Dual station cooperative jamming cancellation method and system based on step selection strategy network

Abstract

The disclosure is that the embodiment provides a dual-station cooperative jamming cancellation method and system based on a step selection strategy network. The method comprises: acquiring the main station and the auxiliary station signals and initializing; performing multiple iterations, in each iteration, calculating the latest state information including the filtering vector, the gradient and the difference thereof; inputting the state information and the current iteration sequence number into the pre-trained step selection strategy network; the network dynamically decides the current optimal step through the cooperative work of the feature extraction, feature fusion, time sequence feature generation and step generation modules; and updating the filtering vector using the optimal step. Finally, the pure main station signal after cancellation is calculated and output based on the final filtering vector. The embodiment of the disclosure realizes intelligent adaptive optimization of the step, significantly reduces the residual interference power in the signal after cancellation, significantly improves the convergence speed and interference cancellation accuracy, and provides higher quality input signals for subsequent application modules.

Description

Technical Field

[0001] The embodiments disclosed herein belong to the field of dual-station cooperative interference cancellation technology, specifically relating to a dual-station cooperative interference cancellation method and system based on a step size selection strategy network. Background Technology

[0002] With the maturation of radar algorithms targeting sidelobe interference, mainlobe interference has become a major threat to radar systems, severely restricting radar performance. Bistatic interference cancellation is an effective technique for combating mainlobe interference, based on the fundamental difference in spatial propagation characteristics between target echoes and interference signals. The system utilizes this difference, adjusting the adaptive filter weights in real-time using an adaptive filtering algorithm to achieve mutual cancellation of interference signals. The convergence speed of the adaptive filtering algorithm is a crucial indicator of its adaptability to interference in non-stationary environments. If interference cancellation cannot be completely achieved within the finite radar operating time, the deviation of the filter weights from the optimal weight vector within the finite observation window will significantly increase, severely impacting interference cancellation performance. Therefore, achieving adaptive optimization of the step size parameter under a finite number of iterations is a key technical challenge for improving the tracking performance of interference cancellation algorithms in non-stationary environments.

[0003] A common method to improve the convergence speed of adaptive filtering algorithms is to use variable step size, such as variable step size adaptive filtering algorithms, including traditional methods based on the Sigmoid function and the inverse hyperbolic tangent function. However, the practical application of these traditional variable step size adaptive filtering algorithms heavily relies on the selection of preset parameters, and they have poor adaptability to changing environments and slow convergence speed. In dynamic interference environments, the filter weights cannot converge to the optimal value quickly and accurately within a finite time, severely affecting the main lobe interference cancellation effect. Summary of the Invention

[0004] The embodiments disclosed herein aim to at least solve one of the technical problems existing in the prior art, and provide a dual-station cooperative interference cancellation method and system based on step size selection strategy network.

[0005] One aspect of this disclosure provides a bi-station cooperative interference cancellation method based on a step-size selection strategy network, the method comprising: Acquire the master station signal and the corresponding slave station signal sequence, set the filter order and maximum number of iterations, and initialize the filter vector and step size; Iterative processing is performed based on the maximum number of iterations. Each iteration is based on the state information at the current time. The current optimal step size is output through the step size selection strategy network, and the filter vector is updated according to the current optimal step size to obtain the final filter vector. The state information includes the filter vector, gradient vector, filter vector difference, and gradient vector difference. The step size selection strategy network includes a feature extraction module, a feature fusion module, a temporal feature generation module, and a step size generation module. Based on the final filter vector, calculate and output the final master station signal after cancellation.

[0006] Furthermore, the feature extraction module is used for: Construct a state matrix based on the current state information; Calculate the covariance matrix of the state matrix; Construct a feature matrix based on the covariance matrix; The feature matrix is ​​mapped to a first feature vector and a second feature vector.

[0007] Furthermore, the construction of the state matrix based on the current state information includes: The current filter vector, gradient vector, filter vector difference, and gradient vector difference are combined into a column vector to obtain the state matrix.

[0008] Furthermore, the feature fusion module is used for: Calculate the correlation coefficient between the first feature vector and the second feature vector to obtain the fused feature; wherein, The included angle correlation coefficient is calculated using the following formula:

[0009] In the formula, The correlation coefficient is the angle between the two sides. The first eigenvector, This is the second feature vector. This represents the L2 norm.

[0010] Furthermore, the time-series feature generation module is used for: Generate a temporal feature vector based on the current iteration number; where... The temporal feature vector has at least three dimensions, and its elements include at least one of the following: the current iteration number, the square of the current iteration number, and the trigonometric function transformation value.

[0011] Furthermore, the step size generation module is used for: The fused features and the temporal feature vector are combined to obtain a comprehensive feature vector; A normalized scaling factor is obtained by performing a linear transformation and nonlinear activation on the comprehensive feature vector. The current optimal step size is calculated based on the preset step size range and the scaling factor.

[0012] Furthermore, the current optimal step size is calculated using the following formula:

[0013] In the formula, The current optimal step size, This is the lower limit of the step size. This is the upper limit of the step size. This is the scaling factor.

[0014] Another aspect of this disclosure provides a bi-station cooperative interference cancellation system based on a step-size selection strategy network, the system comprising: The signal acquisition module is used to acquire the master station signal and the corresponding slave station signal sequence, set the filter order and the maximum number of iterations, and initialize the filter vector and step size. The iterative processing module is used to perform iterative processing according to the maximum number of iterations. Each iteration is based on the state information at the current time, outputs the current optimal step size through the step size selection strategy network, and updates the filter vector according to the current optimal step size to obtain the final filter vector. The state information includes the filter vector, gradient vector, filter vector difference, and gradient vector difference. The step size selection strategy network includes a feature extraction module, a feature fusion module, a temporal feature generation module, and a step size generation module. The cancellation output module is used to calculate and output the final master station signal after cancellation based on the final filter vector.

[0015] Another aspect of this disclosure provides an electronic device, comprising: At least one processor; and, A memory communicatively connected to the at least one processor is used to store one or more programs, which, when executed by the at least one processor, enable the at least one processor to implement the dual-station cooperative interference cancellation method based on step size selection strategy network described above.

[0016] Another aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the bi-station cooperative interference cancellation method based on a step size selection strategy network described above.

[0017] This disclosure discloses a dual-station cooperative interference cancellation method and system based on a step-size selection strategy network. By dynamically optimizing the convergence process during the iteration process through the step-size selection strategy network, the final filter vector is closer to the theoretical optimal weight than the traditional fixed step-size or simple variable step-size methods. This results in a more accurate calculated interference estimate, a significant reduction in the residual interference power in the canceled signal, and an effective improvement in the signal-to-interference ratio. This provides a higher quality input signal for subsequent application modules and improves the overall performance of the entire radar or communication system under strong main lobe interference. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a dual-station cooperative interference cancellation method based on a step size selection strategy network according to an embodiment of this disclosure. Figure 2 This is a schematic diagram of the structure of a dual-station cooperative interference cancellation system based on a step size selection strategy network, according to another embodiment of this disclosure. Figure 3 This is a schematic diagram of the structure of an electronic device according to another embodiment of the present disclosure. Detailed Implementation

[0019] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. Based on the embodiments of this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this disclosure.

[0020] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0021] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0022] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Therefore, the first component discussed below may be referred to as the second component without departing from the teachings of this disclosure. As used in this disclosure, the term "and / or" includes all combinations of any and more of the associated listed items.

[0023] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of exemplary embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing this disclosure, and therefore cannot be used to limit the scope of protection of this disclosure.

[0024] like Figure 1 As shown, one embodiment of this disclosure provides a bi-station cooperative interference cancellation method based on a step-size selection strategy network, the method comprising: Step S1: Obtain the master station signal and the corresponding slave station signal sequence, set the filter order and the maximum number of iterations, and initialize the filter vector and step size.

[0025] Step S1.1, Signal Acquisition and Preprocessing: At the present moment n Synchronous sampling is performed on the main station and the secondary station. The main station signal is denoted as... d ( n ),in n This represents the discrete-time sampling point number. The secondary station signal sequence is denoted as... X ( n For the received raw signal, necessary preprocessing can be performed first, including but not limited to: digital down-conversion, bandpass filtering to extract the target frequency band, analog-to-digital conversion, and amplitude normalization, in order to eliminate DC bias and improve the numerical stability of subsequent processing.

[0026] Step S1.2, Parameter Setting and Sequence Generation: Define the key parameters of the adaptive filter. The filter order is denoted as... L , is a positive integer, typically determined based on the estimated bandwidth of the interfering signal and the desired time resolution. In a preferred embodiment of this disclosure, the filter order is set to . L= 2 l+ 1, of which l It is a positive integer. Correspondingly, the current time's secondary station signal sequence... X ( n ) is a n A finite-length vector centered at:

[0027] in, This represents the received signal sample value from the secondary station. Therefore,X ( n ) is a vector with dimension L×1.

[0028] Simultaneously, a maximum number of iterations T is set. This parameter is a preset positive integer used to control the computational load in a single interference cancellation process, ensuring that the algorithm completes processing within a finite time (e.g., one radar pulse repetition cycle) to meet real-time requirements.

[0029] Step S1.3, Variable Initialization: Initialize filter vector and initial step size Typically, the filter vector It can be initialized as an all-zero vector, or initialized based on prior knowledge (such as the weights of the previous successful cancellation).

[0030] initial step size This can be set empirically, for example, to the median of a preset step size range, or a small positive value to ensure stability at startup. Simultaneously, record the initial gradient vector.

[0031] Step S2: Perform iterative processing based on the maximum number of iterations. Each iteration is based on the current state information. The current optimal step size is output through the step size selection strategy network, and the filter vector is updated according to the current optimal step size to obtain the final filter vector.

[0032] Specifically, after initialization, the first iteration can be performed using either the classic LMS (Least Mean Square Algorithm) algorithm or the method disclosed herein, to obtain the filter vector after the first iteration. w 1 and gradient g 1. This is to calculate the difference information in subsequent steps. Then, an iterative processing loop is performed, starting from iteration number t=2 and continuing until the set maximum iteration number t=T is reached. Each iteration includes the following core sub-steps: Step S2.1, State Information Construction: At the beginning of each iteration, the state information required for the current iteration is constructed based on the results of the previous iteration, including: the current filter vector. w t-1 Current gradient vector g t-1 Filter vector difference s t = w t-1 - w t-2 Gradient vector difference y t = gt-1 - g t-2 .

[0033] The state information vectors mentioned above are combined to form the state matrix for the t-th iteration. .

[0034] Step S2.2: Output the current optimal step size through the step size selection strategy network: The state matrix The current iteration number t is input into a pre-trained step size selection policy network. This network can intelligently determine the optimal step size for the current iteration. η t Its internal processing flow involves the collaborative work of multiple functional modules: 1. Feature Extraction Module (TGM Module): Calculate the covariance matrix of the state matrix: ; Based on covariance matrix Construct the upper triangular characteristic matrix ; triangular feature matrix Stretched into a high-dimensional (e.g., 16-dimensional) vector And through two independent linear transformation layers (network parameters are respectively) and ), generating two different feature vectors , .

[0035] 2. Feature Fusion Module (CP Module): Receive feature vector and Calculate their angle correlation coefficient. As a fusion feature, it is used to capture the degree of deep linear correlation between two features, and is specifically calculated by the following formula:

[0036] In the formula, superscript T Represents the transpose of a vector. This represents the L2 norm.

[0037] 3. Time-series feature generation module (MT module): Generate a multi-dimensional temporal feature vector based on the current iteration number t. In one specific embodiment, the vector can be defined as:

[0038] This vector is used to provide the network with structured timing information related to the iterative process.

[0039] 4. Step size generation module (scaling module): Fusion features With time series characteristics Combine to form a comprehensive feature vector ; Use a linear layer (network parameters are...) ) on the comprehensive feature vector Perform the transformation: .

[0040] right By applying the Sigmoid activation function and mapping it to the (0, 1) interval, a normalized scaling factor can be obtained. :

[0041] Finally, the scaling factor Mapped to a preset physical step range This yields the optimal step size for the current iteration:

[0042] This completes the intelligent decision-making process of the step size selection strategy network.

[0043] Step S2.3: Update the filter vector: Optimal step size determined by network decision This is used to adjust the update magnitude, thereby achieving the fastest convergence and optimal performance in the current state. The optimal step size is then obtained. Then, first calculate the error signal. And calculate the updated gradient vector Here, * indicates an optional complex conjugate operation, depending on whether the signal is complex. Finally, update the filter vector. .

[0044] After repeating steps S2.1 to S2.3 T times, the current time can be obtained. n The corresponding, converged final filter vector This allows for the optimization learning of interference cancellation weights.

[0045] Step S3: Calculate and output the final master station signal after cancellation based on the final filter vector.

[0046] Specifically, the final filter vector obtained using step S2 above... The interference components in the signal received by the main station are finally cancelled.

[0047] The final filter vector With secondary station signal sequence A linear combination is performed to reproduce the estimated interference components in the master station signal that are related to the slave station signal. .in, This represents the portion of the signal extracted from the secondary station signal through adaptive filtering that best matches the interference signal from the primary station.

[0048] Subsequently, signals were received from the original master station. Subtract the estimated value of the disturbance from the middle. This will give you the final master station signal after cancellation. .

[0049] Final master station signal after cancellation The final output of this disclosed method is typically fed into the next-level processing module in a radar system, such as: a constant false alarm rate (CFAR) detector to determine the presence of target echoes; a parameter estimation module to extract target range, velocity, angle, and other information; a Kalman filter for continuous target tracking; and an imaging module for high-resolution imaging. In a communication system, it can be fed into a demodulator, equalizer, or decoder to recover the transmitted information bits; the improvement in the signal-to-interference-plus-noise ratio (SINR) directly translates to a reduction in the communication bit error rate.

[0050] This disclosure discloses a dual-station cooperative interference cancellation method based on a step-size selection strategy network. By dynamically optimizing the convergence process during the iteration process through the step-size selection strategy network, the final filter vector is closer to the theoretical optimal weight than the traditional fixed step-size or simple variable step-size methods. This results in a more accurate calculated interference estimate, a significant reduction in the residual interference power in the canceled signal, and an effective improvement in the signal-to-interference ratio. This provides a higher quality input signal for subsequent application modules and improves the overall performance of the entire radar or communication system under strong main lobe interference.

[0051] like Figure 2 As shown, another embodiment of this disclosure provides a dual-station cooperative interference cancellation system based on a step-size selection strategy network, the system comprising: The signal acquisition module 210 is used to acquire the master station signal and the corresponding slave station signal sequence, set the filter order and the maximum number of iterations, and initialize the filter vector and step size; The iterative processing module 220 is used to perform iterative processing according to the maximum number of iterations. Each iteration is based on the state information at the current time, outputs the current optimal step size through the step size selection strategy network, and updates the filter vector according to the current optimal step size to obtain the final filter vector. The state information includes the filter vector, gradient vector, filter vector difference, and gradient vector difference. The step size selection strategy network includes a feature extraction module, a feature fusion module, a temporal feature generation module, and a step size generation module. The cancellation output module 230 is used to calculate and output the final master station signal after cancellation based on the final filter vector.

[0052] Specifically, the dual-station cooperative interference cancellation system based on step size selection strategy network in this disclosure is used to implement the dual-station cooperative interference cancellation method based on step size selection strategy network described in the above embodiments. The specific implementation process has been described in detail in the above embodiments and will not be repeated here.

[0053] like Figure 3 As shown, another embodiment of this disclosure provides an electronic device, including: At least one processor 301; and a memory 302 communicatively connected to the at least one processor 301 for storing one or more programs that, when executed by the at least one processor 301, enable the at least one processor 301 to implement the dual-station cooperative interference cancellation method based on step size selection strategy network described above.

[0054] The memory 302 and processor 301 are connected via a bus, which can include any number of interconnecting buses and bridges. The bus connects various circuits of one or more processors 301 and memory 302 together. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by processor 301 is transmitted over a wireless medium via an antenna, which further receives data and transmits it to processor 301.

[0055] Processor 301 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory 302 can be used to store data used by processor 301 during operation.

[0056] Another embodiment of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the bi-station cooperative interference cancellation method based on a step size selection strategy network described above.

[0057] The computer-readable storage medium may be included in the systems or electronic devices disclosed herein, or it may exist independently.

[0058] Computer-readable storage media can be any tangible medium that contains or stores a program, and can be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device. More specific examples include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, optical fibers, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0059] Computer-readable storage media may also include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code, specific examples of which include, but are not limited to, electromagnetic signals, optical signals, or any suitable combination thereof.

[0060] It is understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of this disclosure, and this disclosure is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of this disclosure, and these modifications and improvements are also considered to be within the scope of protection of this disclosure.

Claims

1. A two-station cooperative jamming cancellation method based on step length selection policy network, characterized in that, The method includes: Acquire the master station signal and the corresponding slave station signal sequence, set the filter order and maximum number of iterations, and initialize the filter vector and step size; Iterative processing is performed based on the maximum number of iterations. Each iteration is based on the state information at the current time. The current optimal step size is output through the step size selection strategy network, and the filter vector is updated according to the current optimal step size to obtain the final filter vector. The state information includes the filter vector, gradient vector, filter vector difference, and gradient vector difference. The step size selection strategy network includes a feature extraction module, a feature fusion module, a temporal feature generation module, and a step size generation module. Based on the final filter vector, calculate and output the final master station signal after cancellation.

2. The dual-station cooperative interference cancellation method based on step size selection strategy network according to claim 1, characterized in that, The feature extraction module is used for: Construct a state matrix based on the current state information; Calculate the covariance matrix of the state matrix; Construct a feature matrix based on the covariance matrix; The feature matrix is ​​mapped to a first feature vector and a second feature vector.

3. The dual-station cooperative interference cancellation method based on step size selection strategy network according to claim 2, characterized in that, The construction of the state matrix based on the current state information includes: The current filter vector, gradient vector, filter vector difference, and gradient vector difference are combined into a column vector to obtain the state matrix.

4. The dual-station cooperative interference cancellation method based on step size selection strategy network according to claim 3, characterized in that, The feature fusion module is used for: Calculate the correlation coefficient between the first feature vector and the second feature vector to obtain the fused feature; wherein, The included angle correlation coefficient is calculated using the following formula: In the formula, The correlation coefficient is the angle between the two sides. The first eigenvector, This is the second feature vector. This represents the L2 norm.

5. The dual-station cooperative interference cancellation method based on step size selection strategy network according to claim 4, characterized in that, The time-series feature generation module is used for: Generate a temporal feature vector based on the current iteration number; where... The temporal feature vector has at least three dimensions, and its elements include at least one of the following: the current iteration number, the square of the current iteration number, and the trigonometric function transformation value.

6. The dual-station cooperative interference cancellation method based on step size selection strategy network according to claim 5, characterized in that, The step size generation module is used for: The fused features and the temporal feature vector are combined to obtain a comprehensive feature vector; A normalized scaling factor is obtained by performing a linear transformation and nonlinear activation on the comprehensive feature vector. The current optimal step size is calculated based on the preset step size range and the scaling factor.

7. The dual-station cooperative interference cancellation method based on step size selection strategy network according to claim 6, characterized in that, The current optimal step size is calculated using the following formula: In the formula, The current optimal step size, This is the lower limit of the step size. This is the upper limit of the step size. This is the scaling factor.

8. A dual-station cooperative interference cancellation system based on a step-size selection strategy network, characterized in that, The system includes: The signal acquisition module is used to acquire the master station signal and the corresponding slave station signal sequence, set the filter order and the maximum number of iterations, and initialize the filter vector and step size. The iterative processing module is used to perform iterative processing according to the maximum number of iterations. Each iteration is based on the state information at the current time, outputs the current optimal step size through the step size selection strategy network, and updates the filter vector according to the current optimal step size to obtain the final filter vector. The state information includes the filter vector, gradient vector, filter vector difference, and gradient vector difference. The step size selection strategy network includes a feature extraction module, a feature fusion module, a temporal feature generation module, and a step size generation module. The cancellation output module is used to calculate and output the final master station signal after cancellation based on the final filter vector.

9. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor is used to store one or more programs, which, when executed by the at least one processor, enable the at least one processor to implement the dual-station cooperative interference cancellation method based on step size selection strategy network as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the dual-station cooperative interference cancellation method based on step size selection strategy network as described in any one of claims 1 to 7.

Images