Single-target permanent magnet positioning method and device based on magnetic dipole model

Abstract

The application provides a single-target permanent magnet positioning method and device based on a magnetic dipole model, and relates to the technical field of magnetic sensing. The single-target permanent magnet positioning method based on the magnetic dipole model comprises the following steps: generating a uniform magnetic field by using a Hall coil to measure magnetic moment data of a to-be-measured magnetic dipole; the to-be-measured magnetic dipole is a cylindrical permanent magnet; fusing an MSSA algorithm used for near-distance positioning and an ICNN-GRU-Attention neural network algorithm used for far-distance positioning to obtain a fused positioning algorithm; inputting the magnetic moment data and magnetic field intensity data received by a sensor array into the fused positioning algorithm to determine the target position of the to-be-measured magnetic dipole. The positioning region is divided into a near-distance region, a mixed region and a far-distance region, and positioning algorithms with different applicable ranges are fused to generate a suitable fused algorithm, so that the positioning accuracy of the single-target permanent magnet is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of magnetic sensing, in particular to a single-target permanent magnet positioning method and device based on a magnetic dipole model. BACKGROUND

[0002] The magnetic positioning technology has been widely applied in small-range high-precision real-time positioning and tracking systems due to the characteristic of not being limited by visual obstruction. In a complex surgical environment, a surgical medical robot needs to accurately position a target position, and the magnetic positioning technology can ensure accurate positioning even in a visual obstruction or insufficient light condition. Similarly, in tumor and drug tracking, the magnetic positioning technology can also achieve accurate positioning, which provides technical support for the accuracy of tumor treatment and the monitoring of drug efficacy. The wide application of the magnetic positioning technology not only improves the efficiency and accuracy of medical services, but also provides strong technical support for the development of the medical field.

[0003] However, due to the insufficient performance of the magnetic positioning algorithm, the positioning accuracy is easily disturbed by the limitations of sensor sensitivity and range, as well as other external changing magnetic fields such as the geomagnetic field, so that the high accuracy requirement cannot be met. How to adapt to different positioning ranges and improve the positioning accuracy has become a problem to be solved at present. SUMMARY

[0004] The purpose of the present application is to solve the problem of insufficient performance of the current magnetic positioning algorithm, and the limitations of sensor sensitivity and range, as well as the influence of other external changing magnetic fields such as the geomagnetic field, which leads to insufficient positioning accuracy. The application provides a single-target permanent magnet positioning method and device based on a magnetic dipole model.

[0005] The technical scheme of the embodiment of the present application is as follows:

[0006] The first aspect of the embodiment of the present application provides a single-target permanent magnet positioning method based on a magnetic dipole model, comprising:

[0007] A Helmholtz coil is used to generate a uniform magnetic field to measure the magnetic moment data of a to-be-measured magnetic dipole; the to-be-measured magnetic dipole is a cylindrical permanent magnet;

[0008] The MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning are fused to obtain a fusion positioning algorithm;

[0009] The magnetic moment data and the magnetic field intensity data received by the sensor array are input into the fusion positioning algorithm to determine the target position of the to-be-measured magnetic dipole.

[0010] Optionally, the measuring the magnetic moment data of the to-be-measured magnetic dipole by using the Helmholtz coil to generate a uniform magnetic field comprises:

[0011] Determining the magnetic flux parameter of the to-be-measured magnetic dipole by using the Helmholtz coil and the fluxmeter;

[0012] Establishing a mapping relationship between the magnetic flux parameter and the magnetic moment data by the Ampere loop theorem or the superposition principle of magnetic field to determine the magnetic moment data of the to-be-measured magnetic dipole.

[0013] Optionally, the fusion positioning algorithm of the MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning further comprises:

[0014] The SSA Sparrow algorithm is improved by using the mutation cat chaotic mapping, the improver and the joiner ratio coefficient, and the improver position update to obtain the MSSA algorithm for close-range positioning; and specifically comprising:

[0015] The population is initialized by using the mutation cat chaotic mapping, the improver and the joiner ratio coefficient r is updated once for each generation, and the update formula of r is as follows:

[0016] ;

[0017] Wherein, is the initial ratio coefficient set, is the current iteration number, is the maximum number of iterations set, is the set disturbance factor, is a random number in the interval [0, 1];

[0018] The improver position update formula is improved as follows:

[0019]

[0020] Wherein, represents the current iteration number, , represents the maximum iteration number, represents the position information of the th Sparrow in the th dimension, is a random number, and represent the warning value and the safety value respectively, , , is a random number subject to normal distribution, represents a a matrix, wherein all elements in the matrix are 1, when the finder can perform a larger range of search operations, if this indicates that the finder has found the predator, at which time all sparrows need to quickly fly to a safe place to forage.

[0021] Optionally, the MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning are fused to obtain a fusion positioning algorithm, and the fusion positioning algorithm further comprises:

[0022] a convolutional neural network, a gated recurrent unit and an attention mechanism are combined to obtain the ICNN-GRU-Attention neural network algorithm for long-range positioning; and a loss function of the ICNN-GRU-Attention neural network algorithm is a mean square error:

[0023] ;

[0024] wherein, is a matrix, representing the position and attitude information predicted by the network, representing the real position and attitude information .

[0025] Optionally, before inputting the magnetic moment data and the magnetic field strength data received by the sensor array into the fusion positioning algorithm to determine the target position of the magnetic dipole to be measured, the method further comprises:

[0026] fixing the magnetic dipole to be measured by using a positioning plate;

[0027] arranging a plurality of magnetic sensors in an array to obtain magnetic field strength data of the magnetic dipole to be measured at different positions.

[0028] Optionally, the coordinates of the i-th sensor are , , P is the distance from the center of the magnet to the i-th sensor, and the vector is represented as ; the magnetic field strength of the magnetic dipole to be measured at the i-th sensor position is: ;

[0029] ;

[0030] wherein, represents a unit vector in the direction of the z-axis, and the magnetic field strength of the magnet at the i-th sensor is ​​​​ The orthogonal components in the axial direction are respectively , and the expression is as follows:

[0031] ;

[0032] wherein, is the modulus of P, .

[0033] Optionally, the inputting the magnetic moment data and the magnetic field strength data received by the sensor array into the fusion positioning algorithm to determine the target position of the to-be-measured magnetic dipole includes:

[0034] determining the first target position of the to-be-measured magnetic dipole by using the MSSA algorithm;

[0035] determining the second target position of the to-be-measured magnetic dipole by using the ICNN-GRU-Attention neural network algorithm;

[0036] processing the first target position and the second target position by using a weighting method to determine the target position of the to-be-measured magnetic dipole.

[0037] The second aspect of the embodiment of the present application provides a single-target permanent magnet positioning device based on a magnetic dipole model, comprising a data measurement module, an algorithm fusion module and a position determination module, wherein,

[0038] The data measurement module is configured to measure the magnetic moment data of the to-be-measured magnetic dipole by using a Helmholtz coil to generate a uniform magnetic field; the to-be-measured magnetic dipole is a cylindrical permanent magnet;

[0039] The algorithm fusion module is configured to fuse the MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning to obtain a fusion positioning algorithm;

[0040] The position determination module is configured to input the magnetic moment data and the magnetic field strength data received by the sensor array into the fusion positioning algorithm to determine the target position of the to-be-measured magnetic dipole.

[0041] The third aspect of the embodiment of the present application provides an electronic device comprising a processor and a memory; the memory has a computer program stored therein, wherein the computer program, when executed by the processor, implements the single-target permanent magnet positioning method based on the magnetic dipole model of the first aspect.

[0042] The fourth aspect of the embodiment of the present application provides a computer readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps of the method of the first aspect.

[0043] Compared with the prior art, the technical scheme provided by the application has the beneficial effects that:

[0044] The application provides a single-target permanent magnet positioning method and device based on a magnetic dipole model, which measures magnetic moment data of a to-be-measured magnetic dipole by using a Helmholtz coil to generate a uniform magnetic field, and fuses an MSSA algorithm used for close-range positioning and an ICNN-GRU-Attention neural network algorithm used for long-range positioning to obtain a fusion positioning algorithm, so that the magnetic moment data and magnetic field intensity data received by a sensor array are input into the fusion positioning algorithm to determine the target position of the to-be-measured magnetic dipole. The positioning area is divided into a close-range area, a mixed area and a long-range area, and positioning algorithms with different applicable ranges are fused to generate a suitable fusion algorithm, thereby improving the positioning accuracy of the single-target permanent magnet. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 A flowchart of a single-target permanent magnet positioning method based on a magnetic dipole model provided by an embodiment of the application is shown in the figure.

[0046] Figure 2 A structural diagram of a single-target permanent magnet positioning device based on a magnetic dipole model provided by an embodiment of the application is shown in the figure.

[0047] Figure 3 A structural diagram of an electronic device provided by an embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0048] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. It should be understood, however, that the description is merely exemplary and is not intended to limit the scope of the present application. In the following detailed description of the embodiments of the present application, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it would be apparent to those skilled in the art that the embodiments of the present application can be practiced without these specific details. In other instances, well-known structures and methods have been omitted in order to avoid obscuring the concepts of the present application.

[0049] The terms used herein are merely used to describe specific embodiments and are not intended to limit the present application. The terms "include", "comprise" and the like used herein indicate the presence of the described features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

[0050] All terms used herein, including technical and scientific terms, have the meanings commonly understood by one of ordinary skill in the art unless otherwise defined. It should be further understood that the terms used herein should be interpreted as having a meaning that is consistent with the understanding of those terms by those skilled in the relevant art and that the terms should not be interpreted in an overly rigid or overly formal manner unless clearly defined.

[0051] Some of the diagrams illustrated in the drawings are block diagrams and / or flowcharts. It should be understood that some of the blocks in the block diagrams and / or flowcharts, or combinations thereof, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that the instructions executed by the processor can create a means for implementing the functions / operations specified in the block diagrams and / or flowcharts.

[0052] In some embodiments, referring to Figure 1 , Figure 1 A flowchart of a single-target permanent magnet positioning method based on a magnetic dipole model provided by an embodiment of the present application; the single-target permanent magnet positioning method based on a magnetic dipole model provided by an embodiment of the present application includes:

[0053] S110, generating a uniform magnetic field by using a Helmholtz coil to measure magnetic moment data of a to-be-measured magnetic dipole; the to-be-measured magnetic dipole is a cylindrical permanent magnet.

[0054] A Helmholtz coil is a device composed of two coaxial circular coils. When the currents in the two coils are equal in size and the same in direction, the magnetic fields generated by the two coils are uniform in the central region of the coils. The to-be-measured magnetic dipole is placed in the Helmholtz coil, the coil current is adjusted to generate magnetic fields of different intensities, and the force condition of the permanent magnet is recorded. According to the relationship between the force condition and the magnetic field intensity, and the physical parameters (such as mass, volume, etc.) of the to-be-measured magnetic dipole, the magnetic moment of the to-be-measured magnetic dipole can be calculated.

[0055] In some embodiments, S110, generating a uniform magnetic field by using a Helmholtz coil to measure magnetic moment data of a to-be-measured magnetic dipole, includes:

[0056] Determining the magnetic flux parameter of the to-be-measured magnetic dipole by using a Helmholtz coil and a fluxmeter;

[0057] Establishing a mapping relationship between the magnetic flux parameter and the magnetic moment data by the Ampere loop theorem or the superposition principle of magnetic fields to determine the magnetic moment data of the to-be-measured magnetic dipole.

[0058] In this embodiment, measuring the magnetic flux parameter and then obtaining the magnetic moment data can include the following steps: 1) Set up the Helmholtz coil: ensure that the two coils are coaxial and the current directions are the same, and adjust the current size to produce the required magnetic field strength. 2) Place the magnetic dipole to be measured: place the magnetic dipole to be measured in the center of the Helmholtz coil to ensure that it is in a uniform magnetic field. 3) Measure the magnetic flux: use a fluxmeter to measure the magnetic flux generated by the magnetic dipole to be measured in the Helmholtz coil. This magnetic flux will depend on the magnetic moment of the magnetic dipole and its position and direction relative to the coil. 4) Establish a mapping relationship to take the Ampere loop theorem as an example, the Ampere loop theorem shows that the line integral of the magnetic field strength along a closed loop is equal to the sum of the currents enclosed by the loop multiplied by the magnetic permeability. However, when directly applied to the magnetic dipole, this theorem requires some conversion and approximation. Generally, the mathematical relationship between the magnetic flux parameter and the magnetic moment is established by using the formula of the magnetic field distribution generated by the magnetic dipole in space combined with the idea of the Ampere loop theorem. Take the principle of superposition of magnetic fields as an example, which states that the total magnetic field in space is the vector sum of the magnetic fields generated by each magnetic source. For the case of the magnetic dipole to be measured in the Helmholtz coil, the magnetic dipole can be regarded as a small magnetic source, and its generated magnetic field is superimposed with the magnetic field generated by the Helmholtz coil. By measuring the superimposed magnetic field (i.e. magnetic flux), and using the principle of superposition of magnetic fields and the formula of the magnetic field distribution of the magnetic dipole, the magnetic moment of the magnetic dipole can be derived. 5) Calculate the magnetic moment data, after establishing the mapping relationship between the magnetic flux parameter and the magnetic moment, the magnetic moment data of the magnetic dipole can be calculated by substituting the measured magnetic flux.

[0059] S120, fuse the MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning to obtain a fused positioning algorithm.

[0060] Here, the MSSA algorithm is an improved version of the multi-objective sparrow search optimization algorithm. The ICNN-GRU-Attention neural network algorithm is an algorithm that combines convolutional neural networks (CNN), gated recurrent units (GRU), and attention mechanisms. Combining the close-range positioning algorithm MSSA algorithm with the long-range positioning algorithm ICNN-GRU-Attention neural network algorithm forms a full-area fusion positioning algorithm that can expand the positioning area and improve the positioning accuracy at the same time.

[0061] In some embodiments, S120, the MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning are fused to obtain a fused positioning algorithm, and the fused positioning algorithm further comprises:

[0062] The SSA Sparrow algorithm is improved by using the mutation cat chaotic mapping, the improver and the joiner ratio coefficient, and the improver position update to obtain the MSSA algorithm for close-range positioning, and the MSSA algorithm for close-range positioning specifically comprises:

[0063] The population is initialized by using the mutation cat chaotic mapping, the improver and the joiner ratio coefficient r is updated once for each generation, and the update formula of r is as follows:

[0064] ;

[0065] Wherein, is the initial ratio coefficient set, is the current iteration number, is the maximum number of iterations set, is the disturbance factor set, is a random number in the interval [0, 1];

[0066] The improver position update formula is improved as follows:

[0067]

[0068] Wherein, represents the current iteration number, , represents the maximum iteration number, represents the position information of the th Sparrow in the th dimension, is a random number, and represent the warning value and the safety value respectively, , , is a random number subject to normal distribution, represents a matrix, wherein all elements in the matrix are 1, when , the improver can perform a larger range of search operations, if , it means that the improver has found the predator, at this time all the sparrows need to fly to a safe place for foraging.

[0069] In the embodiment, the variant cat mapping is a two-dimensional reversible chaotic mapping, the longitudinal and transverse chaotic sequences generated in [0, 1] are uniformly distributed, the initial population adopts the mode of the variant cat chaotic mapping, and the population uniformly distributed in the set range can be generated, and the more the population quantity is set, the more uniformly the total population is generated. The improved sparrow algorithm has faster convergence speed while keeping the original advantages, and the same target value is reached, the number of generations required for convergence can be reduced by about half, the algorithm running speed is improved, the positioning time is shortened from 0.068s to 0.034s, and the stability is higher, the average convergence is completed for 70 times, and the convergence result error is less than one thousandth.

[0070] In some embodiments, S120, the MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning are fused to obtain a fusion positioning algorithm, and the method further comprises:

[0071] The convolutional neural network, the gated recurrent unit and the attention mechanism are combined to obtain the ICNN-GRU-Attention neural network algorithm for long-range positioning; the loss function of the ICNN-GRU-Attention neural network algorithm is mean square error:

[0072] ;

[0073] Wherein, is a matrix of , represents the position and attitude information predicted by the network, represents the real position and attitude information .

[0074] S130, the magnetic moment data and the magnetic field strength data received by the sensor array are input into the fusion positioning algorithm to determine the target position of the magnetic dipole to be measured.

[0075] Here, the measured magnetic moment data and the magnetic field strength data received by the sensor array are input into the fusion positioning algorithm, and the algorithm outputs the position information of the permanent magnet including the coordinates and the possible error range according to the input magnetic moment and magnetic field strength data.

[0076] In some embodiments, before S130, the magnetic moment data and the magnetic field strength data received by the sensor array are input into the fusion positioning algorithm to determine the target position of the magnetic dipole to be measured, the method further comprises:

[0077] The magnetic dipole to be measured is fixed by using the positioning plate;

[0078] The plurality of magnetic sensors are arranged in an array to obtain magnetic field strength data of the magnetic dipole to be measured at different positions.

[0079] In the embodiment, a mathematical model of magnetic field strength of a single cylindrical permanent magnet is constructed according to a magnetic dipole, a permanent magnet positioning plate, a magnetic sensor array and a MATLAB-based host computer software are designed. A flat plate capable of stably fixing the permanent magnet is designed in advance to ensure that the position of the permanent magnet does not change during the experiment. The material of the positioning plate is non-magnetic material-acrylic material. A MATLAB-based graphical user interface (GUI) is developed for receiving sensor data, processing data, displaying magnetic field distribution map and calculating the position of the permanent magnet.

[0080] In some embodiments, the coordinates of the i th sensor are , , , P is the distance from the center of the magnet to the i th sensor, and the vector is represented as ; the magnetic field strength of the magnetic dipole to be measured at the i th sensor position is:

[0081] ;

[0082] wherein is the unit vector in the direction of the z-axis, and the magnetic field strength of the magnet at the i th sensor is The orthogonal components of the magnetic field strength of the magnet at the i th sensor in the x-axis and y-axis directions are respectively, and the expressions are as follows:

[0083] ;

[0084] wherein is the modulus of P, .

[0085] In the embodiment, a global Cartesian coordinate system is set with the upper left corner of the sensor array of the positioning system as the origin. In the global coordinate system, there is a sensor array composed of N sensors, and these sensors are in the same horizontal plane. The sensor array is used to measure the magnetic field strength in space. Considering electromagnetic compatibility, signal integrity and layout rationality to ensure that the sensor array can accurately and efficiently measure the magnetic field data, the magnetic sensor array is designed as a 3x3 nine-square structure.

[0086] In some embodiments, S130, the magnetic moment data and the magnetic field strength data received by the sensor array are input into the fusion positioning algorithm to determine the target position of the magnetic dipole to be measured, including:

[0087] ​​​​​Determine the first target position of the to-be-tested magnetic dipole by using the MSSA algorithm;

[0088] Determine the second target position of the to-be-tested magnetic dipole by using the ICNN-GRU-Attention neural network algorithm;

[0089] Determine the target position of the to-be-tested magnetic dipole by processing the first target position and the second target position in a weighted manner.

[0090] In an optional embodiment, it is assumed that is the positioning result of the MSSA algorithm, is the positioning result of the ICNN-GRU-Attention algorithm, and the final target position Y can be calculated according to the following formula.

[0091] ;

[0092] wherein, is the weight value, which is measured according to experiments.

[0093] In an example, the situations of different range areas are measured and calculated respectively. In the near distance area, the sensor array is used for experiment, the near distance area is the area 5cm-10cm above the array, 96 experimental points are collected with an interval of 1cm, a total of 576 experimental points, and the MSSA-ICNN-GRU-Attention fusion positioning algorithm is used for positioning experiment.

[0094] In the mixed area, the sensor array is used for experiment, the mixed area is the area 10cm-15cm above the array, 96 experimental points of magnetic field data are collected with an interval of 1cm, a total of 576 experimental points, and the MSSA-ICNN-GRU-Attention fusion positioning algorithm is used for positioning experiment.

[0095] In the far distance area, the sensor array is used for experiment, the far distance area is the area 15cm-20cm above the array, 96 experimental points of magnetic field data are collected with an interval of 2cm, a total of 385 experimental points, and the MSSA-ICNN-GRU-Attention fusion positioning algorithm is used for positioning experiment.

[0096] The embodiment of the application measures the magnetic moment data of the to-be-measured magnetic dipole by using the Helmholtz coil to generate a uniform magnetic field, fuses the MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning, obtains a fusion positioning algorithm, and inputs the magnetic moment data and the magnetic field intensity data received by the sensor array into the fusion positioning algorithm to determine the target position of the to-be-measured magnetic dipole. The positioning area is divided into a close-range area, a mixed area and a long-range area, and the positioning algorithms with different applicable ranges are fused to generate a suitable fusion algorithm, thereby improving the positioning accuracy of a single target permanent magnet.

[0097] In some embodiments, referring to Figure 2 , Figure 2 A structural schematic diagram of a single target permanent magnet positioning device based on a magnetic dipole model is provided for the embodiment of the application. The single target permanent magnet positioning device based on a magnetic dipole model 200 provided by the embodiment of the application comprises a data measurement module 210, an algorithm fusion module 220 and a position determination module 230, wherein

[0098] The data measurement module 210 is configured to measure the magnetic moment data of the to-be-measured magnetic dipole by using the Helmholtz coil to generate a uniform magnetic field. The to-be-measured magnetic dipole is a cylindrical permanent magnet.

[0099] The algorithm fusion module 220 is configured to fuse the MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning to obtain a fusion positioning algorithm.

[0100] The position determination module 230 is configured to input the magnetic moment data and the magnetic field intensity data received by the sensor array into the fusion positioning algorithm to determine the target position of the to-be-measured magnetic dipole.

[0101] In some embodiments, the data measurement module 210 is specifically configured to:

[0102] Determine the magnetic flux parameter of the to-be-measured magnetic dipole by using the Helmholtz coil and the fluxmeter.

[0103] Establish a mapping relationship between the magnetic flux parameter and the magnetic moment data by the Ampere loop theorem or the superposition principle of the magnetic field to determine the magnetic moment data of the to-be-measured magnetic dipole.

[0104] In some embodiments, the algorithm fusion module 220 is specifically configured to:

[0105] Improve the SSA sparrow algorithm by using the variant cat chaotic mapping, the improver and joiner ratio coefficient and the improver position update to obtain the MSSA algorithm for close-range positioning. Specifically, the MSSA algorithm for close-range positioning comprises:

[0106] The population is initialized by using the chaotic mapping of the variation cat, and the ratio coefficient r of the discoverer and the joiner is updated once per generation. The update formula of r is as follows:

[0107] ;

[0108] wherein, is the initial ratio coefficient set, is the current iteration number, is the maximum iteration number set, is the disturbance factor set, is a random number in the interval [0, 1];

[0109] The discoverer position update formula is improved as follows:

[0110]

[0111] wherein, represents the current iteration number, , represents the maximum iteration number, represents the position information of the th sparrow in the th dimension, is a random number, and respectively represent the warning value and the safety value, , , is a random number subject to normal distribution, represents a matrix, wherein each element in the matrix is 1. When , the discoverer can perform a larger range of search operations. If , it indicates that the discoverer has found the predator, and at this time all sparrows need to quickly fly to a safe place to forage.

[0112] In some embodiments, the algorithm fusion module 220 is specifically configured as:

[0113] The convolutional neural network, the gated recurrent unit and the attention mechanism are combined to obtain an ICNN-GRU-Attention neural network algorithm for long-distance positioning. The loss function of the ICNN-GRU-Attention neural network algorithm is mean square error:

[0114] ;

[0115] wherein, is the initial ratio coefficient set, a matrix representing the network predicted position and pose information, representing the real position and pose information .

[0116] In some embodiments, the single-target permanent magnet positioning device 200 based on the magnetic dipole model further comprises a data acquisition module; the data acquisition module is specifically configured to:

[0117] using the positioning plate to fix the to-be-measured magnetic dipole;

[0118] arranging a plurality of magnetic sensors in an array to obtain magnetic field strength data of the to-be-measured magnetic dipole at different positions.

[0119] In some embodiments, the data acquisition module is specifically configured to: set the coordinates of the i-th sensor as , , , P is the distance from the center of the magnet to the i-th sensor, and the vector is represented as ; the magnetic field strength of the to-be-measured magnetic dipole at the i-th sensor position is:

[0120] ;

[0121] wherein, represents a unit vector in the direction of the z-axis, and the magnetic field strength of the magnet at the i-th sensor is the orthogonal components of the magnetic field strength of the magnet at the i-th sensor in the x-axis and y-axis directions are and respectively, and the expression is as follows:

[0122] ;

[0123] wherein, is the modulus of P, .

[0124] In some embodiments, the position determination module 230 is specifically configured to:

[0125] determining the first target position of the to-be-measured magnetic dipole by using the MSSA algorithm;

[0126] determining the second target position of the to-be-measured magnetic dipole by using the ICNN-GRU-Attention neural network algorithm;

[0127] processing the first target position and the second target position by using a weighting method to determine the target position of the to-be-measured magnetic dipole.

[0128] ​​​​The single-target permanent magnet positioning device based on the magnetic dipole model provided in the embodiments of the present application can implement each process in the embodiments corresponding to the single-target permanent magnet positioning method based on the magnetic dipole model, and thus details are not repeated here.

[0129] It should be noted that the single-target permanent magnet positioning device based on the magnetic dipole model provided in the embodiments of the present application is based on the same application concept as the single-target permanent magnet positioning method based on the magnetic dipole model provided in the embodiments of the present application, and thus the specific implementation of this embodiment can be referred to the implementation of the single-target permanent magnet positioning method based on the magnetic dipole model, and details are not repeated here.

[0130] In some embodiments, please refer to Figure 3 , Figure 3 A structural schematic diagram of an electronic device is provided in the embodiments of the present application. The electronic device 300 provided in the embodiments of the present application includes a processor 310 and a memory 320; the memory 320 stores a computer program, wherein the computer program implements the single-target permanent magnet positioning method based on the magnetic dipole model when executed by the processor.

[0131] Specifically, the processor 310 may, for example, include a general-purpose microprocessor, an instruction set processor, and / or a related chipset, and / or a special-purpose microprocessor (such as an application-specific integrated circuit (ASIC)), and the like. The processor 310 can also include an on-board memory for cache use. The processor 310 can be a single processing unit or a plurality of processing units for performing different actions of the method process according to the embodiments of the present application.

[0132] The memory 320 may, for example, be any medium capable of containing, storing, communicating, propagating or transmitting instructions. For example, the memory 320 may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device, apparatus or propagation medium. Specific examples of the memory 320 include a magnetic storage device such as a magnetic tape or a hard disk drive (HDD); an optical storage device such as a compact disc (CD-ROM); and / or a wired / wireless communication link.

[0133] The present application also provides a computer readable medium having a computer program stored thereon, which, when executed by a processor, implements the single-target permanent magnet positioning method based on the magnetic dipole model. The computer readable medium can be included in the device / apparatus / system described in the above embodiments; or can exist separately and not be assembled into the device / apparatus / system. The computer readable medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present application.

[0134] According to the embodiments of the present application, the computer readable medium can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, the computer readable storage medium can be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus or device. In this application, the computer readable signal medium can include a computer readable program code transmitted in baseband or as part of a carrier wave in a propagated signal, in which the computer readable program code contains a program for use by or in connection with an instruction execution system, apparatus or device. The propagated signal can take any suitable form, including but not limited to an electromagnetic signal, an optical signal or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that can be used to carry or store a program for use by or in connection with an instruction execution system, apparatus or device, except for the computer readable storage media described above. The program code contained in the computer readable media can be transmitted in any suitable form, including but not limited to, radio frequency, electrical, optical, acoustic or any suitable combination thereof.

[0135] Those skilled in the art will appreciate that features recited in the various embodiments and / or claims of this application can be combined and / or interchanged, even if this is not explicitly stated in the application. In particular, the features of the various embodiments and / or claims of this application can be combined and / or interchanged, without departing from the spirit and teachings of this application. All combinations and / or interchanges of the features of the various embodiments and / or claims of this application are expressly envisioned and are within the scope of this application. Accordingly, the scope of the application should not be limited to the above-described embodiments, but should be determined by the appended claims and their equivalents.

Claims

1. A single-target permanent magnet positioning method based on a magnetic dipole model, characterized in that, The method comprises the following steps: Measuring the magnetic moment data of a to-be-measured magnetic dipole by using a Helmholtz coil to generate a uniform magnetic field; the to-be-measured magnetic dipole is a cylindrical permanent magnet; Fusing an MSSA algorithm for close-range positioning and an ICNN-GRU-Attention neural network algorithm for long-range positioning to obtain a fusion positioning algorithm; Inputting the magnetic moment data and magnetic field intensity data received by a sensor array into the fusion positioning algorithm to determine a target position of the to-be-measured magnetic dipole, comprising: Determining a first target position of the to-be-measured magnetic dipole by using the MSSA algorithm; Determining a second target position of the to-be-measured magnetic dipole by using the ICNN-GRU-Attention neural network algorithm; Processing the first target position and the second target position by using a weighting method to determine the target position of the to-be-measured magnetic dipole; The final target position Y is calculated according to the following formula: ； wherein, is the positioning result of the MSSA algorithm, is the positioning result of the ICNN-GRU-Attention algorithm, is the weight.

2. The single-target permanent magnet positioning method based on the magnetic dipole model according to claim 1, characterized in that, The step of measuring the magnetic moment data of the to-be-measured magnetic dipole by using the Helmholtz coil to generate the uniform magnetic field comprises the following steps: Determining the magnetic flux parameter of the to-be-measured magnetic dipole by using the Helmholtz coil and a fluxmeter; Establishing a mapping relationship between the magnetic flux parameter and the magnetic moment data by using the Ampere loop theorem or the superposition principle of the magnetic field to determine the magnetic moment data of the to-be-measured magnetic dipole.

3. The single-object permanent magnet positioning method based on the magnetic dipole model according to claim 1, characterized in that, The step of fusing the MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning to obtain the fusion positioning algorithm further comprises the following steps: Improving the SSA sparrow algorithm by using a mutation cat chaotic mapping, a ratio coefficient of discoverers and joiners and discoverer position updating to obtain the MSSA algorithm for close-range positioning; specifically comprising the following steps: Initializing a population by using the mutation cat chaotic mapping, updating the ratio coefficient of discoverers and joiners r once for each generation, and the updating formula of r is as follows: ； wherein, is an initial scaling factor set, is the current iteration number, is the maximum number of iterations set, is a perturbation factor set, is a random number in the interval [0, 1]; Improving the discoverer position updating formula as follows: ； wherein, represents the current iteration number, , represents the maximum iteration number, represents the position information of the th sparrow in the th dimension, is a random number, and respectively represent the warning value and the safety value, , , is a random number subject to normal distribution, represents a matrix, wherein all elements in the matrix are 1, when , the discoverer performs a larger range of search operations, if , it indicates that the discoverer has found the predator, at this time all sparrows need to quickly fly to a safe place to forage.

4. The method of claim 1, wherein, The step of fusing the MSSA algorithm for close-range positioning and the ICNN-GRU-Attention neural network algorithm for long-range positioning to obtain the fusion positioning algorithm further comprises the following steps: Combining a convolutional neural network, a gated recurrent unit and an attention mechanism to obtain the ICNN-GRU-Attention neural network algorithm for long-range positioning; the loss function of the ICNN-GRU-Attention neural network algorithm is a mean square error: ； wherein, is a matrix representing the predicted position and pose information of the network, represents the real position and pose information .

5. The single-object permanent magnet positioning method based on the magnetic dipole model according to claim 1, characterized in that, Before the step of inputting the magnetic moment data and the magnetic field intensity data received by the sensor array into the fusion positioning algorithm to determine the target position of the to-be-measured magnetic dipole, the method further comprises the following steps: Fixing the to-be-measured magnetic dipole by using a positioning plate; Arranging a plurality of magnetic sensors into an array to obtain the magnetic field intensity data of the to-be-measured magnetic dipole at different positions.

6. The single-object permanent magnet positioning method based on the magnetic dipole model according to claim 5, characterized in that, Let the first The coordinates of each sensor are , P is the distance from the center of the magnet to the first... The distance between the sensors is represented as a vector. The magnetic dipole to be tested is in the first... The magnetic field strength at each sensor location is: ； wherein denotes a unit vector in the axial direction, the magnetic field strength of the magnet at the i-th sensor the orthogonal components in the axial direction are respectively , the expressions are as follows:​​ ； wherein the modulus of P, .

7. A single-target permanent magnet positioning device based on a magnetic dipole model, characterized in that, The device comprises a data measurement module, an algorithm fusion module and a position determination module, wherein: The data measurement module is configured to measure the magnetic moment data of a to-be-measured magnetic dipole by using a Helmholtz coil to generate a uniform magnetic field; the to-be-measured magnetic dipole is a cylindrical permanent magnet; ​ The algorithm fusion module is configured to fuse an MSSA algorithm for close-range positioning and an ICNN-GRU-Attention neural network algorithm for long-range positioning to obtain a fusion positioning algorithm. The position determination module is configured to input the magnetic moment data and magnetic field strength data received by the sensor array into the fusion positioning algorithm to determine a target position of the magnetic dipole to be measured, including: determining a first target position of the magnetic dipole to be measured by using the MSSA algorithm; determining a second target position of the magnetic dipole to be measured by using the ICNN-GRU-Attention neural network algorithm; processing the first target position and the second target position by a weighting method to determine the target position of the magnetic dipole to be measured; The final target position Y is calculated according to the following formula: ； wherein, is the positioning result of the MSSA algorithm, is the positioning result of the ICNN-GRU-Attention algorithm, is the weight.

8. An electronic device comprising a processor and a memory; said memory having stored a computer program, wherein, The computer program, when executed by the processor, implements the single-target permanent magnet positioning method based on the magnetic dipole model in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, the program, when executed by a processor, implementing the steps of the method of any one of claims 1 to 6.

Images