Communication transceiving method and system for adaptive frequency hopping filtering

Abstract

The invention relates to the technical field of wireless communication anti-interference, in particular to a communication transceiving method and system for adaptive frequency hopping filtering, and the method comprises the following steps: S1, collecting and storing channel state information for channel quality evaluation and interference behavior prediction through continuously monitoring the interference level, signal-to-noise ratio and frequency spectrum time sequence characteristics of a current communication channel; according to the invention, dynamic optimization generation of the frequency hopping pattern is realized through interference trend prediction and weighted correction based on the attention mechanism-LSTM network, and channel interference is effectively suppressed by combining interference residual feature prediction and adaptive filtering parameter pre-configuration and real-time optimization of the least mean square algorithm. And high-precision blind synchronization is completed through joint detection and maximum likelihood estimation by using implicit pilot frequency and chaos frequency hopping sequence characteristics, and cooperative improvement of anti-interference performance, synchronization reliability and data recovery accuracy of a communication link in a complex electromagnetic environment is finally realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of wireless communication anti-interference technology, in particular to a communication transceiving method and system based on adaptive frequency hopping filtering. BACKGROUND

[0002] In the field of wireless communication, the communication reliability under complex electromagnetic environment (such as industrial interference, multi-user same frequency competition, malicious electromagnetic interference, etc.) has always been a core technical problem. In the prior art, the traditional communication system usually adopts fixed frequency transmission or simple frequency hopping strategy, and the parameters such as frequency hopping pattern and frequency hopping rate are pre-set, which cannot be dynamically adjusted according to the real-time channel interference state, resulting in that the communication link is easily affected by dynamic interference such as burst interference and time-varying interference; at the same time, the receiver often relies on a filter with fixed parameters to suppress interference, which is difficult to adapt to the random change characteristics of interference, and the residual interference is significant; in addition, the traditional synchronization method relies on explicit pilot signals, which is easily affected by interference and causes low synchronization accuracy of the transmitter and receiver, further reducing the effectiveness of data demodulation and error correction, and finally causing poor data recovery reliability and unstable communication quality.

[0003] Based on this, the present application provides a communication transceiving method and system based on adaptive frequency hopping filtering to solve the above technical problems. SUMMARY

[0004] The purpose of the present application is to provide a communication transceiving method and system based on adaptive frequency hopping filtering. The present application dynamically optimizes and generates the frequency hopping pattern based on the interference trend prediction and weighted correction of the attention mechanism-LSTM network, effectively suppresses the channel interference by combining the interference residual feature prediction and the adaptive filter parameter pre-configuration and real-time optimization of the least mean square algorithm, and finally realizes the collaborative improvement of the anti-interference performance, synchronization reliability and data recovery accuracy of the communication link under complex electromagnetic environment by using the implicit pilot and the characteristics of chaotic frequency hopping sequence through joint detection and maximum likelihood estimation to complete high-precision blind synchronization.

[0005] To achieve the above purpose, the present application provides the following technical scheme: The present application provides a communication transceiving method based on adaptive frequency hopping filtering, comprising the following steps: S1: continuously monitor the interference level, signal-to-noise ratio and spectrum timing characteristics of the current communication channel, collect and store the channel state information for channel quality evaluation and interference behavior prediction; S2: evaluate the current channel quality based on the obtained channel state information, and predict the interference trend of the future frequency band by using the interference source behavior prediction model, dynamically generate the frequency hopping pattern sequence which avoids the current and potential interference area and the available channel; S3: encode, encrypt and frequency hopping modulate the transmitted data according to the selected frequency hopping pattern sequence, and dynamically adjust the transmission power combined with the channel condition; S4: At the receiving end, based on the interference residual characteristics in the historical frequency hopping period, the interference distribution of the current period is predicted by a lightweight timing model, the adaptive filter parameters are preconfigured, and the least mean square algorithm is combined for real-time optimization; S5: By utilizing the deterministic characteristics of the implicit pilot signal embedded in the data stream and the chaotic frequency hopping sequence, blind synchronization of the transmitting and receiving ends is performed through joint detection and parameter estimation, and the filtered signal is demodulated, decrypted and error corrected.

[0006] Based on the above method, the application also provides a communication transceiver system for adaptive frequency hopping filtering, comprising an intelligent spectrum sensing unit, a dynamic decision and waveform generation unit, an adaptive transmitting unit, an intelligent anti-interference receiving unit, and a blind synchronization and signal processing unit, wherein: The intelligent spectrum sensing unit is used to continuously monitor the interference level, signal-to-noise ratio and spectrum timing characteristics of the communication channel, collect and store channel state information; The dynamic decision and waveform generation unit is used to evaluate the channel quality based on the channel state information, predict the future interference trend using an interference source behavior prediction model, and dynamically generate a frequency hopping pattern sequence; The adaptive transmitting unit is used to encode, encrypt and frequency hopping modulate the transmitted data according to the frequency hopping pattern sequence, and dynamically adjust the transmitting power according to the channel condition; The intelligent anti-interference receiving unit is used to predict the current interference distribution based on the historical interference residual characteristics, preconfigure the adaptive filter parameters, and combine the least mean square algorithm for real-time optimization to suppress interference and extract effective signals; The blind synchronization and signal processing unit is used to utilize the characteristics of the implicit pilot signal and the chaotic frequency hopping sequence, perform blind synchronization through joint detection and parameter estimation, and demodulate, decrypt and error correct the signal.

[0007] The intelligent spectrum sensing unit comprises a multi-dimensional signal acquisition module, a data preprocessing and storage module, and a feature extraction module, wherein: The multi-dimensional signal acquisition module is used to acquire the original signals of the interference level, signal-to-noise ratio and spectrum timing characteristics of the channel in real time; The data preprocessing and storage module is used to denoise and normalize the acquired original signals, and store them as structured channel state information; The feature extraction module is used to extract key feature parameters for channel quality evaluation and interference prediction from the preprocessed data.

[0008] The dynamic decision and waveform generation unit comprises a channel quality evaluation module, an interference trend prediction module, and a pattern generation module, wherein: The channel quality evaluation module: quantitatively evaluate the communication ability of the current channel based on channel state information; The interference trend prediction module: for analyzing historical data by using an interference source behavior prediction model to predict the interference distribution trend of future frequency bands; The pattern generation module: for synthesizing quality evaluation and prediction results to dynamically generate frequency hopping pattern sequences that avoid interference and channels.

[0009] The interference trend prediction module uses an interference source behavior prediction model to analyze historical data and predict the interference distribution trend of future frequency bands. The specific operation is as follows: A1: Normalize and time series align the historical interference feature data; A2: Input the processed data into the interference source behavior prediction model to output the frequency band interference probability of the next N frequency hopping periods; A3: Combine the current channel quality evaluation results to weight and correct the prediction probability to obtain the final interference distribution trend. The weighting correction formula is as follows: , Where, is the "future tth frequency hopping period, frequency band j interference probability" output by the interference source behavior prediction model, is the channel quality coefficient output by the current channel quality evaluation module, is the "actual interference probability of the (t-1)th frequency hopping period, frequency band j", is the weight coefficient of the historical measured value, is the final interference probability after weighting correction.

[0010] The adaptive transmitting unit includes a source coding and encryption module, a frequency hopping modulation module, and a power adaptive adjustment module, wherein: The source coding and encryption module: for error correction coding and encryption processing of the sending data; The frequency hopping modulation module: for modulating the encoded data to the corresponding frequency band according to the frequency hopping pattern sequence; The power adaptive adjustment module: for dynamically adjusting the transmission power in combination with the real-time channel conditions to balance the communication quality and energy consumption.

[0011] The intelligent anti-interference receiving unit includes an interference feature memory module, an interference prediction and parameter pre-configuration module, and a filter optimization module, wherein: The interference feature memory module: for storing and updating the interference residual feature data in the historical frequency hopping period; The interference prediction and parameter pre-configuration module: for predicting the current period interference distribution by a lightweight time series model and pre-configuring the filter initial parameters; The filter optimization module is configured to run a least mean square algorithm to optimize filter parameters in real time, suppress interference and extract effective signals.

[0012] The interference prediction and parameter pre-configuration module predicts the interference distribution in the current period through a lightweight timing model and pre-configures the initial parameters of the filter, in particular as follows: B1: Call the interference residual feature sequence of the last M frequency hopping periods from the interference feature memory module, and use Z-score standardization processing to eliminate the dimension difference; B2: Input the standardized interference residual sequence into the compressed GRU model to output the interference power prediction value of each sub-band in the current frequency hopping period , the calculation formula is: , wherein, is the standardized historical interference residual feature, is the training parameter set of the lightweight model, and f is the sub-band frequency of the current period; B3: Establish an "interference power prediction value-filter parameter mapping table" to match the initial filter parameters according to ① If , pre-configure the filter order , the step factor ; ② If , pre-configure ; ③ If , pre-configure ; wherein, is the basic order, is the basic step factor, k is the order adjustment coefficient, is the preset interference threshold; B4: Send the initial parameters of the pre-configured filter order and step factor to the filter optimization module.

[0013] The blind synchronization and signal processing unit includes an implicit pilot detection module, a blind synchronization module, a demodulation and error correction module, wherein: The implicit pilot detection module is configured to extract the embedded implicit pilot signal from the received signal; The blind synchronization module is configured to use the deterministic autocorrelation characteristics of the implicit pilot and the chaotic frequency hopping sequence to perform synchronization between the transmitting end and the receiving end through joint detection and parameter estimation; The demodulation and error correction module is configured to demodulate and decrypt the synchronized signal, and recover the original data through an error correction algorithm.

[0014] ​The blind synchronization module utilizes the determinacy of the implicit pilot and the chaotic frequency hopping sequence, and performs synchronization of the transceiver through joint detection and parameter estimation, and the specific operation is as follows: C1: extracting the embedded implicit pilot sequence from the received signal; C2: using the determinacy autocorrelation characteristics of the chaotic frequency hopping sequence, performing time and frequency coarse synchronization through matched filtering; C3: based on the coarse synchronization result, using maximum likelihood estimation to perform joint estimation on the frequency offset and time delay parameters, and completing the transceiver synchronization.

[0015] Compared with the prior art, the beneficial effects of the present application are: The present application realizes dynamic optimization generation of the frequency hopping pattern through interference trend prediction and weighted correction based on the attention mechanism-LSTM network, effectively suppresses channel interference by combining interference residual feature prediction and adaptive filtering parameter pre-configuration and real-time optimization of the least mean square algorithm, and finally realizes the collaborative improvement of the anti-interference performance, synchronization reliability and data recovery accuracy of the communication link in a complex electromagnetic environment. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The system diagram of the adaptive frequency hopping filtering communication transceiver system of the present application.

[0017] Figure 2 The flowchart of the adaptive frequency hopping filtering communication transceiving method of the present application.

[0018] BRIEF DESCRIPTION OF DRAWINGS 1, intelligent spectrum sensing unit; 11, multi-dimensional signal acquisition module; 12, data preprocessing and storage module; 13, feature extraction module; 2, dynamic decision and waveform generation unit; 21, channel quality evaluation module; 22, interference trend prediction module; 23, pattern generation module; 3, adaptive transmitting unit; 31, signal source coding and encryption module; 32, frequency hopping modulation module; 33, power adaptive adjustment module; 4, intelligent anti-interference receiving unit; 41, interference feature memory module; 42, interference prediction and parameter pre-configuration module; 43, filtering optimization module; 5, blind synchronization and signal processing unit; 51, implicit pilot detection module; 52, blind synchronization module; 53, demodulation and error correction module. DETAILED DESCRIPTION

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

[0020] Example 1: like Figure 1 As shown, this embodiment provides a communication transceiver system with adaptive frequency hopping filtering, including an intelligent spectrum sensing unit 1, a dynamic decision-making and waveform generation unit 2, an adaptive transmission unit 3, an intelligent anti-interference receiving unit 4, and a blind synchronization and signal processing unit 5. Specifically: the intelligent spectrum sensing unit 1 continuously monitors the interference level, signal-to-noise ratio, and spectral timing characteristics of the communication channel, collects and stores channel state information; the dynamic decision-making and waveform generation unit 2 evaluates channel quality based on channel state information, predicts future interference trends using an interference source behavior prediction model, and dynamically generates a frequency hopping pattern sequence; the adaptive transmission unit 3 encodes, encrypts, and modulates the transmitted data according to the frequency hopping pattern sequence, and dynamically adjusts the transmission power based on channel conditions; the intelligent anti-interference receiving unit 4 predicts the current interference distribution based on historical interference residual characteristics, pre-configures adaptive filter parameters, and performs real-time optimization using a least mean square algorithm to suppress interference and extract effective signals; and the blind synchronization and signal processing unit 5 utilizes the characteristics of implicit pilot signals and chaotic frequency hopping sequences to perform blind synchronization through joint detection and parameter estimation, and demodulates, decrypts, and corrects the signal.

[0021] It should be noted that the intelligent spectrum sensing unit 1 monitors the channel environment in real time and transmits the status information to the dynamic decision-making and waveform generation unit 2 to generate an anti-interference frequency hopping sequence. This sequence drives the adaptive transmission unit 3 to complete the signal encoding, modulation and power controllable transmission. At the receiving end, the intelligent anti-interference receiving unit 4 predicts and filters out interference based on historical interference characteristics. Finally, the blind synchronization and signal processing unit 5 uses implicit pilot and chaotic characteristics to achieve blind synchronization and signal recovery.

[0022] In this embodiment, it should also be noted that the intelligent spectrum sensing unit 1 includes a multi-dimensional signal acquisition module 11, a data preprocessing and storage module 12, and a feature extraction module 13, wherein: the multi-dimensional signal acquisition module 11 is used to acquire the original signal of the channel's interference level, signal-to-noise ratio, and spectral timing characteristics in real time; the data preprocessing and storage module 12 is used to perform noise reduction and normalization processing on the acquired original signal and store it as structured channel state information; the feature extraction module 13 is used to extract key feature parameters for channel quality assessment and interference prediction from the preprocessed data.

[0023] It should be noted that the multi-dimensional signal acquisition module 11 is responsible for acquiring the original channel signal, and after noise reduction, normalization and structured storage by the data preprocessing and storage module 12, the key feature parameters used for channel quality evaluation and interference prediction are extracted from the feature extraction module 13.

[0024] Further, it should be noted that the multi-dimensional signal acquisition module 11 uses a wideband radio frequency front end, a 12-bit high-speed ADC (sampling rate ≥ 100 MSPS) and a signal-to-noise ratio detector to realize data acquisition with a frequency band of 20MHz-6GHz; wherein the interference level is measured in real time by a power meter (measurement range -120dBm to 0dBm, accuracy ±1dB), the signal-to-noise ratio is calculated by “signal power / noise power” (measurement resolution 0.1dB), and the spectral timing characteristics are obtained by FFT transformation (FFT point number 1024, frequency resolution 97.66kHz) to obtain the power spectral density timing curve. The key feature parameters in the feature extraction module 13 include: channel fading rate, interference signal center frequency and bandwidth, spectral hole duration.

[0025] In this embodiment, it should also be noted that the dynamic decision and waveform generation unit 2 includes a channel quality evaluation module 21, an interference trend prediction module 22, and a pattern generation module 23, wherein: the channel quality evaluation module 21: quantitatively evaluates the communication ability of the current channel based on channel state information; the interference trend prediction module 22: is used to analyze historical data using an interference source behavior prediction model to predict the interference distribution trend of the future frequency band; the specific operation is as follows: A1: normalize and time series align the historical interference feature data; A2: input the processed data into the interference source behavior prediction model, and output the frequency band interference probability of the future N frequency hopping periods; A3: combine the prediction probability with the current channel quality evaluation result to perform weighted correction to obtain the final interference distribution trend, and the weighted correction formula is as follows:

[0026] wherein, is the “interference probability of frequency band j in the future tth frequency hopping period” output by the interference source behavior prediction model, is the channel quality coefficient output by the current channel quality evaluation module 21, is the “actual interference probability of frequency band j in the (t-1)th frequency hopping period”, is the weight coefficient of the historical measured value, is the final interference probability after weighted correction. The pattern generation module 23: is used to comprehensively evaluate and predict the results to dynamically generate a frequency hopping pattern sequence that avoids interference and channels.

[0027] It should be noted that the channel quality evaluation module 21 quantitatively evaluates the current channel communication capability, the interference trend prediction module 22 predicts the future interference distribution trend based on historical data and corrects the probability by weighting, and the pattern generation module 23 dynamically generates the anti-interference frequency hopping sequence according to the evaluation and prediction results.

[0028] Further, it should be noted that the channel quality evaluation module 21 uses a “weighted scoring method” to quantitatively evaluate the channel quality: , wherein SNR is the normalized value of signal-to-noise ratio, representing the relative intensity of the ratio of signal power to noise power, and its original value is obtained by real-time measurement through the signal-to-noise ratio detector in the intelligent spectrum sensing unit 1, with the unit being dB, and then it is linearly mapped to the interval [0, 1] for normalization processing, and the specific formula is:

[0029] wherein, is the minimum acceptable signal-to-noise ratio (for example, 5 dB), is the maximum signal-to-noise ratio supported by the system (for example, 40 dB), thereby ensuring the comparability of the signal-to-noise ratio under different channel conditions; I is the current interference power, is the maximum tolerable interference power, is the normalized value of spectral hole duration, , Q≥80 is a high-quality channel, 60≤Q<80 is a usable channel, and Q<60 is an unusable channel.

[0030] The interference source behavior prediction model in A2 adopts an attention mechanism-LSTM network, and the network structure is ‘input layer (20-dimensional features) → attention layer (based on Bahdanau attention mechanism) → LSTM layer (2 layers, each layer with 64 neurons) → fully connected layer (output layer, dimension is “future N periods × sub-band number”)’; the Adam optimizer is used for model training, the learning rate is 0.001, the training data set is 100,000 groups of historical interference features-actual interference distribution sample pairs, and the prediction period N can be adaptively adjusted within 5-20 frequency hopping periods. In the weighted correction formula in A3, the channel quality coefficient (Q is the channel quality score), and the historical measured weight coefficient . The frequency hopping pattern generation follows three rules: ① preferentially selecting frequency bands with Q≥70 and (low interference probability); ② the frequency hopping interval is ≥2 MHz to avoid adjacent channel interference; ③ generating a pseudo-random frequency hopping sequence using ‘m sequence + interference avoidance constraint’, and the primitive polynomial of the m sequence is , to ensure the anti-interception property of the frequency hopping pattern; the frequency hopping rate is dynamically adjusted according to the channel fading rate: 100 hops / second for slow fading channels and 500 hops / second for fast fading channels.

[0031] In this embodiment, it also needs to be explained that the adaptive transmitting unit 3 includes a source coding and encryption module 31, a frequency hopping modulation module 32, and a power adaptive adjustment module 33, wherein: the source coding and encryption module 31 is used for error correction coding and encryption processing of the sending data; the frequency hopping modulation module 32 is used for modulating the encoded data to the corresponding frequency band according to the frequency hopping pattern sequence; and the power adaptive adjustment module 33 is used for dynamically adjusting the transmitting power in combination with the real-time channel condition to balance the communication quality and energy consumption.

[0032] It needs to be explained that the source coding and encryption module 31 performs error correction coding and encryption processing on the sending data, the frequency hopping modulation module 32 modulates the encoded data to the corresponding frequency band according to the frequency hopping pattern sequence, and the power adaptive adjustment module 33 dynamically adjusts the transmitting power according to the real-time channel condition to balance the communication quality and energy consumption.

[0033] Further, it needs to be explained that the transmitting power adjustment is based on the channel quality score Q: ① if Q≥80 (high-quality channel), the transmitting power is set to 10dBm (optimal energy consumption); ② if 60≤Q<80 (usable channel), the transmitting power is set to 20dBm (balance quality and energy consumption); and ③ if Q<60 (unusable channel), the transmitting power is set to 30dBm (maximum coverage), and the dynamic decision and waveform generation unit 2 is triggered to regenerate the frequency hopping pattern; the response delay of the power adjustment is ≤1ms, which adapts to the real-time changes of the channel.

[0034] In this embodiment, it also needs to be explained that the intelligent anti-interference receiving unit 4 includes an interference feature memory module 41, an interference prediction and parameter pre-configuration module 42, and a filter optimization module 43, wherein: the interference feature memory module 41 is used for storing and updating the interference residual feature data in the historical frequency hopping period; the interference prediction and parameter pre-configuration module 42 is used for predicting the interference distribution in the current period through a lightweight time sequence model and pre-configuring the initial parameters of the filter; and the specific operation is as follows: B1: calling the interference residual feature sequence of the last M frequency hopping periods from the interference feature memory module 41, and adopting Z-score standardization processing to eliminate the dimension difference; B2: inputting the standardized interference residual sequence into the compressed GRU model to output the interference power prediction value of each sub-frequency band in the current frequency hopping period , and the calculation formula is:

[0035] wherein, is the standardized historical interference residual feature, For the training parameter set of the lightweight model, f is the sub-band frequency of the current period; GRU is a variant of recurrent neural network (RNN), mainly used for processing sequence data, and can effectively capture long-term dependencies in sequences. In this embodiment, a compressed GRU model is used to process the historical interference residual feature sequence, and by learning the rules in these historical sequences, the interference power of each sub-band in the current frequency hopping period is predicted; B3: Establishing an "interference power prediction value-filter parameter mapping table", according to Matching filter initial parameters: ① If , the filter order is pre-configured , and the step factor is pre-configured ; ② If , the filter order is pre-configured ; ③ If , the filter order is pre-configured ; wherein, is the basic order, is the basic step factor, k is the order adjustment coefficient, is the preset interference threshold; B4: The pre-configured filter order and step factor initial parameters are sent to the filter optimization module 43. The filter optimization module 43: is used to run the least squares algorithm to optimize the filter parameters in real time, suppress interference and extract valid signals.

[0036] It should be noted that the interference feature memory module 41 stores and updates historical interference feature data, the interference prediction and parameter pre-configuration module 42 predicts the interference distribution and pre-configures the filter parameters based on the data, and the filter optimization module 43 optimizes the filter in real time according to the obtained parameters through the adaptive algorithm and extracts valid signals.

[0037] Further, it should be noted that the core formula of the least squares algorithm is: ① Filter output: ; ② Error calculation: ; ③ Weight update: ; wherein, is the filter coefficient vector at time n, is the input signal vector, is the expected signal, is the error signal, is the step factor (the initial value output by the interference prediction and parameter pre-configuration module 42 is adopted, and is dynamically fine-tuned according to the variance of the error : If > 0.1, μ increases by 10%; if < 0.01, μ decreases by 10%.

[0038] In this embodiment, it should also be noted that the blind synchronization and signal processing unit 5 includes an implicit pilot detection module 51, a blind synchronization module 52, and a demodulation and error correction module 53. Specifically: the implicit pilot detection module 51 extracts the embedded implicit pilot signal from the received signal; the blind synchronization module 52 utilizes the deterministic autocorrelation characteristics of the implicit pilot and the chaotic frequency hopping sequence to perform transceiver synchronization through joint detection and parameter estimation; the specific operations are as follows: C1: Extract the embedded implicit pilot sequence from the received signal; C2: Utilize the deterministic autocorrelation characteristics of the chaotic frequency hopping sequence to perform coarse time and frequency synchronization through matched filtering; C3: Based on the coarse synchronization result, use maximum likelihood estimation to jointly estimate the frequency offset and time delay parameters to complete the transceiver synchronization. The demodulation and error correction module 53 demodulates and decrypts the synchronized signal and recovers the original data through an error correction algorithm.

[0039] It should be noted that the implicit pilot detection module 51 extracts the implicit pilot signal from the received signal, the blind synchronization module 52 uses the pilot signal and the chaotic sequence characteristics to complete the synchronization of the transmitting and receiving ends through joint parameter estimation, and the demodulation and error correction module 53 demodulates, decrypts and corrects the synchronized signal to recover the original data.

[0040] Furthermore, it should be noted that the formula for coarse synchronization of time and frequency using matched filtering in C2 is as follows: Where c(t) is the received chaotic sequence, For time delay; when When the maximum value is reached, the corresponding The coarse synchronization delay is defined as ±1μs. Coarse frequency synchronization is achieved through 'FFT frequency offset estimation', with an estimation range of ±500Hz and an error of ±100Hz. Based on the coarse synchronization results, a maximum likelihood function is constructed in C3. Where r(n) is the received signal and s(n) is the local reference signal. For frequency offset, For time delay, The sampling interval is given; the solution is obtained using the gradient descent method. The minimum value is obtained. Accuracy ±1Hz and With an accuracy of ±0.1μs, precise synchronization is achieved.

[0041] Example 2: like Figure 2 As shown in this embodiment, an adaptive frequency hopping filtering communication transceiver method specifically includes the following steps: S1. Spectrum Sensing and Channel State Information Acquisition S1.1: Multi-dimensional signal acquisition: Real-time acquisition of original channel signals through wideband RF front-end (operating frequency band 20MHz-6GHz), 12-bit high-speed ADC (sampling rate ≥100 MSPS) and signal-to-noise ratio detector; Interference level: real-time measurement by power meter (range -120dBm to 0dBm, accuracy ±1dB); Signal-to-noise ratio: calculate the ratio of signal power to noise power (resolution 0.1dB); Spectrum timing characteristics: obtain power spectral density timing curve through FFT transform (point number 1024, frequency resolution 97.66kHz); S1.2: Data preprocessing and storage: Denoising and normalization of original signals, stored as structured channel state information; S1.3: Feature extraction: Extract key feature parameters from preprocessed data: channel fading rate, interference signal center frequency and bandwidth, spectral hole duration; S2. Dynamic decision and frequency hopping pattern generation S2.1: Channel quality assessment: Quantify channel quality using weighted scoring method:

[0042] Wherein: is the normalized value of signal-to-noise ratio, I is the current interference power, is the maximum tolerable interference power, is the normalized value of spectral hole duration, Q ∈ [0, 100], Q ≥ 80 is a high-quality channel, 60 ≤ Q < 80 is a usable channel, and Q < 60 is an unusable channel; S2.2: Interference trend prediction: ① Data preprocessing: normalize historical interference feature data and align time series; ② Model prediction: input the processed data into the attention mechanism-LSTM network (structure: input layer 20 dimensions → attention layer → LSTM layer (2×64 neurons) → output layer), output the interference probability of each frequency band in the next N periods (N=5-20) ;

[0043] Model training: Adam optimizer (learning rate 0.001), 100,000 historical data samples; ③ Weighted correction: combine current channel quality and historical measured values to correct the prediction probability:

[0044] Wherein, The "future tth frequency hopping period, frequency band j interference probability" output by the interference source behavior prediction model, The channel quality coefficient output by the current channel quality assessment module 21, The "actual interference probability of the (t-1)th frequency hopping period, frequency band j", The weight coefficient of the historical measured value, , The final interference probability after weighting correction; S2.3: Frequency hopping pattern generation: Based on quality assessment (Q value) and interference prediction , dynamically generate the frequency hopping sequence: ① Preferentially select the frequency band with Q≥70 and ; ② Frequency hopping interval ≥2MHz (avoid adjacent channel interference); ③ Adopt m sequence (primitive polynomial Add interference avoidance constraints to generate a pseudo-random sequence); ④ Adaptive frequency hopping rate: 100 hops / s for slow fading channels and 500 hops / s for fast fading channels; S3. Adaptive transmission processing S3.1: Source encoding and encryption: Forward error correction encoding (such as Turbo code) and encryption are performed on the transmitted data; S3.2: Frequency hopping modulation: According to the frequency hopping pattern sequence generated in S2, modulate the encoded data to the corresponding frequency band (such as FSK or QPSK modulation); S3.3: Power adaptive adjustment Based on channel quality score Q to dynamically adjust the transmission power: ① Q≥80: Power is set to 10dBm (optimal energy consumption); ② 60≤Q<80: Power is set to 20dBm (balanced mode); ③ Q<60: Power is set to 30dBm (maximum coverage), and trigger to regenerate the frequency hopping pattern; Power adjustment response delay ≤1ms; S4. Intelligent anti-interference receiving processing S4.1: Interference feature memory: Store and update the interference residual feature data of the historical frequency hopping period; S4.2: Interference prediction and filter preconfiguration: ① Data standardization: Call the interference residual sequence of the last M periods for Z-score standardization; ② Interference prediction: Input the compressed GRU model, and output the current period interference power prediction value :

[0045] wherein, is the normalized historical interference residual feature, is the training parameter set of the light-weight model, and f is the sub-band frequency of the current period; ③ Parameter mapping: look up table according to the predicted value to pre-configure the LMS filter parameters: I. If : order , step factor ; II. If : , ; III. If : , ; S4.3: Filter optimization: Run the LMS algorithm to optimize the filter in real time: Filter output: ; Error calculation: ; Weight update: ; Step Dynamic fine-tuning: if > 0.1, increase by 10%; if < 0.01, reduce by 10%; S5. Blind synchronization and signal processing S5.1: Implicit pilot detection: Extract the embedded implicit pilot sequence from the received signal; S5.2: Blind synchronization: ① Coarse synchronization: Time delay estimation: match through chaos sequence autocorrelation When reaches the maximum value, the corresponding is the coarse synchronization time delay (error ± 1 μs); Frequency offset estimation: FFT frequency offset estimation (range ± 500 Hz, error ± 100 Hz); ② Fine synchronization: Construct the maximum likelihood function: , Optimize the time delay and frequency offset ±0.1 μs and ±1 Hz; S5.3: Demodulation and error correction: The synchronization signal is demodulated (e.g. FSK / QPSK demodulation), decrypted (AES decryption), and the original data is recovered by error correction decoding (e.g. Viterbi decoding).

[0046] In the description of the present specification, the description referring to the terms "one embodiment", "an example", "a specific example" and the like means that the specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In the present specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Also, the specific feature, structure, material or characteristic described can be combined in any suitable manner in one or more embodiments or examples.

[0047] The preferred embodiments of the application disclosed above are only used to help explain the present application. The preferred embodiments do not describe all of the details of the application and limit the application to the specific embodiments described. Obviously, many modifications and variations of the present application can be made in light of the teachings above. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical application of the present application, so that those skilled in the art can well understand and utilize the present application. The present application is limited only by the claims and their full scope and equivalents.

Claims

1. A communication transceiving method of adaptive frequency hopping filtering, characterized by, The method comprises the following steps: S1: Collect and store channel state information for channel quality assessment and interference behavior prediction by continuously monitoring the interference level, signal-to-noise ratio and spectral timing characteristics of the current communication channel; S2: Based on the obtained channel state information, the current channel quality is evaluated, and the interference trend of the future frequency band is predicted using an interference source behavior prediction model, and a frequency hopping pattern sequence that avoids the current and potential interference area and the available channel is dynamically generated; S3: According to the selected frequency hopping pattern sequence, the transmitted data is encoded, encrypted and frequency hopping modulated, and the transmission power is dynamically adjusted in combination with the channel condition; S4: At the receiving end, based on the interference residual characteristics in the historical frequency hopping period, the interference distribution in the current period is predicted by a lightweight timing model, the adaptive filter parameters are pre-configured, and the real-time optimization is performed in combination with the least mean square algorithm; S5: The deterministic characteristics of the implicit pilot signal embedded in the data stream and the chaotic frequency hopping sequence are used for blind synchronization of the transmitting and receiving ends through joint detection and parameter estimation, and the filtered signal is demodulated, decrypted and error corrected.

2. A communication transceiving system with adaptive frequency hopping filtering according to the communication transceiving method with adaptive frequency hopping filtering according to claim 1, characterized in that, The method comprises an intelligent spectrum sensing unit (1), a dynamic decision and waveform generation unit (2), an adaptive transmitting unit (3), an intelligent anti-interference receiving unit (4), a blind synchronization and signal processing unit (5), wherein: The intelligent spectrum sensing unit (1) is used for continuously monitoring the interference level, signal-to-noise ratio and spectral timing characteristics of the communication channel, collecting and storing channel state information; The dynamic decision and waveform generation unit (2) is used for evaluating the channel quality based on the channel state information, and predicting the future interference trend using an interference source behavior prediction model, and dynamically generating a frequency hopping pattern sequence; The adaptive transmitting unit (3) is used for encoding, encrypting and frequency hopping modulating the transmitted data according to the frequency hopping pattern sequence, and dynamically adjusting the transmission power in combination with the channel condition; The intelligent anti-interference receiving unit (4) is used for predicting the current interference distribution based on the historical interference residual characteristics, pre-configuring the adaptive filter parameters, and performing real-time optimization in combination with the least mean square algorithm, suppressing the interference and extracting the effective signal; The blind synchronization and signal processing unit (5) is used for utilizing the characteristics of the implicit pilot signal and the chaotic frequency hopping sequence to perform blind synchronization through joint detection and parameter estimation, and demodulating, decrypting and error correcting the signal.

3. The self-adapting frequency hopping filtering transceiver system according to claim 2, wherein, The intelligent spectrum sensing unit (1) comprises a multi-dimensional signal acquisition module (11), a data preprocessing and storage module (12), and a feature extraction module (13), wherein: The multi-dimensional signal acquisition module (11) is used for real-time acquisition of the original signals of the interference level, signal-to-noise ratio and spectral timing characteristics of the channel; The data preprocessing and storage module (12) is used for noise reduction and normalization processing of the acquired original signals, and storing them as structured channel state information; The feature extraction module (13) is used for extracting key feature parameters for channel quality assessment and interference prediction from the preprocessed data.

4. The self-adapting frequency-hopping filtering transceiver system of claim 2, wherein, The dynamic decision and waveform generation unit (2) comprises a channel quality assessment module (21), an interference trend prediction module (22) and a pattern generation module (23), wherein: The channel quality evaluation module (21) quantitatively evaluates the communication capability of the current channel based on channel state information; The interference trend prediction module (22) is configured to analyze historical data by using an interference source behavior prediction model to predict the interference distribution trend of the future frequency band; The pattern generation module (23) is configured to comprehensively evaluate the quality and prediction results to dynamically generate a frequency hopping pattern sequence for avoiding interference and channel.

5. The self-adapting frequency-hopping filtering communication transceiver system of claim 4, wherein, The interference trend prediction module (22) analyzes historical data by using an interference source behavior prediction model to predict the interference distribution trend of the future frequency band, and the specific operation is as follows: A1: Normalize and time sequence align the historical interference characteristic data; A2: Input the processed data into the interference source behavior prediction model to output the frequency band interference probability of the future N frequency hopping periods; A3: Combine the current channel quality evaluation result to weight and correct the prediction probability to obtain the final interference distribution trend, and the weight correction formula is as follows: ， wherein, "future interference probability of frequency hopping period t, frequency band j" output by the interference source behavior prediction model, channel quality coefficient output by the current channel quality assessment module (21), "actual interference probability of frequency hopping period (t-1), frequency band j", weighting coefficient of historical measured value, final interference probability after weighting correction.

6. The self-adapting frequency-hopping filtering transceiver system according to claim 2, wherein, The adaptive transmitting unit (3) includes a source coding and encryption module (31), a frequency hopping modulation module (32), and a power adaptive adjustment module (33), wherein: The source coding and encryption module (31) is configured to perform error correction coding and encryption processing on the sending data; The frequency hopping modulation module (32) is configured to modulate the coded data to the corresponding frequency band according to the frequency hopping pattern sequence; The power adaptive adjustment module (33) is configured to dynamically adjust the transmitting power in combination with the real-time channel condition to balance the communication quality and energy consumption.

7. The self-adapting frequency-hopping filtering transceiver system of claim 2, wherein, The intelligent anti-interference receiving unit (4) includes an interference characteristic memory module (41), an interference prediction and parameter pre-configuration module (42), and a filter optimization module (43), wherein: The interference characteristic memory module (41) is configured to store and update the interference residual characteristic data in the historical frequency hopping period; The interference prediction and parameter pre-configuration module (42) is configured to predict the current period interference distribution by using a light time sequence model and pre-configure the filter initial parameters; The filter optimization module (43) is configured to run the least mean square algorithm to optimize the filter parameters in real time to suppress the interference and extract the effective signal.

8. The self-adapting frequency-hopping filtering transceiver system of claim 7, wherein, The interference prediction and parameter pre-configuration module (42) predicts the current period interference distribution by using a light time sequence model and pre-configure the filter initial parameters, and the specific operation is as follows: B1: Call the interference residual characteristic sequence of the last M frequency hopping periods from the interference characteristic memory module (41), and adopt Z-score standardization processing to eliminate the dimension difference; B2: input the standardized interference residual sequence into the compression GRU model, and output the interference power prediction value of each sub-band in the current frequency hopping period The calculation formula is: ， wherein, is the standardized historical interference residual feature, is the training parameter set of the light-weight model, and f is the sub-band frequency of the current period. B3: Establishing a "interference power prediction value - filter parameter mapping table" according to Match filter initial parameters: , preconfigured filter order , step factor ;​ If , pre-configure ; ③ If , pre-configure ; wherein, is a base step size factor, k is a step size adjustment factor, is a base step size factor, k is a step size adjustment factor, is a preset interference threshold value; B4: Send the pre-configured filter order and step factor initial parameters to the filter optimization module (43).

9. The self-adapting frequency-hopping filtering transceiver system of claim 2, wherein, The blind synchronization and signal processing unit (5) includes an implicit pilot detection module (51), a blind synchronization module (52), and a demodulation and error correction module (53), wherein: The implicit pilot detection module (51) is configured to extract the embedded implicit pilot signal from the received signal; The blind synchronization module (52) is configured to use the deterministic autocorrelation characteristics of the implicit pilot and the chaotic frequency hopping sequence to perform synchronization between the transmitting end and the receiving end through joint detection and parameter estimation; The demodulation and error correction module (53) is used for demodulating and decrypting the synchronized signal and recovering the original data through an error correction algorithm.

10. The self-adapting frequency-hopping filtering communication transceiver system of claim 9, wherein, The blind synchronization module (52) uses the determinacy of the implicit pilot and the chaotic frequency hopping sequence to perform the transceiver synchronization through joint detection and parameter estimation, and the specific operation is as follows: C1: extracting the embedded implicit pilot sequence from the received signal; C2: using the determinacy autocorrelation characteristics of the chaotic frequency hopping sequence to perform time and frequency coarse synchronization through matched filtering; C3: based on the coarse synchronization result, using maximum likelihood estimation to perform joint estimation on the frequency offset and time delay parameters to complete the transceiver synchronization.

Images