An ultra-wideband amplitude comparison direction finding method based on XGBoost

Abstract

The present invention discloses an ultra-wideband amplitude comparison direction finding method based on XGBoost, and the method comprises: based on historical antenna pattern data, simulating a received signal passing through an antenna pattern at each angle; constructing a data set to be trained according to the received signal; training an XGBoost model according to the data set to be trained; obtaining an antenna with a maximum amplitude of a received signal to be calculated and an adjacent antenna with the maximum amplitude; calculating target features of the antenna with the maximum amplitude and the adjacent antenna; inputting the target features into the XGBoost model to obtain a direction finding result of an incoming wave direction. The present invention uses the XGBoost method to fit the functional relationship between the antenna received signal amplitude and the incoming wave direction, which can improve the accuracy of ultra-wideband direction finding and can be widely used in the field of computer technology.

Description

Technical Field

[0001] The invention relates to the field of computer technology, and in particular to an ultra-wideband amplitude comparison direction finding method based on XGBoost. Background Art

[0002] At present, most of the research on amplitude comparison direction finding methods is based on the ideal antenna radiation pattern fitted by cosine function or sinc function or the antenna radiation pattern based on a single frequency point. When performing direction finding in narrowband conditions, the antenna used is also relatively ideal and has no multi-values. By using the least squares method or other methods to fit the data of these radiation patterns, the analytical expression after the amplitude comparison function approximation can be obtained. At this time, the angle value can be calibrated through the one-to-one correspondence between the amplitude comparison value and the angle. However, for ultra-wideband antennas, due to the wide frequency band of the antenna, the influence of the antenna structure and the influence of the manufacturing process, the antenna radiation pattern of certain frequencies will be distorted to a certain extent, with fluctuations and multi-values. This is an inherent defect of ultra-wideband antennas, which will cause the performance of traditional amplitude comparison direction finding methods to drop sharply on ultra-wideband antenna radiation patterns.

[0003] In summary, the problem of decreased amplitude direction finding accuracy caused by the multi-valued antenna pattern at certain frequency points in the ultra-wideband antenna is solved. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides an ultra-wideband amplitude comparison direction finding method based on XGBoost with high accuracy.

[0005] An aspect of an embodiment of the present invention provides an ultra-wideband amplitude comparison direction finding method based on XGBoost, comprising:

[0006] Simulate the received signal through the antenna pattern at each angle based on historical antenna pattern data;

[0007] Constructing a data set to be trained according to the received signal;

[0008] Train the XGBoost model according to the training data set;

[0009] Obtaining the antenna with the maximum amplitude of the received signal to be calculated and the adjacent antennas of the antenna with the maximum amplitude;

[0010] Calculate target characteristics of the antenna with the largest amplitude and the adjacent antennas;

[0011] The target features are input into the XGBoost model to obtain the direction finding result of the incoming wave direction.

[0012] Optionally, the simulating a received signal through the antenna pattern at each angle based on historical antenna pattern data includes:

[0013] For three directional antennas with different pointing directions but overlapping beams and the same angle between them, based on the existing antenna pattern data, the signal after passing through the three antenna gains at the same signal incident angle is simulated at different frequencies and angles;

[0014] Noise with different signal-to-noise ratios is added to the gained signal to obtain the received signal of each beam.

[0015] Optionally, the calculating target characteristics of the antenna with the maximum amplitude and the adjacent antennas includes:

[0016] Calculate the normalized frequency value of the antenna;

[0017] Calculate the first proportion of the power of the left beam received signal in the sum of the powers of the three beam received signals;

[0018] Calculate the second proportion of the power of the received signal of the middle beam to the sum of the power of the received signals of the three beams;

[0019] Calculate the third proportion of the power of the right beam received signal in the sum of the powers of the three beam received signals;

[0020] Calculate the sum-difference ratio amplitude of the left center beam;

[0021] Calculate the sum-difference ratio amplitude of the center right beam.

[0022] Optionally, the calculation formula of the normalized frequency value is:

[0023] f nor =f / max(f)

[0024] Among them, f nor represents a normalized frequency value, f is a value between 2000MHz and 18000MHz, and max(f)=18000MHz. Optionally, the calculation formula of the first proportion is:

[0025] R L =P L (t) / [P L (t)+P M (t)+P R (t)]

[0026] Among them, R L represents the first proportion of the power of the left beam received signal in the sum of the power of the three beam received signals, P L (t) is the power of the left beam received signal, P M (t) is the power of the received signal in the middle beam, P R (t) is the power of the right beam received signal;

[0027] The calculation formula of the second proportion is:

[0028] R M =P M (t) / [P L (t)+P M (t)+P R (t)]

[0029] Among them, R M represents the second proportion of the power of the medium beam received signal in the sum of the power of the three beam received signals;

[0030] The calculation formula of the third proportion is:

[0031] R R =P R (t) / [P L (t)+P M (t)+P R (t)]

[0032] Among them, R R Represents the third percentage of the power of the right beam received signal in the sum of the power of the three beam received signals.

[0033] Optionally, the calculation formula for the sum-difference ratio amplitude of the left middle beam is:

[0034] R LM =[P M (t)-P L (t)] / [P M (t)+P L (t)]

[0035] The calculation formula of the sum-difference ratio amplitude of the middle right beam is:

[0036] R RM =[P M (t)-P R (t)] / [P M (t)+P R (t)]

[0037] Among them, R LM represents the sum-difference ratio amplitude of the left center beam; R RM represents the sum-difference ratio amplitude of the center and right beams; P L (t) is the power of the left beam received signal, P M (t) is the power of the received signal in the middle beam, P R (t) is the power of the right beam received signal.

[0038] Another aspect of the embodiment of the present invention further provides an ultra-wideband amplitude comparison direction finding device based on XGBoost, comprising:

[0039] A first module is used to simulate a received signal through an antenna pattern at each angle based on historical antenna pattern data;

[0040] The second module is used to construct a data set to be trained according to the received signal;

[0041] The third module is used to train an XGBoost model according to the training data set;

[0042] The fourth module is used to obtain the antenna with the maximum amplitude of the received signal to be calculated and the adjacent antennas of the antenna with the maximum amplitude;

[0043] A fifth module is used to calculate the target characteristics of the antenna with the maximum amplitude and the adjacent antennas;

[0044] The sixth module is used to input the target features into the XGBoost model to obtain the direction finding result of the incoming wave direction.

[0045] Another aspect of an embodiment of the present invention further provides an electronic device, including a processor and a memory;

[0046] The memory is used to store programs;

[0047] The processor executes the program to implement the method described above.

[0048] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0049] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0050] The embodiment of the present invention simulates the received signal through the antenna pattern at each angle based on the historical antenna pattern data; constructs a data set to be trained according to the received signal; obtains an XGBoost model based on the training data set; obtains the antenna with the maximum amplitude of the received signal to be calculated and the adjacent antennas of the antenna with the maximum amplitude; calculates the target features of the antenna with the maximum amplitude and the adjacent antennas; inputs the target features into the XGBoost model to obtain the direction finding result of the incoming wave direction. The present invention uses the XGBoost method to fit the functional relationship between the antenna received signal amplitude and the incoming wave direction, which can improve the accuracy of ultra-wideband direction finding. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 It is a schematic diagram of the three-beam amplitude comparison direction finding model;

[0053] Figure 2 is a schematic diagram of a direction finding antenna;

[0054] Figure 3 An overall step flow chart provided for an embodiment of the present invention;

[0055] Figure 4 A 2100 MHz three-beam pattern provided by an embodiment of the present invention;

[0056] Figure 5 A schematic diagram of the mean absolute error of direction finding at 2100 MHz provided by an embodiment of the present invention;

[0057] Figure 6 A schematic diagram of the 2100 MHz direction finding root mean square error provided by an embodiment of the present invention;

[0058] Figure 7 A 10000MHz three-beam pattern provided by an embodiment of the present invention;

[0059] Figure 8 A schematic diagram of the mean absolute error of direction finding at 10000 MHz provided by an embodiment of the present invention;

[0060] Fig. 9 A schematic diagram of the 10000 MHz direction finding root mean square error provided by an embodiment of the present invention;

[0061] Fig.10 A 16200MHz three-beam pattern provided by an embodiment of the present invention;

[0062] Fig.11 A schematic diagram of the mean absolute error of direction finding at 16200 MHz provided by an embodiment of the present invention;

[0063] Fig.12 A schematic diagram of the 16200 MHz direction finding root mean square error provided by an embodiment of the present invention;

[0064] Fig.13 A three-beam pattern at 18000 MHz provided by an embodiment of the present invention;

[0065] Fig.14 A schematic diagram of the mean absolute error of direction finding at 18000 MHz provided by an embodiment of the present invention;

[0066] Fig.15 A schematic diagram of the 18000 MHz direction finding root mean square error provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] Aiming at the problem that the amplitude direction finding accuracy decreases due to the multi-valued antenna pattern at certain frequency points in ultra-wideband antennas, the present invention uses the XGBoost method to fit the functional relationship between the antenna received signal amplitude and the incoming wave direction.

[0069] Specifically, an aspect of an embodiment of the present invention provides an ultra-wideband amplitude comparison direction finding method based on XGBoost, comprising:

[0070] Simulate the received signal through the antenna pattern at each angle based on historical antenna pattern data;

[0071] Constructing a data set to be trained according to the received signal;

[0072] Train the XGBoost model according to the training data set;

[0073] Obtaining the antenna with the maximum amplitude of the received signal to be calculated and the adjacent antennas of the antenna with the maximum amplitude;

[0074] Calculate target characteristics of the antenna with the largest amplitude and the adjacent antennas;

[0075] The target features are input into the XGBoost model to obtain the direction finding result of the incoming wave direction.

[0076] Optionally, the simulating a received signal through the antenna pattern at each angle based on historical antenna pattern data includes:

[0077] For three directional antennas with different pointing directions but overlapping beams and the same angle between them, based on the existing antenna pattern data, the signal after passing through the three antenna gains at the same signal incident angle is simulated at different frequencies and angles;

[0078] Noise with different signal-to-noise ratios is added to the gained signal to obtain the received signal of each beam.

[0079] Optionally, the calculating target characteristics of the antenna with the maximum amplitude and the adjacent antennas includes:

[0080] Calculate the normalized frequency value of the antenna;

[0081] Calculate the first proportion of the power of the left beam received signal in the sum of the powers of the three beam received signals;

[0082] Calculate the second proportion of the power of the received signal of the middle beam to the sum of the power of the received signals of the three beams;

[0083] Calculate the third proportion of the power of the right beam received signal in the sum of the powers of the three beam received signals;

[0084] Calculate the sum-difference ratio amplitude of the left center beam;

[0085] Calculate the sum-difference ratio amplitude of the center right beam.

[0086] Optionally, the calculation formula of the normalized frequency value is:

[0087] f nor =f / max(f)

[0088] Among them, f nor represents a normalized frequency value, f is a value between 2000MHz and 18000MHz, and max(f)=18000MHz. Optionally, the calculation formula of the first proportion is:

[0089] R L =P L (t) / [P L (t)+P M (t)+P R (t)]

[0090] Among them, R L represents the first proportion of the power of the left beam received signal in the sum of the power of the three beam received signals, P L (t) is the power of the left beam received signal, P M (t) is the power of the received signal in the middle beam, P R (t) is the power of the right beam received signal;

[0091] The calculation formula of the second proportion is:

[0092] R M =P M (t) / [P L (t)+P M (t)+P R (t)]

[0093] Among them, R M represents the second proportion of the power of the medium beam received signal in the sum of the power of the three beam received signals;

[0094] The calculation formula of the third proportion is:

[0095] R R =P R (t) / [P L (t)+P M (t)+P R (t)]

[0096] Among them, R R Represents the third percentage of the power of the right beam received signal in the sum of the power of the three beam received signals.

[0097] Optionally, the calculation formula for the sum-difference ratio amplitude of the left middle beam is:

[0098] R LM =[P M (t)-P L (t)] / [P M (t)+P L (t)]

[0099] The calculation formula of the sum-difference ratio amplitude of the middle right beam is:

[0100] R RM =[P M (t)-P R (t)] / [P M (t)+P R (t)]

[0101] Among them, R LM represents the sum-difference ratio amplitude of the left center beam; R RM represents the sum-difference ratio amplitude of the center and right beams; P L (t) is the power of the left beam received signal, P M (t) is the power of the received signal in the middle beam, P R (t) is the power of the right beam received signal.

[0102] Another aspect of the embodiment of the present invention further provides an ultra-wideband amplitude comparison direction finding device based on XGBoost, comprising:

[0103] A first module is used to simulate a received signal through an antenna pattern at each angle based on historical antenna pattern data;

[0104] The second module is used to construct a data set to be trained according to the received signal;

[0105] The third module is used to train an XGBoost model according to the training data set;

[0106] The fourth module is used to obtain the antenna with the maximum amplitude of the received signal to be calculated and the adjacent antennas of the antenna with the maximum amplitude;

[0107] A fifth module is used to calculate the target characteristics of the antenna with the maximum amplitude and the adjacent antennas;

[0108] The sixth module is used to input the target features into the XGBoost model to obtain the direction finding result of the incoming wave direction.

[0109] Another aspect of an embodiment of the present invention further provides an electronic device, including a processor and a memory;

[0110] The memory is used to store programs;

[0111] The processor executes the program to implement the method described above.

[0112] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0113] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0114] The implementation process of the present invention is described in detail below in conjunction with the accompanying drawings:

[0115] First of all, the current three-beam direction finding method has the following problems:

[0116] The principle of three-beam amplitude comparison direction finding is to use the antenna array to form multiple overlapping beams. Each adjacent overlapping beam covers a certain airspace, and multiple overlapping beams completely cover the entire airspace to complete the direction finding of the radiation source in all directions. When finding the direction, first find the beam with the largest received signal amplitude, and then use the received signal amplitude of this beam and its two adjacent beams to complete the direction finding of the radiation source. Figure 1 As shown, it is assumed that the antenna pattern function is a Gaussian function and is symmetrical with respect to the beam azimuth, that is,

[0117]

[0118] Among them, β is the angle between the incoming wave direction and the direction of the beam maximum value, θ 0.5is the half-power beamwidth and k is a constant.

[0119] Assume that the received signal energy of beam n is the largest, and its adjacent beams are n-1 and n+1 respectively, then the amplitude A of the received signals of the three beams is n (θ), A n-1 (θ) and A n+1 (θ) can be expressed as:

[0120]

[0121]

[0122]

[0123] Among them, A i is the amplitude response of each antenna beam. Figure 1 It is considered that the A of each beam i Equal, θ n is the beam pointing direction of beam n. Then:

[0124]

[0125]

[0126] Then there is

[0127]

[0128] Thus we get

[0129]

[0130] It can be seen that the angle θ and the ratio There is a linear relationship. Through the above formula, combined with the beam pointing of the maximum beam, and the amplitude of the maximum beam and its adjacent beams, the direction of the signal can be determined.

[0131] However, in ultra-wideband antennas, the antenna radiation pattern at certain frequencies will be distorted, resulting in the multi-valued ratio function, that is, the same ratio It may correspond to multiple angles θ, resulting in large errors when the direction is directly measured using the table lookup method.

[0132] Compared with the prior art, the present invention uses three directional antennas with different directions but certain overlapping beams and the same angle between them to perform amplitude comparison direction finding, such as Figure 2As shown, they are recorded as left, middle and right beams in order. Amplitude comparison direction finding can be regarded as the process of obtaining the direction of the incoming wave through the quantitative relationship between the amplitudes of the beam received signals. Regression learning can be performed through the XGBoost machine learning algorithm to fit the functional relationship between the quantitative relationship between the amplitudes of the beam received signals and the direction of the incoming wave. The present invention is based on the data extraction feature training model of the antenna gain pattern, so the method of this patent can only be used under the premise of existing antenna gain pattern data. The antenna gain pattern data refers to the antenna gain data corresponding to different angles.

[0133] The overall flow chart of the present invention is as follows: Figure 3 As shown, the specific steps include the following six steps:

[0134] 1. Simulate the signal through the antenna pattern at each angle.

[0135] For the three antennas, based on the existing antenna pattern data, the signals after passing through the three antenna gains at the same signal incident angle are simulated at different frequencies and angles, and noise with different signal-to-noise ratios is added to obtain the received signal of each beam.

[0136] 2. Calculate features according to the definition and build a data set.

[0137] The feature is defined as:

[0138] (1) Normalized frequency value:

[0139] f nor =f / max(f)

[0140] Wherein f is a value between 2000 MHz and 18000 MHz, and max(f)=18000 MHz.

[0141] (2) The proportion of the power of the left beam received signal in the sum of the power of the three beam received signals:

[0142] R L =P L (t) / [P L (t)+P M (t)+P R (t)]

[0143] Where P L (t) is the power of the left beam received signal, P M (t) is the power of the received signal in the middle beam, P R (t) is the power of the right beam received signal.

[0144] (3) The proportion of the power of the medium beam received signal in the sum of the power of the three beam received signals:

[0145] R M =P M (t) / [P L (t)+P M (t)+P R (t)]

[0146] (4) The proportion of the power of the right beam received signal in the sum of the power of the three beam received signals:

[0147] R R =P R (t) / [P L (t)+P M (t)+P R (t)]

[0148] (5) The sum-difference ratio amplitude of the left middle beam:

[0149] R LM =[P M (t)-P L (t)] / [P M (t)+P L (t)]

[0150] (6) The sum-difference ratio amplitude of the middle and right beams:

[0151] R RM =[P M (t)-P R (t)] / [P M (t)+P R (t)]

[0152] For the signal generated in step 1, the feature is calculated through the above feature definition, and the corresponding signal incident angle is used as the label. The input feature is: Feature = [f nor , R L , R M , R R , R LM , R RM ], the label is the corresponding signal incident angle, and the constructed data set is in the form of {Feature, Ang}, where Ang is the signal incident angle corresponding to the Feature.

[0153] 3. Train the XGBoost model using the dataset.

[0154] Train the XGBoos model using the dataset generated in step 2.

[0155] 4. Select the antenna with the largest received signal amplitude and its adjacent antennas.

[0156] In actual direction finding, it is necessary to select the antenna with the largest received signal amplitude in the antenna array and its adjacent antennas.

[0157] 5. Extract frequency and amplitude, and calculate features.

[0158] The frequencies and amplitudes of the three antennas are extracted by frequency measurement and amplitude measurement respectively, and the features are calculated according to the feature definition in step 2.

[0159] 6. Input the features into the trained XGBoost model to calculate the incoming wave direction.

[0160] The simulation results of the present invention are described below to verify the effect of the method of the present invention.

[0161] Direction finding simulation is performed within the angular range where the gain of the intermediate beam is the largest. During the simulation, only the impact of the noise in the receiver on the signal power is considered and it is assumed that the noise level in each receiver is the same. Assuming that the signal is a single-frequency signal and the frequency is known, the sampling frequency is 4 times the signal frequency, the signal is sampled for ten cycles, and the power of the signal is calculated for direction finding. The simulation frequency points are 2100MHz, 10000MHz, 16200MHz and 18000MHz. The simulation is performed when the signal-to-noise ratio of the intermediate beam is 10dB, and the mean absolute error and root mean square error of the direction finding of the method of this patent and the table lookup method are compared. The table lookup method selects the angle corresponding to the amplitude ratio value closest to the measured amplitude ratio value in the amplitude ratio function as the direction finding result.

[0162] in, Figure 4 A 2100 MHz three-beam pattern provided by an embodiment of the present invention; Figure 5 A schematic diagram of the mean absolute error of direction finding at 2100 MHz provided by an embodiment of the present invention; Figure 6 A schematic diagram of the 2100 MHz direction finding root mean square error provided by an embodiment of the present invention; Figure 7 A 10000MHz three-beam pattern provided by an embodiment of the present invention; Figure 8 A schematic diagram of the mean absolute error of direction finding at 10000 MHz provided by an embodiment of the present invention; Fig. 9 A schematic diagram of the 10000 MHz direction finding root mean square error provided by an embodiment of the present invention; Fig.10 A 16200MHz three-beam pattern provided by an embodiment of the present invention; Fig.11 A schematic diagram of the mean absolute error of direction finding at 16200 MHz provided by an embodiment of the present invention; Fig.12 A schematic diagram of the 16200 MHz direction finding root mean square error provided by an embodiment of the present invention; Fig.13 A three-beam pattern at 18000 MHz provided by an embodiment of the present invention; Fig.14A schematic diagram of the mean absolute error of direction finding at 18000 MHz provided by an embodiment of the present invention; Fig.15 A schematic diagram of the 18000 MHz direction finding root mean square error provided by an embodiment of the present invention;

[0163] The comparison of the overall direction finding average error and root mean square error of each frequency within the direction finding range is shown in Table 1 and Table 2:

[0164] Table 1. Comparison of overall direction finding mean absolute error

[0165]

[0166] Table 2. Comparison of overall direction finding root mean square error

[0167]

[0168] From the results, it can be seen that the method of this patent has improved the direction finding error compared with the table lookup method. At the frequency points of 16200MHz and 18000MHz, the amplitude ratio function has serious multi-values, and directly using the table lookup method for direction finding will result in large errors.

[0169] In summary, when the antenna pattern is distorted and has multi-values, the error is large when the ratio function is directly obtained and the direction finding is performed using the table lookup method. The present invention fits the relationship between the beam receiving signal power and the incoming wave direction through the XGBoost method, and through training with a large amount of simulation data, can obtain better direction finding results when the antenna pattern has multi-values.

[0170] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0171] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0172] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0173] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0174] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0175] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0176] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0177] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0178] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. An ultra-wideband amplitude comparison direction finding method based on XGBoost, characterized in that: include: Simulate the received signal through the antenna pattern at each angle based on historical antenna pattern data; Constructing a data set to be trained according to the received signal; Train the XGBoost model according to the training data set; Obtaining the antenna with the maximum amplitude of the received signal to be calculated and the adjacent antennas of the antenna with the maximum amplitude; Calculate target characteristics of the antenna with the largest amplitude and the adjacent antennas; The target feature is input into the XGBoost model to obtain a direction finding result of the incoming wave direction; The calculating target characteristics of the antenna with the maximum amplitude and the adjacent antennas includes: Calculate the normalized frequency value of the antenna; Calculate the first proportion of the power of the left beam received signal in the sum of the powers of the three beam received signals; Calculate the second proportion of the power of the received signal of the middle beam to the sum of the power of the received signals of the three beams; Calculate the third proportion of the power of the right beam received signal in the sum of the powers of the three beam received signals; Calculate the sum-difference ratio amplitude of the left center beam; Calculate the sum-difference ratio amplitude of the right beam; The calculation formula of the first proportion is: R L =P L (t) / [P L (t)+P M (t)+P R (t)] Among them, R L Represents the first proportion of the power of the left beam received signal in the sum of the power of the three beam received signals, R L (t) is the power of the left beam received signal, P M (t) is the power of the received signal in the middle beam, P R (t) is the power of the right beam received signal; The calculation formula of the second proportion is: R M =P M (t) / [P L (t)+P M (t)+P R (t)] Among them, R M Represents the second proportion of the power of the medium beam received signal in the sum of the power of the three beam received signals: The calculation formula of the third proportion is: R R =P R (t) / [R L (t)+P M (t)+P R (t)] Among them, R R Represents the third proportion of the power of the right beam received signal in the sum of the power of the three beam received signals; The calculation formula of the sum-difference ratio amplitude of the left middle beam is: R LM =[P M (t)-R L (t)] / [P M (t)+R L (t)] The calculation formula of the sum-difference ratio amplitude of the middle right beam is: R RM =[P M (t)-P R (t)] / [P M (t)+P R (t)] Among them, R LM represents the sum-difference ratio amplitude of the left center beam; R RM Represents the sum-difference ratio amplitude of the center and right beams; R L (t) is the power of the left beam received signal, P M (t) is the power of the received signal in the middle beam, P R (t) is the power of the right beam received signal.

2. The ultra-wideband amplitude comparison direction finding method based on XGBoost according to claim 1, characterized in that: The method of simulating a received signal through the antenna pattern at each angle based on historical antenna pattern data includes: For three directional antennas with different pointing directions but overlapping beams and the same angle between them, based on the existing antenna pattern data, the signal after passing through the three antenna gains at the same signal incident angle is simulated at different frequencies and angles; Noise with different signal-to-noise ratios is added to the gained signal to obtain the received signal of each beam.

3. The ultra-wideband amplitude comparison direction finding method based on XGBoost according to claim 1, characterized in that: The calculation formula of the normalized frequency value is: f nor =f / max(f) Among them, f nor Represents the normalized frequency value, f is a value between 2000MHz and 18000MHz, max(f) = 18000MHz.

4. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 3.

5. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 3.

6. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images