Wireless communication method based on vehicle-mounted NVIS short-wave antenna

Abstract

The invention relates to the technical field of wireless communication, and particularly discloses a wireless communication method based on a vehicle-mounted NVIS short-wave antenna, and the method comprises the following steps: S1, collecting environment conditions, and recording target power; obtaining a target factor, and obtaining a target value; s2, grouping the environmental conditions to obtain standard factors and standard values; generating coordinate points, and clustering the coordinate points to obtain a cluster; generating a training sample based on the clustering clusters; s3, training and verifying the prediction model through a training sample; and obtaining the predicted power in real time, and adjusting the signal transmitting power of the target antenna. According to the invention, the communication stability of the vehicle-mounted NVIS short-wave antenna in a complex environment is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless communication, and in particular to a wireless communication method based on a vehicle-mounted NVIS shortwave antenna. Background Art

[0002] NVIS, or near vertical incidence sky-wave technology, is a special method in shortwave communication. In shortwave communication, radio waves propagate mainly in two ways: sky waves and ground waves. NVIS technology uses radio waves that are emitted nearly vertically upward to achieve communication through sky-wave propagation.

[0003] During wireless communication based on the vehicle-mounted NVIS shortwave antenna, due to its propagation characteristics of nearly vertical incident waves, the signal can be effectively reflected back to the ground, thereby achieving coverage in a larger range. This propagation method allows the communication signal to remain stable in an environment with complex terrain or many obstacles, significantly increasing the transmission distance.

[0004] However, in actual situations, different environmental conditions can affect the effect of wireless communication. For example, factors such as the obstruction of buildings and other physical obstacles can cause signal attenuation, and the target receiving end may not be able to receive the signal. Therefore, how to avoid the above situation has become an urgent problem to be solved. Summary of the invention

[0005] The purpose of the present invention is to provide a wireless communication method based on a vehicle-mounted NVIS shortwave antenna to solve the above technical problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A wireless communication method based on a vehicle-mounted NVIS shortwave antenna comprises the following steps:

[0008] S1: collecting environmental conditions at a preset position and recording a target power, where the target power is the signal transmission power of a preset target antenna when the signal quality of wireless communication is equal to a preset signal quality;

[0009] Obtaining a target factor in the environmental condition, the target factor being a factor affecting signal transmission quality, and obtaining a target value, the target value being used to indicate the degree of the target factor;

[0010] S2: grouping the environmental conditions according to the target factors in the environmental conditions, and the environmental conditions in the same group contain the same target factors;

[0011] Taking the target factor corresponding to the environmental condition in the group as the standard factor, and obtaining the target value of the standard factor as the standard value;

[0012] Generate coordinate points (C1, C2, ..., Cn), where Cn represents the standard value of the nth standard factor, and n represents the total number of standard factors in the group, cluster the coordinate points to obtain cluster clusters;

[0013] Record the target power corresponding to the coordinate point in the cluster as the standard power, calculate the average standard power, obtain the coordinate point corresponding to the center of the cluster, use it as a reference point, extract the standard factor and standard value corresponding to the reference point, use them as reference factors and reference values ​​respectively, generate training samples, and a single training sample includes the average standard power, reference factors and reference values;

[0014] S3: Establish a prediction model based on the deep learning model, and train and verify the prediction model through the training samples;

[0015] The current environmental conditions are collected, the target factors and the corresponding target values ​​are obtained, and the target factors and the corresponding target values ​​are input into the verified prediction model, the predicted power A is output, and the signal transmission power of the target antenna is adjusted to the predicted power A.

[0016] As a further solution of the present invention: in the step S2, the process of obtaining the clustering clusters specifically includes:

[0017] Set a standard radius r, take the coordinate point as the center, calculate the density of the coordinate points within the standard radius r, and when the density of the coordinate points is greater than or equal to a preset value Y, generate an initial cluster with the coordinate point as the center;

[0018] The initial clusters containing the same coordinate points are taken as the undetermined clusters, the theoretical centroids of the undetermined clusters are obtained, the undetermined clusters whose distances between the theoretical centroids are less than μ1*r are merged into a standard cluster, and the remaining undetermined clusters are taken as secondary clusters, where μ1 is the preset first coefficient;

[0019] Obtain the distance d between the theoretical center of gravity of the standard cluster and the theoretical center of gravity of the secondary cluster, set the second coefficient μ12, and when the distance d is greater than or equal to μ2*r, use the coordinate point belonging to the secondary cluster and not belonging to the standard cluster as a reference point to obtain the theoretical center of gravity X of the reference point;

[0020] Taking the theoretical center of gravity X as the center, starting from the preset second radius r2, increasing the second radius at a preset radius interval, and recording the corresponding coordinate point density after each increase of the second radius, obtaining the maximum coordinate point density, taking the second radius corresponding to the maximum coordinate point density as the reference radius, and generating a new standard cluster according to the theoretical center of gravity X and the reference radius;

[0021] All standard clusters are taken as clustering clusters.

[0022] As a further solution of the present invention: Calculate the coordinate point density y=N / (πr 2 ), N represents the number of coordinate points within the standard radius r.

[0023] As a further solution of the present invention: in the step S2, during the process of calculating the average standard power, when the difference between a certain standard power and the average standard power is greater than a preset value, the standard power is removed and the average standard power is calculated again.

[0024] As a further solution of the present invention: in the step S1, when recording the target power, the distance between the target antenna and the receiving end remains unchanged.

[0025] As a further solution of the present invention: in the step S1, the target antenna adopts a U-shaped design, and a loading ring with co-directional radiation is added in the middle of the U-shaped half ring.

[0026] As a further solution of the present invention: in the step S3, the prediction model is trained based on the back propagation algorithm, and the prediction model is verified based on the five-fold cross validation.

[0027] As a further solution of the present invention: the step S2 further includes: the number of training samples is greater than or equal to a preset number threshold.

[0028] The beneficial effects of the present invention are as follows: by collecting environmental condition data at different preset locations and recording the antenna transmission power required under specific signal quality; through this process, key environmental factors affecting signal transmission, such as terrain, climate, building obstruction, etc., can be fully identified and quantified, providing high-quality, structured basic data for subsequent data analysis and model training, ensuring that the collected information can accurately reflect the complexity of the actual communication environment, thereby laying a solid foundation for optimizing signal transmission strategies; target values, such as the degree of rain and snow, and the number and height of buildings, etc., different target factors have different measurement standards; through grouping and clustering analysis, environmental conditions with similar target factors are classified, and representative training samples are extracted; by grouping environmental conditions according to key factors, and standardizing the standard factors in these groups, generating multi-dimensional coordinate points and then clustering them, the data structure of complex environments can be effectively simplified; clustering analysis helps It helps to discover the typical transmission power demand patterns under different combinations of environmental conditions, thereby generating high-quality training samples, supporting the construction and optimization of deep learning models, and ensuring that the models can better adapt to the diverse environments in practical applications; finally, using the deep learning model, the signal transmission power of the antenna is dynamically predicted and adjusted according to the environmental conditions collected in real time. By training and verifying the prediction model, it is ensured that it can accurately reflect the impact of environmental changes on signal transmission and output the appropriate transmission power value, thereby realizing the intelligence and adaptability of the communication system, which can automatically respond to environmental changes and ensure the stability of signal quality and the continuity of coverage. The application of deep learning models not only improves the accuracy of prediction, but also improves the communication reliability and efficiency of the vehicle-mounted NVIS shortwave antenna in complex environments through intelligent power adjustment, ensuring that the target receiving end can stably receive signals under various conditions, thereby effectively solving the communication problems caused by signal attenuation and blocking. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The present invention will be further described below in conjunction with the accompanying drawings.

[0030] Figure 1 It is a flow chart of a wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] See also Figure 1As shown, the present invention is a wireless communication method based on a vehicle-mounted NVIS shortwave antenna, comprising the following steps:

[0033] S1: collecting environmental conditions at a preset position and recording a target power, where the target power is the signal transmission power of a preset target antenna when the signal quality of wireless communication is equal to a preset signal quality;

[0034] Obtaining a target factor in the environmental condition, the target factor being a factor affecting signal transmission quality, and obtaining a target value, the target value being used to indicate the degree of the target factor;

[0035] S2: grouping the environmental conditions according to the target factors in the environmental conditions, and the environmental conditions in the same group contain the same target factors;

[0036] Taking the target factor corresponding to the environmental condition in the group as the standard factor, and obtaining the target value of the standard factor as the standard value;

[0037] Generate coordinate points (C1, C2, ..., Cn), where Cn represents the standard value of the nth standard factor, and n represents the total number of standard factors in the group, cluster the coordinate points to obtain cluster clusters;

[0038] Record the target power corresponding to the coordinate point in the cluster as the standard power, calculate the average standard power, obtain the coordinate point corresponding to the center of the cluster, use it as a reference point, extract the standard factor and standard value corresponding to the reference point, use them as reference factors and reference values ​​respectively, generate training samples, and a single training sample includes the average standard power, reference factors and reference values;

[0039] S3: Establish a prediction model based on the deep learning model, and train and verify the prediction model through the training samples;

[0040] The current environmental conditions are collected, the target factors and the corresponding target values ​​are obtained, and the target factors and the corresponding target values ​​are input into the verified prediction model, the predicted power A is output, and the signal transmission power of the target antenna is adjusted to the predicted power A.

[0041] It should be noted that by collecting environmental condition data at different preset locations and recording the antenna transmission power required under specific signal quality; through this process, the key environmental factors affecting signal transmission, such as terrain, climate, building obstruction, etc., can be fully identified and quantified, providing high-quality, structured basic data for subsequent data analysis and model training, ensuring that the collected information can accurately reflect the complexity of the actual communication environment, thereby laying a solid foundation for optimizing signal transmission strategies; target values, such as the degree of rain and snow, the number and height of buildings, etc., different target factors have different measurement standards; through grouping and clustering analysis, environmental conditions with similar target factors are classified, and representative training samples are extracted. By grouping environmental conditions according to key factors, standardizing the standard factors in these groups, generating multi-dimensional coordinate points and then clustering them, the data structure of complex environments can be effectively simplified; clustering analysis helps The typical transmission power demand patterns under different combinations of environmental conditions are discovered to generate high-quality training samples, support the construction and optimization of deep learning models, and ensure that the models can better adapt to the diverse environments in practical applications; finally, the deep learning model is used to dynamically predict and adjust the signal transmission power of the antenna according to the environmental conditions collected in real time. By training and verifying the prediction model, it is ensured that it can accurately reflect the impact of environmental changes on signal transmission and output the appropriate transmission power value, thereby realizing the intelligence and adaptability of the communication system, which can automatically respond to environmental changes and ensure the stability of signal quality and the continuity of coverage. The application of deep learning models not only improves the accuracy of prediction, but also improves the communication reliability and efficiency of the vehicle-mounted NVIS shortwave antenna in complex environments through intelligent power adjustment, ensuring that the target receiving end can stably receive signals under various conditions, thereby effectively solving the communication problems caused by signal attenuation and blocking.

[0042] In another preferred embodiment of the present invention, in step S2, the process of obtaining the clustering clusters specifically includes:

[0043] Set a standard radius r, take the coordinate point as the center, calculate the density of the coordinate points within the standard radius r, and when the density of the coordinate points is greater than or equal to a preset value Y, generate an initial cluster with the coordinate point as the center;

[0044] The initial clusters containing the same coordinate points are taken as the undetermined clusters, the theoretical centroids of the undetermined clusters are obtained, the undetermined clusters whose distances between the theoretical centroids are less than μ1*r are merged into a standard cluster, and the remaining undetermined clusters are taken as secondary clusters, where μ1 is the preset first coefficient;

[0045] Obtain the distance d between the theoretical center of gravity of the standard cluster and the theoretical center of gravity of the secondary cluster, set the second coefficient μ12, and when the distance d is greater than or equal to μ2*r, use the coordinate point belonging to the secondary cluster and not belonging to the standard cluster as a reference point to obtain the theoretical center of gravity X of the reference point;

[0046] Taking the theoretical center of gravity X as the center, starting from the preset second radius r2, increasing the second radius at a preset radius interval, and recording the corresponding coordinate point density after each increase of the second radius, obtaining the maximum coordinate point density, taking the second radius corresponding to the maximum coordinate point density as the reference radius, and generating a new standard cluster according to the theoretical center of gravity X and the reference radius;

[0047] All standard clusters are taken as clustering clusters.

[0048] In another preferred embodiment of the present invention, the coordinate point density y=N / (πr 2 ), N represents the number of coordinate points within the standard radius r.

[0049] In another preferred embodiment of the present invention, in the step S2, during the process of calculating the average standard power, when the difference between a certain standard power and the average standard power is greater than a preset value, the standard power is removed and the average standard power is calculated again.

[0050] In another preferred embodiment of the present invention, in the step S1, when recording the target power, the distance between the target antenna and the receiving end remains unchanged.

[0051] In another preferred embodiment of the present invention, in the step S1, the target antenna adopts a U-shaped design, and a loading ring with co-directional radiation is added in the middle of the U-shaped half ring.

[0052] It can be understood that the vehicle-mounted U-shaped loading ring shortwave antenna adopts a U-shaped design, and adds a loading ring with co-directional radiation in the middle of the U-shaped half ring. This design ensures that within the specified size range (2.0m×1.2m×1.15m), the electrical length and effective radiation area of ​​the antenna are effectively increased, and the gain of the antenna is improved. Compared with the commonly used centralized loading and ring loading methods, this loading design has the following advantages: First, the loading ring is equivalent to the loading coil. Since the coil diameter is the same as the wire diameter of the large ring, its loss resistance is very small; second, the direction of the radiation electromagnetic field of the loading ring is consistent with the direction of the electromagnetic field of the large ring, which improves the directivity coefficient and effective radiation area of ​​the antenna and improves the gain of the antenna; third, the effective length of the antenna is increased, the radiation impedance of the antenna is effectively increased, and the radiation efficiency of the antenna is improved;

[0053] At the same time, the vehicle-mounted U-shaped loading ring shortwave antenna is compatible with the current 125W shortwave radio and antenna tuner, meeting the requirement of standing wave ratio <1.5 within the working bandwidth of 2-30MHz;

[0054] It can be understood that the vehicle-mounted U-shaped loading ring shortwave antenna adopts a loading ring design, and a loading ring with co-directional radiation is added in the middle of the U-shaped half ring. The key design is to ensure that the loading ring and the U-shaped half ring electromagnetic radiation field are in the same direction, thereby improving the directivity coefficient of the antenna, and effectively increasing the electrical length and effective radiation area of ​​the antenna within the specified size, thereby improving the radiation gain of the antenna. Both the loading ring and the U-shaped large ring are made of copper-plated aluminum tube to improve the radiation efficiency of the antenna. This design provides a design direction for improving the gain and miniaturization of the vehicle-mounted shortwave ring antenna. Its design is compatible with the 125W shortwave radio station and antenna tuner currently in service, and meets the requirement of standing wave ratio <1.5 within the system working bandwidth of 2-30MHz; and the vehicle-mounted U-shaped loading ring shortwave antenna, the antenna is bent with a whole Φ32×2 aluminum tube, and the outer surface copper plating process is adopted to reduce the resistivity of the wire and increase the circumference of the wire cross section, thereby ensuring the strength of the antenna body and reducing the loss resistance of the antenna, thereby improving the radiation efficiency of the antenna and reducing the weight and cost of the antenna body.

[0055] In another preferred embodiment of the present invention, in step S3, the prediction model is trained based on a back propagation algorithm, and the prediction model is verified based on a five-fold cross validation.

[0056] In another preferred embodiment of the present invention, the step S2 further includes: the number of training samples is greater than or equal to a preset number threshold.

[0057] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A wireless communication method based on a vehicle-mounted NVIS shortwave antenna, characterized in that: The following steps are involved: S1: collecting environmental conditions at a preset position and recording a target power, where the target power is the signal transmission power of a preset target antenna when the signal quality of wireless communication is equal to a preset signal quality; Obtaining a target factor in the environmental condition, the target factor being a factor affecting signal transmission quality, and obtaining a target value, the target value being used to indicate the degree of the target factor; S2: grouping the environmental conditions according to the target factors in the environmental conditions, and the environmental conditions in the same group contain the same target factors; Taking the target factor corresponding to the environmental condition in the group as the standard factor, and obtaining the target value of the standard factor as the standard value; Generate coordinate points (C1, C2, ..., Cn), where Cn represents the standard value of the nth standard factor, and n represents the total number of standard factors in the group, and cluster the coordinate points to obtain cluster clusters; Record the target power corresponding to the coordinate point in the cluster as the standard power, calculate the average standard power, obtain the coordinate point corresponding to the center of the cluster, use it as a reference point, extract the standard factor and standard value corresponding to the reference point, use them as reference factors and reference values ​​respectively, generate training samples, and a single training sample includes the average standard power, reference factors and reference values; S3: Establish a prediction model based on the deep learning model, and train and verify the prediction model through the training samples; The current environmental conditions are collected, the target factors and the corresponding target values ​​are obtained, and the target factors and the corresponding target values ​​are input into the verified prediction model, the predicted power A is output, and the signal transmission power of the target antenna is adjusted to the predicted power A.

2. A wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to claim 1, characterized in that: In the step S2, the process of obtaining the clustering clusters specifically includes: Set a standard radius r, take the coordinate point as the center, calculate the density of the coordinate points within the standard radius r, and when the density of the coordinate points is greater than or equal to a preset value Y, generate an initial cluster with the coordinate point as the center; The initial clusters containing the same coordinate points are taken as the undetermined clusters, the theoretical centroids of the undetermined clusters are obtained, the undetermined clusters whose distances between the theoretical centroids are less than μ1*r are merged into a standard cluster, and the remaining undetermined clusters are taken as secondary clusters, where μ1 is the preset first coefficient; Obtain the distance d between the theoretical center of gravity of the standard cluster and the theoretical center of gravity of the secondary cluster, set the second coefficient μ12, and when the distance d is greater than or equal to μ2*r, use the coordinate point belonging to the secondary cluster and not belonging to the standard cluster as a reference point to obtain the theoretical center of gravity X of the reference point; Taking the theoretical center of gravity X as the center, starting from the preset second radius r2, increasing the second radius at a preset radius interval, and recording the corresponding coordinate point density after each increase of the second radius, obtaining the maximum coordinate point density, taking the second radius corresponding to the maximum coordinate point density as the reference radius, and generating a new standard cluster according to the theoretical center of gravity X and the reference radius; All standard clusters are taken as clustering clusters.

3. A wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to claim 2, characterized in that: Calculate the coordinate point density y=N / (πr 2 ), N represents the number of coordinate points within the standard radius r.

4. A wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to claim 1, characterized in that: In the step S2, during the process of calculating the average standard power, when the difference between a certain standard power and the average standard power is greater than a preset value, the standard power is removed and the average standard power is calculated again.

5. A wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to claim 1, characterized in that: In the step S1, when recording the target power, the distance between the target antenna and the receiving end remains unchanged.

6. A wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to claim 1, characterized in that: In the step S1, the target antenna adopts a U-shaped design, and a loading ring for unidirectional radiation is added in the middle of the U-shaped half ring.

7. A wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to claim 1, characterized in that: In the step S3, the prediction model is trained based on a back propagation algorithm, and the prediction model is verified based on a five-fold cross validation.

8. A wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to claim 1, characterized in that: The step S2 further includes: the number of training samples is greater than or equal to a preset number threshold.

Images