Communication and navigation integrated signal design method and device based on artificial intelligence

Abstract

The present invention discloses a communication and guidance integrated signal design method and device based on artificial intelligence, which relates to the field of signal processing, including: real-time acquisition of spectrum status data of the current electromagnetic environment and reception performance data of the broadcasted communication and guidance integrated signal; judging whether the deviation between the current spectrum status data and the spectrum status data obtained at the last acquisition moment is greater than a preset state deviation threshold, and whether the reception performance data is within the preset performance requirement range; if the deviation is not greater than the threshold, and the reception performance data is within the range, the communication and guidance integrated signal is generated using the current integrated signal parameters; if the deviation is greater than the threshold or the reception performance data is not within the range, the communication and guidance integrated signal model is determined, the integrated signal parameters are updated using a pre-trained Q value model, and the communication and guidance integrated signal is generated using the updated parameters. The present invention can ensure that the generated communication and guidance integrated signal is always adapted to the current electromagnetic environment and has good reception performance.

Description

Technical Field

[0001] The present invention relates to the field of signal processing technology, and in particular to a communication and guidance integrated signal design method and device based on artificial intelligence. Background Art

[0002] With the increasing cooperation between communication and navigation systems, the integration of communication and navigation can not only reduce the cost of duplicate system construction, but also further improve communication capacity and navigation reliability. Therefore, it has become a hot spot for development in the field of communication and navigation.

[0003] For the design of integrated communication and navigation signals, the current main methods used are time domain sharing or frequency sharing, time division, frequency division and power division to integrate communication and navigation signals. The existing integrated communication and navigation signals mainly include Iridium system satellite time position (STL) signal, time division code orthogonal frequency division multiplexing (TC-OFDM) signal, frequency domain multiplexing OFDM signal, mobile communication positioning reference (PRS) signal, orthogonal time-frequency space modulation (OTFS) signal and ultra-wideband (UWB) signal.

[0004] However, in actual application, since the existing integrated communication and navigation signals fuse communication and navigation signals based on frequency domain sharing or time domain sharing, the fusion method of communication and navigation signals is fixed and can only adapt to specific scenarios. It does not have rapid adaptability to new environments and has poor adaptability. When the use environment is a time-varying and complex electromagnetic environment, it is difficult to apply. Summary of the invention

[0005] In order to solve some or all of the technical problems existing in the above-mentioned prior art, the present invention provides a communication and conduction integrated signal design method and device based on artificial intelligence.

[0006] The technical solution of the present invention is as follows:

[0007] In a first aspect, a communication and guidance integrated signal design method based on artificial intelligence is provided, the method comprising:

[0008] Acquire the spectrum status data of the current electromagnetic environment in real time, and if there is a broadcasted integrated communication and navigation signal, further acquire the reception performance data of the broadcasted integrated communication and navigation signal;

[0009] Determine whether the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition time is greater than a preset state deviation threshold, and if there is reception performance data, determine whether the reception performance data is within a preset performance requirement range;

[0010] If the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition time is not greater than the preset state deviation threshold, and if the reception performance data exists, the reception performance data is within the preset performance requirement range, then the current integrated signal parameters are used to generate the communication and conduction integrated signal;

[0011] If the deviation between the spectrum status data of the current electromagnetic environment and the spectrum status data obtained at the last acquisition moment is greater than the preset state deviation threshold or the receiving performance data is not within the preset performance requirement range, the communication and navigation task mode is determined according to the spectrum status data of the current electromagnetic environment, and the communication and navigation integrated signal model is determined according to the communication and navigation task mode and the current spectrum status data. The communication and navigation integrated signal model is used as input, and the pre-trained Q value model is used to update the integrated signal parameters. The communication and navigation integrated signal is generated using the communication and navigation integrated signal model and the updated integrated signal parameters.

[0012] In some optional implementations, the communication and navigation task modes include: communication priority mode, navigation priority mode, and communication and navigation balance mode.

[0013] In some optional implementations, a pre-trained Bayesian inference model or a neural network model is used to determine the communication and conduction task mode corresponding to the spectrum state data of the current electromagnetic environment.

[0014] In some optional embodiments, the Bayesian reasoning model or the neural network model is trained in the following manner:

[0015] Acquire a training sample set, the training sample including spectrum state data and its corresponding communication and navigation task mode;

[0016] The spectrum state data in the training samples in the training sample set is taken as input, and the communication and guidance task mode corresponding to the input spectrum state data is taken as output to train the Bayesian reasoning model or the neural network model.

[0017] In some optional implementations, the communication-conduction integrated signal model expression is:

[0018] ;

[0019] in, represents the integrated signal model of conduction and communication. Indicates the integrated signal parameters, which are the parameters to be optimized. , represents the signal amplitude, represents the amplitude-phase coding model, Indicates the duration of the signal. represents the signal frequency, Indicates the signal direction angle, Represents a variable, represents a space vector, represents the natural exponential function, represents the imaginary unit, represents the time variable, Represents a rectangular window function.

[0020] In some optional embodiments, the Q value model is trained in the following manner:

[0021] Step 411, initializing the Q value model;

[0022] Step 412, set the iteration number variable eps=1;

[0023] Step 413, selecting a specified state and setting the specified state as the current state, wherein the state is defined according to the communication and conduction integrated signal model;

[0024] Step 414, according to the current state, select an action using the ε-greedy strategy, wherein the action is defined as the selected integrated signal parameter value, and the action space is defined as the value space of the integrated signal parameter;

[0025] Step 415, according to the selected action, obtain the next state and the corresponding action reward, wherein the action reward is obtained by solving the reward function;

[0026] Step 416, based on the current state, the selected action, the next state and the action reward, update the Q value model using the Bellman equation;

[0027] Step 417, taking the next state obtained as the current state, returning to step 414, and executing step 418 after reaching the target state;

[0028] Step 418, determine whether eps is greater than the preset maximum number of iterations, if so, output the updated Q value model, if not, increase the value of eps by 1 and return to step 413.

[0029] In some optional implementations, the state function is expressed as:

[0030] ;

[0031] in, Indicates the status, It represents the fusion gain obtained by executing the intelligent algorithm of the integrated signal model of communication and guidance;

[0032] The action reward function is expressed as:

[0033] ;

[0034] represents the action reward, It indicates the minimum fusion gain that can be obtained when the integrated signal model satisfies the communication task. When the constraints of the communication task optimization problem are not met, the reward value is ;

[0035] The constraints are expressed as:

[0036] ;

[0037] Indicates the signal transmission power corresponding to the integrated communication and conduction signal. Indicates the maximum signal transmission power, represents the signal transmission bandwidth, Indicates the minimum value of the signal transmission bandwidth, Indicates the maximum value of the signal transmission bandwidth, Indicates the ranging accuracy, Indicates the maximum value of ranging accuracy, represents the number of beams, represents the maximum number of beams, Indicates the communication rate, Indicates the minimum value of the communication rate;

[0038] Fusion Gain It is expressed as:

[0039] ;

[0040] Indicates the maximum value of the communication rate. represents the bit error rate, Indicates the maximum value of the bit error rate, Indicates the landing power, Indicates the maximum value of landing power, represents the spectrum utilization rate, Indicates the maximum value of spectrum utilization, represents the geometric dilution of precision, Indicates the maximum value of the geometric precision dilution, represents the quality factor, represents the maximum value of the quality factor, represents the computational effort of signal optimization calculation, Indicates the maximum value of the calculation amount of signal optimization calculation, represents the dimension of the parameter to be optimized, Indicates the number of dimensions to be optimized, Represents reliability, represents the maximum value of reliability, Indicates availability, represents the maximum value of availability, , , , , , , , , and Represents the weight coefficient.

[0041] In a second aspect, a communication and guidance integrated signal design device based on artificial intelligence is also provided, the device comprising:

[0042] A data acquisition unit, used to acquire spectrum status data of the current electromagnetic environment in real time, and if there is a broadcasted communication and guidance integrated signal, further acquire reception performance data of the broadcasted communication and guidance integrated signal;

[0043] A data judgment unit is used to judge whether the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition time is greater than a preset state deviation threshold, and if there is reception performance data, whether the reception performance data is within a preset performance requirement range;

[0044] The communication and conducting integrated signal processing unit is connected to the data acquisition unit and the data judgment unit respectively, and is used to generate a communication and conducting integrated signal using the current integrated signal parameters when the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the previous acquisition moment is not greater than a preset state deviation threshold, and the existing receiving performance data is within the preset performance requirement range; and is used to determine the communication and conducting task mode according to the spectrum state data of the current electromagnetic environment when the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the previous acquisition moment is greater than the preset state deviation threshold or the receiving performance data is not within the preset performance requirement range, determine the communication and conducting integrated signal model according to the communication and conducting task mode and the current spectrum state data, take the communication and conducting integrated signal model as input, use the Q value model to update the integrated signal parameters, and use the communication and conducting integrated signal model and the updated integrated signal parameters to generate the communication and conducting integrated signal.

[0045] The main advantages of the technical solution of the present invention are as follows:

[0046] The artificial intelligence-based communication and conducting integrated signal design method and device of the present invention monitors the spectrum information of the electromagnetic environment and the reception performance results of the broadcasted signals in real time, and based on the spectrum information and the reception performance results, uses reinforcement learning to update and optimize the integrated signal parameters to update the subsequently generated communication and conducting integrated signals. This can ensure that the generated communication and conducting integrated signals are always adapted to the current electromagnetic environment and have good reception performance, and can be applicable to time-varying complex electromagnetic environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The drawings described herein are used to provide a further understanding of the embodiments of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0048] Figure 1 A flow chart of a communication and conduction integrated signal design method based on artificial intelligence provided by an embodiment of the present invention;

[0049] Figure 2 A structural block diagram of an artificial intelligence-based communication and conduction integrated signal design device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0051] The technical solution provided by the embodiments of the present invention is described in detail below with reference to the accompanying drawings.

[0052] refer to Figure 1 In a first aspect, an embodiment of the present invention provides a communication and conduction integrated signal design method based on artificial intelligence, the method comprising the following steps 1 to 4:

[0053] Step 1, obtaining spectrum status data of the current electromagnetic environment in real time, and if there is a broadcasted communication and guidance integrated signal, further obtaining reception performance data of the broadcasted communication and guidance integrated signal;

[0054] In the embodiment of the present invention, the electromagnetic environment is monitored in real time to obtain spectrum status data of the electromagnetic environment, wherein the monitoring cycle or monitoring time interval of the electromagnetic environment is set according to actual needs.

[0055] In the embodiment of the present invention, the spectrum status includes whether there are gaps and abnormal interference, and the conditions of the gaps and abnormal interference.

[0056] It should be noted that if there is no currently broadcasted communication and guidance integrated signal, there is no need to obtain the reception performance data of the communication and guidance integrated signal.

[0057] Step 2: determine whether the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition time is greater than a preset state deviation threshold, and if there is reception performance data, determine whether the reception performance data is within a preset performance requirement range;

[0058] In the embodiment of the present invention, the preset state deviation threshold is set according to actual conditions, specifically according to the state type included in the actually set spectrum state data, and the preset performance requirement range is set according to actual signal performance requirements.

[0059] It should be noted that if the reception performance data of the integrated communication and guidance signal is not currently obtained, there is no need to determine whether the reception performance data is within the preset performance requirement range.

[0060] Step 3: If the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition time is not greater than a preset state deviation threshold, and if the reception performance data exists, the reception performance data is within a preset performance requirement range, then the current integrated signal parameters are used to generate a communication and conduction integrated signal;

[0061] In an embodiment of the present invention, in the absence of reception performance data, if the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition moment is not greater than a preset state deviation threshold, the current communication and conduction integrated signal model and integrated signal parameters are used to generate a communication and conduction integrated signal; in the presence of reception performance data, if the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition moment is not greater than the preset state deviation threshold, and the reception performance data is within the preset performance requirement range, the current communication and conduction integrated signal model and integrated signal parameters are used to generate a communication and conduction integrated signal.

[0062] Step 4: If the deviation between the spectrum status data of the current electromagnetic environment and the spectrum status data obtained at the last acquisition moment is greater than a preset state deviation threshold or the receiving performance data is not within the preset performance requirement range, the communication and navigation task mode is determined according to the spectrum status data of the current electromagnetic environment, and a communication and navigation integrated signal model is determined according to the communication and navigation task mode and the current spectrum status data. The communication and navigation integrated signal model is used as input, and the integrated signal parameters are updated using a pre-trained Q value model. The communication and navigation integrated signal is generated using the communication and navigation integrated signal model and the updated integrated signal parameters.

[0063] In an embodiment of the present invention, the Q-value model is pre-trained using a reinforcement learning algorithm.

[0064] In the embodiment of the present invention, the communication and navigation task mode is specifically set according to actual needs.

[0065] In the embodiment of the present invention, the communication and navigation task modes specifically include: a communication priority mode, a navigation priority mode, and a communication and navigation balance mode.

[0066] In an embodiment of the present invention, the corresponding communication and navigation task mode can be determined by manual judgment based on the spectrum status data of the current electromagnetic environment, or a pre-trained Bayesian reasoning model or a neural network model can be used to determine the communication and navigation task mode corresponding to the spectrum status data of the current electromagnetic environment. Specifically, the spectrum status data of the current electromagnetic environment is input into the pre-trained Bayesian reasoning model or the neural network model to obtain the communication and navigation task mode output by the Bayesian reasoning model or the neural network model.

[0067] The artificial intelligence-based communication and conducting integrated signal design method provided in the embodiment of the present invention monitors the spectrum information of the electromagnetic environment and the reception performance results of the broadcasted signals in real time, and based on the spectrum information and the reception performance results, uses a reinforcement learning method to update and optimize the integrated signal parameters to update the subsequently generated communication and conducting integrated signal. This can ensure that the generated communication and conducting integrated signal is always adapted to the current electromagnetic environment and has good reception performance, and can be applicable to time-varying complex electromagnetic environments.

[0068] Furthermore, in an optional implementation of the embodiment of the present invention, the Bayesian reasoning model or the neural network model is trained in the following manner:

[0069] Acquire a training sample set, the training sample including spectrum state data and its corresponding communication and navigation task mode;

[0070] The spectrum state data in the training samples in the training sample set is taken as input, and the communication and guidance task mode corresponding to the input spectrum state data is taken as output to train the Bayesian reasoning model or the neural network model.

[0071] Specifically, in an embodiment of the present invention, the spectrum state data in the training samples in the training sample set is used as input, and the communication and guidance task mode corresponding to the input spectrum state data is used as output to train the Bayesian reasoning model or the neural network model, further comprising the following steps:

[0072] Step 401, inputting the spectrum state data in all training samples into the Bayesian inference model or the neural network model in batches, and obtaining the communication and navigation task mode corresponding to the spectrum state data output by the Bayesian inference model or the neural network model;

[0073] In an embodiment of the present invention, the spectral state data in the training sample is input from the input end of the Bayesian reasoning model or the neural network model, processed by each layer in the Bayesian reasoning model or the neural network model in sequence, and output from the output end of the Bayesian reasoning model or the neural network model. The information output by the Bayesian reasoning model or the neural network model is the communication and guidance task mode corresponding to the spectral state data.

[0074] In the embodiment of the present invention, the Bayesian reasoning model or the neural network model is the model to be trained, and the model parameters are the initialization parameters. During the training process of the model, the model parameters are continuously updated and learned.

[0075] Step 402, calculating a loss function according to the communication and guidance task mode corresponding to the spectrum state data in the training sample and the communication and guidance task mode output by the Bayesian reasoning model or the neural network model;

[0076] In an embodiment of the present invention, based on a pre-set loss function, the loss function is calculated according to the communication and guidance task mode corresponding to the spectral state data in each training sample input into the Bayesian reasoning model or the neural network model and the communication and guidance task mode output by the Bayesian reasoning model or the neural network model corresponding to the spectral state data.

[0077] In the embodiment of the present invention, the specific type of the loss function is set according to the actual situation, for example, a cross entropy loss function.

[0078] Step 403, determine whether the preset training stop condition is reached. If so, use the current Bayesian inference model or neural network model as the Bayesian inference model or neural network model to complete the training. If not, use the loss function to update the parameters of the Bayesian inference model or neural network model, and return to step 401.

[0079] In the embodiment of the present invention, the training stop condition is specifically set according to the actual situation, for example, the number of training iterations reaches a set number of iterations.

[0080] Furthermore, in an embodiment of the present invention, a stochastic gradient descent method is used to train and update the parameters of a Bayesian inference model or a neural network model.

[0081] Further, in an optional implementation of the embodiment of the present invention, the communication-conduction integrated signal model expression is:

[0082] ;

[0083] in, represents the integrated signal model of conduction and communication. Indicates the integrated signal parameters, which are the parameters to be optimized. , represents the signal amplitude, represents the amplitude-phase coding model, Indicates the duration of the signal. represents the signal frequency, Indicates the signal direction angle, Represents a variable, represents a space vector, represents the natural exponential function, represents the imaginary unit, represents the time variable, Represents a rectangular window function.

[0084] In an embodiment of the present invention, the amplitude and phase coding model is determined based on the modulation method of the integrated communication and conducting signal, wherein the modulation method of the integrated communication and conducting signal includes but is not limited to: Orthogonal Frequency Division Multiplexing (OFDM), Binary Phase Shift Keying (BPSK), Linear Frequency Modulation (LFM), Continuous Phase Modulation (CPM), and Frequency Hopping Spread Spectrum (FHSS).

[0085] In an embodiment of the present invention, the modulation mode of the integrated communication and navigation signal is determined according to the communication and navigation task mode. For example, for the communication priority mode, the modulation mode is: mainly OFDM modulation, interspersed with BPSK, LFM, CPM, and FHSS modulation modes according to the needs of the scene; for the navigation priority mode, the modulation mode is: mainly BPSK modulation, interspersed with LFM, CPM, and FHSS modulation modes according to the needs of the scene; for the communication and navigation balance mode, the modulation mode is: OFDM and BPSK modulation share time and frequency resources, interspersed with LFM, CPM, and FHSS modulation modes according to the needs of the scene.

[0086] Furthermore, in the embodiment of the present invention, the amplitude-phase coding model is determined based on the modulation mode of the integrated communication and conduction signal. For example, when the modulation mode is OFDM modulation, the amplitude-phase coding model expression is:

[0087] ;

[0088] in, Indicates the OFDM signal coding information, and is a variable, represents the OFDM signal sub-algebra, Indicates the number of OFDM signal symbols, represents the natural exponential function, represents the imaginary unit, represents the subcarrier frequency, represents the time variable, represents the sampling interval, and the duration of a symbol is ;

[0089] When the modulation mode is BPSK modulation, the amplitude and phase coding model expression is:

[0090] ;

[0091] in, Indicates BPSK signal encoding information, is a variable, represents the number of modulation symbols, represents the rectangular window function, represents the time variable, Represents the sampling interval, the duration is ;

[0092] When the modulation mode is LFM modulation, the amplitude and phase coding model expression is:

[0093] ;

[0094] in, represents the natural exponential function, represents the imaginary unit, represents the frequency modulation slope, , represents the frequency modulation bandwidth, Indicates duration, represents the time variable, represents the signal frequency, represents the initial phase, represents a rectangular window function;

[0095] When the modulation mode is CPM modulation, the amplitude and phase coding model expression is:

[0096] ;

[0097] in, represents the natural exponential function, represents the imaginary unit, Represents a variable, represents the number of modulation symbols, represents the rectangular window function, represents the time variable, represents the sampling interval, Indicates the CPM symbol phase information, Indicates the CPM signal to be modulated code information, represents the initial phase, and the duration is ;

[0098] When the modulation mode is FHSS modulation, the amplitude and phase coding model expression is:

[0099] ;

[0100] in, Indicates the number of FM signal hops. Represents a variable, Indicates that frequency hopping signals transmit data. represents the natural exponential function, represents the imaginary unit, and Indicates the frequency hopping signal Hopping carrier frequency and phase, represents the time variable, Indicates the first transition moment of the signal. Indicates the time interval between two adjacent signal transition moments. The transition time is , Indicates the width is The rectangular window Indicates duration.

[0101] Further, in an optional implementation of the embodiment of the present invention, the Q value model is trained through the following steps 411 to 418:

[0102] Step 411, initializing the Q value model;

[0103] In the embodiment of the present invention, the Q value model is initialized and set according to actual conditions.

[0104] Step 412, set the iteration number variable eps=1;

[0105] Step 413, selecting a specified state and setting the specified state as the current state;

[0106] In the embodiment of the present invention, the state is defined according to the communication-conduction integrated signal model.

[0107] Step 414, select an action using the ε-greedy strategy according to the current state;

[0108] In the embodiment of the present invention, the action is defined as the selected integrated signal parameter value, and the action space is defined as the value space of the integrated signal parameter.

[0109] In the embodiment of the present invention, the value space of the integrated signal parameter is specifically determined according to actual conditions.

[0110] In order to ensure the executability of the selected action, the value space of the integrated signal parameter is determined under the following constraints:

[0111] ;

[0112] in, Indicates the signal transmission power corresponding to the integrated communication and conduction signal. Indicates the maximum signal transmission power, represents the signal transmission bandwidth, Indicates the minimum value of the signal transmission bandwidth, Indicates the maximum value of the signal transmission bandwidth, Indicates the ranging accuracy, Indicates the maximum value of ranging accuracy, represents the number of beams, represents the maximum number of beams, Indicates the communication rate, Indicates the minimum value of the communication rate;

[0113] In the embodiment of the present invention, the maximum and minimum indexes of the above-mentioned parameters are pre-set according to the actual situation of the signal transceiver object and the spectrum status data of the actual electromagnetic environment.

[0114] In the embodiment of the present invention, the ε-greedy strategy is a random strategy that balances exploration and exploitation. Some actions with the highest Q value are selected with the same probability, while other actions are selected with the same probability. The exploration rate is in the range of 0 to 1. The ε-greedy strategy is specifically defined as:

[0115] ;

[0116] in, Indicates the selected action. Indicates that the Q value The action corresponding to the maximum value , Indicates the status, Represents a normally distributed random number generated. .

[0117] Step 415, according to the selected action, obtain the next state and the corresponding action reward;

[0118] In the embodiment of the present invention, the action reward is obtained by solving a pre-constructed action reward function according to the selected action.

[0119] In an embodiment of the present invention, the action reward function is constructed based on communication and navigation performance indicators, power, and bandwidth constraints.

[0120] In the embodiment of the present invention, the state function is expressed as:

[0121] ;

[0122] in, Indicates the status, It represents the fusion gain obtained by executing the intelligent algorithm of the integrated signal model. represents the integrated signal model of conduction and communication. Indicates integrated signal parameters.

[0123] In this embodiment of the present invention, the action reward function is expressed as:

[0124] ;

[0125] in, represents the action reward, It represents the fusion gain obtained by executing the intelligent algorithm of the integrated signal model. It indicates the minimum fusion gain that can be obtained when the integrated signal model satisfies the communication task. When the constraints of the communication task optimization problem are not met, the reward value is , in order to play the role of "punishment".

[0126] In the embodiment of the present invention, the fusion gain It is expressed as:

[0127] ;

[0128] in, Indicates the integrated signal parameters, Indicates the communication rate, Indicates the maximum value of the communication rate. represents the bit error rate, Indicates the maximum value of the bit error rate, Indicates the landing power, Indicates the maximum value of landing power, represents the spectrum utilization rate, Indicates the maximum value of spectrum utilization, Indicates the ranging accuracy, Indicates the maximum value of ranging accuracy, represents the geometric dilution of precision, Indicates the maximum value of the geometric precision dilution, represents the quality factor, represents the maximum value of the quality factor, represents the computational effort of signal optimization calculation, Indicates the maximum value of the calculation amount of signal optimization calculation, represents the dimension of the parameter to be optimized, Indicates the number of dimensions to be optimized, Represents reliability, represents the maximum value of reliability, Indicates availability, represents the maximum value of availability, , , , , , , , , and Represents the weight coefficient.

[0129] In the embodiment of the present invention, the maximum value index of each parameter mentioned above and each weight coefficient are pre-set according to the actual situation of the signal transceiver object and the spectrum status data of the actual electromagnetic environment.

[0130] Furthermore, in the embodiment of the present invention, the communication rate Determined using the following formula:

[0131] ;

[0132] in, represents the number of beams, Indicates The receiving user attenuation coefficient is Indicates The signal-to-noise ratio of the receiving user is Indicates the number of receiving users.

[0133] Bit Error Rate Determined using the following formula:

[0134] ;

[0135] in, represents the number of beams, represents the code element energy, represents the one-sided noise power spectral density, represents a natural constant, Indicates a base number. and Represents a variable.

[0136] Landing power Determined using the following formula:

[0137] ;

[0138] in, Indicates the signal transmission power corresponding to the integrated communication and conduction signal. represents the antenna transmission gain, Indicates the antenna receiving gain, Indicates the transmission distance. Indicates the number of beams.

[0139] Spectrum Utilization Determined using the following formula:

[0140] ;

[0141] in, represents the information rate, Indicates the signal transmission bandwidth.

[0142] Distance measurement accuracy Determined using the following formula:

[0143] ;

[0144] in, represents the signal energy, represents the white noise power spectral density, represents the power spectral density function of the signal, Indicates the signal frequency.

[0145] Quality Factor Determined using the following formula:

[0146] ;

[0147] in, represents the signal spreading code rate, represents the interference signal power spectral density, represents the power spectral density function of the signal, Indicates the signal frequency.

[0148] Reliability Determined using the following formula:

[0149] ;

[0150] in, Indicates the total number of signal failures within a specified time period. Indicates the duration of the specified time period.

[0151] Availability Determined using the following formula:

[0152] ;

[0153] in, It indicates the mean time between failures during signal transmission and reception. Indicates the average repair time during signal transmission and reception.

[0154] Step 416, based on the current state, the selected action, the next state and the action reward, update the Q value model using the Bellman equation;

[0155] In the embodiment of the present invention, the Bellman equation is expressed as:

[0156] ;

[0157] in, represents the Q-value model, Indicates the status, Indicates the selected action. represents the learning rate, represents the action reward, represents the discount factor, Indicates the next state The maximum Q value obtained under Indicates the next state Select the action you want to take.

[0158] In this embodiment of the present invention, the learning rate and discount factor According to the actual situation, the learning rate and discount factor are set to meet the following requirements: , .

[0159] Step 417, taking the next state obtained as the current state, returning to step 414, and executing step 418 after reaching the target state;

[0160] In the embodiment of the present invention, if the next state obtained is not the target state, the next state obtained is used as the current state, and the process returns to step 414 to continue executing the corresponding steps; if the next state obtained is the target state, step 418 is executed.

[0161] Step 418, determine whether eps is greater than the preset maximum number of iterations, if so, output the updated Q value model, if not, increase the value of eps by 1 and return to step 413.

[0162] In an embodiment of the present invention, if the iteration number variable eps is greater than the preset maximum iteration number, the loop iteration is terminated and the Q value model obtained by the last update is used as the final Q value model; if the iteration number variable eps is not greater than the preset maximum iteration number, based on the updated Q value model, return to step 413 to continue executing the corresponding steps to perform loop iteration.

[0163] The maximum number of iterations is set according to actual conditions.

[0164] Further, in the embodiment of the present invention, in step 4, the integrated signal model is used as input, the integrated signal parameters are updated using the pre-trained Q value model, and the integrated signal model and the updated integrated signal parameters are used to generate the integrated signal, including:

[0165] Based on the determined communication-conducting integrated signal model and the trained Q value model, the maximum Q value under the communication-conducting integrated signal model and the integrated signal parameters corresponding to the maximum Q value are determined, the integrated signal parameters corresponding to the maximum Q value are used as the updated integrated signal parameters, and the communication-conducting integrated signal is generated based on the determined communication-conducting integrated signal model and the updated integrated signal parameters.

[0166] The artificial intelligence-based communication and conducting integrated signal design method provided in the embodiment of the present invention monitors the spectrum information of the electromagnetic environment and the reception performance results of the broadcasted signals in real time, and based on the spectrum information and the reception performance results, uses a reinforcement learning method to update and optimize the integrated signal parameters to update the subsequently generated communication and conducting integrated signal. This can ensure that the generated communication and conducting integrated signal is always adapted to the current electromagnetic environment and has good reception performance, and can be applicable to time-varying complex electromagnetic environments.

[0167] refer to Figure 2 In a second aspect, an embodiment of the present invention further provides a communication and guidance integrated signal design device based on artificial intelligence, the device comprising:

[0168] The data acquisition unit 100 is used to acquire spectrum status data of the current electromagnetic environment in real time, and if there is a broadcasted communication and guidance integrated signal, further acquire reception performance data of the broadcasted communication and guidance integrated signal;

[0169] The data judgment unit 200 is used to judge whether the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition time is greater than a preset state deviation threshold, and if there is reception performance data, whether the reception performance data is within a preset performance requirement range;

[0170] The communication and conducting integrated signal processing unit 300 is connected to the data acquisition unit 100 and the data judgment unit 200, respectively, and is used to generate a communication and conducting integrated signal using the current integrated signal parameters when the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the previous acquisition moment is not greater than a preset state deviation threshold, and the existing receiving performance data is within the preset performance requirement range; and is used to determine the communication and conducting task mode according to the spectrum state data of the current electromagnetic environment when the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the previous acquisition moment is greater than the preset state deviation threshold or the receiving performance data is not within the preset performance requirement range, determine the communication and conducting integrated signal model according to the communication and conducting task mode and the current spectrum state data, use the communication and conducting integrated signal model as input, use the Q value model to update the integrated signal parameters, and use the communication and conducting integrated signal model and the updated integrated signal parameters to generate the communication and conducting integrated signal.

[0171] The above-mentioned units are hardware structures corresponding to the steps of the above-mentioned method. The specific working principle of each unit and its beneficial effects can be found in the above-mentioned method, which will not be repeated here.

[0172] The artificial intelligence-based communication and conducting integrated signal design method and device provided in the embodiments of the present invention monitor the spectrum information of the electromagnetic environment and the reception performance results of the broadcasted signals in real time, and based on the spectrum information and the reception performance results, use the reinforcement learning method to update and optimize the integrated signal parameters to update the subsequently generated communication and conducting integrated signal. This can ensure that the generated communication and conducting integrated signal is always adapted to the current electromagnetic environment and has good reception performance, and can be applicable to time-varying complex electromagnetic environments.

[0173] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0174] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A communication and guidance integrated signal design method based on artificial intelligence, characterized in that: The method comprises: Acquire the spectrum status data of the current electromagnetic environment in real time, and if there is a broadcasted integrated communication and navigation signal, further acquire the reception performance data of the broadcasted integrated communication and navigation signal; Determine whether the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition time is greater than a preset state deviation threshold, and if there is reception performance data, determine whether the reception performance data is within a preset performance requirement range; If the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition time is not greater than the preset state deviation threshold, and if the reception performance data exists, the reception performance data is within the preset performance requirement range, then the current integrated signal parameters are used to generate the communication and conduction integrated signal; If the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition moment is greater than a preset state deviation threshold or the receiving performance data is not within the preset performance requirement range, the communication and navigation task mode is determined according to the spectrum state data of the current electromagnetic environment, and a communication and navigation integrated signal model is determined according to the communication and navigation task mode and the current spectrum state data. The communication and navigation integrated signal model is used as input, and the integrated signal parameters are updated using a pre-trained Q value model. The communication and navigation integrated signal is generated using the communication and navigation integrated signal model and the updated integrated signal parameters, wherein the Q value model is pre-trained using a reinforcement learning algorithm.

2. The artificial intelligence-based integrated communication and conduction signal design method according to claim 1, characterized in that: The communication and navigation task modes include: communication priority mode, navigation priority mode, and communication and navigation balance mode.

3. The method for designing integrated communication and conduction signals based on artificial intelligence according to claim 1, characterized in that: A pre-trained Bayesian inference model or a neural network model is used to determine the communication and navigation task mode corresponding to the spectrum state data of the current electromagnetic environment.

4. The method for designing integrated communication and conduction signals based on artificial intelligence according to claim 3, characterized in that: The Bayesian inference model or the neural network model is trained in the following manner: Acquire a training sample set, the training sample including spectrum state data and its corresponding communication and navigation task mode; The spectrum state data in the training samples in the training sample set is taken as input, and the communication and guidance task mode corresponding to the input spectrum state data is taken as output to train the Bayesian reasoning model or the neural network model.

5. The artificial intelligence-based integrated communication and conduction signal design method according to claim 1, characterized in that: The communication-conduction integrated signal model expression is: ； in, represents the integrated signal model of conduction and communication. Indicates the integrated signal parameters, which are the parameters to be optimized. , represents the signal amplitude, represents the amplitude-phase coding model, Indicates the duration of the signal. represents the signal frequency, Indicates the signal direction angle, Represents a variable, represents a space vector, represents the natural exponential function, represents the imaginary unit, represents the time variable, Represents a rectangular window function.

6. The method for designing integrated communication and conduction signals based on artificial intelligence according to claim 5, characterized in that: The Q-value model is trained in the following way: Step 411, initializing the Q value model; Step 412, set the iteration number variable eps=1; Step 413, selecting a specified state and setting the specified state as the current state, wherein the state is defined according to the communication and conduction integrated signal model; Step 414, according to the current state, select an action using the ε-greedy strategy, wherein the action is defined as the selected integrated signal parameter value, and the action space is defined as the value space of the integrated signal parameter; Step 415, according to the selected action, obtain the next state and the corresponding action reward, wherein the action reward is obtained by solving the reward function; Step 416, based on the current state, the selected action, the next state and the action reward, update the Q value model using the Bellman equation; Step 417, taking the next state obtained as the current state, returning to step 414, and executing step 418 after reaching the target state; Step 418, determine whether eps is greater than the preset maximum number of iterations, if so, output the updated Q value model, if not, increase the value of eps by 1 and return to step 413.

7. The artificial intelligence-based integrated communication and conduction signal design method according to claim 6, characterized in that: The state function is expressed as: ； in, Indicates the status, It represents the fusion gain obtained by executing the intelligent algorithm of the integrated signal model of communication and guidance; The action reward function is expressed as: ； represents the action reward, It indicates the minimum fusion gain that can be obtained when the communication and guidance integrated signal model satisfies the communication and guidance task. When the constraints of the communication and guidance task optimization problem are not met, the reward value is ; The constraints are expressed as: ； Indicates the signal transmission power corresponding to the integrated communication and conduction signal. Indicates the maximum signal transmission power, represents the signal transmission bandwidth, Indicates the minimum value of the signal transmission bandwidth, Indicates the maximum value of the signal transmission bandwidth, Indicates the ranging accuracy, Indicates the maximum value of ranging accuracy, represents the number of beams, represents the maximum number of beams, Indicates the communication rate, Indicates the minimum value of the communication rate; Fusion Gain It is expressed as: ； Indicates the maximum value of the communication rate. represents the bit error rate, Indicates the maximum value of the bit error rate, Indicates the landing power, Indicates the maximum value of landing power, represents the spectrum utilization rate, Indicates the maximum value of spectrum utilization, represents the geometric dilution of precision, Indicates the maximum value of the geometric precision dilution, represents the quality factor, represents the maximum value of the quality factor, represents the computational effort of signal optimization calculation, Indicates the maximum value of the calculation amount of signal optimization calculation, represents the dimension of the parameter to be optimized, Indicates the number of dimensions to be optimized, Represents reliability, represents the maximum value of reliability, Indicates availability, represents the maximum value of availability, , , , , , , , , and Represents the weight coefficient.

8. An integrated communication and guidance signal design device based on artificial intelligence, characterized in that: The device comprises: A data acquisition unit, used to acquire spectrum status data of the current electromagnetic environment in real time, and if there is a broadcasted communication and guidance integrated signal, further acquire reception performance data of the broadcasted communication and guidance integrated signal; A data judgment unit is used to judge whether the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the last acquisition time is greater than a preset state deviation threshold, and if there is reception performance data, whether the reception performance data is within a preset performance requirement range; The communication and conducting integrated signal processing unit is connected to the data acquisition unit and the data judgment unit respectively, and is used to generate a communication and conducting integrated signal using the current integrated signal parameters when the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the previous acquisition moment is not greater than a preset state deviation threshold, and the existing receiving performance data is within the preset performance requirement range; and is used to determine the communication and conducting task mode according to the spectrum state data of the current electromagnetic environment when the deviation between the spectrum state data of the current electromagnetic environment and the spectrum state data obtained at the previous acquisition moment is greater than the preset state deviation threshold or the receiving performance data is not within the preset performance requirement range, determine the communication and conducting integrated signal model according to the communication and conducting task mode and the current spectrum state data, take the communication and conducting integrated signal model as input, use the Q value model to update the integrated signal parameters, and use the communication and conducting integrated signal model and the updated integrated signal parameters to generate the communication and conducting integrated signal.

Images