Vehicle-ground communication multipath interference suppression method, electronic equipment and storage medium

By dynamically selecting the train terminal position and adjusting the sampling interval in the vehicle-to-ground communication scenario, and training the multipath interference suppression model in combination with the train driving length and track length, the poor multipath interference suppression effect in the mobile communication of the vehicle-to-ground communication in the prior art CRRC is solved. The problem is to achieve more efficient channel simulation and stronger adaptability.

CN119031398APending Publication Date: 2024-11-26CHENGDU ETHER NODE TECH CO LTD

Patent Information

Application Number
CN202411048953.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The prior art cannot effectively suppress multipath interference in vehicle-site communication scenarios, and statically selected sampling simulation points cannot balance the number of sampling points and sampling accuracy, resulting in a degradation of communication performance in vehicle-site mobile communication environment.

Method used

Dynamically select the train terminal position in the simulation space, combine the train driving length and track length for multi-path interference suppression model training, channel simulation is performed through ray tracing method, and sampling intervals are dynamically adjusted to balance simulation workload and accuracy, and establish adaptive vehicle-ground movements. Multipath interference suppression model for communication scenarios.

Benefits of technology

Multipath interference suppression in vehicle-to-ground mobile communication scenarios is realized, channel simulation workload is reduced, and accuracy is improved for different communication environments and adaptability is stronger.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119031398A_ABST
    Figure CN119031398A_ABST
Patent Text Reader

Abstract

The invention discloses a train-ground communication multipath interference suppression method, electronic equipment and a storage medium, and the method comprises the steps: S1, building a simulation space according to a train-ground communication scene, and determining the position of a track and the position of a ground base station; s2, presetting a train running direction, selecting a plurality of train terminal positions according to a train running method in a track position length range, simulating train-ground communication modes of train transmitting and ground receiving and ground transmitting and train receiving for each selected train terminal position, performing channel simulation on the basis of a ray tracing method, and performing channel simulation on the basis of the ray tracing method; determining performance parameters of a multipath signal, a direct signal and a composite signal of a receiving end in the two train-ground communication modes; s3, for each selected train terminal position, the train running length is determined based on the train running direction, the train terminal position and the rail position; the track length, the train running length corresponding to the position of a single train terminal and the synthetic signal performance parameters in one train-ground communication mode serve as an input data set, and the direct signal performance parameters in the same train-ground communication mode of the position of the single train terminal serve as a corresponding output data set; and S4, neural network training is carried out based on the input data sets and the output data sets corresponding to all train terminal positions in the same train-ground communication mode, a multipath signal suppression model of the receiving end in the train-ground communication mode is obtained, multipath signal suppression is carried out at the receiving end through the multipath signal suppression model during actual train-ground communication, and direct signals are estimated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of multipath signal suppression, and in particular to a vehicle-to-ground communication multipath interference suppression method, electronic equipment and storage medium. Background Art

[0002] In the actual vehicle-to-ground communication environment, there are many complex situations such as cities, tunnels, bridges, and mountains. There may be many obstacles between the transmitter and the receiver, resulting in the final reception of a composite signal consisting of a standard signal and an interference signal. The interference signal mainly includes multipath signals generated by reflection, diffraction, and reflection from obstacles during signal propagation. In order to remove the interference signal from the composite signal as much as possible to restore the standard signal and improve communication performance, multipath interference suppression is required at the receiver.

[0003] With the development of artificial intelligence technology, there are schemes in the prior art that introduce neural networks into signal processing, such as the "K-clustering intelligent selection of microwave signal multipath interference suppression method" disclosed in Patent No. ZL201911398258.0, which selects 10 sampling points in a simulation environment, collects data with and without interference, takes the composite signal of the interference signal and the direct signal as input, and the direct signal of the same sampling point as output, and performs neural network training to obtain a multipath interference suppression model. However, in the vehicle-to-ground communication scenario, as the position of the train changes, its multipath interference also changes, and the train track is long, and the vehicle-to-ground communication environment at different positions is quite different, that is, the multipath interference generated may be very different. In the prior art, the neural network model trained with the composite signal of the interference signal and the direct signal as input and the direct signal of the same sampling point as output cannot well suppress the multipath interference problem in the vehicle-to-ground mobile communication scenario. In addition, the communication environment changes greatly during vehicle-to-ground mobile communication, and it is necessary to ensure accurate sampling simulation at different communication environments. The method of statically selecting sampling simulation points in the prior art cannot well balance the number of sampling points and sampling accuracy. Summary of the invention

[0004] The purpose of the present invention is to solve the above-mentioned problems of the prior art, and provides a method for suppressing multipath interference in vehicle-to-ground communication, an electronic device and a storage medium. The train terminal position is dynamically selected in the simulation space according to the simulation results to better balance the simulation workload and simulation accuracy, and the multipath interference suppression model is trained in combination with the train running length and the track length to better adapt to the multipath interference suppression in the vehicle-to-ground mobile communication scenario.

[0005] In a first aspect, the present invention provides a method for suppressing multipath interference in vehicle-to-ground communication, the method comprising: S1, establish a simulation space according to the vehicle-ground communication scenario and determine the track position and ground base station position; S2, preset the train travel direction, select several train terminal positions within the track position length range according to the train travel method, and simulate the vehicle-to-ground communication mode as vehicle-to-ground and ground-to-vehicle communication mode and ground-to-vehicle communication mode for each selected train terminal position, perform channel simulation based on ray tracing method, and determine the performance parameters of multipath signals, direct signals and synthetic signals at the receiving end under the two vehicle-to-ground communication modes; S3, for each selected train terminal position, determine the train travel length based on the train travel direction, train terminal position and track position; take the track length, the train travel length corresponding to a single train terminal position and the synthetic signal performance parameter under a train-to-ground communication mode as an input data group, and the direct signal performance parameter of the single train terminal position under the same train-to-ground communication mode as the corresponding output data group; S4, based on the input data group and output data group corresponding to all train terminal positions under the same train-to-ground communication mode, a neural network training is performed to obtain a multipath signal suppression model of the receiving end under the train-to-ground communication mode. During actual train-to-ground communication, multipath signal suppression is performed at the receiving end through the multipath signal suppression model to estimate the direct signal.

[0006] Preferably, the S2 includes: S21, selecting one end of the track position corresponding to the train travel direction as the train terminal position, and setting an initial train terminal position selection interval; S22, for the selected train terminal position, respectively simulate the train-to-ground communication modes of train-to-ground transmission and ground-to-ground transmission, and ground-to-train transmission and ground-to-train transmission, perform channel simulation based on the ray tracing method, and determine the performance parameters of the multipath signal, direct signal, and composite signal of the receiving end under the two train-to-ground communication modes; S23, judging whether the similarity between the channel simulation result at the currently selected train terminal position and the channel simulation result at the previously selected train terminal position is greater than a set threshold, if so, increasing the interval on the basis of the initial train terminal position selection interval and selecting the next train terminal position; if not, maintaining the initial train terminal position selection interval and selecting the next train terminal position; S24, determine whether the train terminal position selected next time exceeds the track position length range, if so, end, if not, jump to S22 to execute.

[0007] Preferably, the process of performing channel simulation based on ray tracing method once in S2 includes: Determine the ray emission angle range and the initial emission angle interval, start ray emission and perform derivative ray tracing to obtain a complete propagation ray; Determine whether the current propagation ray and the previous propagation ray are both invalid propagation rays. If not, keep the initial emission angle interval to perform the next ray emission. If so, increase the angle interval based on the initial emission angle interval to perform the next ray emission. Complete the emission of all rays within the ray emission angle range and the derivative ray tracing, perform channel analysis on the effective propagation ray integration, and determine the performance parameters of multipath signals, direct signals, and synthetic signals.

[0008] Preferably, the performance parameters include one or more of time delay, amplitude, and angle of arrival.

[0009] In a second aspect, the present invention provides an electronic device, including a memory, a computer program stored thereon, and a processor, wherein the processor implements the above-mentioned vehicle-to-ground communication multipath interference suppression method when executing the computer program.

[0010] In a third aspect, the present invention provides a storage medium storing computer executable instructions, which, when loaded and executed by a processor, implement the above-mentioned vehicle-to-ground communication multipath interference suppression method.

[0011] In summary, the present invention has the following beneficial effects: the present invention dynamically selects the train terminal position, and when the similarity of the ray tracing channel simulation results corresponding to two adjacent train terminal positions is greater than a set threshold, the next train terminal position selection interval is increased to reduce the number of selected train terminal positions, that is, to reduce the channel simulation workload; and when the similarity of the ray tracing channel simulation results corresponding to two adjacent train terminal positions is not greater than a set threshold, the initial train terminal position selection interval is maintained to perform channel simulation at different vehicle-to-ground communication environments on the track as much as possible, that is, to improve the accuracy of the channel simulation of the entire vehicle-to-ground communication environment on the track, and comprehensively achieve a better balance between simulation workload and simulation accuracy. In addition, the present invention combines the synthetic signal and direct signal of the channel simulation with the train travel length and the track length to train the multipath interference suppression model, so as to obtain a multipath interference suppression model that is not only related to the synthetic signal, but also related to the position change of the train on the track, so as to achieve better adaptation to the multipath interference suppression in the vehicle-to-ground mobile communication scenario.

[0012] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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 work.

[0014] Figure 1 A schematic diagram of a flow chart of an embodiment of the present application.

[0015] Figure 2 This is a schematic diagram of the process of Example S2 of the present application. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical scheme and advantages disclosed in the embodiments of the present invention clearer, the embodiments of the present invention are further described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention and are not intended to limit the embodiments of the present invention. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions.

[0017] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products or devices.

[0018] With the development of artificial intelligence technology, there are solutions in the prior art that introduce neural networks into multipath interference suppression. However, the neural network model trained in the prior art with the composite signal of the interference signal and the direct signal as input and the direct signal of the same sampling point as output cannot effectively suppress the multipath interference problem in the vehicle-to-ground mobile communication scenario. In addition, the communication environment changes greatly during vehicle-to-ground mobile communication, and it is necessary to ensure accurate sampling simulation in different communication environments. The method of statically selecting sampling simulation points in the prior art cannot well balance the number of sampling points and sampling accuracy.

[0019] An embodiment of the present application provides a method for suppressing multipath interference in vehicle-to-ground communications. The train terminal position is dynamically selected in the simulation space according to the simulation results to better balance the simulation workload and simulation accuracy. The multipath interference suppression model is trained in combination with the train travel length and track length to better adapt to the multipath interference suppression in the vehicle-to-ground mobile communication scenario.

[0020] Specifically, Figure 1 As shown, the method of this embodiment includes, S1, establishing a simulation space according to the vehicle-to-ground communication scenario, and determining the track position and the ground base station position. In this embodiment, the existing modeling technology can be used to establish the simulation space, such as by importing the digital elevation model data produced by the geographic surveying and mapping of the vehicle-to-ground communication scenario and the obstacle data containing the coordinates and length, width and height information of the obstacle into the simulation software to establish the simulation space, and configuring specific parameters such as materials, dielectric constants, and conductivity for the terrain and obstacles in the simulation space.

[0021] The method of this embodiment also includes S2, presetting the train travel direction, selecting a number of train terminal positions within the track position length range according to the train travel method, simulating the vehicle-to-ground communication mode as vehicle-to-ground and ground-to-vehicle communication mode and ground-to-vehicle communication mode for each selected train terminal position, performing channel simulation based on the ray tracing method, and determining the performance parameters of the multipath signal, direct signal, and composite signal of the receiving end under the two vehicle-to-ground communication modes. In this embodiment, the existing ray tracing method can be used for channel simulation, wherein the multipath signal and the direct signal are directly determined by ray tracing, and the composite signal is determined by weighted calculation of the multipath signal and the direct signal, and the performance parameters may include one or more of delay, amplitude, and arrival angle.

[0022] In some embodiments of the present application, Figure 2 As shown, S2 includes: S21, selecting one end of the track position corresponding to the train travel direction as the train terminal position, and setting an initial train terminal position selection interval; S22, for the selected train terminal position, respectively simulate the train-to-ground communication modes of train-to-ground transmission and ground-to-ground transmission, and ground-to-train transmission and ground-to-train transmission, perform channel simulation based on the ray tracing method, and determine the performance parameters of the multipath signal, direct signal, and composite signal of the receiving end under the two train-to-ground communication modes; S23, judging whether the similarity between the channel simulation result at the currently selected train terminal position and the channel simulation result at the previously selected train terminal position is greater than a set threshold, if so, increasing the interval on the basis of the initial train terminal position selection interval and selecting the next train terminal position; if not, maintaining the initial train terminal position selection interval and selecting the next train terminal position; S24, determine whether the train terminal position selected next time exceeds the track position length range, if so, end, if not, jump to S22 to execute.

[0023] In this embodiment, the similarity of the channel simulation results of the two train terminal positions is determined by taking the average of the similarities of the channel simulation results under the two vehicle-to-ground communication modes. Similarly, the similarity of the channel simulation results of the same vehicle-to-ground communication mode at the two train terminal positions is determined by taking the average of the similarities of the performance parameters of the three signals in the channel simulation results. In the case of multiple performance parameters, similarly, the overall similarity of the signal performance parameters is determined by taking the average of the similarities of the multiple performance parameters.

[0024] By dynamically selecting the train terminal position, when the similarity of the ray tracing channel simulation results corresponding to two adjacent train terminal positions is greater than the set threshold, the next train terminal position selection interval is increased to reduce the number of selected train terminal positions, that is, to reduce the workload of channel simulation; and when the similarity of the ray tracing channel simulation results corresponding to two adjacent train terminal positions is not greater than the set threshold, the initial train terminal position selection interval is maintained to perform channel simulation at different vehicle-to-ground communication environments on the track as much as possible, that is, to improve the accuracy of the channel simulation of the entire vehicle-to-ground communication environment on the track, and comprehensively achieve a better balance between simulation workload and simulation accuracy.

[0025] In order to simulate the signal propagation process, during the ray emission and its derivative ray tracing process, the signal strength of the ray or derivative ray will gradually decrease as its propagation distance or number of reflections increases. In order to reduce the tracing workload in the existing ray tracing process, when the signal strength of the ray or derivative ray decreases to exceed the receiving lower limit, the ray tracing will be stopped and the propagation ray will be judged invalid. Several adjacent propagation rays may have similar propagation paths. In order to reduce the tracing of adjacent invalid propagation rays and further reduce the channel simulation workload, in some embodiments of the present application, the process of performing a single channel simulation based on the ray tracing method in S2 includes: Determine the ray emission angle range and the initial emission angle interval, start ray emission and perform derivative ray tracing to obtain a complete propagation ray; Determine whether the current propagation ray and the previous propagation ray are both invalid propagation rays. If not, keep the initial emission angle interval to perform the next ray emission. If so, increase the angle interval based on the initial emission angle interval to perform the next ray emission. Complete the emission of all rays within the ray emission angle range and the derivative ray tracing, perform channel analysis on the effective propagation ray integration, and determine the performance parameters of multipath signals, direct signals, and synthetic signals.

[0026] like Figure 1As shown, the method of this embodiment also includes S3, for each selected train terminal position, determining the train travel length based on the train travel direction, train terminal position and track position; taking the track length, the train travel length corresponding to a single train terminal position and the synthetic signal performance parameters under a vehicle-to-ground communication mode as an input data group, and the direct signal performance parameters of the single train terminal position under the same vehicle-to-ground communication mode as the corresponding output data group.

[0027] S4, based on the input data group and output data group corresponding to all train terminal positions under the same train-to-ground communication mode, neural network training is performed to obtain a multipath signal suppression model at the receiving end under the train-to-ground communication mode; during actual train-to-ground communication, multipath signal suppression is performed at the receiving end through the multipath signal suppression model to estimate the direct signal.

[0028] In this step, existing training methods can be used to train the neural network. For example, the input data group and the output data group are divided into training input, output set and test input, output set, and the neural network is trained and tested; the input layer is set with a matching number of input neurons to input synthetic signal performance parameters, train travel length, and track length; the output layer is set with a matching number of output neurons to output direct signal performance parameters, and the number of hidden layers and the number of hidden layer neurons are set as needed; the weights between neurons are randomly initialized using a standard normal distribution, the activation function selects the Sigmoid function, the objective function is the mean square error between the estimated value of the direct signal performance parameter and the corresponding true value of the output data, and the optimization algorithm uses a gradient descent method, etc.

[0029] The embodiment of the present application also provides an electronic device, including a memory and a processor, and the memory and the processor can be connected via a bus or other means. The memory can be used to store software programs, computer programs and modules, such as the program / module corresponding to the above-mentioned vehicle-to-ground communication multipath interference suppression method; the processor implements the above-mentioned vehicle-to-ground communication multipath interference suppression method by executing the computer program and module in the memory.

[0030] The processor may be a central processing unit, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, etc., and the memory may be a high-speed random access memory, a non-volatile memory, etc.

[0031] The embodiment of the present application also provides a storage medium, wherein the storage medium stores computer executable instructions, and when the computer executable instructions are loaded and executed by a processor, the above-mentioned vehicle-to-ground communication multipath interference suppression method is implemented. The storage medium may be a combination of one or more of a magnetic disk, an optical disk, a read-only storage memory, a random access storage memory, a flash memory, a hard disk, etc.

[0032] It should be noted that the sequence of the above embodiments of the present invention is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0033] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0034] Those skilled in the art will appreciate that all or part of the steps of the above embodiments can be accomplished by hardware, or by programs instructing the relevant hardware to accomplish the steps. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for suppressing multipath interference in vehicle-to-ground communication. It is characterized in that include S1, establish a simulation space according to the vehicle-ground communication scenario and determine the track position and ground base station position; S2, preset the train travel direction, select several train terminal positions within the track position length range according to the train travel method, and simulate the vehicle-to-ground communication mode as vehicle-to-ground and ground-to-vehicle communication mode and ground-to-vehicle communication mode for each selected train terminal position, perform channel simulation based on ray tracing method, and determine the performance parameters of multipath signals, direct signals and synthetic signals at the receiving end under the two vehicle-to-ground communication modes; S3, for each selected train terminal position, determine the train travel length based on the train travel direction, train terminal position and track position; take the track length, the train travel length corresponding to a single train terminal position and the synthetic signal performance parameter under a train-to-ground communication mode as an input data group, and the direct signal performance parameter of the single train terminal position under the same train-to-ground communication mode as the corresponding output data group; S4, based on the input data group and output data group corresponding to all train terminal positions under the same train-to-ground communication mode, a neural network training is performed to obtain a multipath signal suppression model of the receiving end under the train-to-ground communication mode. During actual train-to-ground communication, multipath signal suppression is performed at the receiving end through the multipath signal suppression model to estimate the direct signal.

2. A method for suppressing multipath interference in vehicle-to-ground communication according to claim 1, It is characterized in that The S2 includes: S21, selecting one end of the track position corresponding to the train travel direction as the train terminal position, and setting an initial train terminal position selection interval; S22, for the selected train terminal position, respectively simulate the train-to-ground communication modes of train-to-ground transmission and ground-to-ground transmission, and ground-to-train transmission and ground-to-train transmission, perform channel simulation based on the ray tracing method, and determine the performance parameters of the multipath signal, direct signal, and composite signal of the receiving end under the two train-to-ground communication modes; S23, judging whether the similarity between the channel simulation result at the currently selected train terminal position and the channel simulation result at the previously selected train terminal position is greater than a set threshold, if so, increasing the interval on the basis of the initial train terminal position selection interval and selecting the next train terminal position; if not, maintaining the initial train terminal position selection interval and selecting the next train terminal position; S24, determine whether the train terminal position selected next time exceeds the track position length range, if so, end, if not, jump to S22 to execute.

3. A method for suppressing multipath interference in vehicle-to-ground communication according to claim 1, It is characterized in that The process of performing channel simulation based on ray tracing method once in S2 includes: Determine the ray emission angle range and the initial emission angle interval, start ray emission and perform derivative ray tracing to obtain a complete propagation ray; Determine whether the current propagation ray and the previous propagation ray are both invalid propagation rays. If not, keep the initial emission angle interval to perform the next ray emission. If so, increase the angle interval based on the initial emission angle interval to perform the next ray emission. Complete the emission of all rays within the ray emission angle range and the derivative ray tracing, perform channel analysis on the effective propagation ray integration, and determine the performance parameters of multipath signals, direct signals, and synthetic signals.

4. A method for suppressing multipath interference in vehicle-to-ground communication according to any one of claims 1 to 3, It is characterized in that The performance parameters include one or more of delay, amplitude, and arrival angle.

5. Electronic equipment, including memory and computer programs stored thereon, processors, It is characterized in that When the processor executes the computer program, the method for suppressing multipath interference in vehicle-to-ground communication as described in any one of claims 1 to 4 is implemented.

6. Storage media, It is characterized in that The storage medium stores computer executable instructions, and when the computer executable instructions are loaded and executed by the processor, a method for suppressing multipath interference in vehicle-to-ground communication as described in any one of claims 1-4 is implemented.

Citation Information

Patent Citations

  • K clustering intelligent selection microwave signal multipath interference suppression method

    CN111122989A

Cited By

  • Railway signal data simulation method, device, equipment, storage medium and product

    CN119682821A

  • Railway signal data simulation method, device, equipment, storage medium and product

    CN119682821B