A method and system for monitoring sand movement based on magnetic field positioning

Abstract

This invention relates to a method and system for monitoring sand movement based on magnetic field positioning. The method includes sand to be monitored, several marked magnetic particles embedded in the sand, and a sensor array deployed around or above the area to be monitored. The sensor array includes at least three magnetic field sensors, and the number of magnetic field sensors is the same as the number of marked magnetic particles. This magnetic field positioning technology overcomes the limitations of traditional techniques, enabling real-time, high-precision monitoring.

Description

Technical Field

[0001] This invention relates to a method and system for monitoring sand movement based on magnetic field positioning, belonging to the technical field of real-time monitoring of sand movement. Background Technology

[0002] Sand and soil movement monitoring has wide applications in disaster prevention and mitigation, geological engineering, and infrastructure construction. Traditional methods for sand and soil monitoring commonly include visual sensing, acoustic sensing, and displacement monitoring based on mechanical sensors. However, these methods are only effective in specific applications and are prone to problems such as sensor interference, decreased accuracy after long-term monitoring, and difficulty adapting to complex environments.

[0003] In existing technologies, some studies have attempted to monitor sand movement using labeled particles and optical tracking methods. However, these methods are affected by factors such as line-of-sight obstruction, particle loss, and changes in lighting conditions, making it difficult to guarantee accuracy in dynamic and complex environments. Line-of-sight limitations refer to the susceptibility of visual sensors to obstruction and changes in lighting conditions, leading to decreased monitoring accuracy. Environmental interference means that acoustic and mechanical sensors are easily affected by noise and vibration in complex sandy environments, making it difficult to maintain stable monitoring results. Accuracy limitations exist; existing technologies struggle to maintain high accuracy over long periods and are inadequate in handling minute changes in sand particle movement. Finally, existing monitoring methods are significantly affected by the surrounding environment, making it difficult to objectively monitor the results of sand movement.

[0004] Therefore, it is necessary to study a new technical means to overcome the above limitations and achieve real-time, high-precision monitoring of sand movement in complex environments. Summary of the Invention

[0005] This invention provides a method and system for monitoring sand movement based on magnetic field positioning, which can overcome the limitations of traditional technologies and achieve real-time high-precision monitoring.

[0006] The technical solution adopted by this invention to solve its technical problem is:

[0007] A method for monitoring sand movement based on magnetic field positioning, specifically including the following steps:

[0008] Step S1: Select several qualified magnetic marker particles and implant them into the sand in the monitoring area.

[0009] Step S2: Set up a sensor array consisting of several magnetic field sensors, calibrate the sensor array, and place the calibrated sensor array around or above the monitoring area.

[0010] Step S3: Real-time magnetic field data at different locations are collected by a magnetic field sensor. The data processing module preprocesses the real-time magnetic field data to filter out environmental noise and interference.

[0011] Step S4: The data from several magnetic field sensors processed in step S3 are fused together. The positioning algorithm module uses the changes in the magnetic field to invert the location information of the magnetic field source and determine the specific location of each marked magnetic particle in the monitoring area.

[0012] Step S5: Track the specific location of the marked magnetic particles in real time in the time series, record the changes in the location of the marked magnetic particles, and generate a motion trajectory;

[0013] Step S6: Based on the movement trajectory of the marked magnetic particles generated in step S5, analyze the movement of sand and soil in the monitoring area.

[0014] Furthermore, several magnetic field sensors are located at different heights and horizontal positions, forming a sensor array;

[0015] Furthermore, in step S4, the specific steps for retrieving the location information of the magnetic field source using changes in the magnetic field are as follows:

[0016] Step S41: Construct a physical model, treating each marked magnetic particle as a magnetic dipole, and defining it as x. i A magnetic field sensor is defined as y j Then mark the magnetic particle x i The three-dimensional coordinates are x i =(x i ,y i ,z i ), where i = 1, 2, ..., n, and the magnetic field sensor y j The three-dimensional coordinates are y j =(x j ,y j ,z j ), where j = 1, 2, ..., n, n ≥ 3;

[0017] Step S42, construct a magnetic dipole model, and label magnetic particles x i The magnetic field at a distance r is represented as Its description is as follows:

[0018]

[0019] In the formula, To label magnetic particles x i With magnetic field sensor y j The distance between them

[0020] μ0 is the free permeability.

[0021] m i To label magnetic particles x i Magnetic moment vector;

[0022] Step S43: Construct the measurement equation and determine the magnetic field sensor y in the sensor array. j All marked magnetic particles x were measured i The sum of magnetic fields:

[0023]

[0024] In the formula, B j For all labeled magnetic particles x i The sum of magnetic fields, n≥3;

[0025] Step S44, based on each marked magnetic particle x i Magnetic field and magnetic field sensor y j Based on the spatial location, establish the following relationship:

[0026]

[0027] In the formula, The measurements are obtained by solving the nonlinear equations trained by a neural network, and are represented as a set of unknown coordinates x. i The nonlinear equation;

[0028] Step S45: By solving the nonlinear equation, the labeled magnetic particle x is obtained. i With magnetic field sensor y j Distance between The three-dimensional coordinates of the marked magnetic particles are determined by triangulation of the distance between each marked magnetic particle and the magnetic field sensor, and iterative solution.

[0029] Furthermore, the process of training the nonlinear equations using a neural network based on step S44 is as follows:

[0030] Step S441, Prepare the training dataset Among them, (B) j ,m i ,y j ) is the input feature vector. Output as the target. Indicates all marked magnetic particles x i The sum of magnetic fields B j The predicted value;

[0031] Step S442, define a feedforward neural network, including an input layer, hidden layers, and an output layer. The input layer takes in features (x). i ,m i,y j The output of the hidden layer is then passed to the hidden layer and transformed by a non-linear activation function. The output of the hidden layer is then passed to the output layer to obtain all the labeled magnetic particles x. i The sum of magnetic fields B j Predicted value

[0032]

[0033] In the formula, f NN For a neural network model, θ represents the trainable parameters in the neural network;

[0034] Step S443, calculate the predicted value With the true value B j The error between them is expressed using the mean square error as the error function, specifically:

[0035]

[0036] In the formula, L is the loss function, N is the maximum number of j n, and N≥3;

[0037] Step S444: Use the backpropagation algorithm to calculate the gradient of the loss function L with respect to the trainable parameters θ, i.e.

[0038]

[0039] Step S445: Update the weights of the neural network model using gradient descent or an optimization algorithm, i.e.

[0040]

[0041] In the formula, η is the learning rate;

[0042] Step S446: Repeat steps S442-S445 until the loss function converges to a preset standard minimum value or reaches a preset number of training rounds, completing the process including unknown coordinates x. i Training of nonlinear equation systems;

[0043] Furthermore, in step S45, the specific process of solving the nonlinear equation is as follows:

[0044] Step S451: Determine the three-dimensional coordinates of the marked magnetic particles using a nonlinear equation. Here, the nonlinear equation is:

[0045]

[0046] In the formula, To label magnetic particles x i With magnetic field sensor y j The distance between them is obtained based on the constructed magnetic dipole model, that is...

[0047] Step S452: The nonlinear equation in step S451 is solved using the nonlinear least squares method. Data from each magnetic field sensor is input into the solution to obtain the three-dimensional coordinates that are closest to each marked magnetic particle.

[0048] Furthermore, based on the measurement equation constructed in step S43, an error correction method is used to adjust the magnetic field sensor y. j The measured marked magnetic particles x i The magnetic field data was adjusted;

[0049] Furthermore, in step S5, the specific position of each marked magnetic particle in the monitoring area is determined according to step S4, that is, the three-dimensional coordinates of each marked magnetic particle, the change of position of each marked magnetic particle is recorded, and its motion trajectory is generated.

[0050] Furthermore, in step S6, based on the movement trajectory of the marked magnetic particles, the overall movement characteristics of the sand and soil are analyzed, including the flow velocity, scour depth changes, and soil stress conditions.

[0051] A sand movement monitoring system employs the aforementioned sand movement monitoring method based on magnetic field positioning. The system includes sand to be monitored, with several marked magnetic particles embedded in the sand, and a sensor array deployed around or above the area to be monitored. The sensor array includes at least three magnetic field sensors, and the number of magnetic field sensors is the same as the number of marked magnetic particles.

[0052] By employing the above technical solutions, the present invention has the following beneficial effects compared to the prior art:

[0053] 1. The sand movement monitoring method based on magnetic field positioning provided by this invention, based on magnetic field detection and positioning algorithm of multi-sensor array, can work in irregular and complex sand environment and has strong anti-interference ability.

[0054] 2. The sand movement monitoring method based on magnetic field positioning provided by this invention, which combines data obtained by sensor array with processing methods and algorithms to generate sand movement trajectories, can accurately detect minute displacement changes and achieve higher precision sand movement monitoring.

[0055] 3. The sand movement monitoring system provided by this invention is based on magnetic field positioning technology. It implants micro-marker particles with specific magnetic field characteristics into the sand for monitoring. It can maintain stable high-precision performance during long-term continuous monitoring, and does not depend on external light conditions, making it suitable for long-term dynamic monitoring tasks. Attached Figure Description

[0056] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0057] Figure 1 This is a flowchart of the monitoring method according to a preferred embodiment of the present invention;

[0058] Figure 2 This is a schematic diagram of a preferred embodiment of the present invention;

[0059] Figure 3 This is a result interface display diagram of a preferred embodiment provided by the present invention. Detailed Implementation

[0060] The present invention will now be described in further detail with reference to the accompanying drawings. In the description of this application, it should be understood that the terms "left side," "right side," "upper part," "lower part," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. "First," "second," etc., do not indicate the importance of the components, and therefore should not be construed as a limitation of the present invention. The specific dimensions used in this embodiment are only for illustrating the technical solution and do not limit the scope of protection of the present invention.

[0061] As described in the background section, in existing technologies, whether displacement monitoring is based on visual perception, acoustic wave perception, or mechanical sensors, and some studies have even attempted to use labeled particles and optical tracking methods for sand movement monitoring, all of these are easily affected by factors such as line-of-sight obstruction, particle loss, and changes in lighting conditions, making it impossible to guarantee monitoring accuracy in dynamic and complex environments. Future developments have also considered acoustic wave-based positioning technologies or methods using optical imaging combined with deep learning for motion analysis; however, acoustic waves are also susceptible to environmental noise, and the monitoring accuracy of optical imaging significantly decreases when sand obstructs the view or when ambient lighting conditions change.

[0062] Therefore, this application provides a more accurate, stable, and suitable method for monitoring sand movement in complex environments through magnetic field positioning technology. The entire monitoring method involves implanting marker particles with micro-magnetic field properties into the sand, using magnetic field detection equipment to track the particle's trajectory in real time. The system consists of multiple magnetic field sensor arrays, combined with an efficient positioning algorithm to calculate the three-dimensional positional changes of the marker particles in the sand. Precise measurement of the magnetic field overcomes interference from ambient light and noise, enabling accurate tracking of sand movement.

[0063] Firstly, this application provides a method for monitoring sand movement based on magnetic field positioning, which includes the following steps:

[0064] Step S1: Select several qualified magnetic marker particles and implant them into the sand in the monitoring area.

[0065] The criteria for selecting magnetic marker particles here are that they should possess strong magnetic field properties and be small enough to ensure they can move freely in the sand without affecting its flowability. These particles are typically specially designed magnetic particles or tiny particles containing magnetic materials. These tiny particles offer several advantages: in laboratory sand sample analysis, applying a magnetic field can quickly aggregate the magnetic particles, greatly improving sample processing efficiency; in complex sandy environments, this marking method can accurately identify and locate specific areas of sand, contributing to a more precise understanding of the dynamic behavior of the sand.

[0066] The magnetic properties of magnetic particles make them highly sensitive to changes in their surrounding environment. Even minute changes in stress, strain, or displacement within sand can alter the magnetic properties of these particles, thus enabling the detection of subtle dynamic changes in sand and improving monitoring accuracy. Magnetic particles also possess good stability and durability, allowing them to persist in sand and maintain their magnetic properties for extended periods. This enables long-term dynamic monitoring of sand, which is of great significance for studying the long-term patterns of sand variation and geological evolution.

[0067] After these marked magnetic particles are implanted into the sand in the area to be monitored, the particles will move with the sand. The unique properties of the magnetic particles enable them to accurately reflect the dynamics of the sand even in complex sandy environments, effectively solving the problem of interference factors caused by the environment.

[0068] It should be noted that during the experiment, this application found that at least three labeled magnetic particles need to be implanted for the detected data to be of reference value.

[0069] Step S2: Set up a sensor array consisting of several magnetic field sensors, calibrate the sensor array, and place the calibrated sensor array around or above the monitoring area.

[0070] The number of magnetic field sensors deployed is matched to the number of labeled magnetic particles. Utilizing advanced magnetic monitoring equipment and technology, remote monitoring of the magnetic particles can be achieved without direct contact with the sand sample. This has significant application value for inaccessible or hazardous areas, such as geological disaster monitoring points in remote regions and deep-sea sediment monitoring. The magnetic field sensors are distributed in an array around or above the sand monitoring area because, ideally, the sensor array can cover the entire three-dimensional space of the sand area, thus accurately detecting changes in the position of the labeled magnetic particles.

[0071] It is important to note that, to improve positioning accuracy, the magnetic field sensors should be positioned at different heights and horizontal levels. The distance between the magnetic field sensors should be adjusted according to the size of the sand monitoring area and the magnetic field strength of the marked magnetic particles.

[0072] Once the magnetic field sensors and labeled magnetic particles are deployed, each sensor can measure the magnetic field strength around it in real time. As the labeled magnetic particles move through the sand, the distribution of the magnetic field changes, and the sensors detect these changes to determine the position of the labeled magnetic particles. By fusing data from multiple magnetic field sensors, the three-dimensional position of the labeled magnetic particles in the sand can be deduced from the changes in the magnetic field. The sensor array can capture the magnetic field strength at different locations, and by retrieving the location information of the magnetic field source, the specific position of the labeled magnetic particles within the monitoring area can be determined, completing the three-dimensional positioning operation.

[0073] Of course, the sensor array needs to be calibrated before actual monitoring to ensure the measurement accuracy of each magnetic field sensor. Calibration can be performed by marking magnetic particles at known locations.

[0074] Step S3: Real-time magnetic field data at different locations is collected by a magnetic field sensor. The data processing module preprocesses the real-time magnetic field data to filter out environmental noise and interference. Commonly used signal processing techniques include filtering, noise reduction, and signal enhancement.

[0075] Next, based on the magnetic field strength detected by the magnetic field sensor, the three-dimensional position of the marked magnetic particles is calculated using an inversion algorithm.

[0076] Specifically, step S4 involves fusing the data from several magnetic field sensors after processing in step S3, and using the magnetic field change to invert the location information of the magnetic field source, thereby determining the specific location of each marked magnetic particle within the monitoring area.

[0077] The specific steps for deducing the location information of a magnetic field source by inverting changes in the magnetic field are as follows:

[0078] Step S41: Construct a physical model, treating each marked magnetic particle as a small magnetic dipole, and defining it as x. i A magnetic field sensor is defined as y j Field sensor y j If the magnetic field strength generated by the dipole can be measured, then the magnetic particle x is labeled. i The three-dimensional coordinates are x i =(x i ,y i ,z i ), where i = 1, 2, ..., n, and the magnetic field sensor y j The three-dimensional coordinates are y j=(x j ,y j ,z j ), where j = 1, 2, ..., n, n ≥ 3;

[0079] Step S42, constructing a magnetic dipole model. This step establishes a precise spatial representation method, solving the problem of describing precise displacement in existing technologies. (The text then abruptly shifts to a seemingly unrelated topic: labeling magnetic particles x...) i The magnetic field at a distance r is represented as Its description is as follows:

[0080]

[0081] In the formula, To label magnetic particles x i With magnetic field sensor y j The distance between them

[0082] μ0 is the free permeability.

[0083] m i To label magnetic particles x i Magnetic moment vector;

[0084] Step S43: Construct the measurement equation and determine the magnetic field sensor y in the sensor array. j All marked magnetic particles x were measured i The sum of magnetic fields:

[0085]

[0086] In the formula, B j For all labeled magnetic particles x i The sum of magnetic fields, n≥3;

[0087] This section discusses the construction of the measurement equations. Based on these equations, an error correction method can be used to adjust the magnetic field sensor y. j The measured marked magnetic particles x i The magnetic field data is adjusted, which, in principle, eliminates the problem of existing monitoring methods being easily limited by line of sight, since the sensor may be affected by the ambient magnetic field. This improves the positioning accuracy.

[0088] Step S44, based on each marked magnetic particle x i The generated magnetic field, and the magnetic field sensor y, are also known. j Based on spatial location, the following relationships can be established:

[0089]

[0090] In the formula, The measurements are obtained by solving the nonlinear equations trained by a neural network, and are represented as a set of unknown coordinates x. i The nonlinear equation;

[0091] It should be clarified here that, under normal circumstances, if we want to solve the above nonlinear equation for x... i ,but m i y j The three quantities should be known, but in reality, m i y j Given a constant, when using intelligent methods to solve environmental interference problems, x should be solved directly using a neural network method. i However, due to the complex working conditions of the sandy soil in this application, the excessive possibility of interference may lead to low accuracy of the obtained numerical values. Therefore, the solution is obtained by solving the problem first. This method can improve the accuracy of the solution.

[0092] Regarding the choice of solution The applicant provided an explanation, combining the aforementioned nonlinear equations with the constructed measurement equations, resulting in the corresponding... In other words, for a number of labeled magnetic particles and a number of magnetic field sensors, the training data will include combinations of different positions, magnetic moments, and magnetic field sensors, B j It contains the positional information of each marked magnetic particle; however, in this formula, x... i It is a variable to be solved, and cannot be obtained directly.

[0093] In solving First, the nonlinear equations are trained using a neural network. The training process is as follows:

[0094] Step S441, Prepare the training dataset Among them, (B) j ,m i ,y j ) is the input feature vector. Output as the target. Indicates all marked magnetic particles x i The sum of magnetic fields B j The predicted value;

[0095] For a set of labeled magnetic particles and a set of magnetic field sensors, the training data will include combinations of different positions, magnetic moments, and magnetic field sensors. This includes the positional information of each marked magnetic particle.

[0096] Step S442: Define a feedforward neural network, which includes an input layer, a hidden layer, and an output layer. The input layer takes in features, the hidden layer can be one or more layers, and the output layer outputs the predicted value. Since the magnetic field is a three-dimensional vector, the size of the output layer is 3.

[0097] Forward propagation, the input layer inputs features (x) i ,m i ,y j The output of the hidden layer is then passed to the hidden layer and transformed using a nonlinear activation function (preferably ReLU). The output of the hidden layer is then passed to the output layer to obtain all the labeled magnetic particles x. i The sum of magnetic fields B j Predicted value

[0098]

[0099] In the formula, f NN For a neural network model, θ represents the trainable parameters in the neural network;

[0100] Step S443, Error calculation, calculate the predicted value. With the true value B j The error between them is expressed using the mean square error as the error function, specifically:

[0101]

[0102] In the formula, L is the loss function, N is the maximum number of j n, and N≥3;

[0103] Step S444, backpropagation: Use the backpropagation algorithm to calculate the gradient of the loss function L with respect to the trainable parameters θ, i.e.

[0104]

[0105] Step S445, weight update: Update the weights of the neural network model using gradient descent or an optimization algorithm, i.e.

[0106]

[0107] In the formula, η is the learning rate;

[0108] Step S446: Repeat steps S442-S445 until the loss function converges to a preset standard minimum value or reaches a preset number of training rounds, completing the training process including the unknown coordinate x. i Training of nonlinear equation systems;

[0109] Step S45: By solving the nonlinear equation, the labeled magnetic particle x is obtained. i With magnetic field sensor yj Distance between The three-dimensional coordinates of the marked magnetic particles are determined by triangulation of the distance between each marked magnetic particle and the magnetic field sensor, and iterative solution.

[0110] Step S451, for each magnetic field sensor y j In actual operation, the magnetic field strength vector B of several magnetic field sensors can be measured. j In order to calculate x for each marked magnetic particle i To determine the spatial coordinates of the marked magnetic particles, the following nonlinear equation needs to be solved. The nonlinear equation is as follows:

[0111]

[0112] In the formula, To label magnetic particles x i With magnetic field sensor y j The distance between them is obtained based on the constructed magnetic dipole model, that is...

[0113] In step S452, since this is a nonlinear system of equations, the nonlinear least squares method is used to solve the nonlinear equations in step S451. By inputting the data from each magnetic field sensor, the precise three-dimensional coordinates of each marked magnetic particle can be gradually approximated.

[0114] Finally, using data from the magnetic field sensor, sufficient information is provided to solve for the x value of each marked magnetic particle. i Spatial coordinates.

[0115] Step S5: Based on step S4, the specific location of each marked magnetic particle in the monitoring area is determined through multiple iterations, i.e., the three-dimensional coordinates of each marked magnetic particle. Once the location of the marked magnetic particle is determined, the system can track its movement in real time in the time series, record the changes in the location of each marked magnetic particle, generate its three-dimensional motion trajectory, and finally output it.

[0116] Based on the movement trajectories of marked magnetic particles, the overall movement characteristics of sand and soil can be analyzed, such as flow velocity, scour depth changes, and soil stress. Then, the particle movement trajectories are visualized through software, allowing operators to intuitively observe the dynamic changes within the sand and soil. Long-term sand and soil movement data can be recorded and stored for further analysis, such as predicting sand and soil scour and identifying movement patterns.

[0117] To accomplish the aforementioned monitoring, this application provides a sand movement monitoring system, comprising the sand to be monitored, several marked magnetic particles embedded in the sand, and a sensor array deployed around or above the monitoring area. The sensor array includes at least three magnetic field sensors, with the number of magnetic field sensors matching the number of marked magnetic particles. The entire system, if presented as modules, includes four modules: a magnetic field detection module, which deploys multiple magnetic field sensors to detect the movement of the marked magnetic particles in the sand; a positioning algorithm module, which uses a data fusion algorithm from multiple magnetic field sensors to calculate the trajectory of each marked magnetic particle; a data processing module, which performs data preprocessing, filtering, and visualization of the movement trajectories; and a sand movement analysis module, which analyzes long-term monitoring data to provide trends and dynamic characteristics of sand movement.

[0118] Preferred, such as Figure 2 As shown, this application uses three marked magnetic particles, matched, as... Figure 1 As shown, a flowchart of the monitoring method using three labeled magnetic particles as an example is given, and the final result is as follows: Figure 3 As shown, this is displayed in real time on the integrated interface of the intelligent sand and soil movement monitoring system.

[0119] In summary, the sand movement monitoring method and system based on magnetic field positioning provided in this application aim to address the limitations of traditional methods in sand movement monitoring, particularly the difficulty in accurately locating the movement trajectory of sand particles in complex environments; existing technologies struggle to accurately capture real-time information on sand movement in dynamic and irregular sand environments, and cannot effectively monitor sand changes over long periods under high-precision conditions. It offers the following advantages: unaffected by light – magnetic field positioning technology is independent of external light conditions and suitable for all-weather monitoring; higher accuracy – magnetic field sensors can accurately detect minute displacement changes, achieving higher precision in sand movement monitoring; adaptable to complex environments – the system can operate in irregular and complex sand environments with strong anti-interference capabilities; and stable long-term monitoring – the system maintains stable high-precision performance during long-term continuous monitoring, making it suitable for long-term dynamic monitoring tasks.

[0120] Those skilled in the art will understand that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as herein.

[0121] The meaning of "and / or" as used in this application includes situations where each exists alone or both exist simultaneously.

[0122] The term "connection" as used in this application can mean a direct connection between components or an indirect connection between components through other components.

[0123] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A method of monitoring movement of sand based on magnetic field positioning, characterized by: Specifically comprising the following steps: Step S1, selecting a plurality of labeled magnetic particles meeting the requirements, and implanting the labeled magnetic particles into the sand in the monitoring area; Step S2, setting up a sensor array composed of a plurality of magnetic field sensors, calibrating the sensor array, and arranging the calibrated sensor array around or above the monitoring area; Step S3, collecting real-time magnetic field data at different positions by the magnetic field sensors, and pre-processing the real-time magnetic field data by a data processing module to filter out environmental noise and interference; Step S4, fusing the data of the plurality of magnetic field sensors processed in step S3, and using a magnetic field change condition to inversely deduce the position information of the magnetic field source to determine the specific position of each labeled magnetic particle in the monitoring area; The specific steps of using the magnetic field change condition to inversely deduce the position information of the magnetic field source are: Step S41, construct a physical model, consider each labeled magnetic particle as a magnetic dipole, and define as , the magnetic field sensor is defined as , the three-dimensional coordinates of the labeled magnetic particle are , wherein n , the three-dimensional coordinates of the magnetic field sensor are , wherein n , ; Step S42, constructing a magnetic dipole model, the magnetic field at the marker magnetic particle distance is The magnetic field at the marker magnetic particle is represented as which is described as: ， In the formula, to label magnetic particles with a magnetic field sensor the distance between, , is the vacuum permeability, to mark the magnetic particles the magnetic moment vector of the magnetic particles; Step S43, constructing a measurement equation to determine the magnetic field sensor measured magnetic field sum of all labeled magnetic particles ​ ， In the formula, For all marked magnetic particles The sum of the magnetic fields, ; Step S44, based on the spatial position of each marker magnetic particle 's magnetic field and the magnetic field sensor 's spatial position, the following relationship is established: ， In the formula, The nonlinear equation is solved by neural network training, and the measurement value is represented as a set of nonlinear equations containing unknown coordinates ​ The process of training the nonlinear equation by the neural network is: Step S441, Prepare the training dataset ,in, It is the input feature vector. Output as the target. Indicates all marked magnetic particles The sum of magnetic fields The predicted value; Step S442, define the feedforward neural network, set to include the input layer, hidden layer and output layer, the input layer input features , after passing to the hidden layer, the transformation is carried out through the nonlinear activation function, the output of the hidden layer continues to pass to the output layer, and the predicted value of the magnetic field sum of all labeled magnetic particles ,​​ ， In the formula, is a neural network model, is a trainable parameter in the neural network; Step S443, calculate the prediction value the error between the prediction value and the true value The mean square error is used as the error function, and the specific formula is ， In the formula, is a loss function, is the maximum number of n , and ; Step S444, using backpropagation algorithm to calculate loss function on trainable parameters , i.e. ; Step S445, update the weights of the neural network model by gradient descent or optimization algorithm, that is ; In the formula, is the learning rate; Step S446, repeating steps S442-S445 until the loss function converges to a preset standard smaller value or reaches a preset training round, completing the training of the nonlinear equation set containing unknown coordinates ​ Step S45, obtaining the labeled magnetic particle by solving the nonlinear equation from the magnetic field sensor between the labeled magnetic particle and the magnetic field sensor ; determining the three-dimensional coordinates of the labeled magnetic particle by triangulation on the distance of each labeled magnetic particle from the magnetic field sensor; The specific process of solving the nonlinear equation is: Step S451, determining the three-dimensional coordinates of the labeled magnetic particles by the nonlinear equation, wherein the nonlinear equation is: ； In the formula, to mark the magnetic particles with the magnetic field sensor the distance between them, which is obtained according to the constructed magnetic dipole model, that is ; Step S452, solving the nonlinear equation in step S451 by a nonlinear least squares method, inputting the data of each magnetic field sensor into the nonlinear equation, and obtaining the three-dimensional coordinates closest to each labeled magnetic particle; Step S5, tracking the specific position of the determined labeled magnetic particles in the time sequence in real time, recording the position change of the labeled magnetic particles, and generating a movement trajectory; Step S6, analyzing the movement of the sand in the monitoring area based on the movement trajectory of the labeled magnetic particles generated in step S5.

2. The magnetic field positioning based sand movement monitoring method of claim 1, wherein: The plurality of magnetic field sensors are located at different heights and horizontal positions to form a sensor array.

3. The magnetic field positioning based sand movement monitoring method of claim 1, wherein: Based on the measurement equation constructed in step S43, the magnetic field sensor measured magnetic field data of the marker magnetic particles is adjusted.

4. The magnetic field positioning based sand movement monitoring method of claim 1, wherein: In step S5, the specific position of each labeled magnetic particle in the monitoring area, i.e., the three-dimensional coordinates of each labeled magnetic particle, is determined according to step S4, the position change of each labeled magnetic particle is recorded, and a movement trajectory thereof is generated.

5. The magnetic field positioning based sand movement monitoring method of claim 1, wherein: In step S6, based on the movement trajectory of the labeled magnetic particles, the movement characteristics of the sand as a whole are analyzed, including the flow speed, the change of scouring depth, and the stress condition of the soil body.

6. A sand movement monitoring system characterized by: The sand movement monitoring method based on magnetic field positioning according to any one of claims 1-5 is adopted; the system comprises sand to be monitored, a plurality of labeled magnetic particles are implanted in the sand, and a sensor array is arranged around or above the monitoring area, wherein the sensor array comprises at least three magnetic field sensors, and the number of magnetic field sensors is the same as the number of labeled magnetic particles.

Images