustering |
| CN114666273A (en) * | 2022-04-30 | 2022-06-24 | 东南大学 | Application layer unknown network protocol oriented traffic classification method |
| CN115037805A (en) * | 2022-06-08 | 2022-09-09 | 中国人民解放军陆军工程大学 | Unknown network protocol identification method, system, device and storage medium based on deep clustering |
| CN115130581A (en) * | 2022-04-02 | 2022-09-30 | 北京百度网讯科技有限公司 | Sample generation method, training method, data processing method and electronic device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11558810B2 (en) * | 2021-01-06 | 2023-01-17 | Bae Systems Information And Electronic Systems Integration Inc. | Artificial intelligence radio classifier and identifier |
-
2022
- 2022-10-18 CN CN202211276019.XA patent/CN115664906B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107682216A (en) * | 2017-09-01 | 2018-02-09 | 南京南瑞集团公司 | A kind of network traffics protocol recognition method based on deep learning |
| CN108256488A (en) * | 2018-01-19 | 2018-07-06 | 中国人民解放军陆军装甲兵学院 | A kind of radar target identification method based on micro-Doppler feature extraction and deep learning |
| CN110071885A (en) * | 2019-04-17 | 2019-07-30 | 成都华日通讯技术有限公司 | A kind of deep learning method of discrimination of PSK digital signal subclass Modulation Identification |
| CN113971440A (en) * | 2021-10-21 | 2022-01-25 | 中国人民解放军空军航空大学 | Unsupervised radar signal sorting method based on deep clustering |
| CN115130581A (en) * | 2022-04-02 | 2022-09-30 | 北京百度网讯科技有限公司 | Sample generation method, training method, data processing method and electronic device |
| CN114666273A (en) * | 2022-04-30 | 2022-06-24 | 东南大学 | Application layer unknown network protocol oriented traffic classification method |
| CN115037805A (en) * | 2022-06-08 | 2022-09-09 | 中国人民解放军陆军工程大学 | Unknown network protocol identification method, system, device and storage medium based on deep clustering |
Non-Patent Citations (1)
| Title |
|---|
| 基于半监督聚类集成的未知网络协议识别方法;林荣强;李鸥;李青;刘琰;;小型微型计算机系统(第06期) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115664906A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | WiFi fingerprinting indoor localization using local feature-based deep LSTM | |
| CN115664906B (en) | Method and device for unsupervised clustering of TDMA signal protocol | |
| CN105388500B (en) | The raising method of CPFSK signal carrier tracking accuracies | |
| CN114154545B (en) | Intelligent unmanned aerial vehicle measurement and control signal identification method under strong mutual interference condition | |
| CN113075462B (en) | Electromagnetic field distribution positioning method based on neural network | |
| CN108446599A (en) | A kind of high spectrum image wave band fast selecting method of p value statistic modeling independence | |
| CN113572708B (en) | DFT channel estimation improvement method | |
| CN108574525A (en) | A kind of spaceborne AIS collision alarms separation method based on adaptability moments estimation | |
| CN111050315A (en) | Wireless transmitter identification method based on multi-core two-way network | |
| Liao et al. | Deep learning methods in communication systems: A review | |
| CN103973621B (en) | A kind of parameter identification method of binary Continuous Phase frequency keying modulated signal | |
| CN113609982A (en) | High-discrimination radio frequency fingerprint learning and extracting method based on intelligent carrier synchronization | |
| Qiu et al. | DeepSIG: A Hybrid Heterogeneous Deep Learning Framework for Radio Signal Classification | |
| CN110060510A (en) | A kind of spaceborne AIS collision alarm separation method based on improvement artificial bee colony algorithm | |
| CN114218984A (en) | Radio frequency fingerprint identification method based on sample multi-view learning | |
| CN113241081A (en) | Far-field speaker authentication method and system based on gradient inversion layer | |
| CN112420079A (en) | Voice endpoint detection method and device, storage medium and electronic equipment | |
| CN107708145A (en) | A kind of method synchronously detected and synchronous detection equipment | |
| CN103795428B (en) | Decoder in radio frequency identification data communication | |
| CN115809426A (en) | Radiation source individual identification method and system | |
| CN112883355B (en) | Non-contact user identity authentication method based on RFID and convolutional neural network | |
| CN109067494A (en) | A kind of UAT data-link time synchronization method and device about CPFSK Modulation Types | |
| CN104751412A (en) | Affine invariant feature-based image splicing method | |
| CN103916341A (en) | Blind symbol rate estimation and timing method for MPSK signals formed through raised cosine | |
| CN203708233U (en) | Novel decoder in radio frequency identification data communication |
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 |