WO2023082597A1 - 5g通信信号干扰的处理方法和装置 - Google Patents

5g通信信号干扰的处理方法和装置 Download PDF

Info

Publication number
WO2023082597A1
WO2023082597A1 PCT/CN2022/094759 CN2022094759W WO2023082597A1 WO 2023082597 A1 WO2023082597 A1 WO 2023082597A1 CN 2022094759 W CN2022094759 W CN 2022094759W WO 2023082597 A1 WO2023082597 A1 WO 2023082597A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal set
signal
downhole signal
interference
target
Prior art date
Application number
PCT/CN2022/094759
Other languages
English (en)
French (fr)
Inventor
张立亚
姜玉峰
孟庆勇
连龙飞
郝博南
吴文臻
戴万波
王勇
Original Assignee
煤炭科学技术研究院有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 煤炭科学技术研究院有限公司 filed Critical 煤炭科学技术研究院有限公司
Priority to KR1020237009689A priority Critical patent/KR20230070460A/ko
Publication of WO2023082597A1 publication Critical patent/WO2023082597A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04J—MULTIPLEX COMMUNICATION
    • H04J11/00—Orthogonal multiplex systems, e.g. using WALSH codes
    • H04J11/0023—Interference mitigation or co-ordination
    • H04J11/0026—Interference mitigation or co-ordination of multi-user interference
    • H04J11/0036—Interference mitigation or co-ordination of multi-user interference at the receiver
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00—Baseband systems
    • H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
    • H04L25/03—Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
    • H04L25/03006—Arrangements for removing intersymbol interference
    • H04L25/03012—Arrangements for removing intersymbol interference operating in the time domain
    • H04L25/03019—Arrangements for removing intersymbol interference operating in the time domain adaptive, i.e. capable of adjustment during data reception
    • H04L25/03082—Theoretical aspects of adaptive time domain methods
    • H04L25/03089—Theory of blind algorithms, recursive or not
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
    • H04B1/06—Receivers
    • H04B1/10—Means associated with receiver for limiting or suppressing noise or interference
    • H04B1/1027—Means associated with receiver for limiting or suppressing noise or interference assessing signal quality or detecting noise/interference for the received signal
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H04B17/336—Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00—Arrangements for detecting or preventing errors in the information received
    • H04L1/20—Arrangements for detecting or preventing errors in the information received using signal quality detector
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00—Baseband systems
    • H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
    • H04L25/0202—Channel estimation
    • H04L25/0204—Channel estimation of multiple channels

Definitions

  • the present disclosure relates to the field of signal processing, and in particular to a method and device for processing 5G communication signal interference.
  • the underground tunnels of coal mines are complex, the space is narrow, and there are many large-scale electromechanical equipment, which are prone to superposition of multi-factor interference on the signal.
  • the actual interference conditions considered in related technologies are relatively small, and it is impossible to deal with the actual interference conditions of coal mines in a relatively complete and comprehensive manner.
  • different methods should be used for different interference sources. The direct superposition and integration of multiple methods will make the calculation If the amount is too large, the delay will be too high, which will affect the speed and efficiency of signal anti-jamming processing.
  • a method for processing 5G communication signal interference including:
  • the interference of the mixed downhole signal set transmitted by multi-channel is filtered to obtain the target downhole signal set;
  • the interference components in the downhole signal are adaptively filtered through the separation matrix, which improves the efficiency of signal anti-interference processing.
  • the separation matrix can be updated based on blind source separation, so that the signal The noise ratio is always greater than or equal to a certain value.
  • a processing device for 5G communication signal interference including:
  • the receiving module is used to receive the mixed downhole signal set transmitted by multi-channel;
  • the interference filtering module is used to filter the interference of the mixed downhole signal set transmitted by multiple channels based on the current separation matrix of blind source separation, so as to obtain the target downhole signal set;
  • the interference monitoring module is used to perform interference monitoring on the target downhole signal set when the interference monitoring period is reached, and obtain the signal-to-noise ratio;
  • the matrix update module is configured to perform blind source separation to update the current separation matrix when the signal-to-noise ratio is less than a preset threshold.
  • an electronic device including a memory and a processor
  • the processor runs the program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the method for processing 5G communication signal interference in the embodiment of the first aspect of the present disclosure.
  • a downhole communication device including the processing device or electronic device for 5G communication signal interference as described above.
  • a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method for processing 5G communication signal interference according to the embodiment of the first aspect of the present disclosure is implemented.
  • a computer program product including a computer program.
  • the computer program When the computer program is executed by a processor, the method for processing 5G communication signal interference according to the embodiment of the first aspect of the present disclosure is implemented.
  • FIG. 1 is a flow chart of a method for processing 5G communication signal interference according to an embodiment of the present disclosure
  • Figure 2 is a schematic diagram of the principle of blind source separation
  • Figure 3 is the algorithm flow of blind source separation based on independent component analysis
  • FIG. 4 is a flow chart of a method for processing 5G communication signal interference according to an embodiment of the present disclosure
  • 5 is a flow chart of a method for processing 5G communication signal interference according to an embodiment of the present disclosure
  • FIG. 6 is a flow chart of a method for processing 5G communication signal interference according to an embodiment of the present disclosure
  • FIG. 7 is a structural diagram of a processing device for 5G communication signal interference according to an embodiment of the present disclosure.
  • FIG. 8 is a block diagram of an electronic device used to implement a method for processing 5G communication signal interference according to an embodiment of the present disclosure.
  • Fig. 1 is a flowchart of a method for processing 5G communication signal interference according to an embodiment of the present disclosure. As shown in Fig. 1, the method includes the following steps:
  • the mixed downhole signal is transmitted through wireless communication.
  • radio or other electromagnetic wave wireless technologies such as light, magnetic field, electric field, etc., can be used.
  • the mixed downhole signal set includes downhole 5G communication signals.
  • Blind source separation is a technique that uses a mixture of source signals to recover or extract independent source signals when neither the source signal distribution nor the source signal mixing model is known.
  • the mixed signal is a received mixed downhole signal set.
  • the downhole signal set is regarded as the source signal set. Since both the source signal vector and the mixing matrix A are unknown, solving the separation matrix W is called blind source separation.
  • the separation matrix is obtained based on blind source separation, and the mixed downhole signal set transmitted by multiple channels is multiplied by the current separation matrix to obtain the target downhole signal set. Taking into account the interference suppression capability and low delay characteristics.
  • the blind source separation can use the independent component analysis algorithm.
  • the source signals are statistically independent from each other, the source signals satisfy a non-Gaussian distribution, and the mixing matrix is full rank.
  • the first two conditions are naturally satisfied, and the third condition requires that the number of observation channels is not less than the number of source signals, that is, N ⁇ M.
  • whitening preprocessing is performed on the received mixed signal to "decorrelate" the data to promote the fast convergence of the algorithm.
  • Whitening means that the covariance matrix of the vector is an identity matrix, which is generally realized by eigenvalue decomposition of the covariance matrix.
  • the fourth step is to judge whether W is converged, that is, to judge whether
  • is close to 1, if not converged, n n+1, return to the third step, if converged, output the separation matrix W.
  • SNR is the ratio of signal to noise in an electronic device or electronic system.
  • the signal refers to the output target downhole signal set
  • the noise refers to the random extra signal that does not exist in the mixed downhole signal set, and the noise does not change with the change of the mixed downhole signal set.
  • the interference monitoring period needs to be greater than the sum of the processing duration of interference monitoring and the processing duration of blind source separation. Because when it is detected that the signal quality of the target downhole signal set does not meet the requirements, blind source separation is required to update the separation matrix. After the update is completed, the target downhole signal set will continue to be output. If the interference monitoring period is less than the sum of the processing time of interference monitoring and the processing time of blind source separation, it may happen that the system is updating the separation matrix during interference monitoring and cannot obtain the correct signal-to-noise ratio of the signal.
  • the interference monitoring period can be determined according to the time variation law of the signal-to-noise ratio.
  • the signal-to-noise ratio of the target downhole signal set is monitored in real time for a period of time, and the signal-to-noise ratio of the target downhole signal set will change from the highest value Decrease to the lowest acceptable value, and use this duration as the interference monitoring period.
  • the duration of the interference monitoring period may be shortened, and ensure that the interference monitoring period is greater than the sum of the processing duration of interference monitoring and the processing duration of blind source separation.
  • S104 in response to the signal-to-noise ratio being smaller than the preset threshold, perform blind source separation to update the current separation matrix, and return to receive the mixed downhole signal set transmitted by the multi-channel and follow-up operations.
  • a mixed downhole signal set transmitted by multiple channels is received, blind source separation is performed to obtain a new separation matrix, and a current separation matrix is updated.
  • the mixed downhole signal set transmitted by the multi-channel is multiplied by the updated separation matrix, and the target downhole signal set is continuously obtained, and interference monitoring is performed on the target downhole signal set when the interference monitoring period is reached.
  • blind source separation is performed again to update the current separation matrix, and returns to receive the mixed downhole signal set transmitted by multi-channel and subsequent operations.
  • the mixed downhole signal set transmitted by multi-channel is received, based on the current separation matrix of blind source separation, the interference of the mixed downhole signal set transmitted by multi-channel is filtered to obtain the target downhole signal set, and in response to the arrival interference monitoring period, the target downhole signal set is monitored for interference, and the signal-to-noise ratio is obtained.
  • blind source separation is performed to update the current separation matrix, and returns to the mixed downhole receiving multi-channel transmission.
  • the interference components in the downhole signal are adaptively filtered through the separation matrix, which improves the efficiency of signal anti-interference processing.
  • the separation matrix can be updated based on blind source separation, so that the signal The noise ratio is always greater than a certain value.
  • Fig. 4 is a flowchart of a processing method for 5G communication signal interference according to an embodiment of the present disclosure. On the basis of the above embodiment, further combining with Fig. 4, the process of monitoring the target downhole signal set for interference and obtaining the signal-to-noise ratio Provide an explanation, including the following steps:
  • the convolutional network is essentially an input-to-output mapping, which can learn a large number of mapping relationships between input and output without any precise mathematical expression between input and output, as long as the known
  • the model trains the convolutional network, and the network has the ability to map between input and output pairs.
  • Commonly used convolutional networks include deep complex networks, convolutional neural networks, etc.
  • Deep complex networks are an extension of convolutional neural networks, which have richer representation capabilities and are more robust to noise.
  • the input signals, weights, and activation functions of complex neural networks are all complex numbers, and a special network structure needs to be designed for complex numbers, including complex convolution, complex activation functions, and complex batch normalization.
  • the target downhole signal set is input into the deep complex network, and the feature map of the target downhole signal set is extracted by the feature extraction layer of the deep complex network to obtain the real part and the imaginary part of the feature map.
  • the real and imaginary parts of the feature map are nonlinearly mapped by the complex excitation layer of the deep complex network to obtain the real and imaginary parts of the mapped feature map.
  • the real and imaginary parts of the mapped feature map are pooled by the complex pooling layer of the deep complex network to obtain the pooled feature map.
  • the fully connected layer of the deep complex network performs a fully connected operation on the pooled feature map to output the category of the target downhole signal set.
  • Different signal categories correspond to different signal characteristics, including the signal-to-noise ratio of the signal. According to the signal category of the target downhole signal concentration, the corresponding signal-to-noise ratio is obtained.
  • the target downhole signal set is input into the deep complex network, and the feature map of the target downhole signal set is obtained by the deep complex network, and classification and identification are carried out according to the feature map, and the category of the target downhole signal set is obtained, and according to the target downhole signal set The category of the signal in the signal set to obtain the signal-to-noise ratio.
  • the category of the target downhole signal set is obtained, and the signal-to-noise ratio of the signal is further obtained, so that the signal-to-noise ratio does not need to be obtained through precise mathematical expressions, avoiding errors and improving The accuracy of the signal-to-noise ratio.
  • Fig. 5 is a flowchart of a processing method for 5G communication signal interference according to an embodiment of the present disclosure. On the basis of the above embodiment, further combining with Fig. 5, the process after obtaining the target downhole signal set is explained, including the following steps :
  • the performance of the wireless communication system is greatly affected by the wireless channel, such as shadow fading and frequency selective fading, etc., and the wireless channel is not as fixed and predictable as the wired channel, but has great randomness, so The channel needs to be estimated, so as to provide the required channel information for subsequent signal processing.
  • Channel estimation is the process of estimating the model parameters of an assumed channel model from the received data, and it is a mathematical representation of the influence of the channel on the input signal.
  • the received data is a target downhole signal set, and channel estimation is performed on the target downhole signal set to obtain channel parameters.
  • channel compensation is performed on the target downhole signal set, that is, signals are reinforced through technical means. Through channel compensation, the quality of information transmission can be enhanced, information packet loss can be avoided, and normal information transmission can be guaranteed.
  • Channel equalization refers to an anti-fading measure taken to improve the transmission performance of a communication system in a fading channel. It is mainly to eliminate or weaken the problem of intersymbol interference caused by multipath delay in broadband communication.
  • the received signal is a rectangular pulse wave
  • the signal is sampled to obtain some discrete values at different times. For example, the sample obtained at the first time is 0.9, and the signal is judged. It can be found that the value at this time is very close to 1, therefore, the value of the signal at this time is regarded as 1. Correspondingly, signal judgment is performed on the signal values at other times to judge whether the original value here is 0 or 1.
  • channel estimation is performed on the target downhole signal set
  • channel compensation is performed on the target downhole signal set after channel estimation
  • channel equalization processing is performed on the target downhole signal set after channel compensation
  • a balanced downhole signal set is generated.
  • the downhole signal set performs signal judgment.
  • signal processing is performed on the target downhole signal set, which further improves the anti-interference ability of the signal and improves the signal quality of the signal.
  • FIG. 6 is a flow chart of a processing method for 5G communication signal interference according to an embodiment of the present disclosure. As shown in FIG. 6 , based on the processing method for 5G communication signal interference provided by the present disclosure, the processing process of signal interference in an actual application scenario include the following steps.
  • Step 1 receiving a mixed downhole signal set transmitted by multiple channels.
  • Step 2 Based on the current separation matrix of blind source separation, the interference of the mixed downhole signal set transmitted by the multi-channel is filtered to obtain the target downhole signal set.
  • Step 3 perform channel estimation on the target downhole signal set.
  • Step 4 perform channel compensation on the target downhole signal set after channel estimation.
  • Step 5 Perform channel equalization processing on the target downhole signal set after channel compensation to generate a balanced downhole signal set.
  • Step 6 Carry out signal judgment on the balanced downhole signal set and output it.
  • Step seven in response to reaching the interference monitoring period, perform interference monitoring on the target downhole signal set to obtain a signal-to-noise ratio.
  • Step 8 In response to the signal-to-noise ratio being smaller than the preset threshold, perform blind source separation to update the current separation matrix, and return to receive the mixed downhole signal set transmitted by the multi-channel and follow-up operations.
  • the interference components in the downhole signal are filtered out to the greatest extent, and the separation matrix can be updated based on blind source separation, so that The signal-to-noise ratio of the target downhole signal set is always greater than or equal to a certain value.
  • FIG. 7 is a structural diagram of a processing device for 5G communication signal interference according to an embodiment of the present disclosure. As shown in FIG. 7 , the processing device 700 for 5G communication signal interference includes:
  • a receiving module 710 configured to receive a mixed downhole signal set transmitted by multiple channels
  • the interference filtering module 720 is configured to filter the interference of the mixed downhole signal set transmitted by multiple channels based on the current separation matrix of blind source separation, so as to obtain the target downhole signal set;
  • the interference monitoring module 730 is configured to perform interference monitoring on the target downhole signal set when the interference monitoring period is reached, and obtain a signal-to-noise ratio;
  • the matrix update module 740 is configured to perform blind source separation to update the current separation matrix when the signal-to-noise ratio is less than a preset threshold.
  • the interference components in the downhole signal are adaptively filtered through the separation matrix, which improves the efficiency of signal anti-interference processing.
  • the separation matrix can be updated based on blind source separation, so that the signal The noise ratio is always greater than or equal to a certain value.
  • the interference filtering module 720 is further configured to: multiply the mixed downhole signal set transmitted by multiple channels by the current separation matrix to obtain the target downhole signal set.
  • the interference monitoring module 730 is also configured to: input the target downhole signal set into the deep complex network, obtain the feature map of the target downhole signal set by the deep complex network, and Classify and identify according to the feature map to obtain the category of the concentrated signal of the target downhole signal; obtain the signal-to-noise ratio according to the category of the concentrated signal of the target downhole signal.
  • the interference monitoring module 730 is also used to: use the feature extraction layer of the deep complex network to extract the feature map of the target downhole signal set, so as to obtain the real part of the feature map and the imaginary part; the real part and imaginary part of the feature map are nonlinearly mapped by the complex excitation layer of the deep complex network to obtain the real part and imaginary part of the mapped feature map; the complex pooling layer of the deep complex network maps the The real and imaginary parts of the feature map are pooled to obtain the pooled feature map; the fully connected layer of the deep complex network performs a fully connected operation on the pooled feature map to output the category of the target downhole signal concentration signal.
  • the 5G communication signal interference processing device 700 further includes: a signal processing module 750, configured to perform channel estimation on the target downhole signal set; Channel compensation is performed on the signal set; channel equalization processing is performed on the target downhole signal set after channel compensation to generate a balanced downhole signal set; signal judgment is performed on the balanced downhole signal set.
  • a signal processing module 750 configured to perform channel estimation on the target downhole signal set; Channel compensation is performed on the signal set; channel equalization processing is performed on the target downhole signal set after channel compensation to generate a balanced downhole signal set; signal judgment is performed on the balanced downhole signal set.
  • the interference monitoring period is greater than the sum of the processing duration of interference monitoring and the processing duration of blind source separation.
  • the present disclosure also provides a communication device, an electronic device, a computer-readable storage medium, and a computer program product.
  • a communication device or mobile device in this application may refer to a cellular phone, smart phone, personal or mobile multimedia player, personal data assistant, laptop computer, tablet computer, smart book, palmtop computer, wireless email receiver, support In cellular telephones for multimedia Internet, wireless game controllers, and similar personal electronic devices including programmable processors, memory, and circuitry for connection to one or more mobile communication networks with one or more shared RF resources any or all.
  • FIG. 8 shows a schematic block diagram of an example electronic device 800 that may be used to implement embodiments of the present disclosure.
  • Electronic device is intended to mean various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • FIG. 8 it includes a memory 810, a processor 820, and a computer program stored on the memory 810 and operable on the processor 820.
  • the processor 820 executes the program, it implements the aforementioned 5G communication signal interference processing method.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • non-transitory computer-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable Read Only Memory (EPROM or Flash Memory), Optical Fiber, Compact Disc Read Only Memory (CD-ROM), Optical Storage, Magnetic Storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or Flash Memory erasable programmable Read Only Memory
  • Optical Fiber Compact Disc Read Only Memory
  • CD-ROM Compact Disc Read Only Memory
  • Optical Storage Magnetic Storage
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer.
  • a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or a trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
  • the server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.
  • first and second are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, a feature defined as “first” and “second” may explicitly or implicitly include one or more of these features.
  • “plurality” means two or more, unless otherwise specifically defined.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Power Engineering (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Theoretical Computer Science (AREA)
  • Noise Elimination (AREA)

Abstract

本公开提供了一种5G通信信号干扰的处理方法和装置。该方法包括：接收多通道传输的混合井下信号集；基于盲源分离的当前分离矩阵，对多通道传输的混合井下信号集的干扰进行过滤，以获取目标井下信号集；响应于到达干扰监控周期，则对目标井下信号集进行干扰监控，获取信噪比；响应于信噪比小于预设阈值，则执行盲源分离对当前分离矩阵进行更新，并返回执行接收多通道传输的混合井下信号集及后续操作。

Description

5G通信信号干扰的处理方法和装置
相关申请的交叉引用
本申请基于申请号为202111335292.0、申请日为2021年11月11日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开涉及信号处理领域，尤其涉及一种5G通信信号干扰的处理方法和装置。
背景技术
煤矿井下巷道复杂，空间狭小，大型机电设备众多，容易对信号产生多因素干扰的叠加。相关技术中所考虑的实际干扰情况较少，无法对煤矿的实际干扰情况进行较为完善和全面的处理，同时，针对不同干扰源将应使用不同的方法处理，多种方法直接叠加整合会使得运算量过大，造成时延过高，影响信号抗干扰处理的速度和效率。
发明内容
根据本公开的一方面，提供了一种5G通信信号干扰的处理方法，包括：
接收多通道传输的混合井下信号集；
基于盲源分离的当前分离矩阵，对多通道传输的混合井下信号集的干扰进行过滤，以获取目标井下信号集；
响应于到达干扰监控周期，则对目标井下信号集进行干扰监控，获取信噪比；
响应于信噪比小于预设阈值，则执行盲源分离对当前分离矩阵进行更新，并返回执行接收多通道传输的混合井下信号集及后续操作。
本公开实施例中通过分离矩阵自适应地过滤掉井下信号中的干扰成分，提高了信号抗干扰处理的效率，同时可以基于盲源分离对分离矩阵进行更新，使通过分离矩阵获取的信号的信噪比始终大于等于一个特定值。
根据本公开的另一方面，提供了一种5G通信信号干扰的处理装置，包括：
接收模块，用于接收多通道传输的混合井下信号集；
干扰过滤模块，用于基于盲源分离的当前分离矩阵，对多通道传输的混合井下信号集的干扰进行过滤，以获取目标井下信号集；
干扰监控模块，用于在到达干扰监控周期时，对目标井下信号集进行干扰监控，获取信噪比；
矩阵更新模块，用于在信噪比小于预设阈值，执行盲源分离对当前分离矩阵进行更新。
根据本公开的另一方面，提供了一种电子设备，包括存储器、处理器；
其中，处理器通过读取存储器中存储的可执行程序代码来运行与可执行程序代码对应的程序，以用于实现本公开第一个方面实施例的5G通信信号干扰的处理方法。
根据本公开的另一方面，提供了一种井下通信设备，包括如上所述的5G通信信号干扰的处理装置或电子设备。
根据本公开的另一方面，提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现本公开第一个方面实施例的5G通信信号干扰的处理方法。
根据本公开的另一方面，提供了一种计算机程序产品，包括计算机程序，计算机程序在被处理器执行时实现本公开第一个方面实施例的5G通信信号干扰的处理方法。
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。
附图说明
图1是根据本公开一个实施例的5G通信信号干扰的处理方法的流程图；
图2是盲源分离的原理示意图；
图3是基于独立成分分析的盲源分离的算法流程；
图4是根据本公开一个实施例的5G通信信号干扰的处理方法的流程图；
图5是根据本公开一个实施例的5G通信信号干扰的处理方法的流程图；
图6是根据本公开一个实施例的5G通信信号干扰的处理方法的流程图；
图7是根据本公开一个实施例的5G通信信号干扰的处理装置的结构图；
图8是用来实现本公开实施例的5G通信信号干扰的处理方法的电子设备的框图。
具体实施方式
下面详细描述本发明的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，旨在用于解释本发明，而不能理解为对本发明的限制。
下面结合参考附图描述本公开的5G通信信号干扰的处理方法、装置和电子设备。
图1是根据本公开一个实施例的5G通信信号干扰的处理方法的流程图，如图1所示，该方法包括以下步骤：
S101，接收多通道传输的混合井下信号集。
从N个通道获得N个混合井下信号x i(t)，i＝1,2,...,N，组成混合井下信号集，用向量表示为x＝[x 1(t),x 2(t),...,x N(t)] T，因为所有信号基于相同的时间轴t，所以混合井下信号集的向量可简写为x＝[x 1,x 2,...,x N] T。
混合井下信号通过无线通信方式进行传输，可选地，可以使用无线电，或是其他的电磁波无线技术，例如光、磁场、电场等。
混合井下信号集中包括井下5G通信信号。
S102，基于盲源分离的当前分离矩阵，对多通道传输的混合井下信号集的干扰进行过滤，以获取目标井下信号集。
盲源分离是在既不知道源信号的分布，也不知道源信号混合模型的情况下，利用源信号的混合信号来恢复或提取独立源信号的技术。图2是盲源分离的原理示意图，如图2所示，M个独立源信号通过混合矩阵A后混合为N个混合信号，A是N×M的混合矩阵，当源信号向量s＝[s 1,s 2,...,s M] T，混合信号向量x＝[x 1,x 2,...,x N] T时，x＝As。在本公开实施例中，混合信号为接收到的混合井下信号集。
盲源分离的目标是利用混合信号向量x来恢复源信号向量s，即s≈y＝Wx，在本公开实施例中，即为利用混合井下信号集来得到目标井下信号集，将得到的目标井下信号集视为源信号集。由于源信号向量和混合矩阵A都是未知的，所以求解分离矩阵W被称为盲源分离。
由于进行实时盲源分离会导致系统产生过大时延，本公开实施例中基于盲源分离得到分离矩阵，将多通道传输的混合井下信号集与当前分离矩阵做乘法，获取目标井下信号集，兼顾了干扰抑制能力和低时延特性。
可选地，盲源分离可以采用独立成分分析算法，实现独立成分分析需要满足三个条件：源信号是相互统计独立的，源信号满足非高斯分布，混合矩阵是列满秩的。对于煤矿井下5G通信信号和干扰信号而言，前两个条件是天然满足的，第三个条件要求观测通道个数不低于源信号个数，即N≥M，可借助采样分集技术，算法流程如图3所示。
第一步，对接收到的混合信号进行白化预处理，使数据“去相关”，以促进算法的快速收敛。白化性指的是向量的协方差矩阵是单位矩阵，一般利用协方差矩阵的特征值分解来实现。
第二步，选择初始分离点W 0，进行初始输出y 0＝W 0x。
第三步，通过迭代更新规则，更新分离矩阵W n+1＝W n+μ(I+f(x)x H)W n，其中μ为学习因 子，I为单位阵，f(x)为激活函数，可选择f(x)＝-|x| 3sgn(x)。
第四步，判断W是否收敛，即判断|(W n+1) HW n|是否接近1，如果不收敛，n＝n+1，返回第三步，如果收敛，输出分离矩阵W。
S103，响应于到达干扰监控周期，则对目标井下信号集进行干扰监控，获取信噪比。
设置一个固定时长作为信号的干扰监控周期，每隔一个干扰监控周期，采集此刻输出的目标井下信号集，对目标井下信号集进行干扰监控，获取信噪比。
信噪比是指一个电子设备或者电子系统中信号与噪声的比例。本公开实施例中，信号指的是输出的目标井下信号集，噪声指的是混合井下信号集中并不存在的无规则的额外信号，并且噪声并不随混合井下信号集的变化而变化。
一般来说，信噪比越大，说明混在信号里的噪声越小，信号质量越高；信噪比越小，说明混在信号里的噪声越大，信号质量越低。
在本公开实施例的实现中，干扰监控周期需大于干扰监控的处理时长和盲源分离的处理时长的和值。因为当监测到目标井下信号集的信号质量不满足需求时，需进行盲源分离对分离矩阵进行更新，更新完成后，才会继续输出目标井下信号集。若干扰监控周期小于干扰监控的处理时长和盲源分离的处理时长的和值，可能出现当进行干扰监控时，系统正在对分离矩阵进行更新，无法获取信号正确的信噪比。
干扰监控周期可根据信噪比的时间变化规律而决定，对一段时间内的目标井下信号集的信噪比进行实时监控，观察经过多长时间，目标井下信号集的信噪比会从最高值下降到所能接受的最低值，将这个时长作为干扰监控周期。可选地，为了保证目标井下信号集的信号质量始终保持在较好状态，可缩短干扰监控周期的时长，并保证干扰监控周期大于干扰监控的处理时长和盲源分离的处理时长的和值。
S104，响应于信噪比小于预设阈值，则执行盲源分离对当前分离矩阵进行更新，并返回执行接收多通道传输的混合井下信号集及后续操作。
设置所能接受的最低信号质量所对应的信号的信噪比为信噪比的阈值，当干扰监控获取的信噪比小于预设阈值时，证明目标井下信号集的信号质量未达到所能接受的最低信号质量。
响应于信噪比小于预设阈值，接收多通道传输的混合井下信号集，执行盲源分离获取新的分离矩阵，对当前分离矩阵进行更新。在更新完成后将多通道传输的混合井下信号集与更新后的分离矩阵做乘法，继续获取目标井下信号集，并在到达干扰监控周期时对目标井下信号集进行干扰监控。响应于某次干扰监控获得的信号信噪比小于预设阈值，则再次执行盲源 分离对当前分离矩阵进行更新，并返回执行接收多通道传输的混合井下信号集及后续操作。
本公开实施例中，接收多通道传输的混合井下信号集，基于盲源分离的当前分离矩阵，对多通道传输的混合井下信号集的干扰进行过滤，以获取目标井下信号集，响应于到达干扰监控周期，则对目标井下信号集进行干扰监控，获取信噪比，响应于信噪比小于预设阈值，则执行盲源分离对当前分离矩阵进行更新，并返回执行接收多通道传输的混合井下信号集及后续操作。本公开实施例中通过分离矩阵自适应地过滤掉井下信号中的干扰成分，提高了信号抗干扰处理的效率，同时可以基于盲源分离对分离矩阵进行更新，使通过分离矩阵获取的信号的信噪比始终大于一个特定值。
图4是根据本公开一个实施例的5G通信信号干扰的处理方法的流程图，在上述实施例的基础上，进一步结合图4，将对目标井下信号集进行干扰监控，获取信噪比的过程进行解释说明，包括以下步骤：
S401，将目标井下信号集输入深度复数网络中，由深度复数网络获取目标井下信号集的特征图，并根据特征图进行分类识别，获取目标井下信号集中信号的类别。
卷积网络在本质上是一种输入到输出的映射，它能够学习大量的输入与输出之间的映射关系，而不需要任何输入和输出之间的精确的数学表达式，只要用已知的模式对卷积网络加以训练，网络就具有输入输出对之间的映射能力。常用的卷积网络包括深度复数网络、卷积神经网络等。
深度复数网络是卷积神经网络的扩展，它具有更加丰富的表征能力，且对噪声具有更强的鲁棒性。复数神经网络的输入信号、权值以及激活函数等都是复数，需要针对复数设计专门的网络结构，包括复数卷积、复数激活函数、复数批归一化。
将目标井下信号集输入深度复数网络中，由深度复数网络的特征提取层对目标井下信号集进行特征图提取，以获取特征图的实部和虚部。由深度复数网络的复数激励层对特征图的实部和虚部进行非线性映射，得到映射后特征图的实部和虚部。由深度复数网络的复数池化层对映射后特征图的实部和虚部进行池化操作，获取池化后特征图。由深度复数网络的全连接层对池化后特征图进行全连接操作，以输出目标井下信号集中信号的类别。
S402，根据目标井下信号集中信号的类别，获取信噪比。
不同的信号类别对应不同的信号特征，包括信号的信噪比，根据目标井下信号集中信号的类别，获取到对应的信噪比。
本公开实施例中，将目标井下信号集输入深度复数网络中，由深度复数网络获取目标井下信号集的特征图，并根据特征图进行分类识别，获取目标井下信号集中信号的类别，根据 目标井下信号集中信号的类别，获取信噪比。本公开实施例中基于深度复数网络的学习能力得到目标井下信号集的类别，进一步得到的信号的信噪比，使信号信噪比不需要通过精确的数学表达式得到，避免了误差，提高了信噪比的精确性。
图5是根据本公开一个实施例的5G通信信号干扰的处理方法的流程图，在上述实施例的基础上，进一步结合图5，对获取目标井下信号集之后的过程进行解释说明，包括以下步骤：
S501，对目标井下信号集进行信道估计。
无线通信系统的性能很大程度上受到无线信道的影响，如阴影衰落和频率选择性衰落等等，并且无线信道并不像有线信道一样固定并可预见，而是具有很大的随机性，所以需要对信道进行估计，从而为后续的信号处理提供所需的信道信息。
信道估计，就是从接收数据中将假定的某个信道模型的模型参数估计出来的过程，是信道对输入信号影响的一种数学表示。在本公开实施例中，接收数据为目标井下信号集，对目标井下信号集进行信道估计，得到信道参数。
S502，对经过信道估计的目标井下信号集进行信道补偿。
基于信道估计得到的信道参数，对目标井下信号集进行信道补偿，即通过技术手段补强信号。通过信道补偿，可以加强信息传输的质量，避免信息丢包，保障正常信息传输。
S503，对经过信道补偿的目标井下信号集进行信道均衡处理，生成均衡井下信号集。
信道均衡是指为了提高衰落信道中的通信系统的传输性能而采取的一种抗衰落措施。它主要是为了消除或者是减弱宽带通信时的多径时延带来的码间串扰问题。
对经过信道补偿的目标井下信号集进行信道均衡处理，可选地，对信道或整个传输系统特性进行补偿，生成均衡井下信号集。
S504，对均衡井下信号集进行信号判决。
在信号的传输过程中有各种干扰，如噪声和码间串扰等，经过信号干扰的处理后，仍然可能产生误差，使得到的信号值与实际值不相同。
当接收的信号为矩形脉冲波时，对信号进行抽样，得到在不同的时刻的一些离散的值，如在第一个时刻抽样得到的是0.9，进行信号判决，可以发现此时的值很接近1，因此，此时的信号的值就当成1。相应地，对其他时刻的信号值进行信号判决，判断此处原来的值到底是0还是1。
本公开实施例中，对目标井下信号集进行信道估计，对经过信道估计的目标井下信号集进行信道补偿，对经过信道补偿的目标井下信号集进行信道均衡处理，生成均衡井下信号集， 对均衡井下信号集进行信号判决。本公开实施例中对目标井下信号集进行信号处理，进一步提高了信号的抗干扰能力，提高了信号的信号质量。
图6是根据本公开一个实施例的5G通信信号干扰的处理方法的流程图，如图6所示，基于本公开提供的5G通信信号干扰的处理方法，在实际应用场景下信号干扰的处理过程包括以下步骤。
步骤一，接收多通道传输的混合井下信号集。
步骤二，基于盲源分离的当前分离矩阵，对多通道传输的混合井下信号集的干扰进行过滤，以获取目标井下信号集。
步骤三，对目标井下信号集进行信道估计。
步骤四，对经过信道估计的目标井下信号集进行信道补偿。
步骤五，对经过信道补偿的目标井下信号集进行信道均衡处理，生成均衡井下信号集。
步骤六，对均衡井下信号集进行信号判决并输出。
步骤七，响应于到达干扰监控周期，对目标井下信号集进行干扰监控，获取信噪比。
步骤八，响应于信噪比小于预设阈值，则执行盲源分离对当前分离矩阵进行更新，并返回执行接收多通道传输的混合井下信号集及后续操作。
关于本实施例各个步骤的具体实现可以参见本公开各实施例中相关介绍，此处不再赘述。
本公开实施例中，通过对混合井下信号集进行信号分离、信道补偿、信道均衡等处理，最大程度地过滤掉了井下信号中的干扰成分，同时可以基于盲源分离对分离矩阵进行更新，使目标井下信号集的信噪比始终大于等于一个特定值。
图7是根据本公开一个实施例的5G通信信号干扰的处理装置的结构图，如图7所示，5G通信信号干扰的处理装置700包括：
接收模块710，用于接收多通道传输的混合井下信号集；
干扰过滤模块720，用于基于盲源分离的当前分离矩阵，对多通道传输的混合井下信号集的干扰进行过滤，以获取目标井下信号集；
干扰监控模块730，用于在到达干扰监控周期时，对目标井下信号集进行干扰监控，获取信噪比；
矩阵更新模块740，用于在信噪比小于预设阈值，执行盲源分离对当前分离矩阵进行更新。
本公开实施例中通过分离矩阵自适应地过滤掉井下信号中的干扰成分，提高了信号抗干 扰处理的效率，同时可以基于盲源分离对分离矩阵进行更新，使通过分离矩阵获取的信号的信噪比始终大于等于一个特定值。
需要说明的是，前述对5G通信信号干扰的处理方法实施例的解释说明也适用于该实施例的5G通信信号干扰的处理装置，此处不再赘述。
进一步地，在本公开实施例一种可能的实现方式中，干扰过滤模块720，还用于：将多通道传输的混合井下信号集与当前分离矩阵做乘法，获取目标井下信号集。
进一步地，在本公开实施例一种可能的实现方式中，干扰监控模块730，还用于：将目标井下信号集输入深度复数网络中，由深度复数网络获取目标井下信号集的特征图，并根据特征图进行分类识别，获取目标井下信号集中信号的类别；根据目标井下信号集中信号的类别，获取信噪比。
进一步地，在本公开实施例一种可能的实现方式中，干扰监控模块730，还用于：由深度复数网络的特征提取层对目标井下信号集进行特征图提取，以获取特征图的实部和虚部；由深度复数网络的复数激励层对特征图的实部和虚部进行非线性映射，得到映射后特征图的实部和虚部；由深度复数网络的复数池化层对映射后特征图的实部和虚部进行池化操作，获取池化后特征图；由深度复数网络的全连接层对池化后特征图进行全连接操作，以输出目标井下信号集中信号的类别。
进一步地，在本公开实施例一种可能的实现方式中，5G通信信号干扰的处理装置700还包括：信号处理模块750，用于对目标井下信号集进行信道估计；对经过信道估计的目标井下信号集进行信道补偿；对经过信道补偿的目标井下信号集进行信道均衡处理，生成均衡井下信号集；对均衡井下信号集进行信号判决。
进一步地，在本公开实施例一种可能的实现方式中，干扰监控周期大于干扰监控的处理时长和盲源分离的处理时长的和值。
根据本公开的实施例，本公开还提供了一种通信设备、一种电子设备、一种计算机可读存储介质和一种计算机程序产品。
本申请中的通信设备或移动设备可以是指蜂窝电话、智能电话、个人或移动多媒体播放器、个人数据助理、膝上型计算机、平板电脑、智能书籍、掌上电脑、无线电子邮件接收机、支持多媒体互联网的蜂窝电话、无线游戏控制器，以及包括用于连接到具有一个或多个共享RF资源的一个或多个移动通信网络的可编程处理器、存储器和电路的类似的个人电子设备中的任何一个或全部。
图8示出了可以用来实施本公开的实施例的示例电子设备800的示意性框图。电子设备 旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图8所示，包括存储器810、处理器820及存储在存储器810上并可在处理器820上运行的计算机程序，处理器820执行程序时，实现前述的5G通信信号干扰的处理方法。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。非临时性计算机可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序 来产生客户端和服务器的关系。服务器可以是云服务器，也可以为分布式系统的服务器，或者是结合了区块链的服务器。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。在本发明的描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
尽管上面已经示出和描述了本发明的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本发明的限制，本领域的普通技术人员在本发明的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (15)

  1. 一种5G通信信号干扰的处理方法，包括：
    接收多通道传输的混合井下信号集；
    基于盲源分离的当前分离矩阵，对所述多通道传输的混合井下信号集的干扰进行过滤，以获取目标井下信号集；
    响应于到达干扰监控周期，则对所述目标井下信号集进行干扰监控，获取信噪比；
    响应于所述信噪比小于预设阈值，则执行盲源分离对所述当前分离矩阵进行更新，并返回执行所述接收多通道传输的混合井下信号集及后续操作。
  2. 根据权利要求1所述的方法，其中所述基于盲源分离的当前分离矩阵，对所述多通道传输的混合井下信号集的干扰进行过滤，以获取目标井下信号集，包括：
    将所述多通道传输的混合井下信号集与所述当前分离矩阵做乘法，获取所述目标井下信号集。
  3. 根据权利要求1或2所述的方法，其中所述对所述目标井下信号集进行干扰监控，获取信噪比，包括：
    将所述目标井下信号集输入深度复数网络中，由所述深度复数网络获取所述目标井下信号集的特征图，并根据所述特征图进行分类识别，获取所述目标井下信号集中信号的类别；
    根据所述目标井下信号集中信号的类别，获取所述信噪比。
  4. 根据权利要求3所述的方法，其中所述由所述深度复数网络获取所述目标井下信号的特征图，并根据所述特征图进行分类识别，获取所述目标井下信号中信号的类别，包括：
    由所述深度复数网络的特征提取层对所述目标井下信号集进行特征图提取，以获取所述特征图的实部和虚部；
    由所述深度复数网络的复数激励层对所述特征图的实部和虚部进行非线性映射，得到映射后特征图的实部和虚部；
    由所述深度复数网络的复数池化层对所述映射后特征图的实部和虚部进行池化操作，获取池化后特征图；
    由所述深度复数网络的全连接层对所述池化后特征图进行全连接操作，以输出所述目标井下信号集中信号的类别。
  5. 根据权利要求1至4中任一项所述的方法，其中所述干扰监控周期大于所述干扰监控的处理时长和所述盲源分离的处理时长的和值。
  6. 根据权利要求1至5中任一项所述的方法，其中所述获取目标井下信号集之后，还包 括：
    对所述目标井下信号集进行信道估计；
    对经过信道估计的所述目标井下信号集进行信道补偿；
    对经过信道补偿的所述目标井下信号集进行信道均衡处理，生成均衡井下信号集；
    对所述均衡井下信号集进行信号判决。
  7. 一种5G通信信号干扰的处理装置，包括：
    接收模块，用于接收多通道传输的混合井下信号集；
    干扰过滤模块，用于基于盲源分离的当前分离矩阵，对所述多通道传输的混合井下信号集的干扰进行过滤，以获取目标井下信号集；
    干扰监控模块，用于在到达干扰监控周期时，对所述目标井下信号集进行干扰监控，获取信噪比；
    矩阵更新模块，用于在所述信噪比小于预设阈值，执行盲源分离对所述当前分离矩阵进行更新。
  8. 根据权利要求7所述的装置，其中所述干扰过滤模块，进一步用于：
    将所述多通道传输的混合井下信号集与所述当前分离矩阵做乘法，获取所述目标井下信号集。
  9. 根据权利要求7或8所述的装置，其中所述干扰监控模块，进一步用于：
    将所述目标井下信号集输入深度复数网络中，由所述深度复数网络获取所述目标井下信号集的特征图，并根据所述特征图进行分类识别，获取所述目标井下信号集中信号的类别；
    根据所述目标井下信号集中信号的类别，获取所述信噪比。
  10. 根据权利要求9所述的装置，其中所述干扰监控模块，进一步用于：
    由所述深度复数网络的特征提取层对所述目标井下信号集进行特征图提取，以获取所述特征图的实部和虚部；
    由所述深度复数网络的复数激励层对所述特征图的实部和虚部进行非线性映射，得到映射后特征图的实部和虚部；
    由所述深度复数网络的复数池化层对所述映射后特征图的实部和虚部进行池化操作，获取池化后特征图；
    由所述深度复数网络的全连接层对所述池化后特征图进行全连接操作，以输出所述目标井下信号集中信号的类别。
  11. 根据权利要求7至10中任一项所述的装置，还包括：
    信号处理模块，用于对目标井下信号集进行信道估计；对经过信道估计的目标井下信号集进行信道补偿；对经过信道补偿的目标井下信号集进行信道均衡处理，生成均衡井下信号集；对均衡井下信号集进行信号判决。
  12. 一种电子设备，包括存储器、处理器；
    其中，所述处理器通过读取所述存储器中存储的可执行程序代码来运行与可执行程序代码对应的程序，以用于实现如权利要求1至6中任一项所述的5G通信信号干扰的处理方法。
  13. 一种井下通信设备，包括如权利要求7至11中任一项所述的5G通信信号干扰的处理装置或如权利要求12所述的电子设备。
  14. 一种计算机可读存储介质，其上存储有计算机程序，其上存储有计算机程序，所述程序被处理器执行时实现如权利要求1至6中任一项所述的5G通信信号干扰的处理方法。
  15. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现如权利要求1至6中任一项所述的5G通信信号干扰的处理方法。
PCT/CN2022/094759 2021-11-11 2022-05-24 5g通信信号干扰的处理方法和装置 WO2023082597A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020237009689A KR20230070460A (ko) 2021-11-11 2022-05-24 5g 통신 신호의 간섭 처리 방법 및 장치

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111335292.0 2021-11-11
CN202111335292.0A CN113783813B (zh) 2021-11-11 2021-11-11 5g通信信号干扰的处理方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023082597A1 true WO2023082597A1 (zh) 2023-05-19

Family

ID=78956890

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/094759 WO2023082597A1 (zh) 2021-11-11 2022-05-24 5g通信信号干扰的处理方法和装置

Country Status (3)

Country Link
KR (1) KR20230070460A (zh)
CN (1) CN113783813B (zh)
WO (1) WO2023082597A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113783813B (zh) * 2021-11-11 2022-02-08 煤炭科学技术研究院有限公司 5g通信信号干扰的处理方法、装置、电子设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020136328A1 (en) * 2000-11-01 2002-09-26 International Business Machines Corporation Signal separation method and apparatus for restoring original signal from observed data
CN110046653A (zh) * 2019-03-22 2019-07-23 赣州好朋友科技有限公司 一种基于xrt射线的白钨分选方法和系统
CN111415676A (zh) * 2020-03-10 2020-07-14 山东大学 一种基于分离矩阵初始化频点选择的盲源分离方法及系统
CN112349292A (zh) * 2020-11-02 2021-02-09 深圳地平线机器人科技有限公司 信号分离方法和装置、计算机可读存储介质、电子设备
CN113098853A (zh) * 2020-12-14 2021-07-09 北京航空航天大学合肥创新研究院 车载网络虚假信息注入异常行为检测方法
CN113783813A (zh) * 2021-11-11 2021-12-10 煤炭科学技术研究院有限公司 5g通信信号干扰的处理方法、装置、电子设备及存储介质
CN216356771U (zh) * 2021-11-11 2022-04-19 煤炭科学技术研究院有限公司 5g通信信号干扰的处理装置及井下通信设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6931362B2 (en) * 2003-03-28 2005-08-16 Harris Corporation System and method for hybrid minimum mean squared error matrix-pencil separation weights for blind source separation
KR100647286B1 (ko) * 2004-08-14 2006-11-23 삼성전자주식회사 교차채널 간섭을 제거하기 위한 후처리장치 및 방법과이를 이용한 다채널 음원 분리장치 및 방법
CN113223553B (zh) * 2020-02-05 2023-01-17 北京小米移动软件有限公司 分离语音信号的方法、装置及介质
CN113283572B (zh) * 2021-05-31 2024-06-07 中国人民解放军空军工程大学 基于改进人工蜂群的盲源分离抗主瓣干扰方法及装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020136328A1 (en) * 2000-11-01 2002-09-26 International Business Machines Corporation Signal separation method and apparatus for restoring original signal from observed data
CN110046653A (zh) * 2019-03-22 2019-07-23 赣州好朋友科技有限公司 一种基于xrt射线的白钨分选方法和系统
CN111415676A (zh) * 2020-03-10 2020-07-14 山东大学 一种基于分离矩阵初始化频点选择的盲源分离方法及系统
CN112349292A (zh) * 2020-11-02 2021-02-09 深圳地平线机器人科技有限公司 信号分离方法和装置、计算机可读存储介质、电子设备
CN113098853A (zh) * 2020-12-14 2021-07-09 北京航空航天大学合肥创新研究院 车载网络虚假信息注入异常行为检测方法
CN113783813A (zh) * 2021-11-11 2021-12-10 煤炭科学技术研究院有限公司 5g通信信号干扰的处理方法、装置、电子设备及存储介质
CN216356771U (zh) * 2021-11-11 2022-04-19 煤炭科学技术研究院有限公司 5g通信信号干扰的处理装置及井下通信设备

Also Published As

Publication number Publication date
CN113783813A (zh) 2021-12-10
KR20230070460A (ko) 2023-05-23
CN113783813B (zh) 2022-02-08

Similar Documents

Publication Publication Date Title
CN110600017B (zh) 语音处理模型的训练方法、语音识别方法、系统及装置
US20230040555A1 (en) Systems and Methods for Distributed On-Device Learning with Data-Correlated Availability
CN108735202A (zh) 用于小占用资源关键词检索的卷积递归神经网络
CN111667054A (zh) 生成神经网络模型的方法、装置、电子设备以及存储介质
CN113301442B (zh) 确定直播资源的方法、设备、介质及程序产品
CN110929839B (zh) 训练神经网络的方法和装置、电子设备和计算机存储介质
CN111862987B (zh) 语音识别方法和装置
CN112560996A (zh) 用户画像识别模型训练方法、设备、可读存储介质及产品
WO2023082597A1 (zh) 5g通信信号干扰的处理方法和装置
CN111628946A (zh) 一种信道估计的方法以及接收设备
CN113657467B (zh) 模型预训练方法、装置、电子设备和存储介质
WO2014143447A1 (en) Voice recognition configuration selector and method of operation therefor
CN111863036B (zh) 语音检测的方法和装置
CN113627536A (zh) 模型训练、视频分类方法，装置，设备以及存储介质
CN112784985A (zh) 神经网络模型的训练方法及装置、图像识别方法及装置
CN114936323A (zh) 图表示模型的训练方法、装置及电子设备
WO2024027246A1 (zh) 声音信号处理方法、装置、电子设备和存储介质
Duzenli et al. A new method of spectrum sensing in cognitive radio for dynamic and randomly modelled primary users
US9705646B2 (en) Multi-input multi-output (MIMO) detection systems
CN112748899A (zh) 一种数据处理方法和相关设备
Mukhopadhyay et al. Blind system identification in noise using a dynamic-based estimator
CN114358162A (zh) 一种基于连续小波变换的跌倒检测方法、装置及电子设备
CN114171043A (zh) 回声的确定方法、装置、设备以及存储介质
CN115312042A (zh) 用于处理音频的方法、装置、设备以及存储介质
CN114582332B (zh) 一种音频的处理方法、装置以及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22891407

Country of ref document: EP

Kind code of ref document: A1