An intelligent angle self-adaptive ground-based radar and control system

Abstract

The invention discloses an intelligent angle-adaptive ground-based radar and a control system, which relate to the field of radar detection technology, and include a radar mechanism and a single-axis turntable, wherein the control system includes a data acquisition unit, a prediction and analysis unit, a monitoring partition unit, an angle adjustment unit and a control unit; the invention defines a detection area in a virtual model of a target area, and then performs feature extraction after preprocessing the monitoring signal, constructs a terrain feature time series matrix, and establishes a terrain state evolution model based on a convolutional neural network, and then obtains a terrain evolution trend, evaluates the terrain evolution trend based on a preset terrain deformation judgment standard, and defines a high-frequency monitoring area, a normal monitoring area and a steady-state monitoring area in the detection area according to the evaluation result, so as to accurately predict key hidden danger areas that may undergo deformation or displacement, and then optimizes the monitoring frequency in a targeted manner according to the analysis result, thereby significantly improving the monitoring efficiency and making the observation more flexible.

Description

Technical Field

[0001] The present invention relates to the technical field of radar detection, and particularly to an intelligent angle adaptive ground-based radar and a control system. Background Art

[0002] As a high-resolution imaging radar, synthetic aperture radar (SAR) has been widely used in many fields such as topographic mapping, geological disaster monitoring, and military reconnaissance. After the traditional ground-based SAR system is installed, its observation angle is often relatively fixed and difficult to adapt to complex and changeable actual working conditions. Especially when conducting geological disaster monitoring, the terrain of the mountain is complex, and the fixed-angle SAR system may not be able to accurately obtain information on the hidden target area, and the acquisition frequency often cannot meet the requirements of emergency rescue; with the continuous expansion of application scenarios and the increasing requirements for acquisition frequency, the disadvantage of the lack of flexibility of the traditional ground-based SAR system has become more prominent, and an intelligent SAR system that can automatically adjust the observation angle according to different environments and target characteristics is needed;

[0003] In view of the above technical defects, a solution is proposed now. Summary of the Invention

[0004] The purpose of the present invention is to significantly improve the monitoring efficiency, make the observation more flexible, and is particularly suitable for large slope monitoring scenarios with complex terrain and changing conditions and geological disaster emergency rescue scenarios such as mountain landslides, providing more reliable technical support for ensuring slope safety.

[0005] To achieve the above purpose, the present invention adopts the following technical solution: An intelligent angle adaptive ground-based radar includes a radar mechanism and a single-axis turntable. The radar mechanism is fixedly arranged on the top surface of the single-axis turntable. A retractable support is fixedly arranged on the bottom surface of the single-axis turntable. The radar mechanism includes a radar body and a support arm. The radar body is fixedly arranged on the top surface of the single-axis turntable. The support arm is connected to the outer surface of the radar body, and a transceiver antenna is fixedly arranged at the end of the support arm;

[0006] The single-axis turntable includes a fixed base and a driving motor. The fixed base is fixedly arranged on the top surface of the retractable support. A turntable body is movably connected to the outer side of the top of the fixed base. A driving cavity is opened inside the turntable body. The driving motor is fixedly arranged on the inner wall of the driving cavity. A driving gear is fixedly arranged on the outer surface of the output shaft of the driving motor. A passive gear ring is fixedly arranged on the inner wall of the driving cavity. The driving gear and the passive gear ring are meshed with each other.

[0007] Further, a limit chuck is opened on the top surface of the fixed base, and an annular groove corresponding to the limit chuck is opened on the inner wall of the turntable body. The inner wall of the annular groove is attached to the limit chuck.

[0008] Further, the retractable bracket includes a lateral support shaft and a horizontal support shaft. A number of connection slots are evenly distributed on the outer surface of the fixed base. One end surface of the lateral support shaft is movably connected to one end surface of the horizontal support shaft, and a counterweight seat is movably connected to the other end surfaces of the horizontal support shafts together.

[0009] Further, the number of both the lateral support shafts and the horizontal support shafts is three. The lateral support shaft includes an end connector and a pressure-dividing shaft. The three pressure-dividing shafts are parallelly distributed and are commonly connected to an end connector at one end. The end connector is movably connected to the inner wall of the connection slot. The other ends of the three pressure-dividing shafts are commonly connected to a support connector, and a support column foot is fixedly provided on the bottom surface of the support connector.

[0010] The present invention also provides a control system for an intelligent angle self-adaptive ground-based radar, including a data acquisition unit, a prediction and analysis unit, a monitoring zoning unit, an angle adjustment unit, and a control unit;

[0011] The data acquisition unit is used to acquire geographical data of a target area. The geographical data includes terrain and building layout, and import the geographical data into 3D model software to generate a virtual model of the target area. Mark the coordinate position of the ground-based radar in the virtual model of the target area, and obtain the preset detection range of the ground-based radar, and then delimit a detection area in the virtual model of the target area;

[0012] The prediction and analysis unit is used to acquire a monitoring signal through the ground-based radar, perform feature extraction after preprocessing the monitoring signal, construct a terrain feature time series matrix, and establish a terrain state evolution model based on a convolutional neural network, and then obtain a terrain evolution trend and output it to the monitoring zoning unit;

[0013] The monitoring zoning unit is used to acquire and process the terrain evolution trend, evaluate the terrain evolution trend based on a preset terrain deformation judgment criterion, and delimit a high-frequency monitoring area, a normal monitoring area, and a steady-state monitoring area in the detection area according to the evaluation result;

[0014] The angle adjustment unit is used to acquire the real-time output parameters of the driving motor, establish a real-time operation equation of the ground-based radar, and calculate a speed adjustment value of the driving motor based on the distribution ranges of the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area, and send it to the control unit;

[0015] The control unit is used to acquire the speed adjustment value and control the output parameters of the driving motor, and then drive the radar mechanism to rotate horizontally through a single-axis turntable, so that the radar mechanism scans the monitoring area, and uses synthetic aperture technology to improve the imaging resolution of the radar.

[0016] Further, the specific process of obtaining the terrain evolution trend is as follows:

[0017] S101. Filter the monitoring signal through a Butterworth filter to obtain a filtered signal. Perform Hilbert transform on the filtered signal to extract the instantaneous phase, and perform multi-layer decomposition on the basis of the instantaneous phase using the wavelet packet decomposition algorithm to obtain the low-frequency characteristic coefficients and high-frequency characteristic coefficients of the filtered signal;

[0018] S102. Based on the low-frequency characteristic coefficients and the high-frequency characteristic coefficients, obtain enhanced features through a morphological filter. The enhanced features include slope morphological features, vegetation coverage, and slope values;

[0019] S103. Divide multiple time windows according to the time series of the acquired monitoring signal, establish a terrain feature time series matrix, and perform terrain reconstruction in the virtual model of the target area according to the terrain feature time series matrix to obtain a terrain feature map as a training sample;

[0020] S104. Divide the generated training samples into a training set and a test set according to the ratio of 8:2;

[0021] S105. Download the weight file and load it onto the corresponding network to initialize the transfer network parameters, and determine the number of hidden layer nodes of the BP neural network model according to the number of normal images in the training set;

[0022] S106. Modify the last fully connected layer of the network, keep the input unchanged, set the output to the terrain evolution trend, initialize the weights of the last layer, use the gradient descent algorithm for learning, and use fixed-step decay to optimize the training parameters, and retrain the entire network to obtain a terrain state evolution model;

[0023] S107. Randomly and non-repeatedly extract small batches of normal images from the training set during the training process. After extracting all the normal images in the training set, it is a training cycle. Iterate to a certain number of cycles to complete the training, and then use the test set to evaluate the effect of the terrain state evolution model.

[0024] Further, the specific process of demarcating each monitoring area in the detection area according to the evaluation results is as follows:

[0025] S201. Obtain the terrain evolution trend, which includes the change trend of slope morphological features, the change value A of vegetation coverage, and the change value B of slope;

[0026] S202. Obtain the preset terrain deformation judgment criteria, specifically as follows:

[0027] Slope morphological feature change judgment criteria: The change of slope morphological features tends to be stable, the change of slope morphological features tends to decline, and the change of slope morphological features tends to rise;

[0028] Vegetation coverage change value range (Amin, Amax);

[0029] Slope change value range (Bmin, Bmax);

[0030] S203. If the change of the slope morphological characteristics tends to be stable, the vegetation coverage change value is less than or equal to Amin and the slope change value is less than or equal to Bmin, then the detection tends to be designated as a steady-state monitoring area;

[0031] If the change of the slope morphological characteristics tends to rise or fall, the vegetation coverage change value is greater than Amin and less than Amax, and at the same time the slope change value is greater than Bmin and less than Bmax, then the detection tends to be designated as a normal monitoring area;

[0032] If the change of the slope morphological characteristics tends to rise or fall, the vegetation coverage change value is greater than or equal to Amax, and at the same time the slope change value is greater than or equal to Bmax, then the detection tends to be designated as a high-frequency monitoring area.

[0033] Further, the specific process of calculating the speed adjustment value of the drive motor is as follows:

[0034] S301. Obtain the real-time output parameters of the drive motor, and the real-time output parameters include real-time current data It, real-time power Wt, and the normal monitoring frequency Ft of the monitoring area;

[0035] S302. Obtain the real-time speed Vt of the turntable body through the speed sensor arranged on the outer surface of the turntable body, and then establish the real-time operation formula of the ground-based radar: , where a is a constant, that is, the free rotation speed of the turntable body when the real-time current data It and the real-time power Wt are 0, and b and c are preset proportionality coefficients;

[0036] S303. Obtain the distribution ranges of the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area. According to the preset monitoring frequencies corresponding to the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area, substitute the monitoring frequency Fi into the real-time operation formula of the ground-based radar to obtain the preset speeds Vb corresponding to the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area;

[0037] S304. Calculate the speed adjustment value of the drive motor ΔV = Vb - Vt.

[0038] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are:

[0039] The intelligent angle-adaptive ground-based radar and control system delimits the detection area in the virtual model of the target area, and then extracts features after preprocessing the monitoring signal, constructs a terrain feature time series matrix, and establishes a terrain state evolution model based on a convolutional neural network, thereby obtaining a terrain evolution trend, and evaluates the terrain evolution trend based on a preset terrain deformation judgment standard. According to the evaluation result, a high-frequency monitoring area, a normal monitoring area and a steady-state monitoring area are delimited in the detection area, and the speed adjustment value of the drive motor is correspondingly calculated and sent to the control unit. The radar mechanism is driven to rotate horizontally through a single-axis turntable, so that the radar mechanism scans the monitoring area, and the imaging resolution of the radar is improved by using synthetic aperture technology, so that the key hidden danger area that may be deformed or displaced can be accurately predicted, and then the monitoring frequency is optimized according to the analysis result. Compared with the traditional fixed-angle acquisition mode, the present invention has obvious improvement in monitoring efficiency and more flexible observation. It is particularly suitable for large-scale slope monitoring scenes with complex terrain and changeable conditions and geological disaster emergency rescue scenes such as landslides, and provides more reliable technical support for ensuring slope safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The overall external structure schematic diagram of the present invention is shown;

[0041] Figure 2 Another schematic diagram of the overall external structure of the present invention is shown;

[0042] Figure 3 The internal structure schematic diagram of the single-axis turntable of the present invention is shown;

[0043] Figure 4 A schematic diagram of the control system structure of the present invention is shown;

[0044] Legend: 1. Radar body; 2. Support arm; 3. Transceiver antenna; 4. Fixed base; 5. Turntable body; 6. Drive cavity; 7. Drive motor; 8. Drive gear; 9. Passive gear ring; 10. Limit chuck; 11. Lateral support shaft; 1101. End connector; 1102. Pressure divider shaft; 1103. Support connector; 12. Connecting slot; 13. Horizontal support shaft; 14. Counterweight seat; 15. Support column foot. DETAILED DESCRIPTION

[0045] 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. Example

[0046] As shown Figures 1 - 3 in the figure, an intelligent angle - adaptive ground - based radar includes a radar mechanism and a single - axis turntable. The radar mechanism is fixedly arranged on the top surface of the single - axis turntable. A retractable support is fixedly arranged on the bottom surface of the single - axis turntable. The radar mechanism includes a radar body 1 and a support arm 2. The radar body 1 is fixedly arranged on the top surface of the single - axis turntable. The support arm 2 is connected to the outer surface of the radar body 1. A transceiver antenna 3 is fixedly arranged at the end of the support arm 2. Its function is to increase the equivalent aperture of the radar, enabling the radar to obtain better azimuth resolution and monitoring effect. The transceiver antenna 3 adopts the form of an arc - array antenna, which can transmit and receive electromagnetic wave signals along a predetermined arc trajectory, ensuring more uniform and comprehensive signal coverage of the arc - shaped target area;

[0047] The single - axis turntable includes a fixed base 4 and a drive motor 7. The fixed base 4 is fixedly arranged on the top surface of the retractable support. The outer side of the top of the fixed base 4 is movably connected to a turntable body 5. A drive cavity 6 is opened inside the turntable body 5. The drive motor 7 is fixedly arranged on the inner wall of the drive cavity 6. A drive gear 8 is fixedly arranged on the outer surface of the output shaft of the drive motor 7. A passive gear ring 9 is fixedly arranged on the inner wall of the drive cavity 6. The drive gear 8 and the passive gear ring 9 are meshed with each other.

[0048] A limit chuck 10 is opened on the top surface of the fixed base 4. An annular groove corresponding to the limit chuck 10 is opened on the inner wall of the turntable body 5. The inner wall of the annular groove is in mutual fit with the limit chuck 10.

[0049] The retractable support includes a lateral support shaft 11 and a horizontal support shaft 13. A plurality of connection slots 12 are evenly distributed on the outer surface of the fixed base 4. One end surface of the lateral support shaft 11 is movably connected to one end surface of the horizontal support shaft 13. The other end surfaces of the horizontal support shafts 13 are jointly movably connected to a counterweight seat 14.

[0050] Both the lateral support shaft 11 and the horizontal support shaft 13 are three in number. The lateral support shaft 11 includes an end connector 1101 and a pressure - dividing shaft 1102. The three pressure - dividing shafts 1102 are parallelly distributed and are jointly connected to the end connector 1101 at one end. The end connector 1101 is movably connected to the inner wall of the connection slot 12. The other ends of the three pressure - dividing shafts 1102 are jointly connected to a support connector 1103. A support column foot 15 is fixedly arranged on the bottom surface of the support connector 1103.

[0051] The working principle is as follows:

[0052] Select a suitable monitoring site in the area to be monitored. Push the counterweight seat 14 upward, so that the horizontal support shaft 13 unfolds, and then the lateral support shaft 11 expands outward to form a support structure, and fix the ground - based radar at the monitoring site;

[0053] When the ground-based radar is working, the driving motor 7 drives the passive gear ring 9 to rotate, and then drives the radar body 1 and the transceiver antenna 3 to rotate precisely horizontally through the turntable body 5, enabling the ground-based radar to perform a 360° all-round scan of the surrounding space. By collecting echo signals at different positions and using synthetic aperture technology, the imaging resolution of the ground-based radar is improved. Embodiment

[0054] As Figure 4 shown, a control system for an intelligent angle adaptive ground-based radar includes a data acquisition unit, a prediction and analysis unit, a monitoring partition unit, an angle adjustment unit, and a control unit;

[0055] The data acquisition unit is used to obtain the geographical data of the target area. The geographical data includes topography and building layout, and imports the geographical data into 3D model software to generate a virtual model of the target area. Mark the coordinate position of the ground-based radar in the virtual model of the target area, and obtain the preset detection range of the ground-based radar, and then delimit the detection area in the virtual model of the target area;

[0056] The prediction and analysis unit is used to obtain the monitoring signal through the ground-based radar, perform feature extraction after preprocessing the monitoring signal, construct a terrain feature time series matrix, and establish a terrain state evolution model based on a convolutional neural network, and then obtain the terrain evolution trend and output it to the monitoring partition unit;

[0057] The specific process of obtaining the terrain evolution trend is as follows:

[0058] S101. Filter the monitoring signal through a Butterworth filter to obtain a filtered signal. Perform Hilbert transform on the filtered signal, extract the instantaneous phase, and perform multi-layer decomposition on the instantaneous phase using a wavelet packet decomposition algorithm to obtain the low-frequency feature coefficients and high-frequency feature coefficients of the filtered signal;

[0059] S102. Based on the low-frequency feature coefficients and high-frequency feature coefficients, obtain enhanced features through a morphological filter. The enhanced features include slope surface morphological features, vegetation coverage, and slope values;

[0060] S103. Divide multiple time windows according to the time series of the obtained monitoring signal, establish a terrain feature time series matrix, and perform terrain reconstruction in the virtual model of the target area according to the terrain feature time series matrix to obtain a terrain feature map as a training sample;

[0061] S104. Divide the generated training samples into a training set and a test set according to a ratio of 8:2;

[0062] S105. Download the weight file and load it onto the corresponding network to initialize the migration network parameters, and determine the number of hidden layer nodes of the BP neural network model according to the number of normal images in the training set;

[0063] S106. Modify the last fully connected layer of the network, keep the input unchanged, set the output to the terrain evolution trend, initialize the weights of the last layer, use the gradient descent algorithm for learning, and adopt fixed-step decay to optimize the training parameters, and retrain the entire network to obtain the terrain state evolution model;

[0064] S107. During the training process, randomly and without repetition extract small batches of normal images from the training set. After extracting all the normal images in the training set, it is regarded as one training cycle. Iterate to a certain number of cycles to complete the training, and then use the test set to evaluate the effect of the terrain state evolution model.

[0065] The monitoring partition unit is used to obtain and process the terrain evolution trend, evaluate the terrain evolution trend based on a preset terrain deformation judgment criterion, and delimit high-frequency monitoring areas, normal monitoring areas, and steady-state monitoring areas within the detection area according to the evaluation results;

[0066] The specific process of delimiting each monitoring area within the detection area according to the evaluation results is as follows:

[0067] S201. Obtain the terrain evolution trend, which includes the change trend of the slope surface morphological characteristics, the change value A of the vegetation coverage, and the change value B of the slope;

[0068] S202. Obtain the preset terrain deformation judgment criterion, specifically as follows:

[0069] Slope surface morphological characteristics change judgment criterion: the change of slope surface morphological characteristics tends to be stable, the change of slope surface morphological characteristics tends to decline, and the change of slope surface morphological characteristics tends to rise;

[0070] Range of vegetation coverage change value (Amin, Amax);

[0071] Range of slope change value (Bmin, Bmax);

[0072] S203. If the change of slope surface morphological characteristics tends to be stable, the change value of vegetation coverage is less than or equal to Amin and the change value of slope is less than or equal to Bmin, then this detection area tends to be delimited as a steady-state monitoring area;

[0073] If the change of slope surface morphological characteristics tends to rise or decline, the change value of vegetation coverage is greater than Amin and less than Amax, and at the same time the change value of slope is greater than Bmin and less than Bmax, then this detection area tends to be delimited as a normal monitoring area;

[0074] If the change in slope morphological characteristics tends to increase or decrease, the change value of vegetation coverage is greater than or equal to Amax, and at the same time, the change value of slope is greater than or equal to Bmax, then the detection tends to be designated as a high-frequency monitoring area.

[0075] The angle adjustment unit is used to obtain the real-time output parameters of the driving motor 7, establish the real-time operation equation of the ground-based radar, and calculate the rotational speed adjustment value of the driving motor 7 based on the distribution ranges of the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area, and send it to the control unit;

[0076] The specific process of calculating the rotational speed adjustment value of the driving motor 7 is as follows:

[0077] S301. Obtain the real-time output parameters of the driving motor 7. The real-time output parameters include the real-time current data It, the real-time power Wt, and the normal monitoring frequency Ft of the monitoring area;

[0078] S302. Obtain the real-time speed Vt of the turntable body 5 through the speed sensor arranged on the outer surface of the turntable body 5, and then establish the real-time operation equation of the ground-based radar: , where a is a constant, that is, the free rotational speed of the turntable body 5 when the real-time current data It and the real-time power Wt are 0, and b and c are preset proportionality coefficients;

[0079] S303. Obtain the distribution ranges of the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area. According to the preset monitoring frequencies corresponding to the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area, substitute the monitoring frequency Fi into the real-time operation equation of the ground-based radar to obtain the preset rotational speeds Vb corresponding to the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area;

[0080] S304. Calculate the rotational speed adjustment value of the driving motor 7, ΔV = Vb - Vt.

[0081] The control unit is used to obtain the rotational speed adjustment value and control the output parameters of the driving motor 7, and then drive the radar mechanism to rotate horizontally through the single-axis turntable, so that the radar mechanism scans the monitoring area, and uses synthetic aperture technology to improve the imaging resolution of the radar.

[0082] The present invention demarcates a detection area in the virtual model of the target area, then preprocesses the monitoring signal and extracts features, constructs a terrain feature time series matrix, and establishes a terrain state evolution model based on a convolutional neural network to obtain the terrain evolution trend. The terrain evolution trend is evaluated based on a preset terrain deformation judgment criterion. According to the evaluation results, a high-frequency monitoring area, a normal monitoring area, and a steady-state monitoring area are demarcated in the detection area, and the speed adjustment value of the driving motor 7 is calculated and sent to the control unit accordingly. The radar mechanism is driven by a single-axis turntable to rotate horizontally, so that the radar mechanism scans the monitoring area, and the synthetic aperture technology is used to improve the imaging resolution of the radar. It can accurately predict the key hidden danger areas that may undergo deformation or displacement, and then optimize the monitoring frequency according to the analysis results. Compared with the traditional fixed-angle acquisition mode, the present invention has significantly improved monitoring efficiency and more flexible observation, and is particularly suitable for large-scale slope monitoring scenarios with complex terrain and changing conditions and geological disaster emergency rescue scenarios such as mountain landslides, providing more reliable technical support for ensuring slope safety.

[0083] The setting of the size of the interval is for the convenience of comparison. Regarding the size of the interval value, it depends on the amount of sample data and the number of base numbers set by those skilled in the art for each group of sample data; as long as the proportional relationship between the parameter and the quantified value is not affected.

[0084] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by software simulation of a large amount of collected data to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0085] In the two embodiments provided in the present application, it should be understood that the disclosed devices and systems can be implemented in other ways; for example, the device embodiments described above are only illustrative. For example, the division of the modules is only for logical function division, and there may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed; on the other hand, the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the devices or modules can be in electrical, mechanical or other forms.

[0086] The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent replacements or changes, and should be covered by the protection scope of the present invention.

Claims

1. A control system for an intelligent angle self-adaptive ground-based radar, characterized in that It includes a data acquisition unit, a prediction and analysis unit, a monitoring area division unit, an angle adjustment unit, and a control unit; The data acquisition unit is used to acquire the geographical data of the target area, where the geographical data includes topography and building layout, and import the geographical data into 3D model software to generate a virtual model of the target area. Mark the coordinate positions of the ground-based radar in the virtual model of the target area, and obtain the preset detection range of the ground-based radar, and then delimit the detection area in the virtual model of the target area; The prediction and analysis unit is used to obtain the monitoring signal through the ground-based radar, perform feature extraction after preprocessing the monitoring signal, construct a topographic feature time series matrix, and establish a topographic state evolution model based on a convolutional neural network, and then obtain the topographic evolution trend and output it to the monitoring area division unit; The monitoring area division unit is used to obtain and process the topographic evolution trend, evaluate the topographic evolution trend based on a preset topographic deformation judgment criterion, and delimit high-frequency monitoring areas, normal monitoring areas, and steady-state monitoring areas in the detection area according to the evaluation results; The angle adjustment unit is used to obtain the real-time output parameters of the drive motor, establish a real-time operation equation of the ground-based radar, and calculate the rotation speed adjustment value of the drive motor based on the distribution ranges of the high-frequency monitoring area, normal monitoring area, and steady-state monitoring area, and send it to the control unit; The control unit is used to obtain the rotation speed adjustment value and control the output parameters of the drive motor, and then drive the radar mechanism to rotate horizontally through a single-axis turntable, so that the radar mechanism scans the monitoring area, and uses synthetic aperture technology to improve the imaging resolution of the radar.

2. The control system of an intelligent angle self-adaptive ground-based radar according to claim 1, characterized in that, The specific process of obtaining the topographic evolution trend is as follows: S101. Filter the monitoring signal through a Butterworth filter to obtain a filtered signal. Perform Hilbert transform on the filtered signal to extract the instantaneous phase, and perform multi-layer decomposition on the instantaneous phase using a wavelet packet decomposition algorithm to obtain the low-frequency feature coefficients and high-frequency feature coefficients of the filtered signal; S102. Based on the low-frequency feature coefficients and the high-frequency feature coefficients, obtain enhanced features through a morphological filter. The enhanced features include slope surface morphological features, vegetation coverage, and slope values; S103. Divide multiple time windows according to the time series of the acquired monitoring signal, establish a topographic feature time series matrix, and perform topographic reconstruction in the virtual model of the target area according to the topographic feature time series matrix to obtain a topographic feature map as a training sample; S104. Divide the generated training samples into a training set and a test set according to a ratio of 8:2; S105. Download the weight file and load it onto the corresponding network to initialize the transfer network parameters, and determine the number of hidden layer nodes of the BP neural network model according to the number of normal images in the training set; S106. Modify the last fully connected layer of the network, keep the input unchanged, set the output to the topographic evolution trend, initialize the weights of the last layer, use the gradient descent algorithm for learning, and use a fixed step size decay to optimize the training parameters, and retrain the entire network to obtain a topographic state evolution model; S107. During the training process, randomly and without repetition extract small batches of normal images from the training set. After extracting all the normal images in the training set, it is regarded as one training cycle. Iterate for a certain number of cycles to complete the training, and then use the test set to evaluate the effect of the terrain state evolution model.

3. The control system of an intelligent angle self-adaptive ground-based radar according to claim 1, characterized in that The specific process of demarcating each monitoring area within the detection area according to the evaluation results is as follows: S201. Obtain the terrain evolution trend, where the terrain evolution trend includes the change trend of slope form features, the change value A of vegetation coverage, and the change value B of slope. S202. Obtain the preset terrain deformation judgment criteria, specifically as follows: Slope form feature change judgment criteria: the change of slope form features tends to be stable, the change of slope form features tends to decrease, and the change of slope form features tends to increase. Range of vegetation coverage change value (Amin, Amax); Range of slope change value (Bmin, Bmax); S203. If the change of slope form features tends to be stable, the change value of vegetation coverage is less than or equal to Amin, and the change value of slope is less than or equal to Bmin, then this detection area tends to be demarcated as a steady-state monitoring area; If the change of slope form features tends to increase or decrease, the change value of vegetation coverage is greater than Amin and less than Amax, and at the same time the change value of slope is greater than Bmin and less than Bmax, then this detection area tends to be demarcated as a normal monitoring area; If the change of slope form features tends to increase or decrease, the change value of vegetation coverage is greater than or equal to Amax, and at the same time the change value of slope is greater than or equal to Bmax, then this detection area tends to be demarcated as a high-frequency monitoring area.

4. The control system of an intelligent angle self-adaptive ground-based radar according to claim 1, characterized in that The specific process of calculating the speed adjustment value of the drive motor is as follows: S301. Obtain the real-time output parameters of the drive motor, where the real-time output parameters include real-time current data It, real-time power Wt, and the normal monitoring frequency Ft of the monitoring area; S302. Obtain the real-time speed Vt of the turntable body through the speed sensor set on the outer surface of the turntable body, and then establish the real-time operation equation of the ground-based radar: , where a is a constant, that is, the free rotation speed of the turntable body when the real-time current data It and the real-time power Wt are 0, and b and c are preset proportionality coefficients; S303. Obtain the distribution ranges of the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area. According to the preset monitoring frequencies corresponding to the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area, substitute the monitoring frequency Fi into the real-time operation equation of the ground-based radar to obtain the preset speeds Vb corresponding to the high-frequency monitoring area, the normal monitoring area, and the steady-state monitoring area; S304. Calculate the speed adjustment value of the drive motor ΔV = Vb - Vt.

Images