Moving target detection method and device based on multiple physical fields and medium

Abstract

The invention discloses a moving target detection method and device based on multiple physical fields and a medium, and relates to the technical field of target detection. The method comprises the following steps: before a detector intersects with a moving target, acquiring a magnetic field signal and an electrostatic field signal of the detector for detecting the moving target in multiple physical fields; the multi-physical field comprises a magnetic field and an electrostatic field; fusing the magnetic field signal and the electrostatic field signal to obtain a fused signal, and predicting the number of residual sampling points before the detector reaches the zero crossing point position from the current position according to the fused signal; according to the sampling rate of the detector and the number of residual sampling points, determining a time gap before intersection between the detector and the moving target at the current moment; and determining the distance between the current moment and the zero crossing point position of the detector according to the motion parameters and the time interval of the detector. The method breaks through the static limitation of a fixed threshold value method, and the detection precision of the moving target is remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of target detection, in particular to a moving target detection method, device and medium based on multiple physical fields. BACKGROUND

[0002] In the fields of resource exploration, industrial detection and automatic driving, accurate detection of moving targets is a crucial technology.

[0003] Currently, real-time target detection mainly relies on single physical field detection methods, among which electromagnetic wave detection technology and electrostatic field detection technology are mainly used. However, in the moving target detection scene, single magnetic field or electrostatic field detection is easily disturbed by environmental noise, target material and motion state; and the existing distance determination methods generally have limitations: the limitations of fixed threshold method, which roughly corresponds to the distance by presetting the sensor signal threshold, without considering dynamic factors such as target motion speed, approaching angle and environmental electromagnetic interference, resulting in large distance estimation error. SUMMARY

[0004] Therefore, it is necessary to provide a moving target detection method, device and medium based on multiple physical fields, which breaks through the static limitations of the fixed threshold method and significantly improves the detection accuracy of moving targets.

[0005] The present application adopts the following technical solutions: The present application provides a moving target detection method based on multiple physical fields, comprising: Before the detector intersects with the moving target, the magnetic field signal and the electrostatic field signal of the detector detecting the moving target under multiple physical fields are obtained; the multiple physical fields include magnetic field and electrostatic field; The magnetic field signal and the electrostatic field signal are fused to obtain a fused signal, and the number of remaining sampling points of the detector from the current position to the zero-crossing position is predicted according to the fused signal; the zero-crossing position is the position of the detector when the distance between the detector and the moving target is the shortest at a future time; According to the sampling rate of the detector and the number of remaining sampling points, the time gap before the detector intersects with the moving target at the current time is determined; According to the motion parameters of the detector and the time gap, the distance between the detector and the zero-crossing position at the current time is determined.

[0006] Optionally, the detector and the moving target generate a signal waveform showing a rising trend first and then a falling trend in the intersection motion process, and the position where the detector and the moving target intersect is the intersection point, i.e. the zero-crossing position.

[0007] Optionally, predicting the number of remaining sampling points of the detector from the current position to the zero-crossing position according to the fused signal comprises: The fusion signal is subjected to empirical mode decomposition to extract a low-frequency topographic feature component; The low-frequency topographic feature component is input into a pre-trained distance waveform time sequence mapping model to obtain the remaining sampling point number before the detector reaches the zero-crossing position from the current position; the calculation mode of the distance waveform time sequence mapping model is a matrix multiplication mode or a polynomial calculation mode.

[0008] Optionally, the training process of the distance waveform time sequence mapping model comprises: Obtaining a prior data set under multiple modes; the prior data set is the rising data information before the sample detector intersects with the sample moving target; Taking the remaining sampling point number before reaching the zero-crossing position as an output label, training the pruned long short-term memory network through the prior data set, and testing the trained network until the validation error of the trained network is within a preset range; Extracting the parameter matrix of the network whose validation error is within the preset range, converting the network calculation process into a matrix multiplication or a polynomial calculation mode according to the parameter matrix, and obtaining the distance waveform time sequence mapping model.

[0009] Optionally, obtaining the prior data set under multiple modes comprises: Establishing a magnetic field and electrostatic field dual-mode detection model in a digital space; Constructing an intersection scene of the sample detector and the sample moving target, including a spatial coordinate system, an initial position and a motion trajectory, and a parameter combination of different speed ranges, different detection axial directions and different intersection angles; According to the orthogonal test design method, a multi-parameter combination simulation is performed on the magnetic field and electrostatic field dual-mode detection model, the sample magnetic field signal and the sample electrostatic field signal in the intersection process of the sample detector and the sample moving target are recorded, and the corresponding distance information, time information and label information of the remaining sampling point number before reaching the zero-crossing position are marked for each sampling point; For any kind of parameter combination, the sample magnetic field signal and the sample electrostatic field signal are preprocessed respectively, and the preprocessed sample magnetic field signal and the sample electrostatic field signal are fused to obtain a sample fusion signal; The sample fusion signal is subjected to modal decomposition to obtain a sample low-frequency topographic feature component; The sample low-frequency topographic feature component and the corresponding remaining sampling point number before reaching the zero-crossing position are determined as the prior data set.

[0010] Optionally, the magnetic field detection model is based on a magnetic dipole model, considering the magnetic moment size and direction of the target object, a mathematical model of the magnetic field strength changing with distance is established; the electrostatic field detection model is based on a charge distribution model, considering the charge amount and distribution characteristics of the target object, a mathematical model of the electric field strength changing with distance is established.

[0011] Optionally, according to the sampling rate of the detector and the remaining sampling points, the time gap before the intersection between the detector and the moving target at the current time is determined, comprising: The product of the sampling rate of the detector and the remaining sampling points is determined as the time gap before the intersection between the detector and the moving target at the current time.

[0012] Optionally, the motion parameter includes the speed; according to the motion parameter of the detector and the time gap, the distance between the detector and the zero-crossing point position at the current time is determined, comprising: The product of the speed of the detector at the current time and the time gap is determined as the distance between the detector and the zero-crossing point position at the current time.

[0013] The present application provides a kind of motion target detection device based on multiple physical fields, comprising: The acquisition module is used to obtain the magnetic field signal and electrostatic field signal detected by the detector to the moving target under multiple physical fields before the intersection between the detector and the moving target;Multiple physical fields include magnetic field and electrostatic field; The prediction module is used to fuse the magnetic field signal and electrostatic field signal, obtain fusion signal, and predict the remaining sampling points before the detector reaches zero-crossing point position from current position according to fusion signal;Zero-crossing point position is the position of the detector when the shortest distance between the detector and the moving target at future time; The calculation module is used to determine the time gap before the intersection between the detector and the moving target at the current time according to the sampling rate of the detector and the remaining sampling points;According to the motion parameter of the detector and the time gap, the distance between the detector and the zero-crossing point position at the current time is determined.

[0014] The present application provides a kind of computer readable storage medium, the storage medium stores computer program, the computer program is executed when processor realizes the above motion target detection method based on multiple physical fields.

[0015] The present application provides a kind of computer equipment, including memory, processor and computer program stored on memory and can be run on processor, when the processor executes the program, realizes the above motion target detection method based on multiple physical fields.

[0016] The above-mentioned at least one technical scheme adopted by the present application can achieve the following beneficial effects: In the present application, the noise in the environment is inhibited by the complementary characteristics of the magnetic field disturbance signal and the electrostatic field vector change data, the recognition degree of the signal characteristics in the complex environment is improved, and the noise interference of a single physical field is reduced by combining the double physical field synergy mechanism; based on the regularity of the timing characteristics of the magnetic field disturbance and the electrostatic field vector change in the intersection movement process of the target and the detector, the evolution trend of the signal waveform rising first and then falling, and the zero-crossing point, the signal evolution law before the intersection stage is used to realize the dynamic prediction of the timing of the zero-crossing point; finally, the distance is inversely calculated according to the zero-crossing point timing and the target motion parameters. This method breaks through the static limitation of the fixed threshold method, significantly improves the detection accuracy and response speed of the moving target through dynamic prediction, and provides an efficient solution for real-time detection and interception of moving targets. BRIEF DESCRIPTION OF DRAWINGS

[0017] The drawings described herein are used to provide further understanding of the present application, constitute a part of the present application, and the illustrative embodiments of the present application and the description thereof are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flowchart of a moving target detection method based on multiple physical fields provided by the present application is shown in the figure; Figure 2 A schematic diagram of the zero-crossing point phenomenon in the intersection process of the detector and the moving target in the physical field detection provided by the present application is shown in the figure, wherein (a) is a schematic diagram of the zero-crossing point phenomenon in the intersection process of the detector and the moving target in the magnetic field detection, and (b) is a schematic diagram of the zero-crossing point phenomenon in the intersection process of the detector and the moving target in the electrostatic field detection; Figure 3 A schematic diagram of a signal after extracting the main trend component by mode decomposition provided by the present application is shown in the figure, wherein (a) is a schematic diagram of the original signal before decomposition, and (b) is a schematic diagram of the main trend component extracted by mode decomposition; Figure 4 A modeling schematic diagram of the parallel intersection of the sample detector and the sample moving target in the digital space provided by the present application is shown in the figure; Figure 5 A modeling schematic diagram of the 45° intersection of the sample detector and the sample moving target in the digital space provided by the present application is shown in the figure; Figure 6 A schematic diagram of the zero-crossing intersection trend of the magnetic field detection moving target provided by the present application is shown in the figure; Figure 7 A schematic diagram of the training process of the distance waveform timing mapping model provided by the present application is shown in the figure; Figure 8 A flowchart of another moving target detection method based on multiple physical fields provided by the present application is shown in the figure; Figure 9Another multi-physical field-based moving target detection method flow chart provided by the application; Figure 10 A structure diagram of a multi-physical field-based moving target detection system provided by the application; Figure 11 A computer device schematic diagram for implementing the multi-physical field-based moving target detection method provided by the application. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions and advantages of the application clearer, the technical solutions of the application will be described below in connection with specific embodiments of the application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the application, but not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application.

[0019] Magnetic field detection technology principle: magnetic field detection is based on the disturbance mechanism of target objects to the background magnetic field (such as the geomagnetic field). When the target containing ferromagnetic material (such as a submarine, a mine) enters the detection area, its own magnetic field will change the local space magnetic force line distribution, forming a measurable magnetic anomaly signal. Through high-sensitivity magnetic sensors (such as Hall sensors, TMR sensors), the magnetic field strength, gradient and spatial distribution characteristics are captured, and the position, shape and motion state of the target are analyzed by combining the inversion algorithm. The current technology development trend focuses on improving sensitivity and anti-interference ability.

[0020] Electrostatic field detection technology principle: electrostatic field detection relies on the disturbance effect of the surface charge distribution of the target object on the local electric field. Its physical basis is Coulomb's law and Gauss's theorem: static electric charges form an electrostatic field in space, and when a charged target (such as a high-speed moving frictionally electrified device) or a conductor approaches, it will cause potential line distortion or field strength vector change. By monitoring the electrostatic field distribution characteristics through an electric field sensor, the charge amount, geometric structure and spatial position of the target can be inverted.

[0021] The defects of the current magnetic field and electrostatic field composite detection technology in target distance determination application mainly reflect the static limitation of the fixed threshold method and the lack of dynamic prediction capability. The existing technology mainly depends on the preset signal threshold for distance determination, and does not fully consider dynamic factors such as target motion speed, approaching angle and environmental electromagnetic interference, resulting in large distance estimation error and easy to cause response delay or misjudgment. At the same time, the traditional method only relies on the real-time signal amplitude, and cannot use the time sequence characteristics (such as waveform evolution trend) of the magnetic field disturbance and the electrostatic field vector change in the motion process for forward-looking inference, so it is difficult to meet the real-time demand of high-speed moving target detection. In addition, single physical field detection is easy to be disturbed by environmental noise, target material difference and motion state. The composite detection of magnetic field and electrostatic field is a non-contact target detection technology which combines the disturbance effect of magnetic field and the distribution characteristics of electrostatic field, and the core is to realize the real-time distance determination between the detector and the moving target through the collaborative perception of multiple physical fields. The composite detection can significantly improve the robustness of target recognition through the fusion of multiple physical field information (such as synchronous acquisition of magnetic field anomaly and electrostatic field vector change). However, the existing composite detection technology mainly uses simple threshold superposition or data fusion, and cannot effectively solve the feature complementation problem between magnetic field and electrostatic field, resulting in low signal recognition degree and weak anti-interference ability in complex environment.

[0022] Based on this, the application provides a kind of motion target detection method, device and medium based on multiple physical fields. The method establishes distance waveform time sequence mapping model by excavating the regularity signal waveform (first rise and then fall, and the zero-crossing point is the intersection point) generated when the target and the detector intersect, and uses the distance waveform time sequence mapping model to learn the magnetic field and electrostatic field data characteristics in the non-intersection stage, realizes the dynamic prediction of the zero-crossing point position, so as to inversely calculate the distance according to the zero-crossing point time sequence and motion parameters. The method aims to break through the static limitation of fixed threshold method, improve the dynamic response accuracy and speed through time sequence prediction, and at the same time, fuse the double physical field collaborative mechanism to suppress environmental noise, to provide a high-precision and high-robustness solution for real-time detection of moving targets.

[0023] The technical solutions provided by the embodiments of the application will be described in detail below with reference to the drawings.

[0024] Figure 1 For the flowchart of the motion target detection method based on multiple physical fields in the application, it specifically includes the following steps: S101, before the detector and the moving target intersect, the magnetic field signal and the electrostatic field signal of the detector for detecting the moving target in multiple physical fields are acquired; the multiple physical fields include magnetic field and electrostatic field.

[0025] The detector and the moving target generate a signal waveform showing a trend of first rising and then falling in the intersection movement process, and the position where the detector and the moving target intersect is the intersection point, i.e. the zero-crossing point. The application utilizes the characteristics that the signal zero-crossing point is generated when the detector and the moving target intersect in the magnetic field and electrostatic field detection process, combines the distance waveform timing mapping model, realizes the prediction of the zero-crossing point through the signal rising segment information before the intersection, predicts the time interval from the current position to the zero-crossing point, and combines the motion parameter information obtainable by the detector to calculate the distance information from the target, so as to realize distance measurement.

[0026] As shown in Figure 2 , the Figure 2 is a schematic diagram of the zero-crossing point phenomenon in the intersection process of the detector and the moving target in the physical field detection, Figure 2 , the (a) figure is a schematic diagram of the zero-crossing point phenomenon in the intersection process of the detector and the moving target in the magnetic field detection, Figure 2 , the (b) figure is a schematic diagram of the zero-crossing point phenomenon in the intersection process of the detector and the moving target in the electrostatic field detection.

[0027] Figure 2 The scenario expressed is that the detector and the target fly relative to each other, and the detector is located below the target, Figure 2 , the (a) figure describes the magnetic field detection law in the intersection process: 1. The total field is the mean square value of each axis direction X, Y and Z.

[0028] 2. The X-axis curve is the X-axis direction detection signal in the flying process of the detector and the target. In the intersection process of the target, the signal rises as the distance to the target becomes closer and closer, until it is directly below, and it is considered that the two intersect, and the signal reverses as the intersection is completed, and gradually moves away, showing a downward trend.

[0029] 3. The Y-axis is in parallel relationship with the target and is in the negative half-axis (the detector is below the target), so before the two intersect, they are constantly approaching, and the model gradually weakens as the distance decreases and the magnitude increases.

[0030] 4. The Z-axis is the same as the X-axis, and the difference is that the detection axis direction and the sensitivity are different, so the amplitude and signal show a trend of first falling and then rising.

[0031] Figure 2 The (b) figure describes the electrostatic field detection law in the intersection process, which is consistent with the magnetic field detection law and will not be described again.

[0032] Therefore, before the detector and the moving target intersect, the magnetic field sensor and the electrostatic field sensor synchronously collect signals to obtain the magnetic field signal and the electrostatic field signal respectively, and this process ensures that the magnetic field signal and the electrostatic field signal are accurately synchronized in time.

[0033] S102, fuse the magnetic field signal and the electrostatic field signal to obtain a fused signal, and predict the remaining sampling point number of the probe from the current position to the zero-crossing position according to the fused signal. The zero-crossing position is the position of the probe when the distance between the probe and the moving target is the shortest at a future time.

[0034] Optionally, the magnetic field signal and the electrostatic field signal are preprocessed respectively, and then the preprocessed magnetic field signal and the electrostatic field signal are input into a pre-trained signal fusion model to obtain a fused signal output by the signal fusion model. The preprocessing includes filtering, denoising and normalization processing; wherein, the preliminary filtering is performed by a hardware circuit, and a band-pass filter is used to eliminate low-frequency drift and high-frequency noise.

[0035] In one embodiment, according to the fused signal, the remaining sampling point number of the probe from the current position to the zero-crossing position is predicted, including: performing empirical mode decomposition on the fused signal to extract a low-frequency topographic feature component; inputting the low-frequency topographic feature component into a pre-trained distance waveform time sequence mapping model to obtain the remaining sampling point number of the probe from the current position to the zero-crossing position; the calculation mode of the distance waveform time sequence mapping model is matrix multiplication mode or polynomial calculation mode.

[0036] The fused signal is decomposed into multiple intrinsic mode function (IMF) components by empirical mode decomposition (EMD). First, the decomposed signal will be classified according to time scale (frequency high or low), and the low-frequency signal containing the signal topographic feature is taken as the prefabricated signal for trend prediction. Then, 25% of the total length of the signal is taken as the sampling window length, and the backward difference rate of the data in the window is calculated, that is, When is greater than a certain set threshold (the threshold is negatively related to the prediction sensitivity, if the sensitivity is higher, a lower value can be taken, that is, a slight upward trend is considered to exist target and will soon converge, but it is easy to cause false triggering, and needs to be analyzed according to the specific situation of the application scene), the data in the window is taken as the input signal for trend prediction, that is, the low-frequency topographic feature component, which is used to predict the remaining sampling point number before reaching the zero-crossing position. As shown in Figure 3 Figure 3 is a signal diagram for extracting the main trend component after modal decomposition, Figure 3 (a) of FIG. 1 is a schematic diagram of the original signal before decomposition, Figure 3 (b) of FIG. 1 is a schematic diagram of the main trend component extracted by modal decomposition.

[0037] In one embodiment, the training process of the distance waveform time sequence mapping model includes the following steps: ​S201, acquire prior datasets under multiple modes; the prior datasets are the rising data information before the sample detector and the sample moving target intersect.

[0038] Acquire prior datasets under multiple modes, including: establishing a dual-mode detection model of magnetic and electrostatic fields in digital space; constructing an intersection scenario between the sample detector and the moving sample target, including spatial coordinate system, initial position, and trajectory, as well as parameter combinations for different speed ranges, different detection axes, and different intersection angles; performing multi-parameter combination simulations on the dual-mode detection model based on magnetic and electrostatic fields according to orthogonal experimental design method, recording the sample magnetic field signal and sample electrostatic field signal during the intersection process of the sample detector and the moving sample target, and labeling each sampling point with corresponding distance information, time information, and the number of remaining sampling points before reaching the zero-crossing position; preprocessing the sample magnetic field signal and sample electrostatic field signal for any parameter combination, and fusing the preprocessed sample magnetic field signal and sample electrostatic field signal to obtain the sample fused signal; performing mode decomposition on the sample fused signal to obtain the sample low-frequency morphological feature components; and determining the sample low-frequency morphological feature components and the corresponding number of remaining sampling points before reaching the zero-crossing position as the prior dataset.

[0039] Specifically, using finite element simulation software such as COMSOL Multiphysics and ANSYS, and with the physical parameters (size, material properties, etc.) of the moving target and the performance parameters (sensitivity, frequency response, etc.) of the detector clearly defined, the magnetic and electrostatic fields of different moving targets during the detection process are modeled and simulated. Surrogate models are extracted and imported into systems engineering simulation environments such as MATLAB / Simulink. In the calculation process, the magnetic field detection model is based on a magnetic dipole model, considering the magnitude and direction of the magnetic moment of the target object, and establishing a mathematical model of the magnetic field strength changing with distance; the electrostatic field detection model is based on a charge distribution model, considering the charge quantity and distribution characteristics of the target object, and establishing a mathematical model of the electric field strength changing with distance.

[0040] Secondly, construct the intersection scenario between the sample detector and the moving sample target, including the spatial coordinate system, initial position and trajectory, and set different combinations of parameters such as different speed ranges (e.g., 500m / s-1500m / s), different detection axes (0°-360°), and different intersection angles (0°-90°).

[0041] like Figure 4 and Figure 5 As shown, Figure 4 This is a schematic diagram illustrating the parallel intersection of a sample detector and a moving sample target in digital space. Figure 5 A schematic diagram of the modeling of the sample detector and the moving sample target intersecting at a 45° angle in digital space.

[0042] Then, the parameterized simulation is performed, and the multi-parameter combination simulation is systematically performed according to the orthogonal test design method, and the sample magnetic field and sample electrostatic field signals in the intersection process of the sample probe and the sample moving target are recorded, and the corresponding distance information, time information and zero-crossing point position and other label information are marked for each sampling point, as shown in Figure 6 . Figure 6 The magnetic field probe detects the zero-crossing point intersection trend diagram of the moving target, which constructs the data basis for subsequent supervised learning.

[0043] Finally, the sample magnetic field signal and the sample electrostatic field signal are preprocessed (filtering, denoising and normalization), the preprocessed sample magnetic field signal and the sample electrostatic field signal are fused to obtain a sample fusion signal; the sample fusion signal is modal decomposed to obtain a sample low-frequency topographic feature component; and the sample low-frequency topographic feature component and the corresponding zero-crossing point position sequence number are determined as a priori data set.

[0044] S202, the remaining sampling points before reaching the zero-crossing point position are used as output labels, the pruned long short-term memory network is trained through the priori data set, and the trained network is tested until the validation error of the trained network is within a preset range.

[0045] The priori data set is divided into a training set, a validation set and a test set according to a ratio of 7:2:1, and is stored in a structured format, including sample data information, label information and parameter configuration, forming a zero-crossing point target signal prediction training data set, which is imported into a network training platform for standby, as shown in Figure 7 . Figure 7 The distance waveform time sequence mapping model training process diagram is shown.

[0046] The purpose of this step is to train the distance waveform time sequence mapping model using the zero-crossing point target signal prediction training data set generated in the previous step.

[0047] First, select the basic network framework, considering the limitation of high-speed intersection on network running speed in actual use, select a small-scale parameter network model, and use the pruned long short-term memory network model (Long Short-Term Memory, LSTM) as the basic framework, the network structure at least includes input layer, hidden layer, Dropout and output layer, the number of hidden layer neurons is not less than 50, the hidden layer uses ReLU activation function, and the output layer uses linear activation function.

[0048] Figure 7 The internal structure of a memory cell of the LSTM is also given in , the short-term memory at the last time is (last output), and the long-term memory at the last time is The processing of the three "gates": Forget gate: look at and decide what information to discard from long-term memory . Output a number between 0 and 1 , 0 means "completely forget", 1 means "completely keep".

[0049] Input gate: simultaneously, look at and decide what new information to store in long-term memory. It consists of two parts: a sigmoid layer decides which values to update, resulting in ; a tanh layer creates a new vector of candidate values , which are the new content that may be added.

[0050] Output gate: according to and , calculate and decide what the next short-term memory should be, which controls how much information is read from the current long-term memory and output as .

[0051] Update cell state (long-term memory): This is the most critical step of LSTM: , multiply the old long-term memory by the output of the forget gate, forget the information decided to forget, plus the product of the output of the input gate and the new candidate value, store the new information decided to update, so that the new, updated long-term memory is obtained.

[0052] Output (short-term memory): , scale the new long-term memory through the tanh function, then multiply it by the output of the output gate, to get the final output of this time step , which will also be the input of the short-term memory of the next time step.

[0053] Secondly, network data preparation and training optimization are performed, a trend signal before a zero-crossing point is intercepted as an input, a remaining sample point number before reaching the zero-crossing point position is taken as an output label, in the training process, training data can be expanded by adding noise, time scale transformation and the like, mean squared error (MSE) is taken as a loss function, an Adam optimizer is adopted, an initial learning rate is set to 0.001, training loss and validation loss are monitored in real time, an early stopping mechanism is set to prevent overfitting, and the network training is ended until the network training is ended.

[0054] Then, network performance is evaluated by using prediction accuracy, mean absolute error, root mean square error and the like, network generalization ability is evaluated by using a K-fold cross-validation method, network performance is tested by using small-scale measured equivalent data, and the like, until the optimization verification error is within a preset range (an acceptable range).

[0055] S203, a parameter matrix of the network whose verification error is within the preset range is extracted, a network calculation process is converted into matrix multiplication or polynomial calculation mode according to the parameter matrix, and a distance waveform time sequence mapping model is obtained.

[0056] The parameter matrix of the network is extracted, the network calculation process is converted into matrix multiplication or polynomial calculation mode, the calculation process is further optimized, and redundant parameters are simplified, and thus, the construction of the distance waveform time sequence mapping model is completed.

[0057] In this way, in the actual moving target detection process, a low-frequency topographic feature component obtained after multi-physical field detection is input into the trained distance waveform time sequence mapping model, the low-frequency topographic feature component is operated with the parameter matrix of the network, and a position number to be collected by the detector from the current position to the intersection point is obtained.

[0058] S103, according to the sampling rate of the detector and the remaining sample point number, a time gap before the intersection between the detector and the moving target at the current time is determined; according to the motion parameters of the detector and the time gap, a distance between the detector and the zero-crossing point position at the current time is determined.

[0059] The product of the sampling rate of the detector and the remaining sample point number can be determined as the time gap before the intersection between the detector and the moving target at the current time.

[0060] Alternatively, the remaining sample point number can be converted into a standard time point according to the sampling rate of the detector, and the time gap between the current time point and the standard time point is calculated.

[0061] The detector's motion parameters, including its current velocity and attitude information, are obtained through internal sensors (accelerometers, gyroscopes, etc.). These kinematic parameters are then used to invert the distance between the detector and its zero-crossing position at the current moment. Taking the simplest linear motion model as an example, the detector's velocity at the current moment... With time gap The product of these two factors is used to determine the distance between the detector at the current moment and the zero-crossing position. .

[0062] It should be noted that for variable acceleration motion or attitude correction, a compensation coefficient can be introduced for correction to obtain the distance parameter within a prediction period.

[0063] Throughout the convergence process, the distances measured multiple times are weighted and averaged to improve accuracy. When the distance requirement between the detector and the moving target is met, the response maneuver can be completed to achieve the detection requirements.

[0064] In one embodiment, such as Figure 8 As shown, Figure 8 A flowchart illustrating a moving target detection method based on multiphysics provided by this invention specifically includes: In the target detection modeling simulation and training set generation module, the digital domain model is simulated (COMSOL, Modelica, Simulink, etc.) under different intersection speeds, different intersection angles, different sensor axes, and different intersection directions using physical information empirical formulas to obtain magnetic field and electrostatic field signals. Then, the dataset can be expanded using passive noise interference and active noise interference.

[0065] Based on the above data, a zero-crossing target signal prediction training dataset is constructed. The zero-crossing target signal prediction training dataset is preprocessed, and the network is trained based on the preprocessed data. The parameter matrix is ​​extracted to obtain the distance waveform time-series mapping model.

[0066] Thus, before the detector intersects with the moving target, magnetic field and electrostatic field signals are acquired through the detector's sensor array (multi-mode and multi-axial). These signals are then denoised, fused, and subjected to empirical mode decomposition to extract low-frequency topographic feature components. These low-frequency feature components are then input into a range waveform time-series mapping model. Within this model, the position index of the zero-crossing point is output through calculations with the network's parameter matrix. In the zero-crossing-based distance calculation output, the time gap between the zero-crossing point is predicted using the remaining sampling points from which the detector reaches the zero-crossing point, and the vector distance information between the detector and the zero-crossing point is calculated based on the motion parameters input externally to the detector.

[0067] Based on a combined magnetic field and electrostatic field detection model, a dual-mode target detection model (which can be a systems engineering model or a finite element model) is established in digital space. Using existing physical information empirical formulas combined with simulation deduction of the intersection process, prior information on the target intersection under different speeds, detection axes, and intersection angles is obtained, acquiring prior datasets for multiple modes. Secondly, based on this dataset, a distance waveform time-series mapping model is trained to establish signal feature input segments. and zero-crossing position Mapping relationship between , To preset the input signal segment length, its main function is to input a segment of rising data information before the target intersection. The distance waveform time-series mapping model can perform sequence prediction and obtain zero-crossing position information. Then, the actual collected rising segment information before the target intersection is decomposed to extract low-frequency morphological feature components. The input is fed into the distance waveform time-series mapping model to obtain the number of remaining sampling points before the zero-crossing position after sequence prediction. The zero-crossing time gap is calculated based on the sampling rate information; finally, the appropriate distance from the target position is inverted based on the motion parameters of the detector itself to obtain the final distance information.

[0068] In one embodiment, the present invention also provides a moving target detection method based on multiphysics fields, such as... Figure 9 As shown, it specifically includes: S901, Modeling Simulation and Dataset Generation.

[0069] S902, training distance waveform time-series mapping model.

[0070] S903, real-time signal acquisition and preprocessing.

[0071] S904, zero-crossing position prediction.

[0072] S905, real-time distance inversion calculation.

[0073] S906, Results Optimization and Response.

[0074] The continuous ranging results are weighted and averaged to improve accuracy. When the distance meets the requirements, the final response maneuver is triggered.

[0075] In one embodiment, the method designed in this invention can rely on the following multiphysics-based moving target detection system, including a sensor driver interface, signal conditioning, embedded data acquisition and processing, power supply module, etc. Each system adopts an embedded, customizable design, allowing the algorithm to be directly integrated into the main control unit's data analysis module during development. The specific structure of the multiphysics-based moving target detection system is as follows:Figure 10 As shown, the system comprises a magnetic detection system, an electrostatic field detection system, and an embedded data acquisition and processing system. The magnetic detection system comprises a tunneling magnetoresistance (TMR) sensor, signal filtering, signal conditioning, and analog-to-digital (A / D) conversion. The electrostatic field detection system comprises an induction electrode, charge-to-voltage (Q / V) conversion, signal conditioning, voltage following, and A / D conversion. The embedded data acquisition and processing system comprises a data acquisition subsystem of a master control unit, a data analysis module of the master control unit, and a detection execution mechanism. The data analysis module of the master control unit is the main carrier of the signal processing algorithm mentioned in the method of the present application.

[0076] In operation, the hardware system first acquires magnetic field information in real time using the TMR sensor as the core device of the magnetic detection system. After the TMR sensor output signal is processed by hardware, it is input to the embedded data acquisition and processing system through the A / D conversion module. The signal is further processed by analyzing the magnetic field data acquired by the TMR sensor. Second, the electrostatic field detection module works based on electrostatic field theory to monitor the induction electrode charge in real time. The position of the detector relative to the target is determined based on the change of the Q / V conversion voltage, and the output of the initiation signal is controlled. A small current detection base signal is output by the base voltage power supply adjustment module, and the base signal current is continuously adjusted according to the state of the induction electrode to stabilize the voltage value output. It is mainly used to realize stable work under different environmental conditions and improve the adaptive ability of the system. The process is repeated until the acquired magnetic signal meets the target magnetic characteristics and meets the magnetic target recognition criteria.

[0077] The present application innovatively combines the data-driven distance waveform timing mapping model with the magnetic field and electrostatic field composite detection technology. By constructing a "zero-crossing point prediction-distance inversion" dynamic solving framework, the static limitations of traditional fixed distance methods are broken. Specifically, the core includes: based on the regularity of the timing characteristics of the magnetic field disturbance and the electrostatic field vector change during the intersection of the target and the detector (such as the evolution trend of the signal waveform rising first and then falling, and the intersection point being the zero-crossing point), the signal evolution law in the non-intersection stage is learned using a neural network model to realize dynamic prediction of the zero-crossing timing; combined with the double-physical-field cooperative mechanism, the environmental noise is suppressed through the complementary characteristics of the magnetic field disturbance signal and the electrostatic field vector change data, the recognition degree of the signal characteristics in complex environments is improved, and the noise interference of a single physical field is reduced; finally, the distance is inversely solved according to the zero-crossing timing and the target motion parameters to form a "prediction-verification-correction" closed-loop distance measurement system. This method breaks through the static limitations of the fixed threshold method, significantly improves the distance measurement accuracy and response speed through dynamic prediction, and provides an efficient solution for real-time detection and interception of moving targets.

[0078] In addition, the present application takes the front section information as the input, realizes the zero-crossing point prediction through the distance waveform time sequence mapping model, and finally realizes the inversion method of the distance of the to-be-detected target by combining the motion parameters of the current motion detector. The target detection distance determination process improved by the method can effectively improve the distance determination accuracy.

[0079] The core effect of the technical solution is to improve the distance determination accuracy. The traditional distance determination method uses a fixed signal threshold, and its accuracy is easily affected by the target speed, approaching angle and environmental noise. The technical solution applies a data-driven neural network model to dynamically predict the zero-crossing point position by learning the time sequence characteristics of the magnetic field and electrostatic field signals before the target intersection. This method changes the distance determination basis from static amplitude judgment to dynamic time sequence analysis, aiming to improve the accuracy and stability of the distance determination result.

[0080] In terms of response speed, the technology is optimized for high-speed motion target detection. Traditional technologies are mostly passive responses, which have inherent response delays, which is a limiting factor in high-speed target detection. The present solution uses the forward inference capability of a sequence prediction network (such as LSTM) to predict the zero-crossing time interval and combine the detector motion parameters to invert the distance. This predictive working mode shortens the system response time and is suitable for real-time distance determination requirements of high-speed moving targets.

[0081] The scheme enhances the environmental adaptability of the system through a dual-field fusion strategy. Single physical field detection is easily affected by noise interference or target characteristic changes in complex electromagnetic environments, resulting in decreased reliability. The scheme uses a magnetic field and electrostatic field dual-field fusion strategy to take advantage of the complementarity of the two physical mechanisms in detection principles to mutually verify and correct target information. This composite detection method improves the anti-interference ability and target recognition of the system in complex environments.

[0082] The present application realizes a breakthrough in the field of target distance determination technology in a composite detection background, and creatively converts the zero-crossing phenomenon in the intersection process of moving targets and detectors into a predictable mathematical model, and combines neural networks and multi-physical field collaborative mechanisms to solve the dynamic response lag problem caused by the dependence of traditional methods on static thresholds. By using the common phenomenon in dual-mode composite detection of magnetic field and electric field, the time sequence rule of "first rising and then falling" of the intersection signal is excavated, a distance-waveform mapping model is established, and a sequence prediction network (such as: long short-term memory network, etc.) is used to learn the magnetic field disturbance and electrostatic field vector evolution characteristics in the non-intersection stage to realize dynamic prediction of the zero-crossing point position. This mechanism breaks through the static limitations of traditional threshold response, which will effectively improve the distance determination accuracy between moving targets and detectors, and through the cooperative suppression of environmental noise by composite fields, a new paradigm is provided for composite detection in complex scenarios.

[0083] The novelty of this invention lies in two aspects: a revolutionary prediction paradigm and a multi-physics field fusion mechanism design. Firstly, in terms of prediction paradigm, existing technologies such as magnetic ranging or electrostatic ranging rely on instantaneous signal inversion and fail to utilize temporal characteristics for forward-looking inference. Secondly, in the design of data fusion mechanisms for combined magnetic and electrostatic field detection, traditional combined detection methods often employ simple superposition or threshold fusion, failing to address the issue of feature complementarity between physical fields. This invention and its design method introduce the cross-application concept of "temporal prediction + physical constraint inversion," identifying the evolutionary patterns of the signal sequence before convergence through model training, enabling advance calculation of distance parameters, and possessing robust mutual verification between two independent physical fields. This significantly improves the accuracy of target ranging from both the principle and anti-interference aspects.

[0084] At the engineering application level, this technology has a low deployment threshold. Its core innovation lies primarily in the algorithm, which is compatible with mainstream sensors (such as TMR magnetic sensors and sensing electrodes) without requiring hardware modifications. The method provided by this invention can be directly embedded into existing hardware platforms such as field-programmable gate arrays, microcontrollers, or digital signal processors, resulting in a wide range of applications and low implementation costs. Specifically, the algorithm's functional modules are designed and embedded within the system under development, achieving functional deployment only through software control module upgrades, making implementation easy. This characteristic reduces the implementation cost and deployment difficulty of technology upgrades, enabling its widespread application in existing systems. This invention can be applied in resource exploration and industrial inspection fields.

[0085] When applying the multi-physics-based moving target detection method provided by this invention, it is not necessary to consider... Figure 1 The steps shown are executed in sequence. The specific execution order of each step can be determined as needed, and this invention does not impose any restrictions on it.

[0086] The above describes a multi-physics-based moving target detection method provided by one or more embodiments of the present invention. Based on the same idea, the present invention also provides a corresponding multi-physics-based moving target detection device, which includes: The acquisition module is used to acquire the magnetic field signal and electrostatic field signal of the detector detecting the moving target under multi-physics field conditions before the detector intersects with the moving target; the multi-physics field includes magnetic field and electrostatic field. The prediction module is used to fuse the magnetic field signal and the electrostatic field signal to obtain a fused signal, and based on the fused signal, predict the number of remaining sampling points before the detector reaches the zero-crossing position from the current position; the zero-crossing position is the position of the detector when the distance between the detector and the moving target is the shortest in the future. The computing module is configured to determine a time gap before the intersection between the detector and the moving target at the current time according to a sampling rate of the detector and a remaining sampling point number, and determine a distance between the detector and a zero-crossing point position at the current time according to a motion parameter of the detector and the time gap.

[0087] The specific limitations of the motion target detection device based on multiple physical fields can refer to the limitations of the motion target detection method based on multiple physical fields in the foregoing, which will not be repeated here. Each module in the motion target detection device based on multiple physical fields can be realized by software, hardware, and a combination thereof in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each of the above-mentioned modules.

[0088] The application further provides a computer readable storage medium, which stores a computer program, and the computer program can be used to execute the above-mentioned Figure 1 The application provides a motion target detection method based on multiple physical fields.

[0089] The application further provides a computer readable storage medium, which stores a computer program, and the computer program can be used to execute the above-mentioned Figure 11 The structure schematic diagram of the computer device is shown in the accompanying drawings. Figure 11 As shown in the accompanying drawings, at the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and of course can further include other hardware required by a business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs to realize the above-mentioned Figure 1 The application provides a motion target detection method based on multiple physical fields.

[0090] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments of the methods. In the embodiments of the present application, any reference to memory, storage, database or other medium can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0091] The technical features of the above embodiments can be combined in any way. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

Claims

1. A multi-physical field based moving target detection method, characterized in that, The method comprises: Before the detector intersects with the moving target, acquiring a magnetic field signal and an electrostatic field signal of the detector detecting the moving target under multiple physical fields; the multiple physical fields include a magnetic field and an electrostatic field; Fusing the magnetic field signal and the electrostatic field signal to obtain a fused signal, and predicting a remaining sampling point number of the detector from a current position to a zero-crossing point position according to the fused signal; the zero-crossing point position is a position of the detector when a distance between the detector and the moving target is the shortest at a future time; According to a sampling rate of the detector and the remaining sampling point number, determining a time gap before the detector intersects with the moving target at a current time; According to motion parameters of the detector and the time gap, determining a distance between the detector and the zero-crossing point position at the current time.

2. The method of claim 1, wherein, The detector and the moving target generate a signal waveform showing a rising trend first and then a falling trend in the intersecting motion process, and a position where the detector intersects with the moving target is an intersection point, that is, the zero-crossing point position.

3. The method of claim 2, wherein, According to the fused signal, the remaining sampling point number of the detector from the current position to the zero-crossing point position is predicted, comprising: Performing empirical mode decomposition on the fused signal to extract a low-frequency topographic feature component; Inputting the low-frequency topographic feature component into a pre-trained distance waveform time sequence mapping model to obtain the remaining sampling point number of the detector from the current position to the zero-crossing point position; a calculation mode of the distance waveform time sequence mapping model is a matrix multiplication mode or a polynomial calculation mode.

4. The method of claim 3, wherein, The training process of the distance waveform time sequence mapping model comprises: Acquiring prior data sets in multiple modes; the prior data sets are rising data information before a sample detector intersects with a sample moving target; Taking the remaining sampling point number before reaching the zero-crossing point position as an output label, training a pruned long short-term memory network through the prior data sets, and testing the trained network until a validation error of the trained network is within a preset range; Extracting a parameter matrix of the network within the preset range of the validation error, converting a network calculation process into a matrix multiplication or a polynomial calculation mode according to the parameter matrix to obtain the distance waveform time sequence mapping model.

5. The method of claim 4, wherein, Acquiring the prior data sets in multiple modes comprises: Establishing a magnetic field and electrostatic field dual-mode detection model in a digital space; Constructing an intersection scene of the sample detector and the sample moving target, including a spatial coordinate system, an initial position and a motion trajectory, and a parameter combination of different speed ranges, different detection axial directions and different intersection angles; According to an orthogonal experimental design method, performing multi-parameter combination simulation on the magnetic field and electrostatic field dual-mode detection model, recording sample magnetic field signals and sample electrostatic field signals in the intersection process of the sample detector and the sample moving target, and labeling distance information, time information and label information of a remaining sampling point number before reaching the zero-crossing point position for each sampling point; For any one parameter combination, respectively pre-processing the sample magnetic field signals and the sample electrostatic field signals, and fusing the pre-processed sample magnetic field signals and the sample electrostatic field signals to obtain sample fused signals; Performing modal decomposition on the sample fused signals to obtain sample low-frequency topographic feature components; The sample low-frequency morphology feature component and the corresponding remaining sample point number before reaching the zero-crossing position are determined as a priori data set.

6. The method of claim 5, wherein, The magnetic field detection model is based on a magnetic dipole model, considering the magnetic moment size and direction of the target object, and a mathematical model of the magnetic field strength changing with distance is established; the electrostatic field detection model is based on a charge distribution model, considering the charge amount and distribution characteristics of the target object, and a mathematical model of the electric field strength changing with distance is established.

7. The method of claim 1, wherein, According to the sampling rate of the detector and the remaining sample point number, the time gap before the intersection between the detector and the moving target at the current time is determined, including: The product of the sampling rate of the detector and the remaining sample point number is determined as the time gap before the intersection between the detector and the moving target at the current time.

8. The method of claim 1, wherein, The motion parameters include velocity; according to the motion parameters of the detector and the time gap, the distance between the detector and the zero-crossing position at the current time is determined, including: The product of the velocity of the detector at the current time and the time gap is determined as the distance between the detector and the zero-crossing position at the current time.

9. A multi-physical field based moving target detection device, characterized in that, It includes: The acquisition module is used to acquire the magnetic field signal and the electrostatic field signal detected by the detector under the action of the multiple physical fields before the intersection between the detector and the moving target; the multiple physical fields include magnetic field and electrostatic field; The prediction module is used to fuse the magnetic field signal and the electrostatic field signal to obtain a fusion signal, and to predict the remaining sample point number before the detector reaches the zero-crossing position from the current position according to the fusion signal; the zero-crossing position is the position of the detector when the interval distance between the detector and the moving target is the shortest in the future; The calculation module is used to determine the time gap before the intersection between the detector and the moving target at the current time according to the sampling rate of the detector and the remaining sample point number; and to determine the distance between the detector and the zero-crossing position at the current time according to the motion parameters of the detector and the time gap.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is executed by the processor to realize the method of any one of claims 1-8.

Images