A wireless communication method based on a vehicle-mounted NVIS shortwave antenna

Abstract

The application relates to the technical field of wireless communication, and particularly discloses a wireless communication method based on a vehicle-mounted NVIS shortwave antenna, which comprises the following steps: S1: collecting environmental conditions and recording target power; acquiring target factors and target values; S2: grouping the environmental conditions, acquiring standard factors and standard values; generating coordinate points, clustering the coordinate points, and obtaining clustering clusters; generating training samples based on the clustering clusters; S3: training and verifying a prediction model through the training samples; and acquiring a prediction power in real time and adjusting the signal transmission power of a target antenna. The application effectively improves the communication stability of the vehicle-mounted NVIS shortwave antenna in a complex environment.

Description

TECHNICAL FIELD

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

[0002] NVIS, namely near vertical incidence skywave technology, is a special way in shortwave communication. In shortwave communication, the propagation of electric waves is mainly through two ways: sky wave and ground wave. NVIS technology uses near-vertical upwardly transmitted electric waves to achieve communication through sky wave propagation.

[0003] In the process of wireless communication based on the vehicle-mounted NVIS shortwave antenna, due to the propagation characteristics of the near-vertical incidence wave, the signal can be effectively reflected back to the ground, thereby realizing coverage in a larger range. This propagation mode enables the communication signal to remain stable in an environment with complex terrain or numerous obstacles, significantly improving the transmission distance.

[0004] However, in actual situations, different environmental conditions will affect the effect of wireless communication, such as the blocking of buildings and other physical obstacles, which will cause signal attenuation, and the target receiving end may not be able to receive the signal. Therefore, how to avoid the occurrence of the above situation has become a problem to be solved. SUMMARY

[0005] The purpose of the present application 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 application can be achieved by the following technical solutions:

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

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

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

[0010] S2: Grouping the environmental conditions according to the target factor in the environmental conditions, the environmental conditions in the same group containing the same target factor;

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

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

[0013] Record the coordinate points in the cluster as standard power corresponding to the target power, calculate the average standard power, obtain the coordinate point corresponding to the center of the cluster, take it as a reference point, extract the standard factor and standard value corresponding to the reference point as a reference factor and reference value respectively, generate a training sample, and each training sample includes average standard power, reference factor and reference value;

[0014] S3: based on the deep learning model, a prediction model is established, and the prediction model is trained and verified through the training sample;

[0015] Collect the current environmental conditions, obtain the target factors and corresponding target values, input them into the verified prediction model, output the predicted power A, and adjust the signal transmission power of the target antenna to the predicted power A.

[0016] As a further scheme of the application: in step S2, the process of obtaining the cluster specifically includes:

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

[0018] Take the initial cluster containing the same coordinate point as a pending cluster, obtain the theoretical center of gravity of the pending cluster, merge the pending clusters with a distance between the theoretical centers of gravity less than μ1*r into a standard cluster, and take the remaining pending clusters as secondary clusters, μ1 is a first preset 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 a second coefficient μ12, and when the distance d is greater than or equal to μ2*r, take the coordinate points belonging to the secondary cluster and not belonging to the standard cluster as reference points, and obtain the theoretical center of gravity X of the reference points;

[0020] Take the theoretical center of gravity X as the center, start from a preset second radius r2, increase the second radius by a preset radius interval, and record the corresponding coordinate point density after each increase of the second radius, obtain the maximum coordinate point density, take the second radius corresponding to the maximum coordinate point density as a reference radius, and generate a new standard cluster according to the theoretical center of gravity X and the reference radius;

[0021] Take all the standard clusters as the cluster.

[0022] As a further scheme of the present application: the coordinate point density y=N / (πr 2 ) within the standard radius r is calculated, wherein N represents the number of coordinate points within the standard radius r.

[0023] As a further scheme of the present application: in the step S2, 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 recalculated.

[0024] As a further scheme of the present application: in the step S1, the distance between the target antenna and the receiving end is kept unchanged when the target power is recorded.

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

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

[0027] As a further scheme of the present application: in the step S2, the number of training samples is greater than or equal to a preset number threshold.

[0028] The beneficial effects of the present application: by collecting environmental condition data at different preset positions, and recording the required antenna transmission power at a certain signal quality; through this process, the key environmental factors affecting signal transmission, such as terrain, climate, building obstruction, etc. can be comprehensively 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 strategy; target values, such as snowfall and the number and height of buildings, have different measurement standards; through grouping and clustering analysis, environmental conditions with similar target factors are classified, representative training samples are extracted, and the data structure of complex environments is effectively simplified by grouping environmental conditions by key factors and standardizing the standard factors in these groups, and then clustering after generating multi-dimensional coordinate points; clustering analysis helps to discover typical transmission power demand patterns under different environmental condition combinations, thereby generating high-quality training samples to support the construction and optimization of deep learning models, ensuring that the model can better adapt to the diversified environment in actual application; finally, using a deep learning model, the signal transmission power of the antenna is dynamically predicted and adjusted according to the real-time collected environmental conditions, and the prediction model is trained and verified to ensure that it can accurately reflect the impact of environmental changes on signal transmission and output appropriate transmission power values, thereby realizing the intelligence and adaptability of the communication system, which can automatically respond to environmental changes to ensure the stability of signal quality and the persistence of coverage range, and the application of deep learning model 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 obstruction. BRIEF DESCRIPTION OF DRAWINGS

[0029] The present application will be further described below with reference to the accompanying drawings.

[0030] Figure 1 is a flowchart of a wireless communication method based on a vehicle-mounted NVIS shortwave antenna. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0032] Please refer to Figure 1As shown, this invention is a wireless communication method based on a vehicle-mounted NVIS shortwave antenna, comprising the following steps:

[0033] S1: Collect environmental conditions at a preset location and record the target power, where the target power is the signal transmission power of the preset target antenna when the signal quality of wireless communication is equal to the preset signal quality.

[0034] The target factors in the environmental conditions are obtained, and the target factors are those that affect the signal transmission quality. The target values ​​are obtained to indicate the degree of the target factors.

[0035] S2: Group 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] The target factors corresponding to the environmental conditions in the grouping are used as standard factors, and the target values ​​of the standard factors are used as standard values.

[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 clusters.

[0038] The target power corresponding to the coordinate point in the cluster is recorded as the standard power. The average standard power is calculated, and the coordinate point corresponding to the center of the cluster is obtained and used as the reference point. The standard factors and standard values ​​corresponding to the reference point are extracted and used as reference factors and reference values, respectively, to generate training samples. Each training sample includes the average standard power, reference factors, and reference values.

[0039] S3: Build a prediction model based on a deep learning model, and train and validate the prediction model using the training samples mentioned above;

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

[0041] It should be noted that by collecting environmental condition data at different preset positions and recording the required antenna transmission power at a certain signal quality, the key environmental factors affecting signal transmission, such as terrain, climate, building obstruction, etc. can be comprehensively identified and quantified through this process, providing high-quality, structured basic data for subsequent data analysis and model training, ensuring that the collected information accurately reflects the complexity of the actual communication environment, thereby laying a solid foundation for optimizing signal transmission strategies; target values such as snowfall intensity and the number and height of buildings 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 by key factors and standardizing the standard factors in these groups, multi-dimensional coordinate points are generated and clustered, which can effectively simplify the data structure of complex environments; clustering analysis helps to discover typical transmission power demand patterns under different environmental condition combinations, thereby generating high-quality training samples to support the construction and optimization of deep learning models, ensuring that the model can better adapt to the diverse environments in actual applications; finally, using a deep learning model, the signal transmission power of the antenna is dynamically predicted and adjusted based on real-time collected environmental conditions; by training and validating the prediction model, it ensures that it can accurately reflect the impact of environmental changes on signal transmission and output appropriate transmission power values, thereby achieving the intelligence and adaptability of the communication system, which can automatically respond to environmental changes to ensure the stability of signal quality and the persistence of coverage range; 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 obstruction.

[0042] In another preferred embodiment of the present application, the step S2 includes the following steps:

[0043] A standard radius r is set, and the density of coordinate points within the standard radius r is calculated with the coordinate point as the center. When the coordinate point density is greater than or equal to a preset value Y, an initial cluster is generated with the coordinate point as the center;

[0044] The initial cluster containing the same coordinate point is taken as a pending cluster, and the theoretical center of gravity of the pending cluster is obtained. The pending clusters with a distance between the theoretical centers of gravity less than μ1*r are merged into a standard cluster, and the remaining pending clusters are taken as secondary clusters, where μ1 is a first preset coefficient;

[0045] acquire the distance d between the theoretical barycenter of the standard cluster and the theoretical barycenter of the secondary cluster, set the second coefficient mu12, when the distance d is greater than or equal to mu2*r, take the coordinate point belonging to the secondary cluster and not belonging to the standard cluster as a reference point, acquire the theoretical barycenter X of the reference point;

[0046] take the theoretical barycenter X as the center, start from the preset second radius r2, increase the second radius by a preset radius interval, record the corresponding coordinate point density after each increase of the second radius, acquire the maximum coordinate point density, take the second radius corresponding to the maximum coordinate point density as a reference radius, and generate a new standard cluster according to the theoretical barycenter X and the reference radius;

[0047] take all the standard clusters as clustering clusters.

[0048] In another preferred embodiment of the present application, the coordinate point density y=N / (pi*r 2 ) in the standard radius r is calculated, where N represents the number of coordinate points in the standard radius r.

[0049] In another preferred embodiment of the present application, in the step S2, 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 application, in the step S1, the distance between the target antenna and the receiving end remains unchanged when the target power is recorded.

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

[0052] It can be understood that the vehicle-mounted U-shaped loading ring short wave antenna adopts a U-shaped design, and a co-directional radiation loading ring is added in the middle of the U-shaped half ring. The design ensures that the effective length and effective radiation area of the antenna are effectively increased within a specified size range (2.0m*1.2m*1.15m), and the gain of the antenna is improved. Compared with the commonly used concentrated loading and ring loading methods, the loading design has the following advantages: first, the loading ring is equivalent to a loading coil, and since the coil diameter is the same as the wire diameter of the large ring, the loss resistance is very small; second, the radiation electromagnetic field direction of the loading ring is consistent with the electromagnetic field direction 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] Meanwhile, the vehicle-mounted U-shaped loading ring short-wave antenna is compatible with the active 125W short-wave radio station and antenna tuner, and meets the requirement that the standing wave ratio is less than 1.5 within the working bandwidth of 2-30MHz.

[0054] It can be understood that the vehicle-mounted U-shaped loading ring short-wave antenna adopts a loading ring design, a co-directional radiation loading ring 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 are co-directional in electromagnetic radiation field, the directivity coefficient of the antenna is improved, the electrical length and the effective radiation area of the antenna are effectively increased within the specified size, the radiation gain of the antenna is improved, the loading ring and the U-shaped large ring are both made of copper-plated aluminum pipes, the radiation efficiency of the antenna is improved, the design provides a design direction for improving the gain and miniaturization of the vehicle-mounted short-wave ring antenna, the design is compatible with the active 125W short-wave radio station and antenna tuner, and meets the requirement that the standing wave ratio is less than 1.5 within the working bandwidth of 2-30MHz; and the vehicle-mounted U-shaped loading ring short-wave antenna is made of a whole Φ32*2 aluminum pipe, adopts a copper plating process on the outer surface, reduces the resistivity of the wire, increases the cross-sectional circumference of the wire, ensures the strength of the antenna body and reduces the loss resistance of the antenna, improves the radiation efficiency of the antenna, and reduces the weight and cost of the antenna body.

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

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

[0057] The above describes one embodiment of the present application in detail, but the content described is only the preferred embodiment of the present application, and cannot be considered as limiting the scope of the present application. Any equivalent changes and improvements made according to the scope of the present application should still belong to the patent coverage range of the present application.

Claims

1. A wireless communication method based on a vehicle-mounted NVIS shortwave antenna, characterized in that, Includes the following steps: S1: Collect environmental conditions at a preset location and record the target power, where the target power is the signal transmission power of the preset target antenna when the signal quality of wireless communication is equal to the preset signal quality. The target factors in the environmental conditions are obtained, and the target factors are those that affect the signal transmission quality. The target values ​​are obtained to indicate the degree of the target factors. S2: Group 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; The target factors corresponding to the environmental conditions in the grouping are used as standard factors, and the target values ​​of the standard factors are used as standard values. Generate coordinate points (C1, C2, ..., C n ), C n The coordinate points represent the standard value of the nth standard factor, where n represents the total number of standard factors in the group. Clustering is performed on the coordinate points to obtain clusters. The target power corresponding to the coordinate point in the cluster is recorded as the standard power. The average standard power is calculated, and the coordinate point corresponding to the center of the cluster is obtained and used as the reference point. The standard factors and standard values ​​corresponding to the reference point are extracted and used as reference factors and reference values, respectively, to generate training samples. Each training sample includes the average standard power, reference factors, and reference values. S3: Build a prediction model based on a deep learning model, and train and validate the prediction model using the training samples mentioned above; The current environmental conditions are collected, the target factors and their corresponding target values ​​are obtained, and they are input into the validated prediction model to output the prediction power A. The signal transmission power of the target antenna is then adjusted to the prediction power A.

2. The wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to claim 1, characterized in that, In step S2, the process of obtaining the cluster specifically includes: Set a standard radius r, and calculate the density of coordinate points within the standard radius r with the coordinate point as the center. When the density of coordinate points is greater than or equal to a preset value Y, generate an initial cluster with the coordinate point as the center. Initial clusters containing the same coordinate points are designated as undetermined clusters. The theoretical centroids of these undetermined clusters are obtained, and clusters with a distance less than μ1 between their theoretical centroids are selected. The undetermined clusters of r are merged into a standard cluster, and the remaining undetermined clusters are treated as secondary clusters, with μ1 being the preset first coefficient; Obtain the distance d between the theoretical centroid of the standard cluster and the theoretical centroid of the secondary cluster, and set a second coefficient μ2. When the distance d is greater than or equal to μ2... When r, the coordinate point belonging to the quadratic cluster but not to the standard cluster is used as the reference point, and the theoretical centroid X of the reference point is obtained. Centered on the theoretical centroid X, starting from the preset second radius r2, the second radius is increased at preset radius intervals, and the corresponding coordinate point density is recorded after each increase of the second radius. The maximum coordinate point density is obtained, and the second radius corresponding to the maximum coordinate point density is used as the reference radius. A new standard cluster is generated based on the theoretical centroid X and the reference radius. All standard clusters are treated as clusters.

3. The wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to claim 1, characterized in that, In step S2, during the calculation of the average standard power, if 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.

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

5. A wireless communication method based on a vehicle-mounted NVIS shortwave antenna according to claim 1, characterized in that, In 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 semi-ring.

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

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

Images