Passive radar multi-source electromagnetic positioning matching method and system based on AI

Abstract

The invention provides an AI-based passive radar multi-source electromagnetic positioning matching method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: firstly obtaining a multi-source electromagnetic signal data set of a target region, the multi-source electromagnetic signal data set is electromagnetic radiation signals synchronously captured by a plurality of signal collection devices in a preset time window, and the electromagnetic radiation signals are acquired by a plurality of signal collection devices; secondly, performing feature extraction on the multi-source electromagnetic signal data set to obtain a signal feature set containing signal intensity distribution, frequency domain correlation and time-space correlation features, then fusing the signal feature set based on a dynamic weight distribution strategy to generate a multi-dimensional positioning feature set, and then calling an AI positioning matching model to analyze positioning parameters to obtain a multi-dimensional positioning feature set; and obtaining a spatial position and a signal propagation parameter of the target electromagnetic radiation source. And finally, a positioning optimization instruction is generated according to the parameters and is fed back to the signal acquisition device cluster for parameter calibration, so that the electromagnetic positioning precision and reliability can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular, to a multi-source electromagnetic positioning and matching method and system for passive radar based on AI. Background Art

[0002] In the field of current electromagnetic environment monitoring and target positioning, accurately and efficiently determining the position of electromagnetic radiation sources is of crucial significance, and it is widely applied in many fields such as military reconnaissance, radio management, security monitoring, etc.

[0003] Traditional electromagnetic positioning methods mainly rely on a single signal feature or a small number of fixed features for positioning, such as only relying on signal strength or simple frequency features. Due to the single feature dimension, this method is difficult to comprehensively reflect the complex characteristics of electromagnetic signals. In a complex electromagnetic environment, such as in the presence of multipath effects, signal interference, etc., the positioning accuracy will be severely affected, and the position of the target electromagnetic radiation source cannot be accurately determined.

[0004] Moreover, most of the existing positioning methods lack an effective feedback adjustment mechanism. After completing a positioning, they cannot perform real-time calibration and optimization of the parameters of the signal acquisition device according to the positioning result, cannot adapt to the dynamic changes of the electromagnetic environment, and it is difficult to continuously maintain a high positioning accuracy. Summary of the Invention

[0005] In view of the problems mentioned above, in combination with the first aspect of the present invention, embodiments of the present invention provide a multi-source electromagnetic positioning and matching method for passive radar based on AI, and the method includes: Obtain a multi-source electromagnetic signal data set of a target area, where the multi-source electromagnetic signal data set includes electromagnetic radiation signals synchronously captured by a plurality of signal acquisition devices within a preset time window; Perform signal feature extraction processing on the multi-source electromagnetic signal data set to obtain a signal feature set corresponding to each signal acquisition device, where the signal feature set includes a signal intensity distribution feature, a signal frequency domain correlation feature, and a signal spatio-temporal correlation feature; Based on a preset dynamic weight allocation strategy, perform multi-source feature fusion processing on the plurality of signal feature sets to generate a multi-dimensional positioning feature set of the target electromagnetic radiation source; Call an AI positioning and matching model to perform positioning parameter analysis processing on the multi-dimensional positioning feature set to generate spatial position parameters and signal propagation parameters of the target electromagnetic radiation source; Generate a positioning optimization instruction according to the spatial position parameters and the signal propagation parameters, and feedback the positioning optimization instruction to the signal acquisition device cluster to trigger parameter calibration operations.

[0006] In another aspect, an embodiment of the present invention further provides an AI-based passive radar multi-source electromagnetic positioning and matching system, including a processor and a machine-readable storage medium. The machine-readable storage medium is connected to the processor. The machine-readable storage medium is used to store programs, instructions, or codes, and the processor is used to execute the programs, instructions, or codes in the machine-readable storage medium to implement the above method.

[0007] Based on the above aspects, the present invention obtains a multi-source electromagnetic signal data set of a target area, which aggregates electromagnetic radiation signals synchronously captured by multiple signal acquisition devices within a preset time window. The multi-source electromagnetic signal data set is subjected to signal feature extraction processing to obtain a signal feature set including signal intensity distribution features, signal frequency-domain correlation features, and signal spatio-temporal correlation features, which can deeply explore the internal characteristics of electromagnetic signals from multiple dimensions and comprehensively reflect the essential features of the signals. Based on a preset dynamic weight allocation strategy, multi-source feature fusion processing is performed on multiple signal feature sets to generate a multi-dimensional positioning feature set of the target electromagnetic radiation source, fully considering that the importance of different features changes dynamically with the actual situation, improving the accuracy and comprehensiveness of the positioning features, and overcoming the limitations of single-feature positioning. An AI positioning and matching model is called to perform positioning parameter analysis processing on the multi-dimensional positioning feature set to generate spatial position parameters and signal propagation parameters of the target electromagnetic radiation source. With the powerful learning and analysis capabilities of the AI positioning and matching model, the accuracy and efficiency of positioning parameter analysis are effectively improved. A positioning optimization instruction is generated according to the spatial position parameters and signal propagation parameters and fed back to the signal acquisition device cluster to trigger parameter calibration operations, forming a closed-loop positioning optimization system that can adjust the signal acquisition devices in real time according to the positioning results, continuously improving the accuracy and reliability of subsequent positioning, and realizing high-precision, intelligent, and dynamic optimization of passive radar multi-source electromagnetic positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 is a schematic execution flow diagram of an AI-based passive radar multi-source electromagnetic positioning and matching method provided by an embodiment of the present invention.

[0009] Figure 2 is a schematic diagram of exemplary hardware and software components of an AI-based passive radar multi-source electromagnetic positioning and matching system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0010] The present invention will be specifically described below in conjunction with the accompanying drawings of the specification. Figure 1 is a schematic flow diagram of an AI-based passive radar multi-source electromagnetic positioning and matching method provided by an embodiment of the present invention. The AI-based passive radar multi-source electromagnetic positioning and matching method will be introduced in detail below.

[0011] Step S110: Obtain a multi-source electromagnetic signal data set of the target area, where the multi-source electromagnetic signal data set includes electromagnetic radiation signals synchronously captured by multiple signal acquisition devices within a preset time window.

[0012] In this embodiment, the target area can be a spatial area with a specific range, and its boundary can be defined by geographical coordinates or specific physical identifiers. To comprehensively obtain the electromagnetic signal conditions within the target area, multiple signal acquisition devices can be reasonably deployed within the target area. These signal acquisition devices have the ability to receive electromagnetic radiation signals, and their working principle is based on physical mechanisms such as electromagnetic induction, and can convert the received electromagnetic radiation into electrical signals for subsequent processing.

[0013] The distribution of the signal acquisition devices needs to be planned according to factors such as the topography and electromagnetic environment complexity of the target area. For example, for an area with complex terrain and where electromagnetic signals are easily blocked, it may be necessary to increase the number of signal acquisition devices and adopt a decentralized layout to ensure that electromagnetic signals in all corners can be effectively captured. For an area with relatively flat terrain and a relatively simple electromagnetic environment, the number of devices can be appropriately reduced and a relatively concentrated layout can be adopted.

[0014] The preset time window is a pre-determined time period, denoted by T, whose start time is t1 and end time is t2, that is, T = [t1, t2]. Within this time period, all signal acquisition devices will start the acquisition operation synchronously according to a unified clock signal. The purpose of synchronous acquisition is to ensure that the signals obtained by each device are consistent in time for subsequent accurate signal analysis and processing.

[0015] Each signal acquisition device will continuously receive electromagnetic radiation signals within the preset time window T and convert them into digital signals for storage. Suppose there are n signal acquisition devices in total, and the signal data collected by the i-th signal acquisition device within the preset time window T is denoted by Si(T), where i = 1, 2,..., n. Summing up all the signal data collected by these n signal acquisition devices together constitutes the multi-source electromagnetic signal data set S, that is, S = {S1(T), S2(T),..., Sn(T)}.

[0016] Step S120: Perform signal feature extraction processing on the multi-source electromagnetic signal data set to obtain a signal feature set corresponding to each signal acquisition device, where the signal feature set includes signal intensity distribution features, signal frequency domain correlation features, and signal spatio-temporal correlation features.

[0017] After obtaining the multi-source electromagnetic signal data set S, in order to extract valuable information from these multi-source electromagnetic signals, signal feature extraction processing needs to be performed on them. Since different signal acquisition devices are located at different positions, the received electromagnetic signals will also be different. Therefore, feature extraction needs to be performed separately for each signal acquisition device to obtain their respective corresponding signal feature sets.

[0018] The signal intensity distribution feature is used to describe the intensity change of electromagnetic signals at different times and different positions. It can reflect the intensity distribution law of electromagnetic radiation sources and the attenuation characteristics of signals during propagation. The signal frequency-domain correlation feature mainly focuses on the characteristics of signals in the frequency domain, including the frequency components of signals, the relationships between various frequency components, etc. This is of great value for identifying different types of electromagnetic radiation sources and analyzing the modulation methods of signals. The signal spatio-temporal correlation feature combines the information of signals in time and space. By analyzing the propagation time difference and spatial position relationship between signals in different signal acquisition devices, it can more accurately determine the position and propagation path of electromagnetic radiation sources.

[0019] Step S121: Perform signal preprocessing operations on the electromagnetic radiation signals to obtain standardized electromagnetic signal data. The signal preprocessing operations include signal sampling rate conversion, background noise suppression, and time-frequency alignment processing.

[0020] Before performing signal feature extraction, signal preprocessing operations need to be performed on each signal Si(T) in the multi-source electromagnetic signal data set S to improve the quality and consistency of the signals and obtain standardized electromagnetic signal data.

[0021] Signal sampling rate conversion is the first step of the preprocessing operation. Different signal acquisition devices may have different sampling rates. For the convenience of subsequent processing, the sampling rates of all signals need to be unified. Let the original sampling rate of the i-th signal acquisition device be fi and the target sampling rate be f0. The sampling rate of the signal Si(T) can be converted by methods such as interpolation or decimation. For signals with a sampling rate higher than the target sampling rate, the decimation method is used to reduce the number of sampling points of the signal according to a certain decimation factor; for signals with a sampling rate lower than the target sampling rate, the interpolation method is used to insert appropriate sampling points into the signal to increase the sampling rate. After the sampling rate conversion, the i-th signal becomes Si'(T), and its sampling rate is f0.

[0022] Background noise suppression is the second step of the preprocessing operation. In an actual environment, the electromagnetic signals received by the signal acquisition device are often interfered by various background noises, and these noises will affect the subsequent feature extraction and analysis results. Therefore, it is necessary to adopt a suitable filtering algorithm to suppress the background noise of the signal Si'(T). For example, an adaptive filtering algorithm can be used to automatically adjust the parameters of the filter according to the statistical characteristics of the signal to achieve the best noise suppression effect. After background noise suppression, the i-th signal becomes Si''(T), and its noise level is effectively reduced.

[0023] Time-frequency alignment processing is the third step of the preprocessing operation. Due to certain time and frequency deviations that may exist during the installation and debugging of different signal acquisition devices, the collected signals are inconsistent in time and frequency. To eliminate this inconsistency, it is necessary to perform time-frequency alignment processing on the signal Si''(T). Methods such as correlation analysis can be used to determine the time and frequency deviations by finding the correlation between signals and perform corresponding corrections on the signals. After time-frequency alignment processing, the standardized electromagnetic signal data Si'''(T) is obtained, where i = 1, 2, …, n.

[0024] Step S122: Perform time-frequency joint analysis processing on the standardized electromagnetic signal data to extract signal intensity distribution features, where the signal intensity distribution features include a signal peak intensity sequence, an average intensity fluctuation curve, and an intensity decay trend parameter.

[0025] After obtaining the standardized electromagnetic signal data Si'''(T), perform time-frequency joint analysis processing on it to extract signal intensity distribution features. Time-frequency joint analysis can simultaneously display the changes of the signal in time and frequency, which helps to more comprehensively understand the characteristics of the signal.

[0026] First, perform segmented windowing processing on the standardized electromagnetic signal data Si'''(T) within a preset time interval Δt to generate multiple signal time-frequency analysis windows. Let the start time of the preset time interval Δt be tstart and the end time be tend, and both tstart and tend are within the preset time window T. Segment the standardized electromagnetic signal data Si'''(T) in the time interval [tstart, tend] according to Δt, and each segment of the signal corresponds to a time-frequency analysis window. For the j-th time-frequency analysis window, its time interval is [tj, tj + Δt], and the corresponding signal data is Sij(T).

[0027] Then, perform short-time Fourier transform processing on each signal time-frequency analysis window Sij(T) to obtain a time-frequency energy distribution diagram. The short-time Fourier transform is a commonly used time-frequency analysis method. It performs windowing on the signal and then performs Fourier transform on the signal within each window, thereby obtaining the energy distribution of the signal at different times and frequencies. Let the time-frequency energy distribution diagram of the j-th time-frequency analysis window after short-time Fourier transform be Eij(f, t), where f represents frequency and t represents time.

[0028] Extract the signal peak intensity sequence from the time-frequency energy distribution diagram Eij(f, t). The signal peak intensity sequence contains the maximum energy value and its corresponding timestamp within each analysis window. For the j-th time-frequency analysis window, find the maximum energy value Emaxj and its corresponding timestamp tmaxj in the time-frequency energy distribution diagram Eij(f, t). Combine the maximum energy values and corresponding timestamps of all analysis windows to obtain the signal peak intensity sequence Pj = {(Emax1, tmax1), (Emax2, tmax2), …, (Emaxm, tmaxm)}, where m is the number of analysis windows.

[0029] Calculate the average energy value of all analysis windows and generate an average intensity fluctuation curve. The average intensity fluctuation curve contains trend parameters of energy change over time. For the j-th time-frequency analysis window, calculate its average energy value Eavgj, that is, integrate the time-frequency energy distribution diagram Eij(f, t) over frequency and time, and then divide by the area of the window. Arrange the average energy values of all analysis windows in chronological order to obtain the average intensity fluctuation curve Eavg(t).

[0030] Perform decay model fitting on the signal peak intensity sequence Pj to obtain intensity decay trend parameters. The intensity decay trend parameters include an exponential decay coefficient and a linear decay slope. Methods such as the least squares method can be used to fit the signal peak intensity sequence Pj and select a suitable decay model, such as an exponential decay model or a linear decay model. For the exponential decay model, its expression is E(t) = E0 * exp(-αt), where E0 is the initial energy value and α is the exponential decay coefficient; for the linear decay model, its expression is E(t) = E0 - βt, where β is the linear decay slope. The exponential decay coefficient α and linear decay slope β obtained through fitting are the intensity decay trend parameters.

[0031] Finally, combine and splice the signal peak intensity sequence Pj, the average intensity fluctuation curve Eavg(t), and the intensity decay trend parameters into the signal intensity distribution feature Ii1.

[0032] Step S123: Perform multi-scale frequency-domain decomposition on the standardized electromagnetic signal data to extract signal frequency-domain correlation features, where the signal frequency-domain correlation features include the amplitude spectrum of the main frequency component, the phase difference of the harmonic components, and the frequency band energy ratio distribution.

[0033] Perform multi-scale frequency-domain decomposition on the standardized electromagnetic signal data Si'''(T) to extract signal frequency-domain correlation features. Multi-scale frequency-domain decomposition can decompose the signal into components of different frequency scales, which helps to analyze the frequency structure of the signal and the relationship between frequency components.

[0034] Call a preset wavelet basis function to perform multi-level wavelet decomposition on the standardized electromagnetic signal data Si'''(T) to generate multiple band component signals. Wavelet decomposition is a multi-resolution analysis method that decomposes the signal into wavelet coefficients of different scales and positions by selecting an appropriate wavelet basis function. Let the preset wavelet basis function be ψ(t). After multi-level wavelet decomposition, multiple band component signals Sik(T) are obtained, where k = 1, 2, …, K, and K is the number of decomposition levels.

[0035] Perform energy normalization on each band component signal Sik(T) and calculate the frequency band energy ratio distribution. The frequency band energy ratio distribution includes the fundamental frequency component energy ratio, the second harmonic energy ratio, and the higher harmonic energy ratio. For the k-th band component signal Sik(T), calculate its energy Ek, which is the square integral of the signal Sik(T). Then, calculate the total energy of all band component signals Etotal = ∑Ek, where k = 1, 2, …, K. Finally, calculate the energy ratio of each band component signal Rk = Ek / Etotal, where k = 1, 2, …, K. Denote the energy ratio corresponding to the fundamental frequency component as R1, the energy ratio corresponding to the second harmonic component as R2, and the energy ratios corresponding to the higher harmonic components as R3, R4, …, RK, and then the frequency band energy ratio distribution R = {R1, R2, R3, …, RK} is obtained.

[0036] Perform phase demodulation on the fundamental frequency component signal Si1(T) to extract the amplitude spectrum of the main frequency component. The amplitude spectrum of the main frequency component includes the spectral line distribution of the fundamental frequency amplitude varying with time. Methods such as Hilbert transform can be used to perform phase demodulation on the fundamental frequency component signal Si1(T) to obtain its instantaneous amplitude and phase information. Then, plot the variation of the instantaneous amplitude with time to obtain the amplitude spectrum of the main frequency component A1(t).

[0037] The phase difference of the second harmonic component signal Si2(T) is calculated and processed to obtain the phase difference of the harmonic component. The phase difference of the harmonic component includes the phase offset sequence of the second harmonic relative to the fundamental frequency. The phase offset of the second harmonic relative to the fundamental frequency can be calculated by comparing the phase information of the second harmonic component signal Si2(T) and the fundamental frequency component signal Si1(T). Let the phase offset of the second harmonic relative to the fundamental frequency at the t-th moment be φ(t). Combining the phase offsets at all moments, the phase difference of the harmonic component Φ = {φ(t1), φ(t2), …, φ(tn)} is obtained, where n is the number of signal sampling points.

[0038] Finally, the main frequency component amplitude spectrum A1(t), the phase difference of the harmonic component Φ, and the frequency band energy ratio distribution R are combined into the signal frequency domain correlation feature Ii2.

[0039] Step S124: Perform spatio-temporal correlation analysis and processing on the standardized electromagnetic signal data captured by multiple signal acquisition devices to extract signal spatio-temporal correlation features, where the signal spatio-temporal correlation features include the signal arrival time difference sequence, the propagation path correlation matrix, and the multipath effect interference coefficient.

[0040] Perform spatio-temporal correlation analysis and processing on the standardized electromagnetic signal data Si'''(T) captured by multiple signal acquisition devices, where i = 1, 2, …, n, to extract signal spatio-temporal correlation features. Spatio-temporal correlation analysis can combine the information of the signal in time and space to more accurately determine the position and propagation path of the electromagnetic radiation source.

[0041] First, calculate the signal propagation path difference parameter according to the spatial position coordinates of the signal acquisition devices. Let the spatial position coordinates of the i-th signal acquisition device be (xi, yi, zi), and the spatial position coordinates of the j-th signal acquisition device be (xj, yj, zj). Then the path length difference ΔLij = |Lij - Lji| of the signal propagating from the electromagnetic radiation source to the i-th and j-th signal acquisition devices, where Lij is the path length of the signal from the electromagnetic radiation source to the i-th signal acquisition device, and Lji is the path length of the signal from the electromagnetic radiation source to the j-th signal acquisition device; the path angle difference Δθij can be obtained by calculating the angle between the two signal acquisition devices and the electromagnetic radiation source. Combining the path length differences and path angle differences between all pairs of signal acquisition devices, the propagation path difference parameter D = {ΔLij, Δθij|i, j = 1, 2, …, n; i ≠ j} is obtained.

[0042] Perform cross - correlation analysis on the standardized electromagnetic signal data Si'''(T) captured by multiple signal acquisition devices to generate a signal arrival time difference sequence. Cross - correlation analysis is a commonly used signal processing method, which determines the time delay between two signals by calculating the correlation between them. For the standardized electromagnetic signal data Si'''(T) and Sj'''(T) captured by the i - th signal acquisition device and the j - th signal acquisition device, calculate their cross - correlation function Rij(τ), where τ is the time delay. Find the time delay τij corresponding to the maximum value of the cross - correlation function Rij(τ), and this time delay is the signal arrival time difference between the i - th signal acquisition device and the j - th signal acquisition device. Combine the signal arrival time differences between all pairs of signal acquisition devices to obtain the signal arrival time difference sequence ΔT={ΔTij|i, j = 1, 2, …, n; i≠j}.

[0043] Construct a propagation path correlation matrix based on the propagation path difference parameter D and the signal arrival time difference sequence ΔT. The propagation path correlation matrix includes the time delay consistency coefficient and the path interference weight between each propagation path. Let the time delay consistency coefficient be Cij and the path interference weight be Wij. The time delay consistency coefficient and the path interference weight can be calculated according to the relationship between the propagation path difference parameter and the signal arrival time difference sequence. For example, the time delay consistency coefficient Cij can be calculated by comparing the consistency of the path length difference and the signal arrival time difference, and the path interference weight Wij can be determined according to factors such as the path angle difference and the signal strength. Combine the time delay consistency coefficients and the path interference weights between all pairs of signal acquisition devices to obtain the propagation path correlation matrix M={Cij, Wij|i, j = 1, 2, …, n; i≠j}.

[0044] Perform multipath effect detection on the received signal of each signal acquisition device and calculate the multipath effect interference coefficient. The multipath effect refers to the phenomenon that signals are reflected and refracted due to encountering obstacles during propagation, resulting in signals from multiple different paths arriving at the receiving end simultaneously, thus generating interference. Channel estimation and other methods can be used to detect the multipath effect of the received signal of each signal acquisition device, and calculate the energy ratio of the direct wave to the reflected wave and the normalized delay spread. Let the energy ratio of the direct wave to the reflected wave of the i - th signal acquisition device be Ei and the normalized delay spread be Di. Combine the energy ratios of the direct wave to the reflected wave and the normalized delay spreads of all signal acquisition devices to obtain the multipath effect interference coefficient N={Ei, Di|i = 1, 2, …, n}.

[0045] Finally, combine and splice the signal arrival time difference sequence ΔT, the propagation path correlation matrix M, and the multipath effect interference coefficient N into the signal spatio - temporal correlation feature Ii3.

[0046] Step S125: Combine and splice the signal intensity distribution feature, the signal frequency-domain correlation feature, and the signal spatio-temporal correlation feature into the signal feature set.

[0047] Combine and splice the signal intensity distribution feature Ii1, the signal frequency-domain correlation feature Ii2, and the signal spatio-temporal correlation feature Ii3 obtained in the previous steps together, and the signal feature set Ii = {Ii1, Ii2, Ii3} corresponding to the i-th signal acquisition device is obtained, where i = 1, 2, …, n.

[0048] Step S130: Based on a preset dynamic weight allocation strategy, perform multi-source feature fusion processing on multiple signal feature sets to generate a multi-dimensional positioning feature set of the target electromagnetic radiation source.

[0049] After obtaining the signal feature set Ii corresponding to each signal acquisition device, it is necessary to perform multi-source feature fusion processing on these signal feature sets based on a preset dynamic weight allocation strategy to generate a multi-dimensional positioning feature set of the target electromagnetic radiation source. The dynamic weight allocation strategy can dynamically adjust the weight of each signal feature set according to factors such as the signal quality and environmental conditions, thereby improving the accuracy and reliability of feature fusion.

[0050] Step S131: Obtain the signal quality evaluation parameters corresponding to each signal acquisition device, where the signal quality evaluation parameters include the signal-to-noise ratio level, the signal stability index, and the environmental interference suppression coefficient.

[0051] To implement the dynamic weight allocation strategy, first, it is necessary to obtain the signal quality evaluation parameters corresponding to each signal acquisition device. The signal-to-noise ratio level is used to measure the ratio of the useful signal to the noise in the signal, which reflects the clarity of the signal. The signal-to-noise ratio level can be obtained by calculating the power spectral density of the signal and the power spectral density of the noise, and then finding their ratio. The signal stability index is used to measure the stability of the signal over time, and it can be calculated by analyzing the changes in parameters such as the amplitude and frequency of the signal. The environmental interference suppression coefficient is used to measure the ability of the signal acquisition device to suppress environmental interference, and it can be determined according to factors such as the hardware characteristics of the signal acquisition device and the adopted filtering algorithm. Let the signal-to-noise ratio level of the i-th signal acquisition device be SNR i, the signal stability index be St i, and the environmental interference suppression coefficient be EI i. Then, the signal quality evaluation parameter Qi of the i-th signal acquisition device = {SNR i, St i, EI i}, where i = 1, 2, …, n.

[0052] Step S132: Calculate the initial fusion weight of each signal acquisition device according to the signal quality evaluation parameters, and the initial fusion weight is positively correlated with the signal-to-noise ratio level, the signal stability index, and the environmental interference suppression coefficient.

[0053] Calculate the initial fusion weight of each signal acquisition device according to the signal quality evaluation parameter Qi. Since the initial fusion weight is positively correlated with the signal-to-noise ratio level, the signal stability index, and the environmental interference suppression coefficient, the weighted summation method can be used to calculate the initial fusion weight. Let the weight of the signal-to-noise ratio level be w1, the weight of the signal stability index be w2, and the weight of the environmental interference suppression coefficient be w3, and w1 + w2 + w3 = 1. Then the initial fusion weight Wi0 of the i-th signal acquisition device can be obtained through the following calculation logic: Wi0 = w1 × SNRi + w2 × Sti + w3 × EIi. It should be noted here that the signal-to-noise ratio level, the signal stability index, and the environmental interference suppression coefficient need to be normalized before calculation to ensure that they are in the same dimension and value range, and to avoid the situation of adding different dimension units. The normalization process can use common linear normalization methods. For example, for a parameter x, its normalized parameter x' = (x - min(x)) / (max(x) - min(x)), where min(x) and max(x) are the minimum and maximum values of this parameter among all signal acquisition devices respectively. Through such normalization, each parameter is mapped to the interval [0, 1], thus ensuring the rationality of the calculation of the initial fusion weight in terms of dimension and value.

[0054] Step S133: Perform dynamic adjustment processing on the initial fusion weight to generate a set of dynamic fusion weights. The dynamic adjustment processing includes time decay compensation, spatial consistency constraint, and device state adaptation.

[0055] After obtaining the initial fusion weight Wi0, it is also necessary to perform dynamic adjustment processing on it to generate a set of dynamic fusion weights that are more in line with the actual situation. The dynamic adjustment processing mainly considers three aspects of factors, namely time decay compensation, spatial consistency constraint, and device state adaptation.

[0056] Step S1331: Obtain the historical weight adjustment record of the signal acquisition device and extract the time decay factor. The time decay factor is calculated according to the device operation duration and the most recent calibration time interval.

[0057] First, perform time decay compensation. It is necessary to obtain the historical weight adjustment records of the signal acquisition device and extract the time decay factor from these records. During the operation of the device, its performance may change over time. For example, the sensitivity of the sensor may decrease, resulting in poor signal quality collected. Therefore, it is necessary to calculate the time decay factor based on the device operation duration and the recent calibration time interval. Let the device operation duration be T_run and the recent calibration time interval be T_calib. Then the time decay factor γ can be calculated by a predefined function f(T_run, T_calib), that is, γ = f(T_run, T_calib). This function can be designed according to the actual device performance change law. For example, it can be a linear function or an exponential function. Generally speaking, the longer the device operation duration and the longer the recent calibration time interval, the smaller the value of the time decay factor, which means that the weight of this signal acquisition device needs to be attenuated to a greater extent.

[0058] Step S1332: Calculate the spatial consistency constraint coefficient according to the spatial distribution density among the signal acquisition devices, and the spatial consistency constraint coefficient is proportional to the distribution density.

[0059] Next, consider the spatial consistency constraint. Calculate the spatial consistency constraint coefficient according to the spatial distribution density among the signal acquisition devices. The spatial distribution density reflects the degree of tightness of the signal acquisition devices in the target area. If the signal acquisition devices are distributed densely, the correlation between the signals they collect may be stronger. Therefore, relatively higher weights can be given to these devices; conversely, if the distribution is sparse, the weights can be appropriately reduced. Let the spatial distribution density of the signal acquisition device be ρ. The spatial consistency constraint coefficient β can be calculated by a linear function g(ρ), that is, β = g(ρ), and β is proportional to ρ. For example, when the spatial distribution density increases, the spatial consistency constraint coefficient will also increase accordingly, which means that these signal acquisition devices will play a more important role in the feature fusion process.

[0060] Step S1333: Monitor the working state parameters of the signal acquisition device in real time to generate a device state adaptation coefficient, and the working state parameters include the power supply stability level and the hardware aging index.

[0061] Then, device status adaptation is performed. The working status parameters of the signal acquisition device are monitored in real time, and these parameters include the power supply stability level and the hardware aging index. The power supply stability level reflects the stability of the power supply of the signal acquisition device. If the power supply is unstable, it may cause fluctuations in the acquired signals, affecting the signal quality; the hardware aging index reflects the aging degree of the device hardware, and hardware aging may lead to a decline in device performance. Let the power supply stability level be P_stab and the hardware aging index be H_aging, then the device status adaptation coefficient α can be calculated through a comprehensive function h(P_stab, H_aging), that is, α = h(P_stab, H_aging). This function comprehensively considers the influence of the power supply stability level and the hardware aging index on the device performance. For example, when the power supply stability level is low or the hardware aging index is high, the value of the device status adaptation coefficient will decrease accordingly, thereby reducing the weight of this signal acquisition device.

[0062] Step S1334: Combine the time decay factor, the spatial consistency constraint coefficient, and the device status adaptation coefficient into a dynamic adjustment coefficient matrix.

[0063] Combine the calculated time decay factor γ, spatial consistency constraint coefficient β, and device status adaptation coefficient α into a dynamic adjustment coefficient matrix A. Matrix A is a diagonal matrix, and the elements on its diagonal are the products of γ, β, and α corresponding to each signal acquisition device, that is, Aii = γi × βi × αi, where i represents the i-th signal acquisition device. Such a matrix structure can conveniently adjust the initial fusion weight of each signal acquisition device.

[0064] Step S1335: Perform an element-by-element multiplication operation on the initial fusion weight using the dynamic adjustment coefficient matrix to generate a set of dynamic fusion weights.

[0065] Perform an element-by-element multiplication operation on the initial fusion weight Wi0 using the dynamic adjustment coefficient matrix A to generate a set of dynamic fusion weights Wi. Specifically, for the i-th signal acquisition device, its dynamic fusion weight Wi = Aii × Wi0. Through such dynamic adjustment, the weight of each signal acquisition device can be adjusted in real time according to factors such as time, space, and device status, thereby improving the accuracy and reliability of feature fusion.

[0066] Step S134: Perform weighted fusion splicing processing on multiple signal feature sets based on the set of dynamic fusion weights to obtain a multi-dimensional positioning feature set, and the multi-dimensional positioning feature set includes a fused signal strength feature, a fused frequency domain correlation feature, and a fused spatio-temporal correlation feature.

[0067] After obtaining the dynamic fusion weight set Wi, weighted fusion and splicing processing is performed on multiple signal feature sets Ii based on this set. Since the signal feature set Ii includes the signal intensity distribution feature Ii1, the signal frequency domain correlation feature Ii2, and the signal spatio-temporal correlation feature Ii3, it is necessary to perform weighted fusion on the features in these three aspects respectively.

[0068] For the signal intensity distribution feature, let the signal intensity distribution feature of the i-th signal acquisition device be Ii1, and its dynamic fusion weight be Wi. Then the fused signal intensity feature I1_fused can be obtained by weighted splicing of the signal intensity distribution features of all signal acquisition devices. The specific calculation logic is as follows: First, multiply the signal intensity distribution feature Ii1 of each signal acquisition device by its corresponding dynamic fusion weight Wi to obtain the weighted signal intensity distribution feature Wi×Ii1. Then, splice all the weighted signal intensity distribution features in a set order to form the fused signal intensity feature I1_fused.

[0069] For the signal frequency domain correlation feature, similarly, let the signal frequency domain correlation feature of the i-th signal acquisition device be Ii2, and its dynamic fusion weight be Wi. Then the fused frequency domain correlation feature I2_fused can be obtained by multiplying the signal frequency domain correlation feature Ii2 of each signal acquisition device by its corresponding dynamic fusion weight Wi to obtain the weighted signal frequency domain correlation feature Wi×Ii2, and then splicing all the weighted signal frequency domain correlation features.

[0070] For the signal spatio-temporal correlation feature, let the signal spatio-temporal correlation feature of the i-th signal acquisition device be Ii3, and its dynamic fusion weight be Wi. Then the fused spatio-temporal correlation feature I3_fused can be obtained by multiplying the signal spatio-temporal correlation feature Ii3 of each signal acquisition device by its corresponding dynamic fusion weight Wi to obtain the weighted signal spatio-temporal correlation feature Wi×Ii3, and finally splicing all the weighted signal spatio-temporal correlation features.

[0071] Combining the fused signal intensity feature I1_fused, the fused frequency domain correlation feature I2_fused, and the fused spatio-temporal correlation feature I3_fused together, the multi-dimensional positioning feature set I_fused = {I1_fused, I2_fused, I3_fused} is obtained.

[0072] Step S135: Perform dimensionality reduction and redundancy removal processing on the multi-dimensional positioning feature set to generate an optimized multi-dimensional positioning feature set.

[0073] After obtaining the multi-dimensional positioning feature set $I_{fused}$, in order to reduce the dimension of the features and improve the efficiency of subsequent processing, it is necessary to perform dimensionality reduction and redundancy removal on it. Dimensionality reduction and redundancy removal can be performed using methods such as principal component analysis (PCA). The basic idea of principal component analysis is to transform the original high-dimensional features into a new set of low-dimensional features that are mutually uncorrelated through linear transformation, and these low-dimensional features can retain the information of the original features as much as possible.

[0074] Specifically, first consider the multi-dimensional positioning feature set $I_{fused}$ as a matrix, where each row of the matrix represents a sample and each column represents a feature. Then calculate the covariance matrix of this matrix, and the covariance matrix reflects the correlation between each feature. Next, perform eigenvalue decomposition on the covariance matrix to obtain the eigenvalues and the corresponding eigenvectors. The eigenvalue represents the variance size of each principal component, and the larger the variance, the more information the principal component contains. Select the eigenvectors corresponding to the top $k$ eigenvalues with larger variances, and multiply the original feature matrix by the matrix composed of these $k$ eigenvectors to obtain the feature matrix after dimensionality reduction.

[0075] During the dimensionality reduction process, some redundant features can also be removed. Redundant features refer to those features that contribute little to the final positioning result or are highly correlated with other features. The correlation coefficient between features can be calculated, and the features with higher correlation coefficients can be merged or removed to further reduce the number of features.

[0076] After dimensionality reduction and redundancy removal processing, an optimized multi-dimensional positioning feature set $I_{fused\_optimized}$ is generated. This multi-dimensional positioning feature set not only has a lower dimension but also removes redundant information, and can be more effectively used for subsequent positioning parameter parsing processing.

[0077] Step S140: Invoke the AI positioning matching model to perform positioning parameter parsing processing on the multi-dimensional positioning feature set, and generate the spatial position parameters and signal propagation parameters of the target electromagnetic radiation source.

[0078] After obtaining the optimized multi-dimensional positioning feature set $I_{fused\_optimized}$, invoke the AI positioning matching model to perform positioning parameter parsing processing on it to generate the spatial position parameters and signal propagation parameters of the target electromagnetic radiation source. The AI positioning matching model is a trained intelligent model that can learn the mapping relationship between the multi-dimensional positioning feature set and the spatial position parameters and signal propagation parameters of the target electromagnetic radiation source.

[0079] Step S141: Input the multi-dimensional positioning feature set into the pre-trained AI positioning matching model for feature mapping processing to generate a high-dimensional abstract feature vector.

[0080] First, input the optimized multi-dimensional positioning feature set \(I_{fused\_optimized}\) into the pre-trained AI positioning matching model for feature mapping processing. The AI positioning matching model contains multiple neural network layers inside, such as the input layer, hidden layer, and output layer. During the feature mapping process, the multi-dimensional positioning feature set \(I_{fused\_optimized}\) enters the model from the input layer, undergoes a series of non-linear transformations in the hidden layer, and finally generates a high-dimensional abstract feature vector \(V\) at the output layer. This high-dimensional abstract feature vector \(V\) is an abstract representation of the multi-dimensional positioning feature set \(I_{fused\_optimized}\), which contains more potential information and can more accurately reflect the characteristics of the target electromagnetic radiation source.

[0081] Step S142: Perform regional grid division processing on the high-dimensional abstract feature vector to generate a set of candidate positioning grids, and each candidate positioning grid contains a spatial coordinate range and a signal propagation parameter range.

[0082] After obtaining the high-dimensional abstract feature vector \(V\), perform regional grid division processing on it. Regional grid division is to divide the target area into multiple small grids, and each grid corresponds to a candidate positioning area. Specifically, according to the boundary and resolution requirements of the target area, the target area is spatially divided into multiple small cubic grids, and each grid has a specific spatial coordinate range. At the same time, combining the characteristics of signal propagation and historical data, set the corresponding signal propagation parameter range for each grid, such as the signal propagation speed, path loss coefficient, etc.

[0083] Suppose the coordinate range of the target area in three-dimensional space is \([x_{min}, x_{max}]\), \([y_{min}, y_{max}]\), and \([z_{min}, z_{max}]\), and the resolution of the grid is \(\Delta x\), \(\Delta y\), and \(\Delta z\). Then the target area can be divided into \(N_x=(x_{max}-x_{min}) / \Delta x\), \(N_y=(y_{max}-y_{min}) / \Delta y\), and \(N_z=(z_{max}-z_{min}) / \Delta z\) grids. The spatial coordinate range of each grid can be expressed as \([x_i, x_i + \Delta x]\), \([y_j, y_j + \Delta y]\), and \([z_k, z_k + \Delta z]\), where \(i = 0, 1, \ldots, N_x - 1\), \(j = 0, 1, \ldots, N_y - 1\), \(k = 0, 1, \ldots, N_z - 1\). For each grid, according to historical data and the signal propagation model, set its signal propagation parameter range, such as the signal propagation speed range is \([v_{min}, v_{max}]\), and the path loss coefficient range is \([L_{min}, L_{max}]\). Combine all grids and their corresponding spatial coordinate ranges and signal propagation parameter ranges together to obtain the set of candidate positioning grids \(G = \{G1, G2, \ldots, GN\}\), where \(N = N_x\times N_y\times N_z\).

[0084] Step S143: Calculate the matching degree score between each candidate positioning grid and the high-dimensional abstract feature vector, where the matching degree score is generated based on the feature similarity algorithm and the propagation model constraint conditions.

[0085] Next, calculate the matching degree score between each candidate positioning grid and the high-dimensional abstract feature vector V. The matching degree score is used to measure the matching degree between each candidate positioning grid and the target electromagnetic radiation source. The higher the score, the more likely the grid is the location of the target electromagnetic radiation source. The matching degree score is generated based on the feature similarity algorithm and the propagation model constraint conditions.

[0086] For example, step S1431: Perform block feature extraction processing on the high-dimensional abstract feature vector to generate a signal strength feature block, a frequency domain correlation feature block, and a spatio-temporal correlation feature block.

[0087] First, perform block feature extraction processing on the high-dimensional abstract feature vector V. According to the nature and role of different features in the high-dimensional abstract feature vector V, it is divided into a signal strength feature block V1, a frequency domain correlation feature block V2, and a spatio-temporal correlation feature block V3. For example, according to the dimensions of the feature vector and the correlation between features, the features of the first part of the dimensions can be used as the signal strength feature block V1, the features of the middle part of the dimensions can be used as the frequency domain correlation feature block V2, and the features of the last part of the dimensions can be used as the spatio-temporal correlation feature block V3.

[0088] Step S1432: Calculate the similarity between the preset feature template of each candidate positioning grid and the signal strength feature block to generate a signal strength matching degree.

[0089] For each candidate positioning grid Gi, it has a preset feature template Ti. Calculate the similarity between the signal strength feature part in the preset feature template Ti of the candidate positioning grid Gi and the signal strength feature block V1 to generate a signal strength matching degree Si1. The similarity calculation can use common similarity measurement methods, such as Euclidean distance, cosine similarity, etc. Taking cosine similarity as an example, the signal strength matching degree Si1 can be obtained by calculating the cosine value of the vector angle between the signal strength feature block V1 and the preset signal strength feature part of the candidate positioning grid Gi. The closer the cosine value is to 1, the higher the similarity between the two, and the higher the signal strength matching degree Si1.

[0090] Step S1433: Compare the frequency domain constraint conditions of each candidate positioning grid with the frequency domain correlation feature block to generate a frequency domain compliance score.

[0091] Compare the frequency-domain constraint condition Fi of each candidate positioning grid Gi with the frequency-domain associated feature block V2 to generate a frequency-domain compliance score Si2. The frequency-domain constraint condition Fi is a series of constraints on frequency ranges and frequency relationships set according to the position of the candidate positioning grid and the electromagnetic environment. For example, a certain candidate positioning grid may stipulate that the main frequency of the signal must be within a certain specific frequency range, and the phase difference between harmonic components must satisfy a certain relationship. Compare the frequency information in the frequency-domain associated feature block V2 with the frequency-domain constraint condition Fi. If the constraint condition is satisfied, a higher score is given; if only partially satisfied or not satisfied, a lower score is given.

[0092] Step S1434: Perform a logical verification process on the spatio-temporal constraint condition of each candidate positioning grid and the spatio-temporal associated feature block to generate a spatio-temporal verification score.

[0093] Perform a logical verification process on the spatio-temporal constraint condition Si of each candidate positioning grid Gi and the spatio-temporal associated feature block V3 to generate a spatio-temporal verification score Si3. The spatio-temporal constraint condition Si is a series of constraints on time and space relationships set according to the spatial position of the candidate positioning grid and the signal propagation characteristics. For example, a certain candidate positioning grid may stipulate that the time difference of the signal arriving at different signal acquisition devices must be within a certain specific range, and the propagation path of the signal must conform to a certain geometric relationship. Perform a logical verification on the time and space information in the spatio-temporal associated feature block V3 and the spatio-temporal constraint condition Si. If the constraint condition is satisfied, a higher score is given; if only partially satisfied or not satisfied, a lower score is given.

[0094] Step S1435: Perform a weighted sum of the signal strength matching degree, the frequency-domain compliance score, and the spatio-temporal verification score to generate the matching degree score.

[0095] Perform a weighted sum of the signal strength matching degree Si1, the frequency-domain compliance score Si2, and the spatio-temporal verification score Si3 to generate the matching degree score Si. Let the weight of the signal strength matching degree be w_s1, the weight of the frequency-domain compliance score be w_s2, and the weight of the spatio-temporal verification score be w_s3, and w_s1 + w_s2 + w_s3 = 1. Then the matching degree score Si = w_s1 × Si1 + w_s2 × Si2 + w_s3 × Si3.

[0096] Step S1436: Perform an error compensation process on the matching degree score according to the historical positioning error data to generate an optimized matching degree score.

[0097] Perform error compensation processing on the matching degree score Si according to the historical positioning error data to generate the optimized matching degree score Si_optimized. The historical positioning error data records the actual positioning error conditions of each candidate positioning grid during the past positioning process. Based on these error data, the matching degree score of each candidate positioning grid can be adjusted. For example, if a candidate positioning grid often has a large error in historical positioning, its score can be appropriately reduced in the current matching degree score; conversely, if a candidate positioning grid has a small positioning error, its score can be appropriately increased. The error compensation processing can be implemented using a compensation function f_error(Si, E_history), where Si is the uncompensated matching degree score and E_history is the historical positioning error data. After the error compensation processing, the optimized matching degree score Si_optimized is obtained.

[0098] Step S144: Select the candidate positioning grid with the highest matching degree score as the target positioning grid, and extract the weighted average coordinates within the spatial coordinate range of the target positioning grid as the spatial position parameter. The weighted average coordinates are calculated based on the signal propagation parameter and the historical positioning data within the target positioning grid.

[0099] After obtaining the optimized matching degree score Si_optimized of each candidate positioning grid, select the candidate positioning grid with the highest matching degree score as the target positioning grid G_target. The target positioning grid G_target has the highest matching degree, indicating that it is most likely to be the location of the target electromagnetic radiation source.

[0100] Extract the weighted average coordinates within the spatial coordinate range of the target positioning grid G_target as the spatial position parameter. The calculation of the weighted average coordinates needs to consider the signal propagation parameter and the historical positioning data within the target positioning grid. Let the spatial coordinate range of the target positioning grid G_target be [x_target_min, x_target_max], [y_target_min, y_target_max], and [z_target_min, z_target_max], and the coordinates of each positioning point in the historical positioning data be (x_j, y_j, z_j), and its corresponding signal propagation parameter be p_j, and the weight be wj. First, the relationship between the weight wj and the signal propagation parameter p_j needs to be determined. Generally speaking, the signal propagation parameter can reflect the reliability or accuracy of the signal at this positioning point. For example, when the signal strength is large and the propagation path is clear, the reliability of the corresponding positioning point is high, and the weight should also be large. The weight wj can be calculated through a predefined function, such as wj = g(p_j), which maps the signal propagation parameter p_j to the corresponding weight value.

[0101] Next, calculate the weighted average coordinates. For the x coordinate, the weighted average coordinate x_avg can be obtained by multiplying the x coordinate value xj of each positioning point by its corresponding weight wj, then summing up all the products, and finally dividing by the sum of all weights. That is, first calculate the sum sum_x = ∑(xj * wj) (here the summation is for all historical positioning points within the target positioning grid), and the sum of all weights sum_w = ∑wj, then x_avg = sum_x / sum_w.

[0102] Similarly, for the y coordinate, first calculate the sum sum_y = ∑(yj * wj), and y_avg = sum_y / sum_w. For the z coordinate, first calculate the sum sum_z = ∑(zj * wj), and z_avg = sum_z / sum_w.

[0103] In this way, the weighted average coordinates (x_avg, y_avg, z_avg) within the spatial coordinate range of the target positioning grid are obtained, and they are used as the spatial position parameters of the target electromagnetic radiation source.

[0104] Step S145: Extract the median value of the signal propagation parameter range of the target positioning grid as the signal propagation parameter.

[0105] The target positioning grid G_target has a preset signal propagation parameter range. For example, the signal propagation speed range is [v_min, v_max], and the path loss coefficient range is [L_min, L_max], etc. For each signal propagation parameter, extract the median value of its range as the final signal propagation parameter.

[0106] For the signal propagation speed, its median value v = (v_min + v_max) / 2. For the path loss coefficient, its median value L = (L_min + L_max) / 2. And so on, for other signal propagation parameters involved in the target positioning grid, calculate their median values in this way, and combine these median values to obtain the signal propagation parameters of the target electromagnetic radiation source.

[0107] Step S150: Generate a positioning optimization instruction according to the spatial position parameters and the signal propagation parameters, and feedback the positioning optimization instruction to the signal acquisition device cluster to trigger the parameter calibration operation.

[0108] After obtaining the spatial position parameters and signal propagation parameters of the target electromagnetic radiation source, it is necessary to generate a positioning optimization instruction based on this information, and then feedback this instruction to the signal acquisition device cluster to trigger the parameter calibration operation of the signal acquisition device, so as to improve the accuracy of subsequent positioning.

[0109] Step S151: Compare the spatial position parameters with the geographical location database of the signal acquisition device to generate a positioning deviation vector.

[0110] First, compare the obtained spatial position parameters (x_avg, y_avg, z_avg) of the target electromagnetic radiation source with the geographical location database of the signal acquisition device. The geographical location database of the signal acquisition device records the accurate geographical location information of each signal acquisition device. Let the geographical location coordinates of the i-th signal acquisition device be (xi, yi, zi).

[0111] Calculate the deviation between the spatial position parameters of the target electromagnetic radiation source and the geographical location coordinates of each signal acquisition device. For the x coordinate, the deviation Δxi = x_avg - xi; for the y coordinate, the deviation Δyi = y_avg - yi; for the z coordinate, the deviation Δzi = z_avg - zi. Combine these deviations to obtain the positioning deviation vector ΔVi = (Δxi, Δyi, Δzi) corresponding to the i-th signal acquisition device. Perform such calculations for all signal acquisition devices to obtain the set of positioning deviation vectors {ΔV1, ΔV2,..., ΔVn} of all signal acquisition devices.

[0112] Step S152: Calculate device calibration parameters according to the positioning deviation vector, where the device calibration parameters include antenna pointing adjustment angle, received sensitivity compensation value, and sampling rate optimization coefficient.

[0113] Calculate the device calibration parameters of each signal acquisition device according to the set of positioning deviation vectors {ΔV1, ΔV2,..., ΔVn}. The device calibration parameters include antenna pointing adjustment angle, received sensitivity compensation value, and sampling rate optimization coefficient.

[0114] For the antenna pointing adjustment angle, it is closely related to the positioning deviation vector. The azimuth and angle information of the target electromagnetic radiation source relative to the signal acquisition device can be determined through the positioning deviation vector. For example, the angle deviation in the horizontal direction can be calculated based on the x and y coordinate deviations in the positioning deviation vector, and the angle deviation in the vertical direction can be calculated based on the z coordinate deviation and the information in the horizontal direction. Let the horizontal antenna pointing adjustment angle of the i-th signal acquisition device be θi_hori, and the vertical antenna pointing adjustment angle be θi_vert, which can be calculated according to the positioning deviation vector ΔVi by using trigonometric functions and other methods.

[0115] The received sensitivity compensation value is related to the magnitude of the positioning deviation vector. Generally speaking, a larger positioning deviation may mean that the signal quality received by the signal acquisition device is poor, and the received sensitivity needs to be improved. The received sensitivity compensation value Ci_sens can be calculated through a predefined function h(||ΔVi||), where ||ΔVi|| represents the magnitude of the positioning deviation vector ΔVi, and this function maps the magnitude of the positioning deviation vector to the corresponding received sensitivity compensation value.

[0116] The sampling rate optimization coefficient can also be adjusted according to the positioning deviation vector. If the positioning deviation is large, it may be necessary to increase the sampling rate to obtain more detailed signal information. The sampling rate optimization coefficient Ci_rate can be calculated through a function k(||ΔVi||), and this function maps the magnitude of the positioning deviation vector to the corresponding sampling rate optimization coefficient.

[0117] Combining the antenna pointing adjustment angles θi_hori and θi_vert, the received sensitivity compensation value Ci_sens, and the sampling rate optimization coefficient Ci_rate of each signal acquisition device, the device calibration parameter Pi of the i-th signal acquisition device is obtained: Pi = {θi_hori, θi_vert, Ci_sens, Ci_rate}.

[0118] Step S153: Match the signal propagation parameters with a preset propagation model library to generate a model update instruction, and the model update instruction includes a path loss coefficient correction amount and a multipath effect suppression strategy.

[0119] Match the signal propagation parameters of the target electromagnetic radiation source with a preset propagation model library. The preset propagation model library contains signal propagation models in various different scenarios, and each model has corresponding parameters such as a path loss coefficient and a multipath effect processing method.

[0120] For the path loss coefficient, compare the path loss coefficient L of the target electromagnetic radiation source with the path loss coefficients of each model in the propagation model library. Find the propagation model closest to L, and then calculate the path loss coefficient correction amount ΔL based on the difference between the two. For example, if the path loss coefficient in the propagation model is L_model, then the path loss coefficient correction amount ΔL = L - L_model.

[0121] For the multipath effect suppression strategy, select the most suitable multipath effect suppression strategy according to the signal propagation parameters of the target electromagnetic radiation source and the information in the propagation model library. Different propagation models may correspond to different multipath effect suppression methods, such as using adaptive filtering, beamforming and other technologies. According to the matching result, determine the specific multipath effect suppression strategy and use it as part of the model update instruction.

[0122] Combining the path loss coefficient correction amount ΔL and the multipath effect suppression strategy yields the model update instruction P_model.

[0123] Step S154: Combine the device calibration parameters and the model update instruction into a positioning optimization instruction.

[0124] Combining the device calibration parameter Pi of each signal acquisition device and the model update instruction P_model forms the positioning optimization instruction P_optimize. For the i-th signal acquisition device, its positioning optimization instruction P_optimize_i = {Pi, P_model}. Summarizing the positioning optimization instructions of all signal acquisition devices gives the complete set of positioning optimization instructions {P_optimize_1, P_optimize_2,..., P_optimize_n}.

[0125] Step S155: Perform an executability verification process on the positioning optimization instruction according to the hardware constraint conditions of the signal acquisition device to generate a verified positioning optimization instruction.

[0126] Before feeding the positioning optimization instruction back to the signal acquisition device cluster, an executability verification process needs to be performed on the positioning optimization instruction according to the hardware constraint conditions of the signal acquisition device. The hardware constraint conditions of the signal acquisition device include the maximum adjustment angle of the antenna, the adjustable range of the receiving sensitivity, the maximum and minimum limits of the sampling rate, etc.

[0127] For the antenna pointing adjustment angle, check whether θi_hori and θi_vert are within the maximum adjustment angle range of the antenna. If it exceeds the range, adjust it to the maximum adjustment angle value. For the receiving sensitivity compensation value Ci_sens, check whether it is within the adjustable range of the receiving sensitivity. If it exceeds the range, adjust it to the boundary value of the adjustable range. For the sampling rate optimization coefficient Ci_rate, check whether it is within the maximum and minimum limits of the sampling rate. If it exceeds the range, adjust it to the value within the limit range.

[0128] For the path loss coefficient correction amount ΔL and the multipath effect suppression strategy in the model update instruction, it is also necessary to check whether they match the hardware capabilities of the signal acquisition device. For example, some multipath effect suppression strategies may require specific hardware support. If the signal acquisition device does not have this hardware, other appropriate strategies need to be selected.

[0129] After the executability verification process, the positioning optimization instructions are adjusted accordingly to generate a set of verified positioning optimization instructions {P_optimize_1_verified, P_optimize_2_verified, …, P_optimize_n_verified}. These verified positioning optimization instructions are fed back to the signal acquisition device cluster, and the signal acquisition devices will perform parameter calibration operations according to these instructions, thereby improving the accuracy and reliability of subsequent positioning of the target electromagnetic radiation source.

[0130] Figure 2 FIG. shows a schematic diagram of exemplary hardware and software components of an AI-based passive radar multi-source electromagnetic positioning and matching system 100 that can implement the ideas of the present application provided by some embodiments of the present application. For example, the processor 120 can be used on the AI-based passive radar multi-source electromagnetic positioning and matching system 100 and is used to execute the functions in the present application.

[0131] The AI-based passive radar multi-source electromagnetic positioning and matching system 100 can be a general-purpose server or a special-purpose server, both of which can be used to implement the AI-based passive radar multi-source electromagnetic positioning and matching method of the present application. Although only one server is shown in the present application, for convenience, the functions described in the present application can be implemented in a distributed manner on multiple similar platforms to balance the processing load.

[0132] For example, the AI-based passive radar multi-source electromagnetic positioning and matching system 100 can include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and different forms of storage media 140, such as disks, ROM, or RAM, or any combination thereof. Exemplarily, the AI-based passive radar multi-source electromagnetic positioning and matching system 100 can also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application can be implemented according to these program instructions. The AI-based passive radar multi-source electromagnetic positioning and matching system 100 also includes an I / O interface 150 between the computer and other input / output devices.

[0133] For ease of explanation, only one processor is described in the AI-based passive radar multi-source electromagnetic positioning and matching system 100. However, it should be noted that the AI-based passive radar multi-source electromagnetic positioning and matching system 100 in this application may also include multiple processors. Therefore, the steps performed by one processor described in this application can also be jointly executed or separately executed by multiple processors. For example, if the processor of the AI-based passive radar multi-source electromagnetic positioning and matching system 100 executes step A and step B, it should be understood that step A and step B can also be jointly executed by two different processors or separately executed in one processor. For example, the first processor executes step A, the second processor executes step B, or the first processor and the second processor jointly execute steps A and B.

[0134] In addition, an embodiment of the present invention further provides a readable storage medium, in which computer-executable instructions are preset. When the processor executes the computer-executable instructions, the above-mentioned AI-based passive radar multi-source electromagnetic positioning and matching method is implemented.

[0135] It should be noted that, in order to simplify the description of the present invention disclosure and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of the present invention, sometimes multiple features are merged into one embodiment, drawing, or description thereof.

Claims

1. An AI-based passive radar multi-source electromagnetic positioning and matching method, characterized in that, The method includes: Obtaining a multi-source electromagnetic signal data set of a target area, where the multi-source electromagnetic signal data set includes electromagnetic radiation signals synchronously captured by multiple signal acquisition devices within a preset time window; Performing signal feature extraction processing on the multi-source electromagnetic signal data set to obtain a signal feature set corresponding to each signal acquisition device, where the signal feature set includes a signal intensity distribution feature, a signal frequency-domain correlation feature, and a signal spatio-temporal correlation feature; Based on a preset dynamic weight allocation strategy, performing multi-source feature fusion processing on multiple signal feature sets to generate a multi-dimensional positioning feature set of a target electromagnetic radiation source; Invoking an AI positioning matching model to perform positioning parameter analysis processing on the multi-dimensional positioning feature set to generate spatial position parameters and signal propagation parameters of the target electromagnetic radiation source; Generating a positioning optimization instruction according to the spatial position parameters and the signal propagation parameters, and feeding back the positioning optimization instruction to a signal acquisition device cluster to trigger a parameter calibration operation.

2. The AI-based passive radar multi-source electromagnetic positioning and matching method according to claim 1, wherein The performing signal feature extraction processing on the multi-source electromagnetic signal data set to obtain a signal feature set corresponding to each signal acquisition device includes: Performing signal preprocessing operations on the electromagnetic radiation signals to obtain standardized electromagnetic signal data, where the signal preprocessing operations include signal sampling rate conversion, background noise suppression, and time-frequency alignment processing; Performing time-frequency joint analysis processing on the standardized electromagnetic signal data to extract a signal intensity distribution feature, where the signal intensity distribution feature includes a signal peak intensity sequence, an average intensity fluctuation curve, and an intensity attenuation trend parameter; Performing multi-scale frequency-domain decomposition processing on the standardized electromagnetic signal data to extract a signal frequency-domain correlation feature, where the signal frequency-domain correlation feature includes a main frequency component amplitude spectrum, a harmonic component phase difference, and a frequency band energy ratio distribution; Performing spatio-temporal correlation analysis processing on the standardized electromagnetic signal data captured by multiple signal acquisition devices to extract a signal spatio-temporal correlation feature, where the signal spatio-temporal correlation feature includes a signal arrival time difference sequence, a propagation path correlation matrix, and a multipath effect interference coefficient; Combining and splicing the signal intensity distribution feature, the signal frequency-domain correlation feature, and the signal spatio-temporal correlation feature into the signal feature set.

3. The AI-based passive radar multi-source electromagnetic positioning and matching method according to claim 2, wherein The performing time-frequency joint analysis processing on the standardized electromagnetic signal data to extract a signal intensity distribution feature includes: Performing segmented windowing processing on the standardized electromagnetic signal data at preset time intervals to generate multiple signal time-frequency analysis windows; Performing short-time Fourier transform processing on each signal time-frequency analysis window to obtain a time-frequency energy distribution map; Extracting a signal peak intensity sequence from the time-frequency energy distribution map, where the signal peak intensity sequence includes the maximum energy value and its corresponding timestamp within each analysis window; Calculating the average energy value of all analysis windows and generating an average intensity fluctuation curve, where the average intensity fluctuation curve includes a trend parameter of energy changing with time; Performing attenuation model fitting processing on the signal peak intensity sequence to obtain an intensity attenuation trend parameter, where the intensity attenuation trend parameter includes an exponential attenuation coefficient and a linear attenuation slope; Combine and splice the signal peak intensity sequence, the average intensity fluctuation curve, and the intensity decay trend parameter into the signal intensity distribution feature.

4. The AI-based passive radar multi-source electromagnetic positioning and matching method according to claim 2, wherein Perform multi-scale frequency domain decomposition processing on the standardized electromagnetic signal data to extract signal frequency domain correlation features, including: Call a preset wavelet basis function to perform multi-level wavelet decomposition processing on the standardized electromagnetic signal data to generate multiple band component signals; Perform energy normalization processing on each band component signal, and calculate the energy ratio distribution of each band. The energy ratio distribution of the band includes the fundamental frequency component energy ratio, the second harmonic energy ratio, and the higher harmonic energy ratio; Perform phase demodulation processing on the fundamental frequency component signal to extract the amplitude spectrum of the main frequency component. The amplitude spectrum of the main frequency component includes the spectral line distribution of the fundamental frequency amplitude varying with time; Perform phase difference calculation processing on the second harmonic component signal to obtain the phase difference of the harmonic component. The phase difference of the harmonic component includes the phase offset sequence of the second harmonic relative to the fundamental frequency; Combine the amplitude spectrum of the main frequency component, the phase difference of the harmonic component, and the energy ratio distribution of the band into the signal frequency domain correlation feature.

5. The AI-based passive radar multi-source electromagnetic positioning and matching method according to claim 2, wherein Perform spatio-temporal correlation analysis processing on the standardized electromagnetic signal data captured by multiple signal acquisition devices to extract signal spatio-temporal correlation features, including: Calculate the signal propagation path difference parameter according to the spatial position coordinates of the signal acquisition device. The propagation path difference parameter includes the path length difference and the path angle difference; Perform cross-correlation analysis processing on the standardized electromagnetic signal data captured by multiple signal acquisition devices to generate a signal arrival time difference sequence. The signal arrival time difference sequence includes the time delay amount between two signal acquisition devices; Construct a propagation path correlation matrix based on the propagation path difference parameter and the signal arrival time difference sequence. The propagation path correlation matrix includes the time delay consistency coefficient and the path interference weight between each propagation path; Perform multipath effect detection processing on the received signal of each signal acquisition device to calculate the multipath effect interference coefficient. The multipath effect interference coefficient includes the energy ratio of the direct wave to the reflected wave and the normalized delay spread; Combine and splice the signal arrival time difference sequence, the propagation path correlation matrix, and the multipath effect interference coefficient into the signal spatio-temporal correlation feature.

6. The AI-based passive radar multi-source electromagnetic positioning and matching method according to claim 1, characterized in that Based on a preset dynamic weight allocation strategy, perform multi-source feature fusion processing on multiple signal feature sets to generate a multi-dimensional positioning feature set of the target electromagnetic radiation source, including: Obtain the signal quality evaluation parameter corresponding to each signal acquisition device. The signal quality evaluation parameter includes the signal-to-noise ratio level, the signal stability index, and the environmental interference suppression coefficient; Calculate the initial fusion weight of each signal acquisition device according to the signal quality evaluation parameter. The initial fusion weight is positively correlated with the signal-to-noise ratio level, the signal stability index, and the environmental interference suppression coefficient; Perform dynamic adjustment processing on the initial fusion weight to generate a dynamic fusion weight set. The dynamic adjustment processing includes time decay compensation, spatial consistency constraint, and device state adaptation; Perform weighted fusion splicing processing on the multiple signal feature sets based on the dynamic fusion weight set to obtain a multi-dimensional positioning feature set, where the multi-dimensional positioning feature set includes a fused signal strength feature, a fused frequency domain correlation feature, and a fused spatio-temporal correlation feature; Perform dimensionality reduction and redundancy removal processing on the multi-dimensional positioning feature set to generate an optimized multi-dimensional positioning feature set.

7. The AI-based passive radar multi-source electromagnetic positioning and matching method according to claim 6, characterized in that The dynamic adjustment processing of the initial fusion weight to generate a dynamic fusion weight set includes: Obtain the historical weight adjustment record of the signal acquisition device and extract the time decay factor, which is calculated based on the device operation duration and the recent calibration time interval; Calculate the spatial consistency constraint coefficient according to the spatial distribution density between signal acquisition devices, and the spatial consistency constraint coefficient is proportional to the distribution density; Real-time monitor the working state parameters of the signal acquisition device to generate a device state adaptation coefficient, where the working state parameters include the power supply stability level and the hardware aging index; Combine the time decay factor, the spatial consistency constraint coefficient, and the device state adaptation coefficient into a dynamic adjustment coefficient matrix; Use the dynamic adjustment coefficient matrix to perform element-wise multiplication operations on the initial fusion weights to generate a dynamic fusion weight set.

8. The AI-based passive radar multi-source electromagnetic positioning and matching method according to claim 1, characterized in that, The calling of the AI positioning matching model to perform positioning parameter analysis processing on the multi-dimensional positioning feature set to generate the spatial position parameters and signal propagation parameters of the target electromagnetic radiation source includes: Input the multi-dimensional positioning feature set into a pre-trained AI positioning matching model for feature mapping processing to generate a high-dimensional abstract feature vector; Perform regional grid division processing on the high-dimensional abstract feature vector to generate a candidate positioning grid set, and each candidate positioning grid includes a spatial coordinate range and a signal propagation parameter range; Calculate the matching degree score between each candidate positioning grid and the high-dimensional abstract feature vector, and the matching degree score is generated based on the feature similarity algorithm and the propagation model constraint conditions; Select the candidate positioning grid with the highest matching degree score as the target positioning grid, and extract the weighted average coordinates within the spatial coordinate range of the target positioning grid as the spatial position parameters, where the weighted average coordinates are calculated based on the signal propagation parameters and the historical positioning data within the target positioning grid; Extract the median value of the signal propagation parameter range of the target positioning grid as the signal propagation parameter.

9. The AI-based passive radar multi-source electromagnetic positioning and matching method according to claim 1, characterized in that The generation of the positioning optimization instruction according to the spatial position parameters and the signal propagation parameters includes: Compare the spatial position parameters with the geographical location database of the signal acquisition device to generate a positioning deviation vector; Calculate the device calibration parameters according to the positioning deviation vector, where the device calibration parameters include the antenna pointing adjustment angle, the receiving sensitivity compensation value, and the sampling rate optimization coefficient; Match the signal propagation parameters with a preset propagation model library to generate a model update instruction, where the model update instruction includes a path loss coefficient correction amount and a multipath effect suppression strategy; Combine the device calibration parameters and the model update instruction into a positioning optimization instruction; Perform an executability verification process on the positioning optimization instruction according to the hardware constraint conditions of the signal acquisition device to generate a verified positioning optimization instruction.

10. An AI-based passive radar multi-source electromagnetic positioning and matching system, characterized in that, It includes a processor and a memory. The memory is connected to the processor. The memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the AI-based passive radar multi-source electromagnetic positioning and matching method according to any one of the above claims 1-9.

Images