Simulation method and system for intelligent fusion and dynamic prediction of electronic warfare information

Abstract

The invention provides a simulation method and system for intelligent fusion and dynamic prediction of electronic warfare intelligence. According to the simulation method, electromagnetic signals are collected in real time through a multi-domain sensor, a dynamic adversarial network (DAN) is adopted for frequency spectrum matching and abnormal positioning, and interference data are eliminated in combination with space-time verification; constructing a semantic association map of radar, communication and geographic information, fusing time domain / space domain features through space-time attention, and dynamically allocating confidence to realize multi-source data fusion; predicting a threat evolution trend based on a space-time Transform, outputting a threat level, a threat type and a threat intention, and generating a dynamic situation map in combination with a mixed density network; an online incremental learning framework is adopted to adapt to a new signal mode, a prediction module is updated preferentially, and a multi-path distribution mechanism driven by edge-cloud collaborative optimization reinforcement learning is adopted to dynamically adjust the pushing priority, so that low-delay transmission of key threat intelligence is realized.

Description

Technical Field

[0001] The present invention relates to the field of military communication and simulation technology, in particular to a simulation method and system for intelligent fusion and dynamic prediction of electronic warfare intelligence. Background Art

[0002] Current electronic warfare intelligence processing faces core challenges such as low efficiency in multi-source heterogeneous data fusion, poor adaptability to dynamic environments, and insufficient real-time threat prediction. Traditional methods usually adopt static weight allocation strategies in multi-domain sensor data fusion, which makes it difficult to cope with the dynamic changes of signals in complex electromagnetic environments. For example, conventional K-means clustering algorithms are susceptible to noise interference when processing high-dimensional electromagnetic signal features, resulting in reduced sorting accuracy, and lack the ability to quickly adapt to new signal patterns. In addition, existing dynamic prediction models are mostly based on single-modal data, such as radar pulses or communication protocols, and do not fully explore the synergistic correlation of time-domain and spatial-domain features, resulting in limited comprehensiveness and accuracy of battlefield situation awareness.

[0003] In terms of technological evolution, artificial intelligence technology has been gradually applied to the field of electronic warfare in recent years. For example, the U.S. military has achieved rapid identification of unknown radar signals and generation of jamming strategies through cognitive electronic warfare systems such as F-16 / CADS, but its algorithm relies on a fixed rule base and is difficult to adapt to rapidly evolving modulation types and signal distributions.

[0004] Although multimodal knowledge graph technology has made progress in civilian fields such as semantic search tasks, it lacks the ability to model the dynamic association between radar signal features and geospatial information in military scenarios. In addition, existing incremental learning frameworks mostly use global parameter updates, which can easily lead to catastrophic forgetting problems when the model adapts to new signals. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a simulation method and system for intelligent fusion and dynamic prediction of electronic warfare intelligence, which are used to improve the real-time, adaptability and battlefield survivability of the electronic warfare intelligence system.

[0006] The present invention specifically provides the following technical solutions: A simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence, characterized by comprising: Through multi-domain distributed sensor nodes to collect electromagnetic signal data in real time, the dynamic adversarial network DAN is used to perform spectrum fingerprint matching and anomaly location on the electromagnetic signal data, and the time-space consistency verification mechanism is combined to eliminate invalid data and generate a standardized intelligence stream; Construct a multimodal knowledge graph, define radar signal features as entities, communication protocol metadata as relationships between entities, and geospatial information as entity attributes, perform semantic association modeling, and generate heterogeneous network representations; Based on the abnormal network representation, the spatiotemporal dual-channel attention mechanism is adopted to fuse the time domain characteristics of the radar pulse sequence and the spatial distribution characteristics of the communication signal group to generate a joint semantic vector; the fusion of multi-source heterogeneous data is realized through the confidence dynamic allocation algorithm; based on the joint semantic vector, the spatiotemporal Transformer model is used to dynamically predict the threat evolution trend and output the multi-task prediction results of threat level, target type and behavior intention; combined with the hybrid density network to generate a dynamic battlefield situation panorama; Deploy an online incremental learning framework to detect new signal patterns and fine-tune model parameters in layers, updating the prediction head module to adapt to the dynamic battlefield environment; A reinforcement learning-driven multi-path distribution mechanism is implemented through the edge-cloud collaborative architecture, and the intelligence push priority is dynamically optimized based on the channel state matrix and node security assessment to ensure low-latency transmission of key threat intelligence.

[0007] Optionally, a dynamic adversarial network (DAN) is used to perform spectrum fingerprint matching and anomaly location on the electromagnetic signal data, and a spatiotemporal consistency verification mechanism is combined to eliminate invalid data to generate a standardized intelligence stream, including: In the dynamic adversarial network DAN, an improved spectral clustering algorithm is used and a quantum annealing optimization mechanism is introduced to perform feature sorting and spectrum fingerprint matching on the electromagnetic signal data; the feature sorting is to separate the mixed electromagnetic signal into different groups according to carrier frequency, pulse width, and modulation type; the output result of the feature sorting is used as the input of the spectrum fingerprint matching, and the cluster center vector is dynamically updated to perform similarity comparison with the radiation source characteristics in the fingerprint library to identify abnormal signals and generate standardized intelligence streams; the loss of the spectrum fingerprint matching Designed to:

[0008] in, is the three-dimensional feature vector of the electromagnetic signal sample, is the ith signal sample, For the The cluster center vector at the iteration, N is the total number of valid signal samples participating in the cluster center update in the current iteration, is the quantum tunneling intensity coefficient; is the adaptive cutoff threshold, To maximize the difference between classes Minimizing intra-class variance The comprehensive measure of is the quantum confinement factor; Cluster Center The formula for dynamic update is:

[0009] in, is the learning rate, Gaussian kernel bandwidth The specific adjustments are:

[0010] in, is the distribution shift sensitivity coefficient, KL divergence is the measure of signal distribution change, For the At iteration The joint probability distribution of For the The cluster center vector at the iteration.

[0011] Optionally, a multimodal knowledge graph is constructed, radar signal features are defined as entities, communication protocol metadata as relationships between entities, and geospatial information as entity attributes, semantic association modeling is performed, and a heterogeneous network representation is generated, including: In the construction of the multimodal knowledge graph, a multidimensional feature tensor fusion mechanism is added to define the correlation function between the radar signal modulation type and the communication protocol metadata. for:

[0012] in, is the total number of modulation types, For the The modulation type encoding matrix of the class modulation signal converts the discrete modulation type Mapped to a three-dimensional vector, For the Standard carrier frequency mean value of the modulated signal, used to dynamically adjust the carrier frequency The weight of For tensor product operation, fusion carrier frequency , Pulse Width and time difference ; is a parameter matrix used to adjust the pulse width and time difference The concatenated vector [ ; ] to perform feature mapping; The geographic space information is encoded by using a spherical harmonic function :

[0013] in, is the geographic spatial weight coefficient, is the spherical harmonic basis function, The latitude and longitude coordinates of the signal sources respectively; , , Angular quantum number, magnetic quantum number and maximum harmonic order respectively; The tensor representation generated by the association function serves as the relationship vector between entities in the multimodal knowledge graph, and the spherical harmonic encoding result serves as the entity attribute, which together constitute the heterogeneous network representation containing topological connections and semantic constraints.

[0014] Optionally, a spatiotemporal dual-channel attention mechanism is used to fuse the time domain features of the radar pulse sequence with the spatial distribution features of the communication signal group to generate a joint semantic vector, including: In the spatiotemporal dual-channel attention mechanism, the temporal channel Introduce the carrier frequency-pulse width coupled convolution kernel:

[0015] in, is the carrier frequency difference sensitivity coefficient, is the time domain sliding window length, and are the tth moment and the history The carrier frequency value at the time, For History The pulse width value at the moment, is a function for extracting the periodic characteristics of pulse width; The spatial channel uses pulse width weighted geodesic distance :

[0016] in, is the pulse width difference penalty factor, are the feature vectors of nodes i and j respectively, is the eigenvector angle; The dynamic confidence allocation algorithm defines the modulation type entropy weight as follows:

[0017] in, For the The information entropy of the signal modulation type, C is the total number of signal categories, is the loop variable; The time domain features extracted by the carrier frequency-pulse width coupling convolution kernel and the spatial domain features of the pulse width weighted geodesic distance modeling are dynamically fused through the modulation type entropy weight to generate the joint semantic vector, which is input into the spatiotemporal Transformer model for threat prediction.

[0018] Optionally, in the spatiotemporal Transformer model, a carrier frequency change rate gating mechanism is embedded in the threat prediction module. :

[0019] in, is the carrier frequency change rate, is the pulse width stability index, is the linear transformation matrix; The conditional probability distribution of the mixture density network Modeled as:

[0020] in, is the weight of the kth Gaussian component under the input x, and is the carrier frequency mean and standard deviation of the kth Gaussian component. Beta distribution describes the statistical characteristics of pulse width. and are the shape parameters that control the left-biased and right-biased characteristics of the pulse width distribution, and the Cat distribution represents the probability of modulation type classification. is the modulation type probability vector; The carrier frequency change rate gating mechanism dynamically adjusts the attention weight distribution of each time step in the spatiotemporal Transformer model based on the generated joint semantic vector, wherein the attention weight of the historical pulse width feature is enhanced when the carrier frequency change rate exceeds a threshold; the conditional probability distribution modeling of the mixed density network integrates the geographic space coding features and the signal carrier frequency-pulse width joint distribution to generate a dynamic battlefield situation panorama including the threat thermal field and the signal propagation path.

[0021] Optionally, in the online incremental learning framework, detecting the new signal pattern includes: Adopt modulation type entropy change trigger mechanism Detecting the new signal pattern, the modulation type entropy change trigger mechanism Specifically:

[0022] in, (.) is the indicator function, when the modulation type distribution entropy value of the new signal batch and historical distribution entropy The difference exceeds the threshold When , the update mechanism of the incremental learning model is triggered; Fine-tune model parameters in layers, including: Layered fine-tuning applies quantum noise perturbation to the carrier frequency characteristic layer, specifically:

[0023] in, is the weight matrix of the frequency feature layer, is the average deviation of the signal carrier frequency, is the quantum noise perturbation intensity coefficient.

[0024] In the edge-cloud collaborative architecture, the multipath distribution mechanism is used to define the carrier frequency-bit error rate joint reward function

[0025] in, , , is the weighting coefficient, The carrier frequency f corresponds to the inverse of the channel bit error rate, is the total transmission time of the signal from the transmitter to the receiver, is the delay sensitivity factor, Security evaluation vector for the node.

[0026] Optionally, on the basis of the quantum annealing optimization, a pulse width-modulation type constrained Hamiltonian is added to suppress the interference of carrier frequency drift and pulse width jitter on signal sorting. Combining the carrier frequency cluster center constraint and the pulse width distribution prior knowledge, the Hamiltonian The expression is:

[0027] in, and are the qubit index and the total number of qubits, respectively. and The constraint coefficients of carrier frequency and pulse width respectively, and Respectively The carrier frequency value of quantum bits and the target carrier frequency value, is the reference pulse width distribution, For the The Pauli-Z operator for 1 qubit.

[0028] Optionally, in the dynamic adversarial network DAN, a carrier frequency-pulse width joint robustness loss is defined in the adversarial defense module: :

[0029] in, To find the expected statistical distribution of the input signal x, and are the disturbances for carrier frequency f and pulse width pw, respectively. and are the disturbance amplitudes that limit the carrier frequency and pulse width, respectively. To measure the distribution difference between the electromagnetic signal data x and the adversarial sample x+δ in the feature space f(.), is the modulation type classification loss weight, is the cross entropy loss, which quantifies the difference between the modulation type prediction distribution m(.) of the electromagnetic signal data x and the adversarial sample xadv, is a feature extraction function that maps the input signal x to a high-dimensional feature space. is a modulation type classifier that outputs the modulation type probability distribution of the signal x.

[0030] The present invention also provides a simulation system for intelligent fusion and dynamic prediction of electronic warfare intelligence, the simulation system comprising: The multi-domain data acquisition and preprocessing module is used to collect electromagnetic signal data in real time through multi-domain distributed sensor nodes, use the dynamic adversarial network DAN to perform spectrum fingerprint matching and anomaly location on the electromagnetic signal data, and combine the spatiotemporal consistency verification mechanism to eliminate invalid data and generate a standardized intelligence flow; Multimodal knowledge graph construction module, which is used to construct a multimodal knowledge graph, define radar signal features as entities, communication protocol metadata as relationships between entities, and geospatial information as entity attributes, perform semantic association modeling, and generate heterogeneous network representations; The spatiotemporal feature fusion engine is used to fuse the time domain features of the radar pulse sequence with the spatial distribution features of the communication signal group using the spatiotemporal dual-channel attention mechanism to generate a joint semantic vector; and to achieve the fusion of multi-source heterogeneous data through the confidence dynamic allocation algorithm; The threat prediction and situation generation module is used to dynamically predict the threat evolution trend based on the joint semantic vector using the spatiotemporal Transformer model, output the multi-task prediction results of threat level, target type and behavior intention; and generate a dynamic battlefield situation panorama in combination with a mixed density network; The online incremental learning agent module is used to deploy the online incremental learning framework, detect new signal patterns and fine-tune model parameters in layers, and update the prediction head module to adapt to the dynamic battlefield environment; The edge-cloud collaborative distribution control module is used to implement a reinforcement learning-driven multi-path distribution mechanism through an edge-cloud collaborative architecture, dynamically optimize the intelligence push priority based on the channel state matrix and node security assessment, and ensure low-latency transmission of key threat intelligence.

[0031] The present invention has the following beneficial technical effects: The present invention provides a simulation method and system for intelligent fusion and dynamic prediction of electronic warfare intelligence. The spectral clustering algorithm is improved by introducing a quantum annealing optimization mechanism through the dynamic adversarial network DAN, and high-robust signal sorting is achieved in the carrier frequency, pulse width and modulation type feature dimensions. The quantum constraint factor and the adaptive cutoff threshold are combined to suppress feature drift and enhance the anti-interference ability of spectrum fingerprint matching; a heterogeneous network representation that integrates radar signals, communication protocols and geospatial information is constructed, and a multi-dimensional feature tensor fusion mechanism and spherical harmonic function coding technology are used to achieve cross-domain entity dynamic association modeling, support accurate signal source positioning and threat intention reasoning; based on the time-space dual-channel attention mechanism, the carrier frequency-pulse width coupling convolution kernel is used to extract the time domain frequency hopping law, and the pulse width weighted geodesic distance is combined to analyze the spatial distribution characteristics, and the placement is used. The dynamic allocation algorithm of credibility realizes the differentiated weight fusion of multi-source heterogeneous data and improves the accuracy of threat identification; the modulation type entropy change threshold is used to trigger the model update mechanism, the prediction head module is fine-tuned first and quantum noise perturbation is applied, the new signal mode is quickly adapted, and the risk of historical knowledge forgetting is reduced; based on the multi-path distribution mechanism driven by reinforcement learning, the transmission path is dynamically optimized in combination with the channel state matrix and the node security assessment, and the channel utilization and anti-interference ability are improved through the carrier frequency-bit error rate joint reward function; the pulse width-modulation type constraint Hamiltonian and the carrier frequency-pulse width joint robustness loss function are introduced to construct the feature space energy minimization mechanism at the quantum bit level, suppress the interference of adversarial samples and improve the abnormal response efficiency. The present invention comprehensively solves the problems of low efficiency, poor dynamic adaptability and delayed threat prediction of electronic warfare systems in complex electromagnetic environments, and significantly improves battlefield survivability and intelligent decision-making support efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A flowchart of a simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence provided by an embodiment of the present invention.

[0034] Figure 2 A framework diagram of a dynamic adversarial network (DAN) model provided in an embodiment of the present invention.

[0035] Figure 3 A block diagram of a simulation system for intelligent fusion and dynamic prediction of electronic warfare intelligence provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0037] The following specific examples of the markings are used to illustrate the embodiments of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0038] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any labeled structures and / or functions described herein are merely illustrative. Based on the present application, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number and aspect set forth herein may be used to implement an apparatus and / or practice a method.

[0039] It should also be noted that the illustrations provided in the following embodiments are only used to schematically illustrate the basic concept of the present application.

[0040] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the examples can be practiced without these marked details.

[0041] The purpose of the present invention is to provide a simulation method and system for intelligent fusion and dynamic prediction of electronic warfare intelligence, aiming to improve battlefield survivability and intelligent decision-making support.

[0042] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] Reference Figure 1 , showing a simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence according to an embodiment of the present application, the simulation method comprising: Electromagnetic signal data is collected in real time through multi-domain distributed sensor nodes, and the dynamic adversarial network DAN is used to perform spectrum fingerprint matching and anomaly positioning on the electromagnetic signal data. The spatiotemporal consistency verification mechanism is combined to eliminate invalid data and generate a standardized intelligence stream.

[0044] Specifically, sensor nodes distributed in multiple domains of land, sea and air are deployed, such as airborne radars and shipborne communication detectors, to collect raw electromagnetic signal data in real time. In the dynamic adversarial network DAN, an improved spectral clustering algorithm is used and a quantum annealing optimization mechanism is introduced to perform feature sorting on the electromagnetic signal data. The feature dimensions include carrier frequency, pulse width, and modulation type. The mixed electromagnetic signals are separated into different groups according to carrier frequency, pulse width, and modulation type. The output results of feature sorting are used as the input of the spectrum fingerprint matching. By dynamically updating the cluster center vector and comparing the similarity with the radiation source features in the fingerprint library, abnormal signals are identified and standardized intelligence streams are generated; the loss of the spectrum fingerprint matching is designed as:

[0045] in, is the three-dimensional feature vector of the electromagnetic signal sample, For the The cluster center vector at the iteration, N is the total number of valid signal samples participating in the cluster center update in the current iteration, is the quantum tunneling intensity coefficient, which is 0.8; is the adaptive cutoff threshold, To maximize the difference between classes Minimizing intra-class variance The comprehensive measure of is the quantum confinement factor, Controlling the influence of quantum tunneling effect on feature sorting, smaller It can suppress excessive jumps of quantum bits and balance global exploration and local convergence in complex electromagnetic environments.

[0046] Among them, two core functions are realized simultaneously through the improved spectral clustering algorithm and quantum annealing optimization mechanism. The first is feature sorting, which is to separate the mixed electromagnetic signals into different groups according to carrier frequency, pulse width and modulation type; the second is spectrum fingerprint matching: through the loss function design, the sorting results are dynamically matched with the preset fingerprint library, and the matching accuracy is optimized.

[0047] Cluster center movement The formula for state update is:

[0048] in, is the learning rate, the value is 0.002; Gaussian kernel bandwidth The specific adjustments are:

[0049] in, is the distribution shift sensitivity coefficient, KL divergence is the measure of signal distribution change, For the At iteration The joint probability distribution of For the The cluster center vector at the iteration.

[0050] In the test experiment, the quantum confinement factor was introduced in the carrier frequency dimension = 0.1, by adaptive cutoff threshold =0.05 dynamically eliminates noise interference, which improves the signal sorting accuracy by 12% compared with traditional methods. In the spatiotemporal consistency verification mechanism, by checking the physical constraint relationship between the pulse arrival time difference and the geographic coordinates, the signal propagation speed error is set to ≤5% to eliminate invalid data.

[0051] The output result of the feature sorting is used as the input of the spectrum fingerprint matching. By dynamically updating the cluster center vector and comparing the similarity with the radiation source features in the fingerprint library, abnormal signals are identified and a standardized intelligence stream is generated. Specifically, the sorted signal group is matched with the preset radiation source fingerprint library for similarity, and the matching confidence is calculated based on the dynamically updated cluster center vector. When the confidence is lower than the preset threshold, it is determined to be an abnormal signal and an alarm is triggered.

[0052] Based on the quantum annealing optimization mechanism, the Hamiltonian is introduced to constrain the signal sorting by the pulse width modulation type constraint Hamiltonian, so as to suppress the interference of carrier frequency drift and pulse width jitter on signal sorting. Combining the carrier frequency cluster center constraint and the pulse width distribution prior knowledge, its expression is:

[0053] in, and are the qubit index and the total number of qubits, respectively. and The preferred values ​​of the constraint coefficients of carrier frequency and pulse width are 0.1 and 0.08 respectively; and Respectively The carrier frequency value of quantum bits and the target carrier frequency value, is the reference pulse width distribution, For the The Pauli-Z operator for 1 qubit.

[0054] In the actual experiment, the reference distribution Set it as Gaussian distribution, specifically μ=1.2μs, σ=0.3μs, and KL divergence penalty to make the pulse width estimation mean square error MSE from 0.15μs 2 Down to 0.07μs 2 The signal clustering purity of the same modulation type is increased from 82% to 95%, the false correlation rate is less than 3%, the number of quantum annealing iterations is reduced to 1 / 3 of the traditional method, and the single-task energy consumption is reduced by 58%.

[0055] Figure 2 The framework of the dynamic adversarial network (DAN) is shown. The model structure is designed around the spectrum fingerprint matching and anomaly location requirements of electromagnetic signal processing. It combines multimodal feature fusion and adversarial training mechanisms to build an end-to-end dynamic adaptive network. The model takes the original electromagnetic signal as input. First, the time domain signal is converted into a time-frequency domain spectrum through the short-time Fourier transform (STFT) preprocessing module to achieve the time-frequency joint representation of signal features. The parameter settings of window length 256 and overlap rate 75% can balance time accuracy and frequency resolution. In the shared encoder, the preprocessed spectrum is input to the shared encoder that combines multi-scale convolution and multi-head attention: the multi-scale convolution block uses different kernel sizes such as 3×3, 5×5, and 7×7 to extract local frequency band features in parallel, including the instantaneous frequency point features of radar pulses; the Transformer encoding layer captures the global correlation across frequency bands through the multi-head self-attention mechanism, including focusing on the carrier mutation area of ​​the frequency hopping communication signal to suppress noise interference. In the multi-task collaborative branch, the encoded features are diverted to two parallel task branches: the first branch is the spectrum fingerprint matching branch, which compares the known signal templates based on the dynamically updated memory library, including the radar radiation source fingerprint library, and calculates the cosine similarity between the input signal and the template through the dynamic prototype alignment loss. The threshold ≥0.9 is considered a match; the signal type / ID and matching probability are output to support high-precision recognition in small sample scenarios; the second branch is the anomaly positioning branch, which uses the U-Net decoder to upsample the encoded features and restore the spatial resolution in the time-frequency domain; generates a pixel-level anomaly heat map, including pulse loss or frequency deviation abnormal areas, and combines the binary mask to output the abnormal frequency band and timestamp coordinates, with a positioning error of ≤0.5ms / 2MHz. In the adversarial training optimization, the gradient reversal layer GRL reverses the gradient sign of the feature extractor, forcing the encoder to generate robust features that are independent of the interference environment; the multi-domain discriminator designs independent classification heads for different electromagnetic interference scenarios, including strong noise and multipath effects, and dynamically adjusts the adversarial loss weights. The initial weight λ=0.3 increases to 1.2 with training to achieve cross-domain adaptation. The final output layer integrates the results of the two branches, including fingerprint matching results: identifying signal types in the form of classification probability, including radar model LFM / FSK; anomaly positioning mask: binary thermal images mark abnormal areas, support real-time threat warning in electronic warfare, and the measured end-to-end delay is ≤50ms.

[0056] In the dynamic adversarial network DAN, the robustness of carrier frequency and pulse width characteristics is jointly optimized to improve the defense capability against adversarial samples.

[0057] Define carrier frequency-pulse width joint robustness loss in the adversarial defense module :

[0058] in, To find the expectation of the statistical distribution of the input signal x, ensure that the robustness loss covers all possible signal scenarios; and are the disturbances for carrier frequency f and pulse width pw, respectively. and is the maximum allowable boundary for counteracting disturbances, which are the disturbance amplitudes that limit the carrier frequency and pulse width, respectively. =0.1GHz, =5μs; To measure the distribution difference between the electromagnetic signal data x and the adversarial sample x+δ in the feature space f(.), is the modulation type classification loss weight, which is 0.3 after tuning; is the cross entropy loss, which quantifies the electromagnetic signal data x and the adversarial sample x adv The difference in the modulation type prediction distribution m(.), is a feature extraction function that maps the input signal x to a high-dimensional feature space. is a modulation type classifier that outputs the modulation type probability distribution of the signal x.

[0059] A multimodal knowledge graph is constructed, radar signal features are defined as entities, communication protocol metadata as relationships between entities, and geospatial information as entity attributes. Semantic association modeling is performed and a heterogeneous network representation is generated.

[0060] Specifically, in the construction of the multimodal knowledge graph, a multidimensional feature tensor fusion mechanism is added to define the correlation function between the radar signal modulation type and the protocol metadata. for:

[0061] in, is the total number of modulation types, is the modulation type encoding matrix, which converts the discrete modulation type Mapped to a three-dimensional vector, For the Standard carrier frequency mean value of the modulated signal, used to dynamically adjust the carrier frequency The weight of For tensor product operation, fusion carrier frequency , Pulse Width and time difference ; is a parameter matrix used to adjust the pulse width and time difference The concatenated vector [ ; ] to perform feature mapping; The geographic space information is encoded by using a spherical harmonic function :

[0062] in, is the geographic spatial weight coefficient, is the spherical harmonic basis function, The latitude and longitude coordinates of the signal sources respectively; , , angular quantum number, magnetic quantum number and maximum harmonic order respectively.

[0063] The tensor representation generated by the association function is used as the relationship vector between entities in the knowledge graph, and the spherical harmonic coding result is used as the entity attribute, together forming a heterogeneous network representation containing topological connections and semantic constraints. Specifically, the association function is used to define the dynamic coordination rules between radar signals and communication protocols and generate interpretable semantic relationships; while the spherical harmonic coding is used to achieve high-precision modeling of geographic spatial attributes and embedding of signal propagation characteristics.

[0064] For example, radar signal entity: {ID: RS001, type: linear frequency modulation, carrier frequency: 9.5GHz, pulse width: 1.2μs}; communication protocol entity: {ID: CP002, type: Link-16, encryption level: AES-256, rate: 1Mbps}; geographic entity: {ID: G003, longitude: 116.4°, latitude: 39.9°, signal strength: -80dBm}. The cross-domain entity relationship is mined through the knowledge reasoning engine. For example, when a radar signal group in a certain area, whose carrier frequency is 9.5GHz±0.2GHz, and abnormal communication protocol metadata, such as an unknown encryption algorithm, appear at the same time, a potential electronic warfare attack alarm is triggered. In the experiment, The three-dimensional vector mapping can characterize the signal time-frequency-modulation characteristics. The BPSK mapping is [0.2, 0.7, -0.1], and the QPSK mapping is [0.5, -0.3, 0.8]. Regarding the parameter matrix W, Xavier initialization is used, and the dimension is 2×d, where d is the concatenated vector dimension. In the test, the feature mapping effect is optimal when d=128; when L=6, the average positioning error is 0.48°. When the order is greater than 6, the positioning error decreases slowly, and the amount of calculation increases exponentially. When L=6, the error is 0.82°, which is 41% higher than when L=3.

[0065] A spatiotemporal dual-channel attention mechanism is adopted to fuse the time domain characteristics of the radar pulse sequence and the spatial distribution characteristics of the communication signal group to generate a joint semantic vector; the fusion of multi-source heterogeneous data is achieved through a confidence dynamic allocation algorithm.

[0066] In the spatiotemporal dual-channel attention mechanism, the temporal channel Introduce the carrier frequency-pulse width coupled convolution kernel:

[0067] in, is the carrier frequency difference sensitivity coefficient, and its value is 0.15; is the time domain sliding window length, and are the tth moment and the history The carrier frequency value at the time, For History The pulse width value at the moment, is a function for extracting the periodic characteristics of pulse width; The spatial channel uses pulse width weighted geodesic distance :

[0068] in, is the pulse width difference penalty factor, the value is 0.6; are the feature vectors of nodes i and j respectively, is the eigenvector angle; The dynamic confidence allocation algorithm defines the modulation type entropy weight as follows:

[0069] in, For the The information entropy of the signal modulation type, C is the total number of signal categories, Is the loop variable.

[0070] The time domain features extracted by the carrier frequency-pulse width coupling convolution kernel and the spatial domain features of the pulse width weighted geodesic distance modeling are dynamically fused through the modulation type entropy weight to generate a joint semantic vector, which is input into the spatiotemporal Transformer model for threat prediction.

[0071] For example, in the spatiotemporal dual-channel attention mechanism, the carrier frequency-pulse width coupling convolution kernel w=5 is used in the time domain channel to capture the carrier frequency hopping sequence, and the frequency hopping interval of the frequency-agile radar is ≤1ms; the spatial channel quantifies the signal group distribution density through the pulse width weighted geodesic distance α=0.3, ≥50 pulses per square kilometer. The confidence dynamic allocation algorithm assigns differentiated weights to heterogeneous data according to the entropy weight of the modulation type, such as ω=0.8 for conventional communication signals and ω=1.2 for frequency hopping signals. Simulation tests show that this mechanism increases the distinction between communication interference signals and real threats by 2.7 times.

[0072] Based on the joint semantic vector, the spatiotemporal Transformer model is used to dynamically predict the threat evolution trend, and the multi-task prediction results of threat level, target type and behavioral intention are output; combined with the mixed density network, a dynamic battlefield situation panorama is generated.

[0073] Specifically, in the spatiotemporal Transformer model, a carrier frequency change rate gating mechanism is embedded in the threat prediction module. :

[0074] in, is the carrier frequency change rate, It is the pulse width stability index; The conditional probability distribution of the mixture density network Modeled as:

[0075] in, is the weight of the kth Gaussian component under the input x, and is the carrier frequency mean and standard deviation of the kth Gaussian component. Beta distribution describes the statistical characteristics of pulse width. and are the shape parameters that control the left-biased and right-biased characteristics of the pulse width distribution, and the Cat distribution represents the probability of modulation type classification. is the modulation type probability vector.

[0076] The carrier frequency change rate gating mechanism dynamically adjusts the attention weight distribution of each time step in the spatiotemporal Transformer model based on the generated joint semantic vector, wherein the attention weight of the historical pulse width feature is enhanced when the carrier frequency change rate exceeds a threshold; the conditional probability distribution modeling of the mixed density network integrates the geographic space coding features with the signal carrier frequency-pulse width joint distribution to generate a dynamic battlefield situation panorama including the threat thermal field and the signal propagation path. For example, In order to control the contribution weight of the carrier frequency change rate to threat prediction, the Sigmoid function output range is [0,1]. =0.8 indicates a high level of concern about carrier frequency mutations; is a linear transformation matrix that maps the input features to the gated space, with a dimension of 128×64, 64 input features, 128 hidden layers, and Xavier initialization; is the carrier frequency change per unit time, the frequency-agile radar signal =0.5 MHz / ms; is the statistical stability of the pulse width sequence, calculated as the inverse of the standard deviation of the pulse width within a sliding window, length r, stable radar pulse σ = 0.1μs → Stability = 8.0; is the mixed weight of the kth Gaussian component, generated by Softmax. When K=3, π=[0.6, 0.3, 0.1], indicating that the main threat comes from category 1; is the carrier frequency center value of the kth Gaussian component, S-band radar μ1=3.0GHz, X-band μ2=9.5GHz; is the discrete degree of carrier frequency distribution, σ=50MHz for conventional radar and σ=200MHz for frequency hopping radar; To control the left / right deviation of pulse width distribution, when κ>λ, it is left-biased. Specifically, short pulse width is concentrated, regular pulse κ=2.0, λ=5.0 (right deviation); burst pulse κ=5.0, λ=2.0 (left deviation); is the probability distribution of modulation type, such as the confidence of [BPSK, QPSK, LFM], p=[0.7, 0.2, 0.1] means the probability of BPSK is 70%. The mixture density network MDN models the conditional probability distribution through the Gaussian mixture model GMM.

[0077] Deploy an online incremental learning framework to detect new signal patterns and fine-tune model parameters in layers, giving priority to updating the prediction head module to adapt to the dynamic battlefield environment.

[0078] Among them, the prediction head module is a built-in component of the online incremental learning framework, and its update logic, parameter adjustment, and function execution all rely on the framework's detection and scheduling mechanism. This design ensures the model's ability to quickly adapt to dynamic battlefield environments, while balancing stability and flexibility through a hierarchical update strategy.

[0079] Specifically, in the online incremental learning framework, the detection of the new signal adopts a modulation type entropy change trigger mechanism Specifically:

[0080] When the modulation type distribution entropy value of the new signal batch and historical distribution entropy The difference exceeds the threshold When , the update mechanism of the incremental learning model is triggered; Layered fine-tuning applies quantum noise perturbation to the carrier frequency characteristic layer, specifically:

[0081] in, is the weight matrix of the frequency feature layer, is the average deviation of the signal carrier frequency, is the quantum noise perturbation intensity coefficient.

[0082] For example, the modulation type entropy value The value range is 0~log2(C), where C is the total number of modulation types. For example, when C=5, the maximum entropy is ≈2.32; the modulation type entropy change trigger threshold =0.2, it can effectively capture significant changes in the modulation type distribution, such as the low probability of intercept signal of the newly emerging LPI radar, while avoiding false triggering caused by noise. =1.0, corresponding to BPSK / QPSK mixed mode; new batch entropy value , added LFM signal, difference Δ=0.4> =0.2→trigger update. Quantum noise perturbation intensity coefficient =0.5, the noise disturbance amplitude is about 5% of the weight. In the X-band radar signal, the carrier frequency is 9.5GHz, and the frequency deviation interference of ±0.5MHz can be tolerated. The initial weight of the carrier frequency feature layer is =[0.8, -0.3, 1.2]; after adding noise, it is updated to =[0.8+0.05·N(0,1), -0.3+0.05·N(0,1), 1.2+0.05·N(0,1)]; learning rate =0.005, the model can adapt to new signals, such as FHSS frequency hopping signals, within 10 iterations, and the convergence speed is increased by 40%, and the average carrier frequency offset is =2.5MHz→ =0.92; Weight update amount: ΔW=0.005×N(0,0.05²)×0.92≈±0.0023; =3.0MHz, Sigmoid(3.0)=0.95, the noise disturbance weight is increased to 95%; the enemy radar carrier frequency jumps from 9.5GHz to 9.503GHz→ =3.0MHz → trigger high sensitivity update.

[0083] A reinforcement learning-driven multi-path distribution mechanism is implemented through the edge-cloud collaborative architecture, and the intelligence push priority is dynamically optimized based on the channel state matrix and node security assessment to ensure low-latency transmission of key threat intelligence.

[0084] Specifically, in the edge-cloud collaborative architecture, the multipath distribution mechanism is used to define the carrier frequency-bit error rate joint reward function

[0085] in, , , is the weighting coefficient, The carrier frequency f corresponds to the inverse of the channel bit error rate, is the total transmission time of the signal from the transmitter to the receiver, is the delay sensitivity factor, Security evaluation vector for the node.

[0086] For example, in a conventional tactical communication scenario: =0.3 represents the bit error rate weight, and the tolerance BER≤e -4 , avoid frequent channel switching affecting timeliness; =0.5 represents the delay weight, emphasizing low-latency transmission and requiring end-to-end delay ≤50ms; =0.2 represents the security weight, and the tolerance for node security assessment differences is high. ≤0.3; =50ms, when the delay exceeds 50ms, the reward value decays rapidly; =e 4 , =40ms, =[0.8, 0.9]. In the critical threat intelligence transmission scenario, =0.2 represents the bit error rate weight, requiring the channel bit error rate to be extremely low BER≤e -6 , select high-quality links; =0.3 represents the delay weight, which allows a slightly higher delay and requires the end-to-end delay to be ≤80ms, but requires stable transmission; =0.5 represents the safety weight, strictly limiting the safety difference, ≤0.1; =100ms, the delay penalty decays slowly, avoiding excessive sacrifice of stability; =e 6 , =70ms, =[1.0, 1.0]. In the emergency scenario of strong interference environment, =0.4 represents the bit error rate weight, giving priority to anti-interference links (such as spread spectrum communication, BER≤e -3 ; =0.4 represents the delay weight, requiring the delay to be ≤100ms to support fast response; =0.2 represents the safety weight, temporarily relaxing safety requirements, such as enabling emergency communication protocols; =30ms, =e 3 , =90ms, =[0.6, 0.7], indicating a temporarily enabled emergency node with a degraded safety level but available.

[0087] In one embodiment of the present application, Figure 3 As shown, a simulation system for intelligent fusion and dynamic prediction of electronic warfare intelligence is also provided, and the simulation system includes: The multi-domain data acquisition and preprocessing module is used to collect electromagnetic signal data in real time through multi-domain distributed sensor nodes, use the dynamic adversarial network DAN to perform spectrum fingerprint matching and anomaly location on the electromagnetic signal data, and combine the spatiotemporal consistency verification mechanism to eliminate invalid data and generate a standardized intelligence flow; The multimodal knowledge graph construction module is used to construct a multimodal knowledge graph, perform semantic association modeling on radar signal features, communication protocol metadata, and geospatial information, and generate a heterogeneous network representation containing entities, relationships, and attributes; The spatiotemporal feature fusion engine is used to fuse the time domain features of the radar pulse sequence with the spatial distribution features of the communication signal group using the spatiotemporal dual-channel attention mechanism to generate a joint semantic vector; and to achieve the fusion of multi-source heterogeneous data through the confidence dynamic allocation algorithm; The threat prediction and situation generation module is used to dynamically predict the threat evolution trend based on the joint semantic vector using the spatiotemporal Transformer model, output the multi-task prediction results of threat level, target type and behavior intention; and generate a dynamic battlefield situation panorama in combination with a mixed density network; The online incremental learning agent module is used to deploy the online incremental learning framework, detect new signal patterns and fine-tune model parameters in layers, and prioritize updating the prediction head module to adapt to the dynamic battlefield environment; The edge-cloud collaborative distribution control module is used to implement a reinforcement learning-driven multi-path distribution mechanism through an edge-cloud collaborative architecture, dynamically optimize the intelligence push priority based on the channel state matrix and node security assessment, and ensure low-latency transmission of key threat intelligence.

[0088] Based on the same inventive concept, according to another aspect of the present invention, an embodiment of the present invention further provides a computer device, including: at least one processor; and The memory stores a computer program that can be run on the processor, and the processor executes the steps of any one of the above simulation methods when executing the program.

[0089] Based on the same inventive concept, according to another aspect of the present invention, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer program instructions. When the computer program instructions are executed by a processor, the steps of any one of the above simulation methods are performed. Finally, it should be noted that a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only storage memory (ROM) or a random access memory (RAM), etc. The above-mentioned computer program embodiments can achieve the same or similar effects as the corresponding above-mentioned arbitrary method embodiments.

[0090] In addition, typically, the devices and equipment disclosed in the embodiments of the present invention may be various electronic terminal devices, such as mobile phones, personal digital assistants (PDAs), tablet computers (PADs), smart TVs, etc., or large terminal devices, such as servers, etc. Therefore, the protection scope disclosed in the embodiments of the present invention should not be limited to a certain type of device or equipment. The client disclosed in the embodiments of the present invention may be applied to any of the above electronic terminal devices in the form of electronic hardware, computer software, or a combination of the two. In addition, the method disclosed in the embodiment of the present invention can also be implemented as a computer program executed by a CPU, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the CPU, the above functions defined in the method disclosed in the embodiment of the present invention are performed. In addition, the above method steps and system units may also be implemented using a controller and a computer-readable storage medium for storing a computer program that enables the controller to implement the above steps or unit functions. The above are exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications may be made without departing from the scope disclosed in the embodiments of the present invention as defined in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any marked order. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in individual form, they may also be understood as multiple unless explicitly limited to the singular. In this specification, the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments described later, the description is relatively simple, and the relevant parts can be referred to the partial description of the previous embodiments.

[0091] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence, characterized in that: The simulation method comprises: Through multi-domain distributed sensor nodes to collect electromagnetic signal data in real time, the dynamic adversarial network DAN is used to perform spectrum fingerprint matching and anomaly location on the electromagnetic signal data, and the time-space consistency verification mechanism is combined to eliminate invalid data and generate a standardized intelligence stream; Construct a multimodal knowledge graph, define radar signal features as entities, communication protocol metadata as relationships between entities, and geospatial information as entity attributes, perform semantic association modeling, and generate heterogeneous network representations; Based on the heterogeneous network representation, a spatiotemporal dual-channel attention mechanism is adopted to fuse the time domain features of the radar pulse sequence and the spatial distribution features of the communication signal group to generate a joint semantic vector; the fusion of multi-source heterogeneous data is achieved through a confidence dynamic allocation algorithm; Based on the joint semantic vector, the spatiotemporal Transformer model is used to dynamically predict the threat evolution trend and output the multi-task prediction results of threat level, target type and behavior intention; combined with the hybrid density network, a dynamic battlefield situation panorama is generated; Deploy an online incremental learning framework to detect new signal patterns and fine-tune model parameters in layers, updating the prediction head module to adapt to the dynamic battlefield environment; A reinforcement learning-driven multi-path distribution mechanism is implemented through the edge-cloud collaborative architecture, and the intelligence push priority is dynamically optimized based on the channel state matrix and node security assessment to ensure low-latency transmission of key threat intelligence.

2. The simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence according to claim 1 is characterized in that: The dynamic adversarial network DAN is used to perform spectrum fingerprint matching and anomaly location on the electromagnetic signal data, and the invalid data is eliminated by combining the spatiotemporal consistency verification mechanism to generate a standardized intelligence flow, including: In the dynamic adversarial network DAN, an improved spectral clustering algorithm is used and a quantum annealing optimization mechanism is introduced to perform feature sorting and spectrum fingerprint matching on the electromagnetic signal data; the feature sorting is to separate the mixed electromagnetic signal into different groups according to carrier frequency, pulse width, and modulation type; the output result of the feature sorting is used as the input of the spectrum fingerprint matching, and the cluster center vector is dynamically updated to perform similarity comparison with the radiation source characteristics in the fingerprint library to identify abnormal signals and generate standardized intelligence streams; the loss of the spectrum fingerprint matching Designed to: in, is the three-dimensional feature vector of the electromagnetic signal sample, is the i-th signal sample, For the The cluster center vector at the iteration, N is the total number of valid signal samples participating in the cluster center update in the current iteration, is the quantum tunneling intensity coefficient; is the adaptive cutoff threshold, To maximize the difference between classes Minimizing intra-class variance The comprehensive measure of is the quantum confinement factor; Cluster Center The formula for dynamic update is: in, is the learning rate, Gaussian kernel bandwidth The specific adjustments are: in, is the distribution shift sensitivity coefficient, is the KL divergence measure of signal distribution change, For the At iteration The joint probability distribution of For the The cluster center vector at the iteration.

3. The simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence according to claim 2 is characterized in that: Construct a multimodal knowledge graph, define radar signal features as entities, communication protocol metadata as relationships between entities, and geospatial information as entity attributes, perform semantic association modeling, and generate heterogeneous network representations, including: In the construction of the multimodal knowledge graph, a multidimensional feature tensor fusion mechanism is added to define the correlation function between the radar signal modulation type and the communication protocol metadata. for: in, is the total number of modulation types, For the The modulation type encoding matrix of the class modulation signal converts the discrete modulation type Mapped to a three-dimensional vector, For the Standard carrier frequency mean value of the modulated signal, used to dynamically adjust the carrier frequency The weight of For tensor product operation, fusion carrier frequency , Pulse Width and time difference ; is a parameter matrix used to adjust the pulse width and time difference The concatenated vector [ ; ] to perform feature mapping; The geographic space information is encoded by using a spherical harmonic function : in, is the geographic spatial weight coefficient, is the spherical harmonic basis function, The latitude and longitude coordinates of the signal sources respectively; , , Angular quantum number, magnetic quantum number and maximum harmonic order respectively; The tensor representation generated by the association function serves as the relationship vector between entities in the multimodal knowledge graph, and the spherical harmonic encoding result serves as the entity attribute, which together constitute the heterogeneous network representation containing topological connections and semantic constraints.

4. The simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence according to claim 3 is characterized in that: The spatiotemporal dual-channel attention mechanism is used to fuse the time domain features of the radar pulse sequence and the spatial distribution features of the communication signal group to generate a joint semantic vector, including: In the spatiotemporal dual-channel attention mechanism, the temporal channel Introduce the carrier frequency-pulse width coupled convolution kernel: in, is the carrier frequency difference sensitivity coefficient, is the time domain sliding window length, and are the tth moment and the history The carrier frequency value at the time, For History The pulse width value at the moment, is a function for extracting the periodic characteristics of pulse width; The spatial channel uses pulse width weighted geodesic distance : in, is the pulse width difference penalty factor, are the feature vectors of nodes i and j respectively, is the eigenvector angle; The confidence dynamic allocation algorithm defines the modulation type entropy weight Specifically: in, For the The information entropy of the signal modulation type, C is the total number of signal categories, is the loop variable; The time domain features extracted by the carrier frequency-pulse width coupling convolution kernel and the spatial domain features of the pulse width weighted geodesic distance modeling are dynamically fused through the modulation type entropy weight to generate the joint semantic vector, which is input into the spatiotemporal Transformer model for threat prediction.

5. The simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence according to claim 4 is characterized in that: In the spatiotemporal Transformer model, a carrier frequency change rate gating mechanism is embedded in the threat prediction module. : in, is the carrier frequency change rate, is the pulse width stability index, is the linear transformation matrix; The conditional probability distribution of the mixture density network Modeled as: in, is the weight of the kth Gaussian component under the input x, and is the carrier frequency mean and standard deviation of the kth Gaussian component. Beta distribution describes the statistical characteristics of pulse width. and are the shape parameters that control the left-biased and right-biased characteristics of the pulse width distribution, and the Cat distribution represents the probability of modulation type classification. is the modulation type probability vector; The carrier frequency change rate gating mechanism dynamically adjusts the attention weight distribution of each time step in the spatiotemporal Transformer model based on the generated joint semantic vector, wherein the attention weight of the historical pulse width feature is enhanced when the carrier frequency change rate exceeds a threshold; the conditional probability distribution modeling of the mixed density network integrates the geographic space coding features and the signal carrier frequency-pulse width joint distribution to generate a dynamic battlefield situation panorama including the threat thermal field and the signal propagation path.

6. The simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence according to claim 5 is characterized in that: In the online incremental learning framework, detecting the new signal pattern includes: Adopt modulation type entropy change trigger mechanism Detecting the new signal pattern, the modulation type entropy change trigger mechanism Specifically: in, (.) is the indicator function, when the modulation type distribution entropy value of the new signal batch and historical distribution entropy The difference exceeds the threshold When , the update mechanism of the incremental learning model is triggered; Fine-tune model parameters in layers, including: Layered fine-tuning applies quantum noise perturbation to the carrier frequency characteristic layer, specifically: in, is the weight matrix of the frequency feature layer, is the average deviation of the signal carrier frequency, is the quantum noise perturbation intensity coefficient.

7. The simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence according to claim 6 is characterized in that: Implement a reinforcement learning-driven multi-path distribution mechanism through an edge-cloud collaborative architecture, including: In the edge-cloud collaborative architecture, the multipath distribution mechanism is used to define the carrier frequency-bit error rate joint reward function Specifically: in, , , is the weighting coefficient, The carrier frequency f corresponds to the inverse of the channel bit error rate, is the total transmission time of the signal from the transmitter to the receiver, is the delay sensitivity factor, is the node security assessment vector, is the reference safety vector.

8. The simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence according to claim 2 is characterized in that: On the basis of the quantum annealing optimization, a pulse width-modulation type constrained Hamiltonian is added to suppress the interference of carrier frequency drift and pulse width jitter on signal sorting. The Hamiltonian Combining the carrier frequency cluster center constraint and the pulse width distribution prior knowledge, the Hamiltonian The expression is: in, and are the qubit index and the total number of qubits, respectively. and The constraint coefficients of carrier frequency and pulse width respectively, and Respectively The carrier frequency value of quantum bits and the target carrier frequency value, is the reference pulse width distribution, For the The Pauli-Z operator for 1 qubit.

9. The simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence according to claim 2 is characterized in that: In the dynamic adversarial network DAN, the carrier frequency-pulse width joint robustness loss is defined in the adversarial defense module : in, To find the expected statistical distribution of the input signal x, and are the disturbances for carrier frequency f and pulse width pw, respectively. and are the disturbance amplitudes that limit the carrier frequency and pulse width, respectively. To measure the distribution difference between the electromagnetic signal data x and the adversarial sample x+δ in the feature space f(.), is the modulation type classification loss weight, is the cross entropy loss, which quantifies the electromagnetic signal data x and the adversarial sample x adv The difference in the modulation type prediction distribution m(.), is a feature extraction function that maps the input signal x to a high-dimensional feature space. is a modulation type classifier that outputs the modulation type probability distribution of the signal x.

10. A simulation system for intelligent fusion and dynamic prediction of electronic warfare intelligence, used to implement a simulation method for intelligent fusion and dynamic prediction of electronic warfare intelligence as claimed in any one of claims 1 to 9, characterized in that: The simulation system comprises: The multi-domain data acquisition and preprocessing module is used to collect electromagnetic signal data in real time through multi-domain distributed sensor nodes, use the dynamic adversarial network DAN to perform spectrum fingerprint matching and anomaly location on the electromagnetic signal data, and combine the spatiotemporal consistency verification mechanism to eliminate invalid data and generate a standardized intelligence stream; The multimodal knowledge graph construction module is used to construct a multimodal knowledge graph, define radar signal features as entities, communication protocol metadata as relationships between entities, and geospatial information as entity attributes, perform semantic association modeling, and generate heterogeneous network representations; The spatiotemporal feature fusion engine is used to fuse the time domain features of the radar pulse sequence with the spatial distribution features of the communication signal group using the spatiotemporal dual-channel attention mechanism to generate a joint semantic vector; and to achieve the fusion of multi-source heterogeneous data through the confidence dynamic allocation algorithm; The threat prediction and situation generation module is used to dynamically predict the threat evolution trend based on the joint semantic vector using the spatiotemporal Transformer model, output the multi-task prediction results of threat level, target type and behavior intention; and generate a dynamic battlefield situation panorama in combination with a mixed density network; The online incremental learning agent module is used to deploy the online incremental learning framework, detect new signal patterns and fine-tune model parameters in layers, and update the prediction head module to adapt to the dynamic battlefield environment; The edge-cloud collaborative distribution control module is used to implement a reinforcement learning-driven multi-path distribution mechanism through an edge-cloud collaborative architecture, dynamically optimize the intelligence push priority based on the channel state matrix and node security assessment, and ensure low-latency transmission of key threat intelligence.

Images