Intelligent adaptive underwater acoustic communication system

Abstract

The invention relates to the technical field of self-learning underwater acoustic communication, and provides an intelligent self-adaptive underwater acoustic communication system. The multi-system transmitter comprises a data transmitting unit used for transmitting communication data, a system switching unit used for switching a transmitting signal modulation mode, and a transmitting signal modulation unit used for modulating a signal. The intelligent multi-system receiver comprises a synchronization unit, a Doppler estimation and compensation unit, an intelligent modulation mode identification unit, a data processing unit, an intelligent signal interpretation unit and a digital demodulation unit. Wherein the channel information identification unit is used for identifying the signal-to-noise ratio and the channel maximum time delay of an underwater acoustic channel and transmitting the signal-to-noise ratio and the channel maximum time delay to the system switching unit, and the system switching unit adjusts and switches a transmitting signal modulation mode according to the signal-to-noise ratio and the channel maximum time delay. The intelligent modulation mode identification unit employs a lightweight neural network to intelligently identify a signal modulation mode of an underwater acoustic channel signal, and the intelligent signal interpretation unit employs a deep learning neural network to intelligently interpret an underwater acoustic communication signal so as to recover communication data.

Description

Technical Field

[0001] The present invention relates to the technical field of self-learning underwater acoustic communication, and in particular to an intelligent adaptive multi-standard underwater acoustic communication system. Background Art

[0002] In view of the limitations of optical communication and radio frequency communication in water, underwater acoustic communication is currently the only solution for underwater long-distance wireless communication and is an important part of marine information collection, transmission and processing. With the growing demand for long-term real-time observation of the ocean and large-scale dynamic observation, the demand for high-quality underwater acoustic communication technology is becoming increasingly urgent. However, the underwater acoustic channel is a wireless channel with much worse transmission conditions than the radio frequency wireless channel on land. There are large and time-varying transmission delays (the propagation speed of underwater acoustics is 5 orders of magnitude smaller than the propagation speed of radio frequency), complex environmental noise (additive noise and multiplicative noise), energy fading related to distance and frequency, strong multipath effects, strong Doppler frequency expansion, etc. Especially in complex application scenarios such as long-term real-time observation of marine information (such as real-time observation of engineering geological parameters during natural gas hydrate mining), underwater networking observation in complex environments (such as monitoring and protection of coral reef ecosystems), and underwater large-scale dynamic networking observation (such as underwater target detection based on dynamic networks, seabed resource exploration, etc.), the time-varying performance of the underwater acoustic channel and its impact are more prominent, and the realization of high-quality underwater acoustic communication technology faces greater challenges.

[0003] In the known prior art, the underwater acoustic signal of the underwater acoustic communication system adopts a single carrier mode, such as FSK, PSK, OFDM, etc. The system performance is limited by the worst underwater acoustic channel in complex application scenarios, which limits the application of the underwater acoustic communication system in complex application scenarios such as long-term real-time underwater observation, underwater networking observation in complex environments, and large-scale dynamic networking. It is difficult to meet the needs of high-quality underwater acoustic communication that fully utilizes the channel bandwidth, and it is necessary to develop channel adaptive underwater acoustic communication technology.

[0004] The channel adaptive underwater acoustic communication system can adjust the parameters of the underwater acoustic communication system according to the underwater acoustic channel of complex application scenarios. According to the signal modulation method of the underwater acoustic communication system, the channel adaptive underwater acoustic communication system is mainly divided into two categories, one is a single-mode multi-parameter adaptive underwater acoustic communication system using a single signal modulation method, and the other is a multi-mode adaptive underwater acoustic communication system using multiple signal modulation methods. The single-mode multi-parameter adaptive underwater acoustic communication system mainly adapts to the changes of the underwater acoustic channel by adjusting the baseband coding method, digital modulation method, etc., and is limited by the single signal modulation method. The channel adaptation range of the single-mode multi-parameter adaptive underwater acoustic communication system is limited. The multi-mode adaptive underwater acoustic communication system can adopt different signal modulation methods to adapt to the changes of the underwater acoustic channel, such as single carrier, multi-carrier, spread spectrum and their combination, etc., which can better adapt to the changes of the underwater acoustic channel to make full use of the bandwidth of the underwater acoustic channel. However, it is known that the receiver of the existing multi-mode adaptive underwater acoustic communication system adopts the channel estimation and signal channel equalization method based on the traditional signal processing technology. Limited by the channel estimation and channel equalization performance, the performance of the multi-mode adaptive underwater acoustic communication system based on the traditional signal processing technology is limited.

[0005] In response to the demand for improving the performance of underwater acoustic communication systems in complex time-varying underwater acoustic channels, intelligent underwater acoustic communication technologies based on machine learning and deep learning networks have emerged. However, it is known that the existing intelligent underwater acoustic communication technologies are based on a single signal modulation method, and there is still the problem of limited channel adaptability of the single signal modulation method. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent adaptive underwater acoustic communication system. Aiming at the high-quality underwater acoustic communication application requirements of complex time-varying underwater acoustic channels in complex underwater application scenarios, the limitations of existing underwater acoustic communication technologies are comprehensively considered and an intelligent adaptive multi-standard underwater acoustic communication system based on deep learning is proposed.

[0007] To achieve the above object, the technical solution adopted by the present invention is:

[0008] An intelligent adaptive underwater acoustic communication system, comprising:

[0009] The multi-standard transmitter includes a data transmission unit for transmitting communication data, a standard switching unit for switching the transmission signal modulation mode, and a transmission signal modulation unit for modulating the signal; the data transmission unit, the standard switching unit and the transmission signal modulation unit are connected in sequence; the output end of the multi-standard transmitter is connected to the underwater acoustic channel;

[0010] Intelligent multi-standard receiver: including a synchronization unit, a Doppler estimation and compensation unit, an intelligent modulation mode identification unit, a data processing unit, an intelligent signal interpretation unit and a digital demodulation unit; the synchronization unit receives the underwater acoustic communication signal passing through the underwater acoustic channel, and performs data frame synchronization processing on the underwater acoustic communication signal; the Doppler estimation and compensation unit receives the output data of the synchronization unit, estimates and compensates the Doppler frequency shift of the underwater acoustic channel; the intelligent modulation mode identification unit is connected to the signal output end of the Doppler estimation and compensation unit, and is used to intelligently identify the modulation mode of the underwater acoustic communication signal according to the bandpass underwater acoustic signal; the data processing unit is connected to the signal output end of the intelligent modulation mode identification unit; the intelligent signal interpretation unit is connected to the signal output end of the data processing unit and the output end of the intelligent modulation mode identification unit, and is used to perform intelligent signal interpretation on the underwater acoustic communication frequency domain signal after fast Fourier transform in combination with the identified modulation mode to obtain communication data; the digital demodulation unit is connected to the signal output end of the intelligent signal interpretation unit, and modulates the communication data to the data receiving unit;

[0011] Channel information identification unit: its input end is connected to the signal output end of the synchronization unit of the intelligent multi-standard receiver, and its output end is connected to the standard switching unit of the multi-standard transmitter;

[0012] Among them, the channel information identification unit is used to identify the signal-to-noise ratio and the maximum channel delay of the underwater acoustic channel and transmit them to the system switching unit. The system switching unit adjusts and switches the transmission signal modulation mode according to the signal-to-noise ratio and the maximum channel delay. The intelligent modulation mode identification unit uses a lightweight neural network to intelligently identify the signal modulation mode of the underwater acoustic passband signal. The intelligent signal interpretation unit uses a deep learning neural network to intelligently interpret the underwater acoustic communication signal to recover the communication data.

[0013] In some embodiments of the present invention, the transmission signal modulation unit includes:

[0014] Digital modulation unit: connected to the output end of the system switching unit;

[0015] The spectrum spreading unit comprises a first spectrum spreading branch and a second spectrum spreading branch, wherein the first spectrum spreading branch is provided with a switch component and a spectrum spreading module; the output end of the digital modulation unit is respectively connected to the first spectrum spreading branch and the second spectrum spreading branch; the first spectrum spreading branch and the second spectrum spreading branch are connected and converged to form the output end of the spectrum spreading unit;

[0016] The inverse fast Fourier transform unit comprises a first transform branch and a second transform branch, wherein the first transform branch is provided with a switch component and an inverse Fourier transform module; the output end of the spectrum spreading unit is respectively connected to the first transform branch and the second transform branch; the output ends of the first transform branch and the second transform branch intersect to form the output end of the inverse fast Fourier transform unit;

[0017] Framing unit: used to add pilot sequence and cyclic prefix to the output data of the inverse fast Fourier transform unit;

[0018] Frequency conversion modulation unit: used for frequency conversion processing of the output data of the framing unit;

[0019] The signal output end of the frequency conversion modulation unit outputs the signal to the underwater acoustic channel.

[0020] In some embodiments of the present invention, the multi-standard transmitter is configured to be able to transmit one of the following modulation signal types: a single-carrier cyclic prefix signal, a single-carrier time-domain spread spectrum signal, an orthogonal frequency division multiplexing signal, and a multi-carrier frequency-domain spread spectrum signal:

[0021] When the multi-standard transmitter is configured to transmit a single-carrier cyclic prefix signal, the second spreading branch is turned on, and the second transform branch is turned on;

[0022] When the multi-standard transmitter is configured to transmit a single-carrier time-domain spread spectrum signal, the first spread spectrum branch is turned on and the second conversion branch is turned on;

[0023] When the multi-standard transmitter is configured to transmit an orthogonal frequency division multiplexing signal, the second spread spectrum branch is turned on and the first conversion branch is turned on;

[0024] When the multi-standard transmitter is configured to transmit a multi-carrier frequency domain spread spectrum signal, the first spread spectrum branch is turned on, and the first conversion branch is turned on.

[0025] In some embodiments of the present invention, the transmission signal of the multi-standard transmitter is defined as s(n), where n=1, 2, 3, ..., Q S , n represents the serial number of the transmitted signal, Q S is the number of transmitted signals s(n):

[0026] The single carrier cyclic prefix signal is expressed as:

[0027] s(n)=x[k],k=1,2,3,…,Q S , n=k, where x[k] represents the transmitted data after digital modulation, and k represents the sequence number of the transmitted data;

[0028] The single-carrier time-domain spread spectrum signal is expressed as:

[0029] s(n)=x[k]c[i], i=1,2,3,…,N p , n=(k-1)N p +i, where c[i] is the spreading sequence, i is the sequence number of the spreading sequence, and N p is the spreading sequence length;

[0030] The OFDM signal is expressed as:

[0031] l=1,2,3,…,Q s , n=l,k=1,2,3,…,NQ S , where N is the fast

[0032] Number of subcarriers for fast Fourier transform;

[0033] The multi-carrier frequency domain spread spectrum signal is expressed as:

[0034] l=1,2,3,…,Q s , n = l, where y(p) is the data sequence after spread spectrum, y(p) = x[k]c[i], i=1,2,3,…,N p , p=(k-1)N p +i.

[0035] In some embodiments of the present invention, the data processing unit of the intelligent multi-standard receiver includes:

[0036] Frequency conversion demodulation unit: connected to the output end of the intelligent modulation mode recognition unit, used to set the frequency conversion strategy according to the modulation mode recognized by the intelligent modulation mode recognition unit, and perform frequency conversion demodulation processing on the underwater acoustic communication signal;

[0037] Deframing unit: connected to the output end of the frequency conversion demodulation unit, used to perform deframing processing on the underwater acoustic signal after frequency conversion demodulation processing according to the modulation mode identified by the intelligent modulation mode identification unit;

[0038] Fast Fourier transform unit: connected to the output end of the deframing unit, used to perform fast Fourier transform on the underwater acoustic communication signal after deframing according to the modulation mode identified by the intelligent modulation mode identification unit, and obtain the frequency domain signal of the underwater acoustic communication signal, including the pilot sequence frequency domain signal and the data sequence frequency domain signal of the underwater acoustic communication signal;

[0039] The intelligent signal interpretation unit is connected to the output end of the fast Fourier transform unit and the output end of the intelligent modulation mode identification unit, and is used to perform intelligent signal interpretation on the underwater acoustic communication frequency domain signal after the fast Fourier transform in combination with the identified modulation mode to obtain communication data.

[0040] In some embodiments of the present invention, the intelligent modulation mode identification unit includes:

[0041] Signal conversion module: used to convert the underwater acoustic communication signal time series signal into a time-frequency image signal;

[0042] A signal recognition neural network receives the time-frequency image signal and identifies a signal modulation mode based on the time-frequency image signal;

[0043] Among them, the signal recognition neural network adopts a lightweight neural network, including ShuffleNet, EfficientNet and MobileNet.

[0044] In some embodiments of the present invention, the intelligent signal interpretation unit includes a deep learning network, which is a data-driven optimized DNN neural network, or a data-driven LSTM neural network, or a model-driven ModelDriven-Net neural network. The input end of the deep learning network is connected to the output end of the fast Fourier transform unit, and the underwater acoustic communication frequency domain signal after the fast Fourier transform is intelligently interpreted to obtain communication data:

[0045] The data-driven optimized DNN neural network is configured to set the number of available network layers and the number of network nodes according to the identified modulation mode: if the identified signal modulation mode is a single-carrier cyclic prefix signal or an orthogonal frequency division multiplexing signal, the DNN network is configured to include a first number of network layers and a second number of network nodes; if the identified signal modulation mode is a single-carrier time domain spread spectrum signal or a multi-carrier frequency domain spread spectrum signal, the DNN network is configured to include a third number of network layers and a fourth number of network nodes; the third number is less than the first number, and the fourth number is less than the second number;

[0046] The data-driven LSTM neural network is configured as a double-layer LSTM network;

[0047] The model-driven ModelDriven-Net neural network is a deep learning network that combines an intelligent signal interpretation network with a traditional channel estimation and channel equalization algorithm, including a channel estimation subnet and a channel equalization subnet;

[0048] The channel estimation subnet comprises:

[0049] Least squares module: obtain the pilot sequence signal y output by the fast Fourier transform unit of the intelligent multi-standard receiver p , and the pilot sequence signal x sent by the multi-standard transmitter p , and then generate the channel impulse response after least squares processing Channel impulse response Divided into real information and imaginary information;

[0050] Channel Estimation Neural Network: Input Channel Impulse Response The real and imaginary information of the channel is output as an estimate of the channel impulse response.

[0051] The channel equalization subnet comprises:

[0052] Minimum mean square error module: connects to the output of the channel estimation neural network to obtain the estimated value of the output channel impulse response And input the data sequence signal y output by the fast Fourier transform unit of the intelligent multi-standard receiver D ; After the minimum variance calculation, the minimum mean square error signal x is output MMSE , the output x MMSE The signal is divided into real information and imaginary information;

[0053] Signal equalization neural network: For single-carrier cyclic prefix signal and single-carrier time domain spread spectrum signal, obtain the output x MMSE Real and imaginary information of the signal, output data balanced signal Signal, The data equalization signal is processed by hard decision to obtain data For OFDM signals and multi-carrier frequency domain spread spectrum signals, the neural network simultaneously obtains the estimated value of the output channel impulse response The data sequence signal y output by the fast Fourier transform unit of the intelligent multi-standard receiver D , minimum mean square error signal x MMSE , output data equalization signal Signal, The data equalization signal is processed by hard decision to obtain data

[0054] The intelligent adaptive multi-standard underwater acoustic communication system provided by the present invention has the beneficial effects of: inventing an intelligent adaptive multi-standard underwater acoustic communication system based on deep learning, the channel adaptive multi-standard transmitter supports four signal modulation modes: single carrier cyclic prefix (SC-CP), single carrier time domain spread spectrum (SC-TDSS), orthogonal frequency division multiplexing (OFDM), and multi-carrier frequency domain spread spectrum (MC-FDSS), and adaptively switches the signal modulation mode based on the channel signal-to-noise ratio and the maximum channel delay. The intelligent multi-standard receiver includes intelligent modulation mode recognition based on a lightweight network, intelligent signal interpretation based on a deep learning network, synchronization, Doppler estimation and compensation, frequency conversion demodulation, deframing, FFT and other modules, which realize the intelligent recognition of underwater acoustic communication signal modulation mode and the intelligent channel estimation and equalization processing of the four underwater acoustic communication signal modulation modes. It can adaptively adapt the appropriate underwater acoustic communication signal modulation mode to the time-varying underwater acoustic channel in complex application scenarios, and also realize the intelligent recognition and intelligent signal interpretation of various underwater acoustic communication modulation modes. Compared with the traditional channel estimation and equalization signal processing methods, it improves the performance of signal interpretation and processing, and also solves the limitations of the existing single-standard single-parameter underwater acoustic communication, single-standard multi-parameter underwater acoustic communication, multi-standard underwater acoustic communication based on traditional signal processing, and intelligent single-standard underwater acoustic communication in the face of time-varying underwater acoustic channels in complex application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0056] Figure 1 The intelligent adaptive underwater acoustic communication system of the present invention;

[0057] Figure 2 This is a data frame structure diagram of the intelligent adaptive underwater acoustic communication system of the present invention;

[0058] Figure 3a It is a time-frequency analysis diagram of a single-carrier cyclic prefix signal;

[0059] Figure 3b It is a time-frequency analysis diagram of a single-carrier time-domain spread spectrum signal;

[0060] Figure 3c It is the time-frequency analysis diagram of OFDM signal;

[0061] Figure 3d It is a time-frequency analysis diagram of multi-carrier frequency domain spread spectrum signal;

[0062] Figure 4Schematic diagram of the channel estimation subnetwork structure;

[0063] Figure 5 Flowchart for channel estimation subnetwork training;

[0064] Figure 6 A schematic diagram of the structure of an implementation scheme of a channel equalization subnet;

[0065] Figure 7 It is a schematic diagram of another implementation structure of the channel equalization subnet;

[0066] Figure 8 This is a comparison chart of the accuracy of different neural network models in identifying signal modulation methods;

[0067] Figure 9a This is the bit error rate diagram of single carrier cyclic prefix modulation mode;

[0068] Figure 9b This is the bit error rate diagram of single carrier time domain spread spectrum modulation;

[0069] Fig.9c It is the bit error rate diagram of the OFDM modulation mode;

[0070] Figure 9d It is the bit error rate diagram of multi-carrier frequency domain spread spectrum modulation mode;

[0071] Fig.10 This is a comparison chart of the bit error rate performance of intelligent signal interpretation under CH1 channel conditions;

[0072] Fig.11 This is a comparison chart of the bit error rate performance of intelligent signal interpretation under CH2 channel conditions;

[0073] Fig.12 This is a comparison chart of the bit error rate performance of intelligent signal interpretation under CH3 channel conditions. DETAILED DESCRIPTION

[0074] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0075] In the embodiments of the present application, prefixes such as "first" and "second" are used only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present application does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "multiple" is two or more.

[0076] The technical solution in the embodiment of the present application will be described below in conjunction with the drawings in the embodiment of the present application. In the description of the embodiment of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0077] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0078] According to the known existing technologies, underwater acoustic communication technology mainly includes single-standard single-parameter underwater acoustic communication, single-standard multi-parameter underwater acoustic communication, multi-standard underwater acoustic communication, and intelligent single-standard underwater acoustic communication.

[0079] In terms of single-mode and single-parameter underwater acoustic communications, the performance of single-mode and single-parameter underwater acoustic communication systems (such as FSK, PSK, OFDM, etc.) that have been developed for a long time is often limited by the worst conditions of the underwater acoustic channel in complex application scenarios, which limits its application in long-term real-time underwater observation, underwater networking observation in complex environments, and large-scale dynamic networking. It is difficult to meet the needs of high-quality underwater acoustic communications that fully utilize the channel bandwidth.

[0080] In terms of single-mode multi-parameter underwater acoustic communication, the changes in the underwater acoustic channel are mainly adapted by adjusting the baseband coding method and digital modulation method. Due to the limitation of a single carrier modulation method, the channel adaptation range of the single-mode multi-parameter adaptive underwater acoustic communication system is limited.

[0081] In terms of multi-standard underwater acoustic communication, its receiver adopts channel estimation and signal channel equalization methods based on traditional signal processing technology. Limited by the channel estimation and channel equalization performance, the multi-standard adaptive underwater acoustic communication system based on traditional signal processing technology is difficult to effectively adapt to complex time-varying underwater acoustic channels.

[0082] Intelligent single-mode underwater acoustic communication is currently mainly developed based on the OFDM carrier modulation method. It is also limited by the single carrier modulation method. The channel adaptability range of the intelligent single-mode underwater acoustic communication system is limited.

[0083] In order to solve the above problems, the present invention proposes an intelligent adaptive underwater acoustic communication system.

[0084] refer to Figure 1 The present invention provides an intelligent adaptive underwater acoustic communication system, the structure of which includes: a multi-standard transmitter, a channel information identification unit, and an intelligent multi-standard receiver.

[0085] Multi-standard transmitter: It includes a data transmission unit for sending communication data, a standard switching unit for switching the modulation mode of the transmission signal, and a transmission signal modulation unit for modulating the signal; the data transmission unit, the standard switching unit and the transmission signal modulation unit are connected in sequence, and the standard switching unit serves as the receiving end of the transmitted data, and outputs modulation signals of different standards after the transmission signal is modulated. Its data frame format refers to Figure 2 .

[0086] Channel information identification unit: its input end is connected to the signal output end of the synchronization unit of the intelligent multi-standard receiver, and its output end is connected to the standard switching unit of the multi-standard transmitter.

[0087] The channel information identification unit of the intelligent adaptive underwater acoustic communication system is used to identify the signal-to-noise ratio and maximum channel delay of the underwater acoustic channel, and transmit them to the mode switching unit. The mode switching unit adjusts the signal modulation mode of the switching transmission signal according to the signal-to-noise ratio and maximum channel delay.

[0088] In order to adapt to the underwater acoustic time-varying channels of different underwater acoustic communication scenarios, in some embodiments of the present invention, the multi-standard transmitter is configured to be able to transmit one of the following modulation signal types: single carrier cyclic prefix signal (SC-CP), single carrier time domain spread spectrum signal (SC-TDSS), orthogonal frequency division multiplexing signal (OFDM), multi-carrier frequency domain spread spectrum signal (MC-FDSS). Table 1 gives the specific design description of the four signal modulation methods.

[0089] Table 1 Design of four signal modulation methods

[0090] Signal modulation method Digital modulation Spread Spectrum Spreading code length Signal subcarrier number SC-CP QPSK no -- 1 SC-TDSS QPSK yes 16 1 OFDM QPSK no -- 1024 MC-FDSS QPSK yes 16 1024

[0091] In some embodiments of the present invention, the output modulation mode of the underwater acoustic signal is switched by changing the configuration of the transmission signal modulation unit. In order to realize the function of outputting multiple signal modulation modes, the transmission signal modulation unit includes:

[0092] Digital modulation unit: connected to the output end of the system switching unit;

[0093] The spectrum spreading unit includes a first spectrum spreading branch and a second spectrum spreading branch, wherein the first spectrum spreading branch is provided with a switch component and a spectrum spreading module; the output end of the digital modulation unit is respectively connected to the first spectrum spreading branch and the second spectrum spreading branch; the first spectrum spreading branch and the second spectrum spreading branch are connected and converged to form the output end of the spectrum spreading unit; it should be understood that the output signal of the digital modulation unit can be sent to the next level after being subjected to spectrum spreading processing or not;

[0094] The inverse fast Fourier transform unit includes a first transform branch and a second transform branch, wherein the first transform branch is provided with a switch component and an inverse Fourier transform module; the output end of the spectrum spreading unit is respectively connected to the first transform branch and the second transform branch; the output ends of the first transform branch and the second transform branch are combined to form the output end of the inverse fast Fourier transform unit; it should be understood that the output signal of the spectrum spreading unit can be sent to the next stage after being subjected to inverse Fourier transform or not;

[0095] Framing unit: used to add pilot sequence and cyclic prefix to the output data of the inverse fast Fourier transform unit;

[0096] Frequency conversion modulation unit: used for frequency conversion processing of the output data of the framing unit;

[0097] The signal output signal of the frequency conversion modulation unit is sent to the underwater acoustic channel.

[0098] As shown above, in order to achieve the output of one of the single-carrier cyclic prefix signal, single-carrier time domain spread spectrum signal, orthogonal frequency division multiplexing signal, and multi-carrier frequency domain spread spectrum signal, the following signal modulation method is designed. The transmission signal of the multi-standard transmitter is defined as S(n), n = 1, 2, 3, ..., Q s , n represents the serial number of the transmitted signal, Q s is the number of transmitted signals s(n).

[0099] The time-frequency diagram of the data frame of four signal modulation methods: single carrier cyclic prefix (SC-CP), single carrier time domain spread spectrum (SC-TDSS), orthogonal frequency division multiplexing (OFDM), and multi-carrier frequency domain spread spectrum (MC-FDSS) is shown in the figure. Figure 3a to Figure 3b shown.

[0100] SC-CP is a single carrier modulation technology. After modulation, the data is mapped on a single carrier. In order to resist frequency selective fading, a cyclic prefix is ​​added at the beginning of each symbol period. At the receiving end, the signal is first converted to the frequency domain through FFT and then intelligent signal interpretation is performed. It is more suitable for long-distance underwater acoustic communication.

[0101] The single carrier cyclic prefix signal is expressed as:

[0102] s(n)=x[k],k=1,2,3,…,Q S , n=k, where x[k] represents the transmitted data after digital modulation, and k represents the sequence number of the transmitted data.

[0103] When the multi-standard transmitter is configured to transmit a single-carrier cyclic prefix signal, the second spreading branch is turned on, the second transform branch is turned on, and the framing unit adds a cyclic prefix to the signal.

[0104] The single-carrier time-domain spread spectrum modulation technology SC-TDSS adds spread spectrum technology to SC-CP. The information signal is divided into multiple sub-channels, and each sub-channel has its own time-domain spread sequence. The time-domain spread sequence is multiplied with the data of each sub-channel to achieve time-domain expansion of the signal. The spread spectrum technology used in this modulation signal reduces the data transmission rate. The signal has better anti-interference, anti-multipath, and anti-fading capabilities under the conditions of high delay and low signal-to-noise ratio. It is more suitable for underwater acoustic communication environments with more complex environments and harsh conditions.

[0105] The single-carrier time-domain spread spectrum signal is expressed as:

[0106] s(n)=x[k]c[i], i=1,2,3,…,N p , n=(k-1)N p +i, where c[i] is the spreading sequence, i is the sequence number of the spreading sequence, and N p is the spreading sequence length.

[0107] When the multi-standard transmitter is configured to transmit a single-carrier time-domain spread spectrum signal, the first spread spectrum branch is turned on, the second transform branch is turned on, and the signal is spread and inverse Fourier transformed.

[0108] Orthogonal frequency division multiplexing technology OFDM improves data transmission efficiency by transmitting multiple low-speed data streams simultaneously. It has a faster transmission rate and good performance in combating multipath interference and frequency selective fading, but it has high requirements for the channel signal-to-noise ratio.

[0109] The OFDM signal is expressed as:

[0110] l=1,2,3,…,Q s , n=l,k=1,2,3,…,NQ S , where N is the fast

[0111] The number of subcarriers for the fast Fourier transform.

[0112] When the multi-standard transmitter is configured to transmit an orthogonal frequency division multiplexing signal, the second spread spectrum branch is turned on and the first conversion branch is turned on.

[0113] MC-FDSS is a multi-carrier frequency domain spread spectrum technology. By adding spread spectrum technology on the basis of OFDM, data is distributed to different subcarriers, thereby improving channel capacity and anti-interference ability, and is more suitable for relatively harsh channel environments.

[0114] When the multi-standard transmitter is configured to transmit a single-multi-carrier frequency domain spread spectrum signal, the first spread spectrum branch is turned on, the second conversion branch is turned on, and the framing unit adds a cyclic prefix to the signal.

[0115] The multi-carrier frequency domain spread spectrum signal is expressed as:

[0116] l=1,2,3,…,Q s , n = l, where y(p) is the data sequence after spread spectrum, y(p) = x[k]c[i], i=1,2,3,…,N p , p=(k-1)N p +i.

[0117] The intelligent multi-standard receiver is connected to the underwater acoustic channel, receives the output signal of the underwater acoustic channel, identifies the modulation mode of the output signal of the underwater acoustic channel, and analyzes the output signal of the underwater acoustic channel.

[0118] The intelligent multi-standard receiver mainly completes intelligent signal modulation mode recognition and intelligent signal interpretation and processing.

[0119] In some embodiments of the present invention, the intelligent multi-standard receiver includes: a synchronization unit, a Doppler estimation and compensation unit, an intelligent modulation mode identification unit, a frequency conversion demodulation unit, a deframing unit, a fast Fourier transform unit and an intelligent signal interpretation unit.

[0120] Synchronization unit: receiving the underwater acoustic communication signal passing through the underwater acoustic channel, and performing data frame synchronization processing on the underwater acoustic communication signal to realize the underwater acoustic communication data frame synchronization;

[0121] Doppler estimation and compensation unit: connected to the signal output end of the synchronization unit, used to estimate and compensate the Doppler frequency shift of the underwater acoustic channel;

[0122] Intelligent modulation mode identification unit: connected to the signal output end of the Doppler estimation and compensation unit, used to intelligently identify the modulation mode of the underwater acoustic communication signal based on the bandpass underwater acoustic signal.

[0123] The intelligent modulation mode recognition unit mainly completes the signal modulation mode recognition based on the passband signal. Considering that the characteristics of the time series signal are not obvious, the present invention adopts the time-frequency analysis method to convert the time series signal into a time-frequency image signal for recognition. The specific time-frequency analysis method adopted is the smoothed pseudo-Wigner-Ville distribution.

[0124] The mathematical definition of smooth pseudo-Wigner-Ville distribution can be expressed as:

[0125]

[0126] Among them, SPWD z (t,f) represents the smoothed pseudo-Wigner-Ville distribution of the signal z(t), m(τ) is the time window function, g(ut) is the frequency window function, t and f are time and frequency respectively, and u and τ are integral variables.

[0127] Based on this, in some embodiments of the present invention, the step of intelligently identifying the modulation mode of the underwater acoustic communication signal according to the bandpass underwater acoustic signal includes:

[0128] Signal conversion module: used to convert the underwater acoustic communication signal time series signal into a time-frequency image signal;

[0129] Signal recognition neural network: receives the time-frequency image signal and identifies the signal modulation mode based on the time-frequency image signal.

[0130] The time-frequency diagram of the data frame of four signal modulation methods: single carrier cyclic prefix (SC-CP), single carrier time domain spread spectrum (SC-TDSS), orthogonal frequency division multiplexing (OFDM), and multi-carrier frequency domain spread spectrum (MC-FDSS) is shown in the figure. Figure 3a to Figure 3b shown.

[0131] The present invention uses a lightweight neural network that is easy to deploy in an embedded system to identify signal modulation methods. In different implementations, three typical lightweight neural networks ShuffleNet, EfficientNet and MobileNet can be used, and the parameters of the three lightweight neural networks are shown in Table 2.

[0132] The recognition result of the intelligent modulation mode recognition unit is mainly used in two aspects: on the one hand, it is used to select appropriate signal frequency conversion demodulation, deframing, and FFT processing; on the other hand, it is used to select an appropriate intelligent signal interpretation network model.

[0133] Table 2 Lightweight neural network parameters for signal modulation recognition

[0134] Network Model Parameters Params (M) Floating point operations FLOPs ShuffleNet 1.37 0.04 EfficientNet 5.3 1.0 MobileNet 3.5 0.31

[0135] The frequency conversion demodulation unit is connected to the output end of the intelligent modulation mode identification unit, and is used to set the frequency conversion strategy according to the modulation mode identified by the intelligent modulation mode identification unit, and perform frequency conversion demodulation processing on the underwater acoustic communication signal;

[0136] The de-framing unit is connected to the output end of the frequency conversion demodulation unit, and is used to perform de-framing processing on the underwater acoustic signal after the frequency conversion demodulation processing according to the modulation mode recognized by the signal intelligent modulation mode recognition unit;

[0137] The fast Fourier transform unit is connected to the output end of the deframing unit, and is used to perform fast Fourier transform on the underwater acoustic communication signal after deframing according to the modulation mode identified by the intelligent modulation mode identification unit, so as to obtain the frequency domain signal of the underwater acoustic communication signal, including the pilot sequence frequency domain signal and the data sequence frequency domain signal of the underwater acoustic communication signal;

[0138] The intelligent signal interpretation unit is connected to the output end of the fast Fourier transform unit and the output end of the intelligent modulation mode identification unit, and is used to interpret the underwater acoustic communication signal after the fast Fourier transform in combination with the identified modulation mode to obtain communication data.

[0139] The input of the intelligent signal interpretation unit is the frequency domain signal of the pilot sequence and data sequence after fast Fourier transform processing, and the output is the baseband signal before digital demodulation. Signal interpretation is realized based on a deep learning network, which adopts a data-driven deep learning network and a model-driven deep learning network respectively. The data-driven deep learning network is specifically the optimized DNN and LSTM neural networks, and the model-driven deep learning network is specifically the designed ModelDriven-Net neural network.

[0140] In some embodiments of the present invention, the intelligent signal interpretation unit adopts an LSTM network, connected to the output end of the fast Fourier transform unit, and interprets the underwater acoustic communication signal after the fast Fourier transform. The present invention adopts a double-layer LSTM network. The network structure is shown in Table 3.

[0141] Table 3 LSTM network structure

[0142] Serial number Layer(name) type size 1 sequence Sequence Input 256 2 lstm_1 LSTM 128 3 lstm_2 LSTM 64 4 fc Fully connected 16 (spread spectrum) / 8 (non-spread spectrum) 5 regressionoutput Regression Output --

[0143] In some embodiments of the present invention, the intelligent signal interpretation unit uses an optimized DNN network, connected to the output end of the fast Fourier transform unit, performs signal analysis on the underwater acoustic signal after the Fourier transform, and obtains the analysis signal. The DNN network is configured to set the number of available network layers and the number of network nodes according to the recognized modulation mode;

[0144] If the identified signal modulation mode is a single carrier cyclic prefix signal or an orthogonal frequency division multiplexing signal, the DNN network is configured to include a first number of network layers and a second number of network nodes;

[0145] If the modulation mode of the slave signal is identified as a single-carrier time-domain spread spectrum signal or a multi-carrier time-domain spread spectrum signal, the DNN network is configured to include a third number of network layers and a fourth number of network nodes;

[0146] The third number is less than the first number, and the fourth number is less than the second number.

[0147] According to the characteristics of signal modulation, the structure of DNN neural network is optimized. For SC-CP and OFDM non-spread spectrum modulation signals, DNN network structure with more layers and nodes is adopted; for SC-TDSS and MC-FDSS spread spectrum modulation signals, the number of parameters is reduced and DNN network with fewer layers and nodes is adopted. The specific DNN network structures are shown in Table 4 and Table 5.

[0148] Table 4 DNN network structure of non-spread spectrum modulation signal

[0149] Serial number Layer(name) type size 1 sequence Sequence Input 256 2 fc_1 Fully connected 500 3 relu_1 ReLU -- 4 fc_2 Fully connected 250 5 relu_2 ReLU -- 6 fc_3 Fully connected 120 7 relu_3 ReLU -- 8 fc_4 Fully connected 16 9 regressionoutput Regression Output --

[0150] Table 5 DNN network structure of spread spectrum modulation signal

[0151] Serial number Layer(name) type size 1 sequence Sequence Input 256 2 fc_1 Fully connected 500 3 relu_1 ReLU -- 4 fc_2 Fully connected 250 5 relu_2 ReLU -- 6 fc_3 Fully connected 8 7 regressionoutput Regression Output --

[0152] In some embodiments of the present invention, reference Figures 4 to 7 ,The intelligent signal interpretation unit adopts the model-driven ModelDriven-Net neural network, which specifically includes a channel estimation subnet and a channel equalization subnet.

[0153] The channel estimation subnet includes: a least squares module (LS module) and a channel estimation neural network (BP neural network).

[0154] Least squares module (LS module): obtains the pilot sequence signal y output by the fast Fourier transform unit of the intelligent multi-standard receiver p , and the pilot sequence signal x sent by the multi-standard transmitter p , and then generate the channel impulse response after least squares processing Channel impulse response Divided into real information and imaginary information;

[0155] Channel estimation neural network (BP neural network): input channel impulse response The real and imaginary information of the channel is output as an estimate of the channel impulse response.

[0156] Specifically, the LS algorithm receives the pilot signal y p The pilot signal x p Perform the least squares operation to obtain a rough estimate of the channel impulse response At the same time, the real part and the imaginary part of the complex channel impulse response are separated and input into the BP neural network for further optimization. After optimization, the real part and the imaginary part are combined to obtain the channel impulse response

[0157] The structure of the BP neural network of the channel estimation subnet is shown in Table 6.

[0158] Table 6 Estimated subnet network structure

[0159] Serial number Layer(name) type size 1 sequence Sequence Input 128 2 fc_1 Fully connected 256 3 relu_1 ReLU -- 4 fc_2 Fully connected 128 5 regressionoutput Regression Output --

[0160] The training process of the channel estimation subnetwork is as follows: Figure 5 As shown in Figure 2, the channel estimation subnet extracts data from the noisy underwater acoustic channel output as the training set and validation set, and uses the non-noisy underwater acoustic channel output as the label of the training set and validation set.

[0161] The channel equalization subnet includes: a minimum mean square error module (MMSE module) and a signal equalization neural network module.

[0162] Minimum mean square error module: connects to the output of the channel estimation neural network to obtain the estimated value of the output channel impulse response And input the data sequence signal y output by the fast Fourier transform unit of the intelligent multi-standard receiver D ; After the minimum variance calculation, the minimum mean square error signal x is output MMSE , the output x MMSE The signal is divided into real information and imaginary information;

[0163] Signal equalization neural network: For single-carrier cyclic prefix signal and single-carrier time domain spread spectrum signal, obtain the output x MMSE Real and imaginary information of the signal, output communication data balanced signal Signal, The communication data equalization signal is processed by hard decision to obtain the communication data before digital demodulation For OFDM signals and multi-carrier frequency domain spread spectrum signals, the neural network simultaneously obtains the estimated value of the output channel impulse response The data sequence signal y output by the fast Fourier transform unit of the intelligent multi-standard receiver D , minimum mean square error signal x MMsE , output communication data balanced signal Signal, The communication data equalization signal is processed by hard decision to obtain the communication data before digital demodulation

[0164] The signal equalization neural network uses BP network and DNN network.

[0165] Table 7 Single carrier channel equalization subnet structure

[0166]

[0167]

[0168] Table 8 Multi-carrier signal channel equalization subnet

[0169] Serial number Layer(name) type size 1 imageinput Image Input 6×64×1 2 fc_1 Fully connected 250 3 relu_1 ReLU -- 4 fc_2 Fully connected 120 5 relu_2 ReLU -- 6 fc_3 Fully connected Non-spread spectrum: 16 / Spread spectrum: 8 7 regressionoutput Regression Output --

[0170] The system simulation analysis process and results of the intelligent adaptive underwater acoustic communication system provided by the present invention are as follows.

[0171] (1) Underwater acoustic channel modeling

[0172] The system simulation is based on the Millica underwater acoustic channel model. Only the influence of large-scale factors is considered in the process of model establishment. Three typical channel models are established by changing the water depth, transmission distance and relative position, as shown in Table 9. The three channels are represented by CH1, CH2 and CH3 respectively. The relative position I means that the transceiver is at a distance of H / 2 from the bottom of the water, and the relative position II means that the transmitter is at a distance of 3H / 4 from the bottom of the water, and the receiver is at a distance of H / 4 from the bottom of the water.

[0173] Due to the combined influence of multiple complex factors such as water movement, temperature and salinity changes, dynamic characteristics of the sea surface and seabed, signal frequency dependence, refraction and scattering effects, nonlinear propagation effects, and changes in environmental noise and interference sources, under the same underwater acoustic channel conditions, the maximum channel delay and the number of multipaths will also be different accordingly, but the overall characteristics of the channel are basically the same. Therefore, 3,600 communication situations were selected under each channel.

[0174] Table 9 Communication scenario parameters for underwater acoustic channel modeling

[0175] Channel Water depth H Transmission distance D Relative Position Number of channels Maximum delay CH1 100m 1000m Ⅰ 3600 30ms CH2 100m 5000m Ⅱ 3600 48ms CH3 500m 1000m Ⅱ 3600 21ms

[0176] (2) Dataset Construction

[0177] 1) Construction of dataset for intelligent signal modulation recognition

[0178] Under the conditions of channel CH1 signal-to-noise ratio of -5dB, 0dB, 5dB, 10dB and 15dB, 2000 images are generated for neural network training, and 200 images for each signal-to-noise ratio are tested.

[0179] The dataset construction and parameter settings for network training are shown in Table 10.

[0180] Table 10 Communication scenario parameters for underwater acoustic channel modeling

[0181]

[0182] 2) Construction of data set for intelligent signal interpretation

[0183] A) Dataset Construction for Data-Driven Networks

[0184] The data-driven network uses DNN and LSTM. The input of the data set is the signal after FFT processing, and the real and imaginary parts of the signal are separated and input into the neural network. The label is the bit signal sent by the transmitter. The data set is generated under the condition of a signal-to-noise ratio of 25dB, generating 50,000 frames of data, divided into 35,000 frames of training sets and 15,000 frames of validation sets. The optimization algorithm uses Adam optimization, the validation set evaluation frequency is 500, the number of training rounds is changed to 13 rounds, and the number of iterations per round is 3500. And in the range of -10 to 10dB, a 2000-frame test set is generated every 2dB to verify the performance of the model.

[0185] B) Dataset Construction for Model-Driven Networks

[0186] The channel estimation subnet is trained under a signal-to-noise ratio of 25 dB. The input of the data set is the rough channel impulse response estimated by the traditional LS algorithm, and the label is the perfect channel impulse response without noise. The training set and validation set are divided into 7:3, with 35,000 frames and 15,000 frames respectively. The optimization algorithm uses Adam optimization, and the validation set evaluation frequency is 500. Compared with data-driven neural networks, model-driven neural networks are simpler to train, with less computation and faster training. Therefore, the number of training rounds is changed to 10 rounds, with 3500 iterations per round. L2 regularization is used to prevent overfitting, and the value of L2 regularization is set to 0.002. After the training is completed, the parameters of the channel estimation subnet are fixed.

[0187] The channel equalization subnet is also trained at a signal-to-noise ratio of 25dB, and the data set is also divided in a ratio of 7:3. The network training has a certain degree of complexity compared to the previous one, and 10 rounds of training is not optimal for the network. Here, the number of network training rounds is set to 20 rounds, and the number of iterations per round is 1750. The other parameters are set the same. After the training is completed, a test set of 2000 frames is generated every 2dB in the range of -10 to 10dB to verify the performance of the model.

[0188] (3) Network training parameters

[0189] The network training parameters of the data-driven neural network and the model-driven neural network are shown in Tables 10 and 11.

[0190] Table 10 Data-driven neural network training parameters

[0191] Serial number Main parameters Parameter settings 1 Training signal-to-noise ratio 25dB 2 Optimization Algorithm Adam 3 Training Dataset 35000 4 Validation Dataset 15000 5 Validation set evaluation frequency 500 6 Maximum number of training rounds 13 7 Number of iterations per round 3500 8 Learning Rate Initial: 0.001, after two rounds × 0.8 9 L2 Regularization 0.002

[0192] Table 11 Model-driven neural network training parameters

[0193]

[0194]

[0195] (4) System simulation test results and analysis

[0196] 1) Test results of intelligent signal modulation recognition

[0197] Figure 8 The figure shows the comparison of recognition accuracy of three neural networks. According to the results, it can be seen that as the signal-to-noise ratio increases, the signal recognition rate also increases. Under the condition of a signal-to-noise ratio of 0dB, the recognition rates achieved by the three networks all reach more than 90%.

[0198] 2) Performance test results of intelligent signal interpretation

[0199] After training the neural network according to the network structure and network training parameters, the system simulated and tested the performance of intelligent signal interpretation of the three networks under the CH1 channel condition. The simulation test results are as follows: Figure 8 As shown in the figure. The results show that the performance of the signal processing module of the intelligent algorithm is significantly better than that of the traditional LS+ZF and LS+MMSE algorithms, and the performance of the three intelligent methods is relatively similar. For SC-CP, SC-TDSS, and OFDM signal modulation methods, the model-driven underwater acoustic communication intelligent receiver has better performance; for MC-FDSS signal modulation method, the performance of the model-driven underwater acoustic communication intelligent receiver is similar to that of the LSTM underwater acoustic communication intelligent receiver, but is slightly worse than DNN overall.

[0200] The results of intelligent signal interpretation of different signal modulation modes are shown in Figure 9. It can be seen that the channel adaptability of the four signal modulation modes SC-CP, SC-TDSS, OFDM, and MC-FDSS is different, and the bit error rate is less than 10 -4 In the case of CH1 channel conditions, OFDM can be used in scenarios where the SNR is above 8dB, SC-CP can be used in scenarios where the SNR is above 5dB, MC-FDSS can be used in scenarios where the SNR is above -3dB, and SC-TDSS can be used in scenarios where the SNR is above -7dB, demonstrating the channel adaptability of the intelligent multi-standard communication method.

[0201] In order to verify the generalization performance of the three neural networks, the system further simulated and tested the performance of the intelligent signal interpretation of the three networks under the conditions of CH2 and CH3 channels. The test results are as follows: Fig.11 , Fig.12 As shown in the results, it can be seen that the communication performance of the three intelligent signal interpretation methods in CH2 and CH3 channels is similar to that in CH1 channel, and has good generalization performance.

[0202] (5) Network computational complexity analysis

[0203] The statistical comparison of network parameters of the three neural networks is shown in Table 12. It can be seen that the model-driven neural network has smaller parameters. Considering that the performance of the three networks is comparable, the model-driven neural network is more suitable for deployment in embedded systems with limited computing resources.

[0204] Table 12 Comparison of parameters of three neural networks

[0205]

[0206]

[0207] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent adaptive underwater acoustic communication system, characterized in that: include: The multi-standard transmitter includes a data transmission unit for transmitting communication data, a standard switching unit for switching the transmission signal modulation mode, and a transmission signal modulation unit for modulating the signal; the data transmission unit, the standard switching unit and the transmission signal modulation unit are connected in sequence; the output end of the multi-standard transmitter is connected to the underwater acoustic channel; Intelligent multi-standard receiver: including synchronization unit, Doppler estimation and compensation unit, intelligent modulation mode identification unit, data processing unit, intelligent signal interpretation unit and digital demodulation unit; The synchronization unit receives the underwater acoustic communication signal passing through the underwater acoustic channel and performs data frame synchronization processing on the underwater acoustic communication signal; the Doppler estimation and compensation unit receives the output data of the synchronization unit, estimates and compensates the Doppler frequency shift of the underwater acoustic channel; The intelligent modulation mode identification unit is connected to the signal output end of the Doppler estimation and compensation unit, and is used to intelligently identify the modulation mode of the underwater acoustic communication signal according to the bandpass underwater acoustic signal; the data processing unit is connected to the signal output end of the intelligent modulation mode identification unit; the intelligent signal interpretation unit is connected to the signal output end of the data processing unit, and The output end of the intelligent modulation mode identification unit is used to perform intelligent signal interpretation on the underwater acoustic communication frequency domain signal after fast Fourier transformation in combination with the identified modulation mode to obtain communication data; the digital demodulation unit is connected to the signal output end of the intelligent signal interpretation unit, and modulates the communication data to the data receiving unit; Channel information identification unit: its input end is connected to the signal output end of the synchronization unit of the intelligent multi-standard receiver, and its output end is connected to the standard switching unit of the multi-standard transmitter; Among them, the channel information identification unit is used to identify the signal-to-noise ratio and the maximum channel delay of the underwater acoustic channel and transmit them to the system switching unit. The system switching unit adjusts and switches the transmission signal modulation mode according to the signal-to-noise ratio and the maximum channel delay. The intelligent modulation mode identification unit uses a lightweight neural network to intelligently identify the signal modulation mode of the underwater acoustic passband signal. The intelligent signal interpretation unit uses a deep learning neural network to intelligently interpret the underwater acoustic communication signal to recover the communication data.

2. The intelligent adaptive underwater acoustic communication system according to claim 1, characterized in that: The transmission signal modulation unit comprises: Digital modulation unit: connected to the output end of the system switching unit; The spectrum spreading unit comprises a first spectrum spreading branch and a second spectrum spreading branch, wherein the first spectrum spreading branch is provided with a switch component and a spectrum spreading module; the output end of the digital modulation unit is respectively connected to the first spectrum spreading branch and the second spectrum spreading branch; the first spectrum spreading branch and the second spectrum spreading branch are connected and converged to form the output end of the spectrum spreading unit; The inverse fast Fourier transform unit comprises a first transform branch and a second transform branch, wherein the first transform branch is provided with a switch component and an inverse Fourier transform module; the output end of the spectrum spreading unit is respectively connected to the first transform branch and the second transform branch; the output ends of the first transform branch and the second transform branch intersect to form the output end of the inverse fast Fourier transform unit; Framing unit: used to add pilot sequence and cyclic prefix to the output data of the inverse fast Fourier transform unit; Frequency conversion modulation unit: used for frequency conversion processing of the output data of the framing unit; The signal output end of the frequency conversion modulation unit outputs the signal to the underwater acoustic channel.

3. The intelligent adaptive underwater acoustic communication system according to claim 2, characterized in that: The multi-standard transmitter is configured to be able to transmit one of the following modulation signal types: a single-carrier cyclic prefix signal, a single-carrier time-domain spread spectrum signal, an orthogonal frequency division multiplexing signal, and a multi-carrier frequency-domain spread spectrum signal: When the multi-standard transmitter is configured to transmit a single-carrier cyclic prefix signal, the second spreading branch is turned on, and the second transform branch is turned on; When the multi-standard transmitter is configured to transmit a single-carrier time-domain spread spectrum signal, the first spread spectrum branch is turned on and the second conversion branch is turned on; When the multi-standard transmitter is configured to transmit an orthogonal frequency division multiplexing signal, the second spread spectrum branch is turned on and the first conversion branch is turned on; When the multi-standard transmitter is configured to transmit a multi-carrier frequency domain spread spectrum signal, the first spread spectrum branch is turned on, and the first conversion branch is turned on.

4. The intelligent adaptive underwater acoustic communication system according to claim 3, characterized in that: Define the transmission signal of the multi-standard transmitter before frequency conversion modulation as s(n), n = 1, 2, 3, ..., Q S , n represents the serial number of the transmitted signal, Q S is the number of transmitted signals s(n): The single carrier cyclic prefix signal is expressed as: s(n)=x[k],k=1,2,3,…,Q S , n=k, where x[k] represents the transmitted data after digital modulation, and k represents the sequence number of the transmitted data; The single-carrier time domain spread spectrum signal is expressed as: Where c[i] is the spreading sequence, i is the serial number of the spreading sequence, and N p is the spreading sequence length; The OFDM signal is expressed as: Where N is the number of subcarriers of the Fast Fourier Transform; The multi-carrier frequency domain spread spectrum signal is expressed as: Among them, y(p) is the data sequence after spread spectrum, 5. The intelligent adaptive underwater acoustic communication system according to any one of claims 1 to 4, characterized in that: The data processing unit of the intelligent multi-standard receiver includes: Frequency conversion demodulation unit: connected to the output end of the intelligent modulation mode recognition unit, used to set the frequency conversion strategy according to the modulation mode recognized by the intelligent modulation mode recognition unit, and perform frequency conversion demodulation processing on the underwater acoustic communication signal; Deframing unit: connected to the output end of the frequency conversion demodulation unit, used to perform deframing processing on the underwater acoustic signal after frequency conversion demodulation processing according to the modulation mode identified by the intelligent modulation mode identification unit; Fast Fourier transform unit: connected to the output end of the deframing unit, used to perform fast Fourier transform on the underwater acoustic communication signal after deframing according to the modulation mode identified by the intelligent modulation mode identification unit, and obtain the frequency domain signal of the underwater acoustic communication signal, including the pilot sequence frequency domain signal and the data sequence frequency domain signal of the underwater acoustic communication signal; The intelligent signal interpretation unit is connected to the output end of the fast Fourier transform unit and the output end of the intelligent modulation mode identification unit, and is used to perform intelligent signal interpretation on the underwater acoustic communication frequency domain signal after the fast Fourier transform in combination with the identified modulation mode to obtain communication data.

6. The intelligent adaptive underwater acoustic communication system according to claim 5, characterized in that: The intelligent modulation mode identification unit comprises: Signal conversion module: used to convert the underwater acoustic communication signal time series signal into a time-frequency image signal; A signal recognition neural network receives the time-frequency image signal and identifies a signal modulation mode based on the time-frequency image signal; Among them, the signal recognition neural network adopts a lightweight neural network, including ShuffleNet, EfficientNet and MobileNet.

7. The intelligent adaptive underwater acoustic communication system according to claim 5, characterized in that: The intelligent signal interpretation unit includes a deep learning network, which is a data-driven optimized DNN neural network, or a data-driven LSTM neural network, or a model-driven ModelDriven-Net neural network. The input end of the deep learning network is connected to the output end of the fast Fourier transform unit, and the underwater acoustic communication frequency domain signal after the fast Fourier transform is intelligently interpreted to obtain communication data: The data-driven optimized DNN neural network is configured to set the number of available network layers and the number of network nodes according to the identified modulation mode: if the identified signal modulation mode is a single-carrier cyclic prefix signal or an orthogonal frequency division multiplexing signal, the DNN network is configured to include a first number of network layers and a second number of network nodes; if the identified signal modulation mode is a single-carrier time domain spread spectrum signal or a multi-carrier frequency domain spread spectrum signal, the DNN network is configured to include a third number of network layers and a fourth number of network nodes; the third number is less than the first number, and the fourth number is less than the second number; The data-driven LSTM neural network is configured as a double-layer LSTM network; The model-driven ModelDriven-Net neural network is a deep learning network that combines an intelligent signal interpretation network with a traditional channel estimation and channel equalization algorithm, including a channel estimation subnet and a channel equalization subnet; The channel estimation subnet comprises: Least squares module: obtain the pilot sequence signal y output by the fast Fourier transform unit of the intelligent multi-standard receiver p , and the pilot sequence signal x sent by the multi-standard transmitter p , and then generate the channel impulse response after least squares processing Channel impulse response Divided into real information and imaginary information; Channel Estimation Neural Network: Input Channel Impulse Response The real and imaginary information of the channel is output as an estimate of the channel impulse response. The channel equalization subnet comprises: Minimum mean square error module: connects to the output of the channel estimation neural network to obtain the estimated value of the output channel impulse response And input the data sequence signal y output by the fast Fourier transform unit of the intelligent multi-standard receiver D ; After the minimum variance calculation, the minimum mean square error signal x is output MMSE , the output x MMSE The signal is divided into real information and imaginary information; Signal equalization neural network: For single-carrier cyclic prefix signal and single-carrier time domain spread spectrum signal, obtain the output x MMSE Real and imaginary information of the signal, output communication data balanced signal Signal, The communication data equalization signal is processed by hard decision to obtain the communication data before digital demodulation For OFDM signals and multi-carrier frequency domain spread spectrum signals, the neural network simultaneously obtains the estimated value of the output channel impulse response The data sequence signal y output by the fast Fourier transform unit of the intelligent multi-standard receiver D , minimum mean square error signal x MMSE , output data equalization signal Signal, The communication data equalization signal is processed by hard decision to obtain the communication data before digital demodulation

Images