CN115130379B - Magnet modeling and magnetic field estimation method and device - Google Patents
Magnet modeling and magnetic field estimation method and device Download PDFInfo
- Publication number
- CN115130379B CN115130379B CN202210738001.0A CN202210738001A CN115130379B CN 115130379 B CN115130379 B CN 115130379B CN 202210738001 A CN202210738001 A CN 202210738001A CN 115130379 B CN115130379 B CN 115130379B
- Authority
- CN
- China
- Prior art keywords
- magnetic
- magnetic field
- virtual point
- training
- virtual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000013528 artificial neural network Methods 0.000 claims abstract description 141
- 238000012549 training Methods 0.000 claims abstract description 122
- 238000009826 distribution Methods 0.000 claims description 16
- 230000010365 information processing Effects 0.000 claims description 2
- 238000005259 measurement Methods 0.000 description 63
- 238000010586 diagram Methods 0.000 description 18
- 238000004364 calculation method Methods 0.000 description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000000691 measurement method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005358 geomagnetic field Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
Magnet modeling and magnetic field estimation methods and apparatus are provided. The provided target magnet modeling method comprises the following steps: establishing one or more virtual point sources representing the target magnet; setting a plurality of training measuring points in the space around the target magnet; measuring the magnetic field intensity of each training measuring point under the influence of a target magnet; generating training samples according to the magnetic field intensity of each training measuring point and the positions of the training measuring points to train one or more neural networks; the virtual point magnetic sources are respectively provided with one or more corresponding neural networks, and the neural networks corresponding to the virtual point magnetic sources are trained so that the output of the neural networks represents the magnetic source parameters of the virtual point magnetic sources corresponding to the neural networks; and using the respective positions and magnetic source parameters of the one or more virtual point magnetic sources as a magnetic model of the target magnet.
Description
Technical Field
The application relates to the technology of magnetism and neural networks, in particular to a method and a device for modeling a magnet by using a neural network and estimating the magnetic field intensity of any point by using a constructed magnet model.
Background
There is a need to measure and predict the magnetic field strength. When the magnet model of the target magnet cannot be known, the magnetic field strength of a specified position around the target magnet can be obtained through measurement. The magnetic field strength of the location can be obtained by means of, for example, a triaxial magnetometer. However, for locations in space that are difficult to access or reach, it is not possible to measure with a magnetometer. For example, in sailing, the ship's hull is magnetized by the earth's magnetic field and forms a magnetic field in space. The intensity of the magnetic field formed by the relative position of the ship in the water is difficult to measure by using a magnetometer.
The traditional ship magnetic field measurement method mainly comprises a submarine large-area array method, a submarine driving measurement method and a manual measurement method. The former two measurement accuracy is high, but the construction cost and the maintenance cost are extremely high, and only the field intensity on a fixed plane can be measured, so that the magnetic field distribution condition in the whole space can not be measured. The manual measurement method has low efficiency, and the position and the gesture of a measurement point are difficult to accurately control, so that the measured magnetic field has high accuracy of only vertical components, and the overall distribution condition of the magnetic field is also difficult to obtain.
There are methods of calculating (or estimating) the magnetic field strength at a specified location in space from a magnet model. For example, a formula (an inverse cube formula, a dipole formula, etc.) for calculating magnetic field strength from magnetic moment is proposed in "calculating magnetic field strength from magnetic moment" (Zhang Xinbang et al, "digital ocean and underwater attack and defense", month 6 of 2019, volume 2, phase 2).
Fig. 1A shows a schematic diagram of measuring the strength of an underwater magnetic field around a ship body in the prior art.
The magnetic field intensity measuring equipment is arranged under the water of the ship body berthing position through facilities such as wharfs and dock, and the magnetic field intensity is measured through the measuring equipment when the ship berthes. The drawbacks of this approach are evident, on the one hand, in dependence on large, vessel-accommodated berthing arrangements, and in the need to arrange measurement equipment underwater, which require a significant cost; on the other hand, the ships are required to enter the facilities and berth for measurement completion, and a great deal of time overhead is also brought and other tasks of the ships are affected. And the magnetic field intensity measured is only the magnetic field intensity of the position where the measuring equipment is positioned, and the magnetic field intensity of other positions of the water area nearby the ship body still cannot be obtained.
Fig. 1B shows a schematic diagram of estimating magnetic field strength using a neural network.
The neural network is used to predict the magnetic field strength at a given location. In training of the neural network, the position P of the measuring device, such as a magnetometer, is provided as input to the neural network, which outputs the estimated magnetic field strength of the position P. And obtaining errors of the actual magnetic field intensity obtained by measuring the position P of the magnetometer according to the magnetic field intensity of the position P estimated by the neural network and the actual magnetic field intensity of the position P, and feeding the errors back to the neural network. The neural network is trained by the position data of the plurality of positions P and the plurality of measured real magnetic field intensity data, and the neural network for estimating the magnetic field intensity of any position is obtained.
For a trained neural network, it is suitable for estimating the magnetic field strength of any location of a specified target magnet. By inputting the position information thereto, the neural network outputs a predicted value of the magnetic field strength for the position.
However, this network structure is extremely prone to overfitting. In the estimation of the magnetic field intensity, when the distribution of the positions to be estimated (also referred to as measuring points) coincides with the distribution of the positions where the magnetic field intensity data is collected during training, the prediction result of the neural network is accurate. However, if the measurement point to be estimated is inconsistent with the measurement point distribution of the magnetic field intensity data acquired during training, for example, when the measurement points are on different sides of the target magnet, the result predicted by the neural network has a high probability of generating a great error, and even generating a situation opposite to the direction of the actual value.
Disclosure of Invention
It is hoped to obtain the magnet model of the target magnet with any shape to be measured, and the magnetic field distribution of the space around the magnet formed by the target magnet can be obtained according to the magnet model, so that the magnetic field intensity of any position of the space around the magnet can be obtained, and the burden of measuring the magnetic field on site is eliminated. For this purpose, there is also a need for a method of modeling a magnet model of an arbitrarily shaped target magnet, which can accurately obtain the magnet model of the target magnet.
According to an embodiment of the present application, an arbitrary (complex shape) target magnet is modeled by magnetic field intensity data acquired at a part of observation points, and the magnetic field intensity at an arbitrary point is calculated from this model. Further, the method realizes modeling of the magnet model of the ship by using field intensity data obtained from onshore measurement, further estimates field intensity distribution of a water area around the ship, and realizes indirect measurement of magnetic field intensity.
According to a first aspect of the present application, there is provided a first target magnet modeling method according to the first aspect of the present application, comprising: establishing one or more virtual point magnetic sources representing the target magnet, the point virtual point magnetic sources having specified locations within the space occupied by the target magnet; setting a plurality of training measuring points in the space around the target magnet, wherein the training measuring points have specified positions; measuring the magnetic field intensity of each training measuring point under the influence of a target magnet; generating training samples according to the magnetic field intensity of each training measuring point and the positions of the training measuring points to train one or more neural networks; the virtual point magnetic sources are respectively provided with one or more corresponding neural networks, and the neural networks corresponding to the virtual point magnetic sources are trained so that the output of the neural networks represents the magnetic source parameters of the virtual point magnetic sources corresponding to the neural networks; calculating the magnetic field intensity generated by the one or more virtual point magnetic sources at the positions of the training measuring points of the training sample according to the magnetic source parameters and the positions of the one or more virtual point magnetic sources output by the neural network and the positions of the training measuring points in the training sample, and taking the magnetic field intensity as an estimated magnetic field intensity; training errors of the neural network corresponding to each of the one or more virtual point magnetic sources according to the difference between the estimated magnetic field intensity and the magnetic field intensity of the training sample; using the output of the trained neural network as the magnetic source parameter of the virtual point magnetic source corresponding to the output; and using the respective positions and magnetic source parameters of the one or more virtual point magnetic sources as a magnetic model of the target magnet.
According to a first target magnet modeling method of a first aspect of the present application, there is provided a second target magnet modeling method according to the first aspect of the present application, wherein the one or more virtual point magnetic sources are arranged at equal intervals within a space occupied by the target magnet.
According to a first or second target magnet modeling method of the first aspect of the present application, there is provided a third target magnet modeling method according to the first aspect of the present application, wherein the target magnet is represented by a single virtual point magnetic source; or setting the one or more virtual point magnetic sources so that 6 times of the distance between any virtual point magnetic sources is smaller than the distance between any training measuring point and any virtual point magnetic source.
According to one of the first to third target magnet modeling methods of the first aspect of the present application, there is provided a fourth target magnet modeling method according to the first aspect of the present application, further comprising: to train the one or more neural networks, virtual inputs are provided to each of the one or more neural networks, the virtual inputs provided to the one or more neural networks obeying a specified distribution.
According to a fourth object magnet modeling method of the first aspect of the present application, there is provided a fifth object magnet modeling method of the first aspect of the present application, wherein the one or more neural networks are trained such that the estimated magnetic field strength at each training measurement point calculated from the magnetic source parameters of each virtual point magnetic source obtained from the output of the one or more neural networks is as consistent as possible with the magnetic field strength of the corresponding training sample.
According to a fifth object magnet modeling method of the first aspect of the present application, there is provided the sixth object magnet modeling method of the first aspect of the present application, wherein the one or more neural networks are trained such that the magnetic source parameters of the respective virtual point magnetic sources obtained from the outputs of the one or more neural networks are as uniform as possible in the case of different virtual inputs.
According to a sixth target magnet modeling method of the first aspect of the present application, there is provided a seventh target magnet modeling method according to the first aspect of the present application, wherein the one or more virtual point magnetic sources each have a corresponding plurality of neural networks; using the statistics of the outputs of the plurality of neural networks corresponding to the one or more virtual point magnetic sources as the magnetic source parameters of the virtual point magnetic source represented by the statistics; the difference between the outputs of the plurality of neural networks corresponding to each of the one or more virtual point sources is taken as a further error in training the neural networks.
According to a seventh object magnet modeling method of the first aspect of the present application, there is provided the eighth object magnet modeling method of the first aspect of the present application, wherein in training of the neural network, a superposition of magnetic field strengths generated by each of all virtual point magnetic sources at positions of training points of the training sample is calculated as an estimated magnetic field strength according to a magnetic field strength formula from magnetic source parameters and positions of all virtual point magnetic sources obtained from the neural network and positions of training points in the training sample.
According to an eighth object magnet modeling method of the first aspect of the present application, there is provided the ninth object magnet modeling method of the first aspect of the present application, wherein a plurality of virtual inputs are provided, each obeying a distribution identical to each other, the number of the plurality of virtual inputs being identical to the number of the plurality of neural networks to which the one or more virtual point magnetic sources each correspond; providing one of the plurality of virtual inputs for each of a plurality of neural networks to which the one or more virtual point magnetic sources correspond respectively; each of the plurality of virtual inputs is simultaneously provided to a respective one of a plurality of neural networks for each virtual point magnetic source.
According to a ninth object magnet modeling method of the first aspect of the present application, there is provided a tenth object magnet modeling method according to the first aspect of the present application, wherein a background magnetic field strength of each training measurement point is measured in the absence of the object magnet; measuring the real magnetic field intensity of each training measuring point under the condition that the target magnet exists; and obtaining the magnetic field intensity of each training measuring point under the influence of the target magnet according to the difference between the real magnetic field intensity and the background magnetic field intensity.
According to a second aspect of the present application, there is provided a method of estimating the magnetic field strength of a target site under the influence of a target magnet according to the second aspect of the present application, comprising: one of the target magnet modeling methods according to the first aspect of the present application builds a magnetic model of a target magnet represented by one or more virtual point magnetic sources; and calculating the superposition of the magnetic field intensities generated by all the virtual point magnetic sources of the one or more virtual point magnetic sources at the positions of the target measuring points according to the magnetic source parameters and the positions of the one or more virtual point magnetic sources and a magnetic field intensity formula to obtain the magnetic field intensity estimation of the target measuring points under the influence of the target magnet.
According to a third aspect of the present application, there is provided an information processing apparatus comprising a memory, a processor and a program stored on the memory and executable on the processor, characterized in that the processor implements one of the methods according to the first and second aspects of the present application when executing the program.
Drawings
The application, as well as a preferred mode of use and further objectives and advantages thereof, will best be understood by reference to the following detailed description of illustrative embodiments when read in conjunction with the accompanying drawings, wherein:
fig. 1A shows a schematic diagram of measuring the strength of an underwater magnetic field around a ship body in the prior art.
Fig. 1B shows a schematic diagram of estimating magnetic field strength using a neural network.
Fig. 2 shows a schematic diagram of an array of set point magnetic sources for a target magnet (magnetic bar).
FIG. 3 illustrates a schematic diagram of magnet modeling and magnetic field strength prediction using a neural network, according to an embodiment of the application.
Fig. 4 shows a flow chart for modeling a target magnet and estimating magnetic field strength according to the present application.
FIG. 5 illustrates a schematic diagram of modeling a target magnet and estimating magnetic field strength according to an embodiment of the application.
FIG. 6 shows a schematic diagram of modeling a target magnet and estimating magnetic field strength according to yet another embodiment of the application.
FIG. 7 shows a schematic diagram of modeling a target magnet and estimating magnetic field strength according to yet another embodiment of the application.
Fig. 8 shows a schematic diagram of magnet modeling and magnetic field strength prediction using a neural network according to yet another embodiment of the present application.
Fig. 9 shows a schematic diagram of modeling a target magnet and estimating magnetic field strength according to yet another embodiment of the application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.
According to an embodiment of the present application, a target magnet is fitted using an array of point magnetic sources formed of a plurality of point magnetic sources (referred to as virtual point magnetic sources). The magnetic source parameters of the magnetic sources of the virtual points are predicted through machine learning by utilizing a neural network (instead of predicting the magnetic field intensity of the specified positions), and the magnetic field intensity of the specified positions under the influence of the magnetic sources of the virtual points is calculated according to the magnetic source parameters of the magnetic sources of the virtual points, so that the magnetic field intensity (calculated) generated by superposition of the magnetic sources of the virtual points at any positions is as close as possible to the measured value of the corresponding positions.
The target magnet has a prescribed shape, for example, a ship is generally in a shuttle shape. The plurality of virtual point magnetic sources are arranged at specified positions so that the point magnetic source array formed by the plurality of virtual point magnetic sources presents a shape similar to the target magnet. It can be appreciated that by setting more virtual point magnetic sources, the shape of the point magnetic source array is more similar to the shape of the target magnet, which is beneficial to improving the accuracy of magnet modeling and magnetic field strength prediction, but correspondingly increases the complexity and calculation amount. According to embodiments of the present application, accurate geomagnetic field strength predictions can already be achieved with a small number of virtual point magnetic sources arranged in a shape substantially similar to that of the target magnet, for example, modeling of a ship magnet can be achieved with a magnetic source array formed of 3 virtual point magnetic sources arranged in a straight line. For another example, for a vehicle target magnet having a substantially rectangular shape, a virtual point magnetic source is set in the vehicle interior space by selecting, for example, 8 points, the rectangular hexahedron of which 8 points enclose a city having a shape similar to that of a vehicle, and the vehicle target magnet is fitted with an array of point magnetic sources formed by the 8 virtual point magnetic sources. For another example, when the target magnet is farther from the survey point (e.g., the position of the survey point relative to the target magnet exceeds 6 times the size of the target magnet), the target magnet can be better fitted by a single virtual point magnetic source.
In some embodiments of the application, a virtual point magnetic source is modeled as a point with a spatial location and magnetic source parameters. In yet other examples, the virtual point source may also have a volume or shape. The magnetic field intensity formed by the magnetic source at the space designated position can be calculated according to the magnetic source parameters of the virtual point magnetic source whether the virtual point magnetic source represents a point or has designated volume or shape.
As an example, to create an array of point sources for fitting to a target magnet, the spatial positions of the virtual point sources are set within the outline of the target magnet and distributed as uniformly (equally spaced) as possible. Generally, the more complex the shape of the target magnet, the closer the region of magnetic field strength to be estimated is to the target magnet, the more virtual point sources are needed to achieve the same accuracy. The number and spacing of the spot sources is related to the size of the target magnet to be modeled and the distance of the spot relative to the target magnet, as well as to the accuracy of the field strength estimation that needs to be achieved. Generally, the more the number of point magnetic sources used for fitting, the higher the accuracy of fitting, but the more training measurement point data needs to be acquired when training the neural network.
When the distance of the target measuring point relative to the target magnet exceeds 6 times the target magnet size, the target magnet can be approximately regarded as one point (error is within 1%, see "calculate magnetic field strength from magnetic moment"). At the moment, only a single virtual point magnetic source is arranged at the center of the target magnet, and the target magnet is modeled by the virtual point magnetic source, so that the target magnet can be fitted well.
The position of the target spot depends on the need to estimate the magnetic field strength. For example, to estimate the magnetic field strength around a ship, the distance from a target measurement point to the ship is not generally satisfactory because of the large size of the ship itself, given that the distance of the measurement point from the target magnet exceeds 6 times the size of the target magnet. In such a case, by arranging a plurality of virtual point magnetic sources at equal intervals within the outline range of the target magnet, each virtual point magnetic source represents a part of the magnet to be measured, and the distance from the target measuring point to the nearest virtual point magnetic source exceeds, for example, 6 times of the distance between adjacent virtual point magnetic sources, the point magnetic source array can be better fitted to the target magnet.
Fig. 2 shows a schematic diagram of an array of set point magnetic sources for a target magnet (magnetic bar).
By way of example, the target magnet is a bar magnet 1 meter in length and 1cm in diameter. The target measuring point P is at 0.6 meter from the central side of the magnetic rod. 11 virtual point magnetic sources M are arranged at equal intervals along the length direction of the magnetic rod, so that the distance between adjacent virtual point magnetic sources is within 0.1 meter, and the distance from the target measuring point to the nearest virtual point magnetic source exceeds 6 times of the distance between the virtual point magnetic sources.
It will be appreciated that in some cases (e.g., where the required accuracy requirements are not high, and/or where the spatial positions of the target magnet and the measurement point are limited), the array of point sources is arranged such that the distance of the target measurement point from the nearest virtual point source is less than 6 times the distance between adjacent virtual point sources, although this can affect the accuracy of the magnetic field strength estimation, the objective of modeling the target magnet can also be achieved.
FIG. 3 illustrates a schematic diagram of magnet modeling and magnetic field strength prediction using a neural network, according to an embodiment of the application.
In the example of fig. 3, 2 virtual point magnetic sources (a and B, respectively, not shown) are used to fit the target magnet. The virtual point magnetic source has a known spatial location.
According to an embodiment of the application, for each virtual point magnetic source for fitting to a target magnet, a multi-layer neural network (310, 312) is provided, for example. The multi-layer neural network is in one-to-one correspondence with the virtual point magnetic sources, for example. The neural network (310, 312) is trained to output the magnetic source parameters of the virtual point magnetic source it represents. The magnetic source parameter is used to describe that the virtual point magnetic source is a parameter that can represent the magnetic characteristics of the virtual point magnetic source. For example, to calculate the magnetic field strength using the inverse cubic equation of "calculate magnetic field strength from magnetic moment", the corresponding geomagnetic source parameter is magnetic moment. If a magnetic dipole model is used to calculate the magnetic field strength, the corresponding magnetic source parameters include the magnetic pole strength and the inter-pole distance. If the current loop model is used to calculate the magnetic field strength, the corresponding magnetic source parameters include the current loop area and the current.
The operation of the neural network requires an input. According to an embodiment of the application, the input provided to each neural network (10, 312) is, for example, a specified constant. Optionally, virtual inputs are also provided to each neural network (310, 312). The virtual input is a random variable subject to a certain distribution (e.g., a uniform distribution subject to interval 0, 1).
A magnetic field intensity calculation unit (320, 322) calculates the magnetic field intensity generated at the measurement point by the virtual point magnetic source based on the magnetic source parameters and positions of the virtual point magnetic source and the position of the measurement point provided by the neural network (310, 312). In the example of fig. 3, the magnetic field strength calculation unit 320 calculates the magnetic field strength generated by the virtual point magnetic source a at each measurement point according to the magnetic source parameter and the position of the virtual point magnetic source a; the magnetic field strength calculating unit 322 calculates the magnetic field strength generated by the virtual point magnetic source B at each measuring point according to the magnetic source parameters and the position of the virtual point magnetic source B. There are also a plurality of measuring points (denoted as P). The number of stations P with different locations is large to provide enough training samples to train the neural network (310, 312).
The method for calculating the magnetic field intensity generated by the virtual point magnetic source at the designated position (measuring point) according to the magnetic source parameters and the position of the virtual point magnetic source belongs to the prior art. For example, an inverse cubic equation, a dipole equation, and the like are provided in "calculate magnetic field strength from magnetic moment".
The magnetic field strength at the measurement point is, for example, the superposition (e.g., vector sum) of the magnetic field strengths generated at the measurement point by all virtual point magnetic sources. The outputs of the magnetic field strength calculation units (320, 322) are provided to a summation unit. The summing unit sums the outputs of the respective magnetic field strength calculation units (320, 322) to obtain an estimated value of the magnetic field strength generated in common by, for example, 2 virtual point magnetic sources at the respective measuring points P.
Also in the presence of the target magnet, at each measurement point, a measurement of the strength of the magnetic field generated by the target magnet at each measurement point P is measured, for example, with a magnetometer.
The estimated value and the measured value of the magnetic field intensity at each measuring point P are compared, and the difference value is fed back to each neural network (310, 312) as an error to supervise learning of the neural network (310, 312). The learning objective (objective one) of the neural network (310, 312) is to make the estimated value of the magnetic field intensity output by the summation unit and the magnetic field intensity measured value of the corresponding measuring point approximate as much as possible by the magnetic source parameters of each virtual magnetic source point output by the neural network.
In order to obtain training samples of the neural network, the measured value of the magnetic field intensity generated by the target magnet at each measuring point P is measured at each measuring point in the presence of the target magnet, and the training samples are recorded as < measuring point coordinates and measuring point magnetic field intensity measured values >. Based on each training sample (from the measuring point Pi), the neural network (310, 312) generates an output (the training samples are not directly provided to the neural network (310, 312), the input of the neural network (310, 312) is from a virtual input), an estimated value of the magnetic field strength of the measuring point Pi is calculated by the magnetic field strength calculating unit (320, 322) and the summing unit, and an error is generated and fed back to the neural network (310, 312) according to the measured value of the magnetic field strength of the measuring point provided by the training samples. Wherein the measurement point position and the virtual point magnetic source position are each, for example, three-dimensional coordinates.
Further, the further learning goal (goal two) of the neural network (310, 312) is to make the magnetic source parameters of the virtual point magnetic source of its output fixed no matter what value is taken by its virtual input.
The training neural network converges to meet the first training target and the second optional target, and at this time, the magnetic source parameters output by the neural network (310, 312) are the magnetic source parameters of the virtual point magnetic source A and the magnetic source parameters of the virtual point magnetic source B respectively, so that the virtual point magnetic source A and the virtual point magnetic source B are obtained. And the obtained virtual point magnetic source A and the virtual point magnetic source B can be effectively fitted with the target magnet. The virtual point source a and virtual point source B being able to fit effectively to the target magnet means that around the target magnet, the magnetic field strength generated by the target magnet at a spatially specified point is consistent with the sum of the magnetic field strengths generated by the virtual point source a and virtual point source B at that specified point.
When the respective magnetic source parameters of the virtual point magnetic source a and the virtual point magnetic source B are obtained, the target magnet model represented by the virtual point magnetic source a and the virtual point magnetic source B, each having a known position (in the space where the target magnet is located), is also obtained. The magnetic field strength (generated by the target magnet) at any point in the space around the target magnet can also be estimated by the target magnet model represented by the virtual point magnetic source a and the virtual point magnetic source B. For example, for a specified point Pj (having a specified position) around the target magnet, the magnetic field intensities generated by the virtual point magnetic source a and the virtual point magnetic source B at the point Pj are calculated from the respective positions and magnetic source parameters of the virtual point magnetic source a and the virtual point magnetic source B, respectively, and the sum is an estimated value of the magnetic field intensities generated by the target magnet at the point Pj.
Fig. 4 shows a flow chart for modeling a target magnet and estimating magnetic field strength according to the present application.
To model the target magnet, one or more virtual point magnetic sources representing the target magnet are established (410). For example, the number of virtual point magnetic sources used to model the target magnet is determined based on the position (distance) of the measurement point relative to the target magnet. Modeling the target magnet using a smaller number of virtual point magnetic sources when the measurement point is farther from the target magnet; when the measuring point is close to the target magnet, the target magnet is modeled by using a larger number of virtual point magnetic sources. By way of example, by arranging virtual point magnetic sources uniformly or at equal intervals in the space where the target magnet is located, the position (coordinates) thereof is set for each virtual point magnetic source. It will be appreciated that the virtual point magnetic source is not an actual existing magnetic source, but rather an object for modeling the target magnet setup, with specified position and unknown magnetic source parameters, for the magnetic field strength calculation.
The measurement points (420) used to train the neural network are set relative to the target magnet. The measurement points are position points in the space around the target magnet. The number of stations is typically large to obtain training samples for training the neural network with each station. The measurement points used to collect training samples are referred to as training measurement points. The measurement point at which the magnetic field strength needs to be estimated is referred to as a target measurement point.
According to embodiments of the present application, the location of the training station need not be close to the target station. Optionally, the training stations are distributed, for example, over different curved surfaces and over different curved surfaces, so that the magnetic field distribution around the target magnet is described as much as possible by the position distribution of the training stations. In measuring the magnetic field strength using the magnetometer, optionally, on the spot around the target magnet, the change in magnetic field strength in space is obtained from the magnetometer, and the intervals/positions of the stations are adjusted accordingly so that a greater number of training stations (or a decrease in the intervals of the set training stations) are set in the area (or direction) where the change in magnetic field strength is greater (faster), and a smaller number of training stations (or an increase in the intervals of the set training stations) are set in the area (or direction) where the change in magnetic field strength is less (slower). By way of example, the number of training stations is not less than 3 times the number of virtual point sources used to model the target magnet, and preferably is more than 6 times the number of virtual point sources used to fit the target magnet.
The magnetic field strength and spatial coordinates are collected as training samples at each training station in the presence of the target magnet (430). Optionally, when the training sample is acquired, the influence of the earth magnetic field or the environment magnetic field on the magnetic field intensity of the training measuring point is eliminated. For example, first, in the absence of a target magnet, the magnetic field strength, referred to as the background field strength, is measured at each training station using a magnetometer and data is recorded. Next, the target magnet is brought to a specified location (which is the same location where the target magnet modeled by the virtual point magnetic source was located in step 410), and the magnetic field strength (also referred to as apparent field strength) is measured at each training station. When the training sample is collected, each training measuring point records the coordinates of the training measuring point, and the 'field intensity value caused by the target magnet' obtained by subtracting the background field intensity value from the measured value of the magnetometer when the training sample exists is recorded in association with the coordinates as the labeling magnetic field intensity of the training sample. Alternatively, the external environment (e.g., weather conditions) at which the background field strength is measured is kept as consistent as possible with the external environment at which the apparent field strength of the training station is measured.
Each neural network (440) is trained using the collected training samples. Referring also to FIG. 3, one or more neural networks (310, 312) are provided, each corresponding to one of the virtual point sources created in step 410. The input of the neural network is a fixed value or a virtual input conforming to a specified distribution, and the output of the neural network is the magnetic source parameter of the corresponding virtual point magnetic source. And calculating the magnetic field intensity generated by all the virtual point magnetic sources at each training measuring point according to the point magnetic source parameters output by each neural network and the positions of the corresponding virtual point magnetic sources. The neural network is trained, so that the magnetic field intensity generated by all virtual point magnetic sources at the calculated position at each training measuring point is consistent with the magnetic field intensity marked in a training sample representing the training measuring point as much as possible. For example, the difference between the calculated magnetic field strength and the magnetic field strength in the training sample is made smaller than a specified threshold.
For each neural network after training, the magnetic source parameters of the corresponding virtual point magnetic source are output. Therefore, the virtual point magnetic source with the magnetic source parameters is obtained, a magnetic model of the target magnet is obtained, and modeling of the target magnet is completed. By using the magnetic model of the target magnet, the magnetic field intensity of any position around the target magnet can be obtained according to the existing magnetic field intensity calculation method.
When it is desired to estimate the magnetic field strength of a target site specified around the target magnet, the position (coordinates) of the target site is acquired (450), and the sum of the magnetic field strengths generated at the target site by all virtual point magnetic sources representing the target magnet is calculated as an estimate of the magnetic field strength of the target site (460). The magnetic source parameters of the magnetic sources of the virtual points are obtained from the output of the neural networks trained in step 440.
FIG. 5 illustrates a schematic diagram of modeling a target magnet and estimating magnetic field strength according to an embodiment of the application.
In fig. 5, a rectangle surrounded by a dot-dash line represents a target magnet, a single virtual point magnetic source (rectangle surrounded by a dotted line) is disposed inside a space position where the target magnet is located, and a surrounding space outside the target magnet includes a plurality of measurement points (rectangle surrounded by a solid line). In the example of fig. 5, a single virtual point magnetic source has been able to effectively fit the magnetic model of the target magnet due to the fact that the measurement point is far from the target magnet.
In fig. 5, the measurement points to the right and below the target magnet are training measurement points (denoted by P1, P2 … … Pm … … Pn), and the measurement point to the left of the target magnet is a target measurement point (denoted by Pq). Thus, the training station need not be adjacent to the target station, thereby facilitating acquisition of the training sample (as the target station may be inconvenient or unreachable in position or may not be provided with a magnetometer).
In order to obtain training samples, when a target magnet exists, position coordinates of measuring points and magnetic field intensity of the measuring points are acquired at the positions of the training measuring points. Optionally, at each measurement point, the background field intensity (magnetic field intensity at the measurement point when the target magnet is not present) and the apparent field intensity (magnetic field intensity at the measurement point when the target magnet is present) are also collected, and the difference between the apparent field intensity and the local field intensity is used as the magnetic field intensity of the measurement point in the training sample.
And training the neural network by using the training sample to obtain the magnetic source parameters of the virtual point magnetic source. And calculating the magnetic field intensity of the target measuring point (Pq) by using the position of the virtual point magnetic source and the magnetic source parameter, and taking the magnetic field intensity as the estimation of the magnetic field intensity generated by the target magnet at the target measuring point.
FIG. 6 shows a schematic diagram of modeling a target magnet and estimating magnetic field strength according to yet another embodiment of the application.
In fig. 6, a rectangle surrounded by a chain line represents a bar-shaped target magnet (magnetic bar 600), a plurality of virtual point magnetic sources (rectangles surrounded by broken lines) (denoted as A1, A2 … … An) are provided inside the space position where the magnetic bar 600 is located, and a plurality of measuring points (represented by rectangles surrounded by solid lines) (denoted as P1, P2 … … Pm) are included in the surrounding space outside the target magnet. In the example of FIG. 6, a plurality of virtual point magnetic sources are used to fit the magnetic model of the magnetic rod 600 due to the close proximity of the measurement points to the magnetic rod 600. Optionally, the virtual point magnetic sources are arranged such that 6 times the spacing between the virtual point magnetic sources is still less than the distance from any measurement point to any virtual point magnetic source.
In FIG. 6, the stations include training stations (labeled by P1, P2 … … Pm) and target stations (labeled by Pq). To obtain training samples, the position coordinates of the measurement points and the magnetic field strength of the measurement points are acquired at the positions of the respective training measurement points when the magnetic rod 600 exists. Optionally, at each measurement point, the background field intensity (magnetic field intensity at the measurement point when the magnetic rod 600 is not present) and the apparent field intensity (magnetic field intensity at the measurement point when the magnetic rod 600 is present) are also collected, and the difference between the apparent field intensity and the local field intensity is used as the magnetic field intensity of the measurement point in the training sample.
And training the neural network by using the training sample to obtain the magnetic source parameters of the virtual point magnetic source. And calculating the magnetic field intensity of the target measuring point (Pq) by using the position of the virtual point magnetic source and the magnetic source parameter as an estimate of the magnetic field intensity generated by the magnetic rod 600 at the target measuring point (Pq).
FIG. 7 shows a schematic diagram of modeling a target magnet and estimating magnetic field strength according to yet another embodiment of the application.
In fig. 7, an ellipse enclosed by a dash-dot line represents a target magnet (ship). To facilitate acquisition of training samples, the vessel is moored in a port or dock. The port or dock is in a groove shape, and the two sides of the ship are provided with lands, so that training measuring points (P1 and P2 … … Pm) are conveniently arranged. The target station (Pg) is in water under for example a ship, where it is inconvenient to set up a magnetic field strength measuring device. A plurality of virtual point magnetic sources (rectangles surrounded by dashed lines) (noted A, B … … C) are placed inside the spatial location occupied by the hull of the vessel to fit the target magnet (the vessel).
In the example of fig. 7, since the location of the survey point is limited by the site conditions of the port or dock, the arrangement and number of virtual spot magnetic sources are selected according to the relationship between the survey point-to-ship distance and the ship's own size. For example, a magnetic model of a ship is fitted by three virtual point magnetic sources (A, B and C).
And acquiring training samples at each training measuring point, and training three neural networks to obtain the magnetic source parameters of the virtual point magnetic sources (A, B and C). And then the magnetic field intensity of the virtual point magnetic sources A, B and C at the target measuring point Pg is calculated as the estimation of the magnetic field intensity generated by the ship at the measuring point Pg.
It will be appreciated that after the source parameters for virtual point sources A, B and C are obtained, the field strength at any point around the vessel can be estimated. Also, the ship is not limited to being located in a port or dock where the training sample is obtained, but the magnetic field strength of the target survey point may be estimated from the magnetic source parameters of the virtual point magnetic sources A, B and C at any position and according to the relative position of the target survey point and the ship.
Fig. 8 shows a schematic diagram of magnet modeling and magnetic field strength prediction using a neural network according to yet another embodiment of the present application.
In the example of fig. 8, 2 virtual point magnetic sources (a and B, respectively, not shown) are used to fit the target magnet. The virtual point magnetic source has a known spatial location.
In order to stabilize the magnetic source parameters of the virtual point magnetic sources estimated by the neural network, a plurality of neural networks are provided for each virtual point magnetic source. Referring to fig. 8, neural networks 810 and 812 are used to estimate the magnetic source parameters of virtual point magnetic source a, and neural networks 820 and 822 are used to estimate the magnetic source parameters of virtual point magnetic source B. The outputs of each of a plurality of neural networks (e.g., neural networks 810 and 812) corresponding to the virtual point magnetic source are utilized to estimate the magnetic source of the virtual point magnetic source, for example. In the example of fig. 8, the outputs of the neural networks 810 and 812, respectively, are averaged (840) as an estimate of the magnetic source parameters of the virtual point magnetic source a. The outputs of the neural networks 820 and 822, respectively, are averaged 844 as an estimate of the magnetic source parameters of the virtual point magnetic source B. The consistency or variance of the outputs of each of the plurality of neural networks corresponding to the same virtual point magnetic source is also evaluated as an additional error for training the neural networks. In the example of fig. 8, the mean square error (842) of the outputs of the neural networks 810 and 812, respectively, is calculated to evaluate the consistency of their inputs, and the mean square error (846) of the outputs of the neural networks 820 and 822, respectively, is calculated to evaluate the consistency of their inputs.
A magnetic field intensity calculation unit 850 for calculating the magnetic field intensity generated by the virtual point magnetic source a at each measuring point according to the estimated magnetic source parameters and positions of the virtual point magnetic source a; the magnetic field strength calculation unit 852 calculates the magnetic field strength generated by the virtual point magnetic source B at each measuring point according to the magnetic source parameters and the position of the virtual point magnetic source B. The magnetic field intensities calculated at the respective measurement points by the magnetic field intensity calculation unit 850 and the magnetic field intensity calculation unit 852 are summed (860) to obtain an estimated value of the magnetic field intensity generated at the respective measurement points by the virtual point magnetic source a and the virtual point magnetic source B together. There are a plurality of measuring points (denoted as P). The number of stations P with different locations is large to provide enough training samples to train the neural network (810, 812, 820, and 822).
At each measuring point, a measurement value of the magnetic field strength generated by the target magnet at each measuring point P is measured. The estimated and measured values of the magnetic field strength at each measurement point P are compared, and the difference is fed back as an error to each neural network (810, 812, 820, 822) to supervise the learning of the neural network (810, 812, 820, 822). In the example of fig. 8, the mean square error (842) of the outputs of the respective neural networks 810 and 812 and the mean square error (846) of the outputs of the respective neural networks 820 and 822 are summed (862) and fed back as further errors to the neural networks (810, 812, 820 and 822).
According to the embodiment of fig. 8, virtual inputs 815 and 825 each follow the same distribution, while multiple neural networks corresponding to the same virtual point source share weights. For example, neural networks 810 and 812 share weights, while neural networks 820 and 822 share weights. Thus, the field intensity can be calculated by using one of the magnetic source parameters calculated by the two networks, and the field intensity can be calculated by using the average value of the two parameters. Virtual input 815 is provided to one of a plurality of neural networks corresponding to the same virtual point magnetic source and virtual input 825 is provided to one of a plurality of neural networks corresponding to the same virtual point magnetic source such that each neural network virtually corresponding to the same virtual point magnetic source receives a different virtual input. In the example of fig. 8, virtual input 815 is provided to neural networks 810 and 820, and virtual input 825 is provided to neural networks 812 and 822. In training the neural networks (810, 812, 820, and 822), differences in the outputs of the neural networks corresponding to the same virtual point magnetic source are also set as close as possible to the training target. For example, the difference between the outputs of the plurality of neural networks corresponding to the same virtual point magnetic source is made as 0 as possible or as close as possible to a specified super parameter, and the value of the super parameter is adjusted in the implementation to achieve the goal that the magnetic source parameters of the virtual point magnetic sources outputted by the neural networks (810, 812, 820 and 822) are fixed (the difference is as small as possible) no matter what value the virtual input takes.
Optionally, for each virtual point magnetic source, other numbers of neural networks are used to estimate the magnetic source parameters of the virtual point magnetic source, or RNNs (Recurrent Neura l Network, cyclic neural networks) are used to estimate the magnetic source parameters of the virtual point magnetic source, so as to achieve the goal that the magnetic source parameters of each virtual point magnetic source output by the neural network are fixed no matter what value is taken by the virtual input.
Fig. 9 shows a schematic diagram of modeling a target magnet and estimating magnetic field strength according to yet another embodiment of the application.
Fig. 9 shows a spatial coordinate system of a space in which the target magnet is located, an origin of the coordinate system is denoted as O, a horizontal plane is an XOY plane, and a Z axis is perpendicular to the horizontal plane. The size of the circumscribing cube of the target magnet is (1,0.1,0.1), the center of the target magnet is at the origin), and the coordinates are (0, 0). As an example, three virtual point sources with coordinates (-0.5, 0), (0, 0), (0.5, 0) are used to fit the unknown magnet (the virtual point sources are represented by black squares in fig. 9), and a fixed value of 1 is used as the virtual input provided to the neural network.
By way of example, the neural network used to estimate the magnetic source parameters is a 3-layer 30-dimensional fully connected network. Magnetic moment is selected as the magnetic source parameter. The theoretical formula for calculating the field strength according to the measuring point coordinates, the virtual point magnetic source coordinates and the magnetic moment uses the inverse cubic formula provided in the magnetic moment calculation of the magnetic field strength.
Referring to fig. 9, a plurality of training measurement points are set above both sides of the x-axis of the target magnet for collecting training samples (the training measurement points are represented by black circles in fig. 9), and the collected sets of < measurement point coordinates, measurement point magnetic field strength > are used as training data. The Mean Square Error (MSE) of the estimated and actual values of the measured point field strength is used as the error fed back to the neural network. A plurality of target measurement points (the target measurement points are represented by lower triangles in fig. 9) are set below the target magnet for fitting results of the test model.
Alternatively, when the measuring point measures the magnetic field strength, a plurality of magnetometers can be mounted at designated positions on the frame of the non-magnetically permeable material to acquire a plurality of magnetic field strength data at different positions. And then multiple sets of data are acquired by continuously translating the frame on the non-magnetically permeable track.
Although the examples referred to in the present application are described for illustrative purposes only and not to be limiting of the application, modifications, additions and/or deletions to the embodiments may be made without departing from the scope of the application.
Many modifications and other embodiments of the applications set forth herein will come to mind to one skilled in the art to which these embodiments pertain having the benefit of the teachings presented in the foregoing descriptions and the associated drawings. Therefore, it is to be understood that the applications are not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended claims. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.
Claims (10)
1. A method of modeling a target magnet, comprising:
establishing one or more virtual point magnetic sources representing the target magnet, the virtual point magnetic sources having specified locations within the space occupied by the target magnet;
setting a plurality of training measuring points in the space around the target magnet, wherein the training measuring points have specified positions;
Measuring the magnetic field intensity of each training measuring point under the influence of a target magnet;
Generating training samples according to the magnetic field intensity of each training measuring point and the positions of the training measuring points to train one or more neural networks; wherein the method comprises the steps of
The one or more virtual point magnetic sources are respectively provided with one or more corresponding neural networks, and the neural networks corresponding to the virtual point magnetic sources are trained so that the output of the neural networks represents the magnetic source parameters of the virtual point magnetic sources corresponding to the neural networks;
calculating the magnetic field intensity generated by the one or more virtual point magnetic sources at the positions of the training measuring points of the training sample according to the magnetic source parameters and the positions of the one or more virtual point magnetic sources output by the neural network and the positions of the training measuring points in the training sample, and taking the magnetic field intensity as an estimated magnetic field intensity;
Training errors of the neural network corresponding to each of the one or more virtual point magnetic sources according to the difference between the estimated magnetic field intensity and the magnetic field intensity of the training sample;
using the output of the trained neural network as the magnetic source parameter of the virtual point magnetic source corresponding to the output;
And using the respective positions and magnetic source parameters of the one or more virtual point magnetic sources as a magnetic model of the target magnet.
2. The method of claim 1, wherein
Representing the target magnet with a single virtual point magnetic source; or alternatively
And setting the one or more virtual point magnetic sources so that the distance between any virtual point magnetic sources is 6 times smaller than the distance between any training measuring point and any virtual point magnetic source.
3. The method of claim 1 or 2, further comprising:
To train the one or more neural networks, virtual inputs are provided to each of the one or more neural networks, the virtual inputs provided to the one or more neural networks obeying a specified distribution.
4. A method according to claim 3, wherein
And training the one or more neural networks to ensure that the estimated magnetic field intensity at each training measuring point calculated according to the magnetic source parameters of each virtual point magnetic source obtained by the output of the one or more neural networks is as consistent as possible with the magnetic field intensity of the corresponding training sample.
5. The method of claim 4, wherein
And training the one or more neural networks to ensure that the magnetic source parameters of the magnetic sources of the virtual points obtained according to the output of the one or more neural networks are consistent as much as possible under the condition of different virtual inputs.
6. The method of claim 5, wherein
The one or more virtual point magnetic sources each have a corresponding plurality of neural networks;
Using the statistics of the outputs of the plurality of neural networks corresponding to the one or more virtual point magnetic sources as the magnetic source parameters of the virtual point magnetic source represented by the statistics;
the difference between the outputs of the plurality of neural networks corresponding to each of the one or more virtual point sources is taken as a further error in training the neural networks.
7. The method of claim 6, wherein
Providing a plurality of virtual inputs, wherein the respective obeyed distributions of the plurality of virtual inputs are identical to each other, and the number of the plurality of virtual inputs is identical to the number of the plurality of neural networks corresponding to the one or more virtual point magnetic sources;
providing one of the plurality of virtual inputs for each of a plurality of neural networks to which the one or more virtual point magnetic sources correspond respectively;
Each of the plurality of virtual inputs is simultaneously provided to a respective one of a plurality of neural networks for each virtual point magnetic source.
8. The method of claim 7, wherein,
Measuring the background magnetic field intensity of each training measuring point under the condition that the target magnet is not present;
Measuring the real magnetic field intensity of each training measuring point under the condition that the target magnet exists;
And obtaining the magnetic field intensity of each training measuring point under the influence of the target magnet according to the difference between the real magnetic field intensity and the background magnetic field intensity.
9. The magnetic field intensity estimation method of the target measuring point under the influence of the target magnet comprises the following steps:
The method according to one of claims 1-8, establishing a magnetic model of a target magnet represented by one or more virtual point magnetic sources;
And calculating the superposition of the magnetic field intensities generated by all the virtual point magnetic sources of the one or more virtual point magnetic sources at the positions of the target measuring points according to the magnetic source parameters and the positions of the one or more virtual point magnetic sources and a magnetic field intensity formula to obtain the magnetic field intensity estimation of the target measuring points under the influence of the target magnet.
10. An information processing apparatus comprising a memory, a processor and a program stored on the memory and executable on the processor, characterized in that the processor implements the method according to one of claims 1-9 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210738001.0A CN115130379B (en) | 2022-06-27 | 2022-06-27 | Magnet modeling and magnetic field estimation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210738001.0A CN115130379B (en) | 2022-06-27 | 2022-06-27 | Magnet modeling and magnetic field estimation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115130379A CN115130379A (en) | 2022-09-30 |
| CN115130379B true CN115130379B (en) | 2024-05-24 |
Family
ID=83380104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210738001.0A Active CN115130379B (en) | 2022-06-27 | 2022-06-27 | Magnet modeling and magnetic field estimation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115130379B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702568B (en) * | 2023-08-04 | 2023-11-10 | 天津天达图治科技有限公司 | Magnetic resonance imaging permanent magnet design method, system, equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103675719A (en) * | 2013-12-17 | 2014-03-26 | 复旦大学 | Method for determining magnetic induction intensity maximum value by adoption of second-order polynomial curve fitting and implementation system |
| WO2016139135A1 (en) * | 2015-03-02 | 2016-09-09 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e. V. | Method and assembly for determining the position of a magnetic body by means of magnetic field sensors |
| CN110146845A (en) * | 2019-04-17 | 2019-08-20 | 杭州电子科技大学 | A kind of event driven set time electromagnet source localization method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8862200B2 (en) * | 2005-12-30 | 2014-10-14 | DePuy Synthes Products, LLC | Method for determining a position of a magnetic source |
| FR3080186B1 (en) * | 2018-04-16 | 2020-05-08 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | CALIBRATION METHOD OF A NETWORK OF MAGNETOMETERS |
-
2022
- 2022-06-27 CN CN202210738001.0A patent/CN115130379B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103675719A (en) * | 2013-12-17 | 2014-03-26 | 复旦大学 | Method for determining magnetic induction intensity maximum value by adoption of second-order polynomial curve fitting and implementation system |
| WO2016139135A1 (en) * | 2015-03-02 | 2016-09-09 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e. V. | Method and assembly for determining the position of a magnetic body by means of magnetic field sensors |
| CN110146845A (en) * | 2019-04-17 | 2019-08-20 | 杭州电子科技大学 | A kind of event driven set time electromagnet source localization method |
Non-Patent Citations (4)
| Title |
|---|
| 基于等效磁矩的永磁体磁性测量方法研究;姜浩;周鹰;杨云;;电子世界;20160708(第13期);全文 * |
| 潜艇空间磁场的建模分析与运用;章尧卿 等;《 舰船电子工程》;20180120;全文 * |
| 由磁矩计算磁场强度;张新邦 等;《数字海洋与水下攻防》;20190615;第第2卷卷(第第2期期);全文 * |
| 磁性目标的单点模量测距方法;万成彪;罗诗途;王伟;张琦;翁飞兵;;测试技术学报;20140225(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115130379A (en) | 2022-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104019813B (en) | Method and system of target immediate location and map establishing | |
| WO2017052712A2 (en) | System and method for characterizing ferromagnetic material | |
| CN104374385A (en) | Submarine magnetic sensor array target positioning new method | |
| CN115130379B (en) | Magnet modeling and magnetic field estimation method and device | |
| CN110007357B (en) | Aviation TEM and aviation MT joint inversion method | |
| CN104245499B (en) | System for accuracy control of erection on marine floating dock | |
| CN103926627A (en) | Underwater carrier geomagnetic three-component measuring method | |
| CN106441279A (en) | Robot positioning method based on self-positioning and edge searching and system | |
| CN115238550A (en) | Self-adaptive unstructured grid landslide rainfall geoelectric field numerical simulation calculation method | |
| CN112180450B (en) | Three-dimensional reconstruction and imaging method of direct current cable based on magnetic field measurement | |
| CN109579845A (en) | A kind of ship tracking localization method based on electric field detecting array | |
| CN109828307A (en) | A kind of detection method of transient electromagnetic multi-frequency fusion and application | |
| CN115144796B (en) | Modeling and magnetic field estimation method and device for residual magnetism and magnetic induction of magnet in geomagnetic field | |
| JPH07151866A (en) | Method and apparatus for detecting thunder and lightning | |
| CN109633539A (en) | A kind of the static immobilization device and static immobilization method of magnetic source | |
| CN114488314B (en) | Geological inversion method based on land and underwater direct current combined measurement | |
| Specht et al. | Metrological aspects of the Tombolo effect investigation–Polish case study | |
| Zhao et al. | Construction method of geomagnetic reference map for satellite communication navigation through Kriging method | |
| CN114114438A (en) | Quasi-three-dimensional inversion method for loop source ground-air transient electromagnetic data | |
| CN110531429A (en) | A kind of time-domain electromagnetic data object inversion method based on supervision descent method | |
| US20220290966A1 (en) | Wall thinning detection system, wall thinning detection method and non-transitory computer readable storage medium | |
| Liang et al. | Research on modeling simulation and stability of underwater magnetic field for underwater target detection | |
| CN113535672B (en) | Turbidity data processing method based on autonomous underwater robot platform | |
| CN116719092B (en) | Quick scanning device and method for water leakage detection | |
| Wang et al. | Comprehensive image matching algorithm based on local GLCM for gravity-gradient-aided navigation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |