CN116297620B - Magnetic variable measurement method and system for nuclear magnetic resonance apparatus - Google Patents
Magnetic variable measurement method and system for nuclear magnetic resonance apparatus Download PDFInfo
- Publication number
- CN116297620B CN116297620B CN202310309167.5A CN202310309167A CN116297620B CN 116297620 B CN116297620 B CN 116297620B CN 202310309167 A CN202310309167 A CN 202310309167A CN 116297620 B CN116297620 B CN 116297620B
- Authority
- CN
- China
- Prior art keywords
- magnetic flux
- magnetic
- detection
- intensity
- atlas
- 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
- 238000005481 NMR spectroscopy Methods 0.000 title claims abstract description 54
- 238000000691 measurement method Methods 0.000 title claims abstract description 13
- 230000004907 flux Effects 0.000 claims abstract description 229
- 238000001514 detection method Methods 0.000 claims abstract description 140
- 230000002159 abnormal effect Effects 0.000 claims abstract description 134
- 238000005259 measurement Methods 0.000 claims abstract description 123
- 238000006243 chemical reaction Methods 0.000 claims abstract description 42
- 238000001228 spectrum Methods 0.000 claims abstract description 35
- 230000008859 change Effects 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000012216 screening Methods 0.000 claims abstract description 25
- 230000010354 integration Effects 0.000 claims abstract description 15
- 230000035515 penetration Effects 0.000 claims description 22
- 230000004927 fusion Effects 0.000 claims description 21
- 238000013135 deep learning Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 abstract description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000011160 research Methods 0.000 description 15
- 238000012545 processing Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 239000000126 substance Substances 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000012827 research and development Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000329 molecular dynamics simulation Methods 0.000 description 1
- 150000002894 organic compounds Chemical class 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N24/00—Investigating or analyzing materials by the use of nuclear magnetic resonance, electron paramagnetic resonance or other spin effects
- G01N24/08—Investigating or analyzing materials by the use of nuclear magnetic resonance, electron paramagnetic resonance or other spin effects by using nuclear magnetic resonance
-
- 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
Abstract
The invention belongs to the technical field of magnetic variable measurement, and particularly relates to a magnetic variable measurement method and system for a nuclear magnetic resonance spectrometer, wherein the method comprises the following steps: acquiring a magnetic flux detection signal set, performing image editing on the magnetic flux detection signal set, and performing special region identification and screening so as to acquire a magnetic flux change chart set; performing spectrum conversion and space integration on the magnetic flux change atlas, thereby obtaining a waveform atlas space set; carrying out space modeling according to the waveform map space set and carrying out fixed-point coordinate construction, thereby obtaining a final three-dimensional space model; performing directional measurement and locking and re-marking on the final three-dimensional space model, so as to generate a measurement result space model; counting the measurement results of the abnormal data information set, so as to generate measurement result data; the invention performs measurement through hardware and data integration by artificial intelligence, and can more intuitively display the measurement result of the magnetic variable.
Description
Technical Field
The invention belongs to the technical field of magnetic variable measurement, and particularly relates to a magnetic variable measurement method and system for a nuclear magnetic resonance spectrometer.
Background
At present, nuclear magnetic resonance is rapidly developed into a powerful tool for measuring the structure of an organic compound, more than ten thousand compounds are identified by matching the nuclear magnetic resonance with other instruments, the sensitivity of the instrument is greatly improved by using a strong magnetic field superconducting nuclear magnetic resonance instrument, the application in the field of biology is rapidly expanded, the nuclear magnetic resonance technology can provide information on the chemical structure and molecular dynamics of molecules, and the nuclear magnetic resonance technology is a conventional technical means for analyzing the molecular structure and representing the physical and chemical properties of substances, is widely applied in the fields of physics, chemistry, biology, medicine, food and the like, and is an indispensable means in the chemistry; the existing nuclear magnetic resonance measurement technology already has a certain hardware foundation, however, as the development of nuclear magnetic resonance, hardware facilities enter a bottleneck period, more noise data and invalid data are generated in the magnetic variable measurement process, so that the measurement accuracy cannot meet the scene with higher requirements.
Disclosure of Invention
In view of the above, the present invention provides a magnetic variable measurement method and system for nuclear magnetic resonance apparatus to solve at least one of the above-mentioned problems.
In order to achieve the above object, the present invention provides a magnetic variable measurement method for a nuclear magnetic resonance apparatus, the magnetic variable measurement method for a nuclear magnetic resonance apparatus comprising the steps of:
Step S1: acquiring a magnetic flux conventional signal set of a nuclear magnetic resonance instrument, performing image editing on the magnetic flux conventional signal set and performing spatial ordering, thereby acquiring a conventional magnetic flux atlas;
step S2: acquiring a magnetic flux detection signal set, performing image editing on the magnetic flux detection signal set to acquire a detection magnetic flux atlas, and performing special area identification and screening on the detection magnetic flux atlas according to a conventional magnetic flux atlas to acquire a magnetic flux change atlas;
step S3: performing spectrum conversion on the magnetic flux change atlas to generate a magnetic variable waveform atlas, and performing spatial integration on the magnetic variable waveform atlas to obtain a waveform atlas spatial set;
step S4: performing space modeling according to the waveform map space set so as to generate an initial three-dimensional space model; then, constructing fixed-point coordinates of the initial three-dimensional space model, so as to obtain a final three-dimensional space model;
step S5: directional measurement is carried out on the final three-dimensional space model, so that directional measurement data are obtained, and locking is carried out on the directional measurement data, so that an abnormal data information set is obtained;
step S6: marking the abnormal data information in the abnormal data information set to the final three-dimensional space model, so as to generate a measurement result space model;
Step S7: and carrying out measurement result statistics on the abnormal data information set so as to generate measurement result data, integrating the measurement result space model with the measurement result data, and marking the measurement result space model as a magnetic variable measurement result.
According to the embodiment, the situation that errors are increased due to environmental changes can be reduced when the sample is measured, the measurement accuracy of the sample is improved, the harsh conditions of the nuclear magnetic resonance apparatus on an operation site can be reduced by measuring the current environment, the application range of the nuclear magnetic resonance apparatus is improved, information is conveniently checked, extracted and analyzed by converting signals into images, the processing capacity of the data is enhanced, related noise data and invalid data are removed by primarily screening the conventional magnetic flux diagram concentrated by the conventional magnetic flux diagram and the detection magnetic flux diagram concentrated by the detection magnetic flux diagram, the data amount of subsequent processing is reduced, the processing capacity of the system on the data, the processing speed and the measurement accuracy of magnetic variables are improved, the information contained in the sample can be further analyzed by converting the map, the three-dimensional space model is established, the research of the appearance characteristics of the sample is facilitated, the information contained in different areas of the sample is facilitated, the different information of different areas of the sample can be intuitively embodied, and the representing capacity of the information is improved.
In one embodiment of the present specification, step S1 includes the steps of:
step S21: transmitting a first intensity signal to the surrounding environment for preliminary detection, and receiving the first intensity signal so as to obtain a magnetic flux conventional signal set of the nuclear magnetic resonance instrument;
step S22: performing image conversion on the magnetic flux normal signals in the magnetic flux normal signal set through the magnetic flux signal image conversion model obtained through deep learning, so as to obtain a discrete magnetic flux image set;
step S23: acquiring a detection spatial sequence, and performing spatial sequence ordering on the discrete magnetic flux images in the discrete magnetic flux image set according to the detection spatial sequence, so as to acquire a sequential magnetic flux image set;
step S24: sequential magnetic flux images in the sequential magnetic flux image set are sequentially encoded to obtain an image code, and the image code is marked into the sequential magnetic flux image to obtain a conventional magnetic flux image set.
According to the embodiment, the first intensity signal is transmitted to the environment, so that the interference layer degree of the interference magnetic field of the surrounding environment to the experimental field is detected conveniently, the nuclear magnetic resonance instrument can transmit a proper opposite magnetic field to offset larger interference, interference to the experiment is reduced, the current magnetic field condition is analyzed, the current measured conventional magnetic flux atlas is used as a model to screen the follow-up detection magnetic flux atlas, and the interference of the weak magnetic field to the current field can be reduced.
In one embodiment of the present specification, step S2 includes the steps of:
step S31: the first detection transmits a first intensity signal to the surrounding environment for early detection, and receives the first intensity signal, so as to obtain a first detection signal set;
step S32: the second detection transmits a second intensity signal to the surrounding environment for medium-term detection, and receives the second intensity signal, so that a second detection signal set is obtained;
step S33: transmitting a third intensity signal to the surrounding environment for post detection and receiving the third intensity signal, thereby obtaining a third detection signal set;
step S34: the first detection signal set, the second detection signal set and the third detection signal set are whipped and integrated, so that a magnetic flux detection signal set is obtained, wherein the magnetic field intensity of the first-intensity signal is larger than that of the second-intensity signal, and the magnetic field intensity of the second-intensity signal is larger than that of the third-intensity signal;
step S35: performing image conversion on the magnetic flux detection signals in the magnetic flux detection signal set by the magnetic flux signal image conversion model obtained by deep learning, thereby obtaining a detection magnetic flux atlas;
Step S36: matching the detected magnetic flux patterns in the detected magnetic flux patterns according to the conventional magnetic flux patterns, and summarizing the detected magnetic flux patterns with the matching smaller than a detection threshold value, so as to obtain a screening magnetic flux pattern set;
step S37: classifying and marking the magnetic field intensity of the screened magnetic flux patterns in the screened magnetic flux patterns, so as to obtain classified magnetic flux patterns, convolutionally identifying the classified magnetic flux patterns in the classified magnetic flux patterns through regional matching convolution check of image matching degree, and extracting a special region, so that a magnetic flux change pattern is obtained.
According to the embodiment, the three signals with different intensities are used for measuring the sample, the characteristics of the appearance of the sample under the magnetic fields with different intensities are fully mined, the information extraction of the sample is improved, the three different detection signal sets are integrated, the information error caused by the error in the processing process is improved, the measurement accuracy of the nuclear magnetic resonance spectrometer is further improved, and the artificial intelligence is added to process the data to realize the powerful hardware and the powerful software data processing.
In one embodiment of the present specification, step S3 includes the steps of:
Performing spectrum conversion on the magnetic flux change atlas, thereby generating a magnetic variable waveform atlas;
classifying magnetic field intensity of the magnetic variable waveform atlas, so as to obtain a first intensity magnetic variable waveform atlas, a second intensity magnetic variable waveform atlas and a third intensity magnetic variable waveform atlas;
and respectively carrying out space integration on the first intensity magnetic variable waveform spectrum set, the second intensity magnetic variable waveform spectrum set and the third intensity magnetic variable waveform spectrum set, so as to obtain a first intensity waveform spectrum space set, and uniformly marking and integrating the second intensity waveform spectrum space set and the third intensity waveform spectrum space set into the waveform spectrum space set.
According to the embodiment, through carrying out the wave conversion on the magnetic flux change atlas, the internal structure of the sample and the form and composition of the substance can be displayed more intuitively, so that the display of the sample measurement information is improved, the magnetic variable waveform patterns detected by the magnetic fields with different intensities are classified and spatially integrated, three groups of sample waveform patterns under the condition of different intensities are formed, the integration of the subsequent sample information and the error reduction are facilitated, and the measurement precision of the sample is further improved.
In one embodiment of the present specification, step S4 includes the steps of:
acquiring a waveform map mapping color data set, performing color mapping on waveform maps in a waveform map space set according to the waveform map mapping color data set, so as to obtain color maps, classifying according to marked magnetic field intensity, and performing space stacking according to the space sequence in the waveform map space set, so as to obtain three color stacking three-dimensional models;
fusing the three color stacking three-dimensional models according to a preset fusion denoising algorithm, so as to obtain a color three-dimensional space model;
and reconstructing the virtual space model of the color three-dimensional space model to obtain an initial three-dimensional space model, and constructing fixed-point coordinates of the initial three-dimensional space model to obtain a final three-dimensional space model.
According to the embodiment, the color mapping is carried out through the color information degree waveform patterns corresponding to various types of information, so that the internal structure composition of a sample can be intuitively displayed, the software can conveniently identify the information on the waveform patterns, a preliminary three-dimensional model is formed by stacking the color patterns, the three-dimensional model formed by stacking the color patterns obtained by measuring different magnetic field intensities is fused, the purpose of noise reduction is achieved, the initial three-dimensional model is formed by reconstructing the virtual space model of the color three-dimensional model, the more ideal and more intuitive space model is provided for research personnel according to the actual situation, the coordinate construction is carried out on the initial three-dimensional model, the information on the model is conveniently positioned, and the observation and locking of a demand area and information display are facilitated.
In one embodiment of the present disclosure, three color stacked three-dimensional models are fused according to a preset fusion denoising algorithm, where a fusion denoising calculation formula of the preset fusion denoising algorithm is specifically the following calculation formula:
wherein K is denoted as a noise reduction fusion parameter, t is denoted as a time of one intensity measurement of nuclear magnetic resonance, a is denoted as a magnetic field intensity of the first intensity signal, b is denoted as a magnetic field intensity of the second intensity signal, c is denoted as a magnetic field intensity of the third intensity signal, θ is denoted as an opposite impact interference magnetic field intensity, β is denoted as a magnetic flux penetration weight of the measured sample property, and g is denoted as a bias adjustment term.
In this embodiment, fusion of the noise reduction fusion parameter K is calculatedCombining denoising calculation formulas, comparing and calculating the magnetic field intensity under different magnetic field intensities by using the magnetic field intensity a of the first intensity signal, the magnetic field intensity b of the second intensity signal and the magnetic field intensity c of the third intensity signal, and usingThe relation between the magnetic field intensity and the generated noise point are calculated and analyzed, the influence of the magnetic fields with different intensities on the sample measurement data is fully considered, the interference of external conditions on the sample measurement result is reduced, and the magnetic field intensity theta of opposite impact interference and the magnetic flux penetration weight beta of the measured sample attribute are utilized to pass >And performing calculation so as to further reduce the magnetic field interference of the external magnetic field to the current environment.
In one embodiment of the present specification, step S5 includes the steps of:
step S71: obtaining standard proportion, and performing space measurement on the final three-dimensional space model according to the standard proportion so as to generate model basic data;
step S72: acquiring a conventional detection data set, performing conventional threshold screening on model basic data according to the conventional detection data set, and extracting the model basic data when the matching degree of the model basic data and conventional detection data in the conventional detection data set is smaller than the conventional threshold, so as to acquire an abnormal data set;
step S73: according to the abnormal data in the abnormal data set, carrying out directional measurement on the area where the abnormal data is located, thereby obtaining directional measurement data;
step S74: abnormal data condition matching information is obtained, abnormal information matching is conducted on the directional measurement data according to the abnormal data condition matching information, and an abnormal area is locked, so that an abnormal data information set is obtained.
According to the embodiment, the final three-dimensional space model is subjected to space measurement through the standard proportion, various attribute characteristics of a standard real sample are facilitated, the authenticity and the reliability of data are improved, conventional detection data matching selection of model basic data is facilitated, labeling and identification of an abnormal area are improved, the effectiveness of data generated by a measurement result is improved, the abnormal area is subjected to directional measurement, the accuracy of the data of the abnormal area is ensured, the accuracy of the data measurement is improved, and information matching is performed on abnormal conditions, so that research personnel can intuitively know the abnormality generated by the sample, the workload of research personnel is reduced, and the working efficiency is improved.
In one embodiment of the present specification, step S6 includes the steps of:
and carrying out edge judgment on the abnormal data information in the abnormal data information set according to a preset abnormal edge judgment formula, so as to obtain abnormal region edge information, and marking the abnormal region edge information to the final three-dimensional space model, so as to generate a measurement result space model.
According to the method, the device and the system, the abnormal data information is subjected to edge judgment through the preset abnormal edge judgment formula, the range of the abnormal area can be effectively obtained, the abnormal situation is held, the abnormal area edge information is marked to the final three-dimensional space model, the size and the direction of the abnormal area can be known through cleaning of the research personnel, and the research personnel can quickly find an effective solution.
In one embodiment of the present specification, edge determination is performed on abnormal data information in the abnormal data information set according to a preset abnormal edge determination formula, wherein the preset abnormal edge determination formula is specifically the following calculation formula:
wherein: l is denoted as an abnormal edge determination weight, γ is denoted as a magnetic flux intensity change rate of the measurement magnetic field, α is denoted as a magnetic flux penetration weight of a sample property of the abnormal region, β is denoted as a magnetic flux penetration weight of the measurement sample property, σ is denoted as a magnetic flux penetration weight in air, and μ is denoted as a deviation adjustment term.
In this embodiment, calculateAbnormal edge determination formula of abnormal edge determination weight L is performed by using magnetic flux penetration weight alpha of sample property of abnormal region and magnetic flux penetration weight beta of measured sample property by measuring magnetic flux intensity change rate gamma of magnetic fieldCalculating, wherein the influence of different objects on the magnetic field is different from the influence of the magnetic field on different material properties, so that the edge of the object is divided into different weights, the edge division precision of an abnormal region is improved by fully considering various conditions, and the magnetic flux penetration weight beta of the measured sample property and the magnetic flux penetration weight sigma in the air are used for->And calculating, thereby reducing the deviation value.
In one embodiment of the present specification, a magnetic variable measurement system for a nuclear magnetic resonance apparatus includes:
a processor, and
at least one memory electrically connected to the processor, wherein a computer program is stored in the memory, and the computer program is used for executing the magnetic variable measurement method for nuclear magnetic resonance apparatus according to any one of claims 1-9.
According to the embodiment, the measurement accuracy of the nuclear magnetic resonance apparatus is improved through the combination of software and hardware, a series of data obtained through measurement is processed in multiple directions, information hidden behind the data is further mined, the measurement accuracy and range are improved, research personnel can fully know information of all aspects of a sample, and a solid data base is provided for research and development.
Drawings
FIG. 1 is a schematic flow chart of a method and system for measuring magnetic variables for nuclear magnetic resonance apparatus according to the present application;
FIG. 2 is a detailed flowchart illustrating the implementation of step S1 in FIG. 1;
FIG. 3 is a detailed flowchart illustrating the implementation of step S2 in FIG. 1;
FIG. 4 is a detailed flowchart illustrating the implementation of step S5 in FIG. 1;
the achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides a magnetic variable measuring method and system for a nuclear magnetic resonance spectrometer. The execution subject of the magnetic variable measurement method for nuclear magnetic resonance apparatus includes, but is not limited to, a console, a single server, a server cluster, a cloud server, or a cloud server cluster, etc., which can use the system of the present application.
Step S1: acquiring a magnetic flux conventional signal set of a nuclear magnetic resonance instrument, performing image editing on the magnetic flux conventional signal set and performing spatial ordering, thereby acquiring a conventional magnetic flux atlas;
step S2: acquiring a magnetic flux detection signal set, performing image editing on the magnetic flux detection signal set to acquire a detection magnetic flux atlas, and performing special area identification and screening on the detection magnetic flux atlas according to a conventional magnetic flux atlas to acquire a magnetic flux change atlas;
Step S3: performing spectrum conversion on the magnetic flux change atlas to generate a magnetic variable waveform atlas, and performing spatial integration on the magnetic variable waveform atlas to obtain a waveform atlas spatial set;
step S4: performing space modeling according to the waveform map space set so as to generate an initial three-dimensional space model; then, constructing fixed-point coordinates of the initial three-dimensional space model, so as to obtain a final three-dimensional space model;
step S5: directional measurement is carried out on the final three-dimensional space model, so that directional measurement data are obtained, and locking is carried out on the directional measurement data, so that an abnormal data information set is obtained;
step S6: marking the abnormal data information in the abnormal data information set to the final three-dimensional space model, so as to generate a measurement result space model;
step S7: and carrying out measurement result statistics on the abnormal data information set so as to generate measurement result data, integrating the measurement result space model with the measurement result data, and marking the measurement result space model as a magnetic variable measurement result.
According to the embodiment, the situation that errors are increased due to environmental changes can be reduced when the sample is measured, the measurement accuracy of the sample is improved, the harsh conditions of the nuclear magnetic resonance apparatus on an operation site can be reduced by measuring the current environment, the application range of the nuclear magnetic resonance apparatus is improved, information is conveniently checked, extracted and analyzed by converting signals into images, the processing capacity of the data is enhanced, related noise data and invalid data are removed by primarily screening the conventional magnetic flux diagram concentrated by the conventional magnetic flux diagram and the detection magnetic flux diagram concentrated by the detection magnetic flux diagram, the data amount of subsequent processing is reduced, the processing capacity of the system on the data, the processing speed and the measurement accuracy of magnetic variables are improved, the information contained in the sample can be further analyzed by converting the map, the three-dimensional space model is established, the research of the appearance characteristics of the sample is facilitated, the information contained in different areas of the sample is facilitated, the different information of different areas of the sample can be intuitively embodied, and the representing capacity of the information is improved.
In the embodiment of the present invention, as described with reference to fig. 1, a schematic flow chart of steps of a magnetic variable measurement method and system for a nuclear magnetic resonance apparatus according to the present invention is provided, where in the present embodiment, the magnetic variable measurement method for a nuclear magnetic resonance apparatus includes:
step S1: acquiring a magnetic flux conventional signal set of a nuclear magnetic resonance instrument, performing image editing on the magnetic flux conventional signal set and performing spatial ordering, thereby acquiring a conventional magnetic flux atlas;
in the embodiment of the invention, the magnetic flux normal signal set of the nmr refers to a magnetic flux normal signal set which is tested in the current environment before the sample is measured, and the image editing and the spatial ordering of the magnetic flux normal signal set refer to the situation that the magnetic field is uniformly distributed in the current environment and can be tested according to the sequence of the space and the time of the received magnetic flux tested in the current environment by the nmr.
Step S2: acquiring a magnetic flux detection signal set, performing image editing on the magnetic flux detection signal set to acquire a detection magnetic flux atlas, and performing special area identification and screening on the detection magnetic flux atlas according to a conventional magnetic flux atlas to acquire a magnetic flux change atlas;
In the embodiment of the invention, the magnetic flux detection signal set refers to the condition of magnetic field signals for measuring a sample, and the special area identification and screening of the detection magnetic flux atlas according to the conventional magnetic flux atlas refers to the fact that different areas formed by measurement under the same spatial position are represented as special areas, and the areas are areas where the magnetic field changes due to the fact that the measuring environment or the field is added into the sample under the same condition, and the areas are also areas where the sample is located, and the workload of measuring and researching the sample can be effectively reduced by screening the magnetic field signals of the areas.
Step S3: performing spectrum conversion on the magnetic flux change atlas to generate a magnetic variable waveform atlas, and performing spatial integration on the magnetic variable waveform atlas to obtain a waveform atlas spatial set;
in the embodiment of the invention, the spectrum conversion of the magnetic flux change atlas refers to the spectrum conversion of the magnetic flux change atlas through an information conversion model obtained by deep learning, so that the properties and characteristics contained in the sample can be further known by changing different angles, the spatial integration of the magnetic variable waveform atlas refers to the spatial ordering of the magnetic variable waveform atlas according to the time sequence and the spatial time sequence of magnetic flux detection signals, and then the stacking combination is performed, so that the discrete magnetic variable waveform atlas is changed into a set with a certain spatial rule.
Step S4: performing space modeling according to the waveform map space set so as to generate an initial three-dimensional space model; then, constructing fixed-point coordinates of the initial three-dimensional space model, so as to obtain a final three-dimensional space model;
in the embodiment of the invention, the spatial modeling of the waveform spectrum space set refers to the construction of a preliminary spatial model of a sample according to the characteristics of the waveform spectrum, the construction of the fixed-point coordinates of the initial three-dimensional spatial model refers to the selection of a point as an initial coordinate zero point of a spatial rectangular coordinate system in the initial three-dimensional spatial model, and the horizontal and vertical extension is performed according to the initial coordinate zero point, so that the spatial rectangular coordinate system is established.
Step S5: directional measurement is carried out on the final three-dimensional space model, so that directional measurement data are obtained, and locking is carried out on the directional measurement data, so that an abnormal data information set is obtained;
in the embodiment of the invention, the directional measurement of the final three-dimensional space model refers to the measurement mode performed according to the measurement direction and the measurement target set according to the requirement of the sample, the locking of the directional measurement data refers to the reference of the identified abnormal region according to the basic information or the qualified information of the sample, and the locking and marking of the identified abnormal region are performed so as to avoid the occurrence of the identification loss condition of the region.
Step S6: marking the abnormal data information in the abnormal data information set to the final three-dimensional space model, so as to generate a measurement result space model;
in the embodiment of the invention, the marking of the abnormal data information in the abnormal data information set to the final three-dimensional space model refers to the detailed description and display of the data information and the azimuth expressed by the data.
Step S7: counting the measurement results of the abnormal data information set so as to generate measurement result data, integrating the measurement result space model with the measurement result data, and marking the measurement result space model as a magnetic variable measurement result;
in the embodiment of the invention, the counting of the measurement result of the abnormal data information set means that because too much data information cannot be displayed in the measurement result space model, more detailed and accurate information is required to be counted and arranged again, so that the display and the viewing of the data are facilitated.
In one embodiment of the present specification, step S1 includes the steps of:
step S21: transmitting a first intensity signal to the surrounding environment for preliminary detection, and receiving the first intensity signal so as to obtain a magnetic flux conventional signal set of the nuclear magnetic resonance instrument;
step S22: performing image conversion on the magnetic flux normal signals in the magnetic flux normal signal set through the magnetic flux signal image conversion model obtained through deep learning, so as to obtain a discrete magnetic flux image set;
Step S23: acquiring a detection spatial sequence, and performing spatial sequence ordering on the discrete magnetic flux images in the discrete magnetic flux image set according to the detection spatial sequence, so as to acquire a sequential magnetic flux image set;
step S24: sequential magnetic flux images in the sequential magnetic flux image set are sequentially encoded to obtain an image code, and the image code is marked into the sequential magnetic flux image to obtain a conventional magnetic flux image set.
According to the embodiment, the first intensity signal is transmitted to the environment, so that the interference layer degree of the interference magnetic field of the surrounding environment to the experimental field is detected conveniently, the nuclear magnetic resonance instrument can transmit a proper opposite magnetic field to offset larger interference, interference to the experiment is reduced, the current magnetic field condition is analyzed, the current measured conventional magnetic flux atlas is used as a model to screen the follow-up detection magnetic flux atlas, and the interference of the weak magnetic field to the current field can be reduced.
In the embodiment of the present invention, as described with reference to fig. 2, a detailed step flow diagram of step S2 in fig. 1 is shown, and in this example, the method includes the following steps:
step S21: transmitting a first intensity signal to the surrounding environment for preliminary detection, and receiving the first intensity signal so as to obtain a magnetic flux conventional signal set of the nuclear magnetic resonance instrument;
In the embodiment of the invention, the primary detection of transmitting the first intensity signal to the surrounding environment means that the environment is measured before the sample is measured, so that the detection of the external magnetic field interfered in the current environment is facilitated, and the arrangement of the opposite magnetic field for balancing the interference of the external magnetic field is facilitated;
the setting of the first intensity signal can be set independently according to the measurement condition of the sample to be detected and the current environment.
Step S22: performing image conversion on the magnetic flux normal signals in the magnetic flux normal signal set through the magnetic flux signal image conversion model obtained through deep learning, so as to obtain a discrete magnetic flux image set;
in the embodiment of the invention, the magnetic flux signal image conversion model obtained through deep learning is that a basic image recognition model and a basic image conversion model are established, a mass magnetic flux signal image is provided for training the basic image recognition model and the basic image conversion model, when the recognition and conversion deviation of the two models reaches the standard error range, the two models accord with corresponding work at present, the two models are integrated and packaged into a whole, and the Torons test is performed to ensure the packaging qualification, so that the magnetic flux signal image conversion model is formed.
Step S23: acquiring a detection spatial sequence, and performing spatial sequence ordering on the discrete magnetic flux images in the discrete magnetic flux image set according to the detection spatial sequence, so as to acquire a sequential magnetic flux image set;
in the embodiment of the present invention, the detection spatial sequence refers to that a detection sequence of the nuclear magnetic resonance apparatus in a detection process includes a temporal sequence and a spatial sequence.
Step S24: sequentially encoding sequential magnetic flux images in the sequential magnetic flux image set to obtain an image code, and marking the image code into the sequential magnetic flux image to obtain a conventional magnetic flux image set;
in the embodiment of the invention, the sequential magnetic flux images concentrated in the sequential magnetic flux images are sequentially encoded, namely, the unique identification codes of the images are edited according to the image information, the sequential information of the images and the content characteristic information of the images are contained, the image encoding and the sequential magnetic flux images are in one-to-one correspondence, and the possibility of the same exists.
In one embodiment of the present specification, step S2 includes the steps of:
step S31: the first detection transmits a first intensity signal to the surrounding environment for early detection, and receives the first intensity signal, so as to obtain a first detection signal set;
Step S32: the second detection transmits a second intensity signal to the surrounding environment for medium-term detection, and receives the second intensity signal, so that a second detection signal set is obtained;
step S33: transmitting a third intensity signal to the surrounding environment for post detection and receiving the third intensity signal, thereby obtaining a third detection signal set;
step S34: the first detection signal set, the second detection signal set and the third detection signal set are whipped and integrated, so that a magnetic flux detection signal set is obtained, wherein the magnetic field intensity of the first-intensity signal is larger than that of the second-intensity signal, and the magnetic field intensity of the second-intensity signal is larger than that of the third-intensity signal;
step S35: performing image conversion on the magnetic flux detection signals in the magnetic flux detection signal set by the magnetic flux signal image conversion model obtained by deep learning, thereby obtaining a detection magnetic flux atlas;
step S36: matching the detected magnetic flux patterns in the detected magnetic flux patterns according to the conventional magnetic flux patterns, and summarizing the detected magnetic flux patterns with the matching smaller than a detection threshold value, so as to obtain a screening magnetic flux pattern set;
Step S37: classifying and marking the magnetic field intensity of the screened magnetic flux patterns in the screened magnetic flux patterns, so as to obtain classified magnetic flux patterns, convolutionally identifying the classified magnetic flux patterns in the classified magnetic flux patterns through regional matching convolution check of image matching degree, and extracting a special region, so that a magnetic flux change pattern is obtained.
According to the embodiment, the three signals with different intensities are used for measuring the sample, the characteristics of the appearance of the sample under the magnetic fields with different intensities are fully mined, the information extraction of the sample is improved, the three different detection signal sets are integrated, the information error caused by the error in the processing process is improved, the measurement accuracy of the nuclear magnetic resonance spectrometer is further improved, and the artificial intelligence is added to process the data to realize the powerful hardware and the powerful software data processing.
In the embodiment of the present invention, as described with reference to fig. 3, a detailed step flow diagram of step S3 in fig. 1 is shown, and in this example, the method includes the following steps:
step S31: the first detection transmits a first intensity signal to the surrounding environment for early detection, and receives the first intensity signal, so as to obtain a first detection signal set;
In the embodiment of the invention, the first detection of transmitting the first intensity signal to the surrounding environment for early detection refers to the intensity signal with consistent magnetic field intensity used when the surrounding environment is detected, and is a control group which is set for referring to the situation of the magnetic field when a sample exists and the situation of the magnetic field when the sample does not exist;
the setting of the first intensity signal can be set independently according to the measurement condition of the sample to be detected and the current environment.
Step S32: the second detection transmits a second intensity signal to the surrounding environment for medium-term detection, and receives the second intensity signal, so that a second detection signal set is obtained;
in the embodiment of the invention, the second detection of transmitting the second intensity signal to the surrounding environment for the middle detection refers to the signal intensity set according to the content of the sample to be measured and the material of the sample;
the setting of the second intensity signal can be set independently according to the measurement condition of the sample to be detected and the current environment.
Step S33: transmitting a third intensity signal to the surrounding environment for post detection and receiving the third intensity signal, thereby obtaining a third detection signal set;
In the embodiment of the invention, the third detection step of transmitting a third intensity signal to the surrounding environment for post detection refers to signal intensity set according to the content of the sample to be measured and the material of the sample;
the setting of the third intensity signal can be set autonomously according to the measurement condition of the sample to be detected and the current environment.
Step S34: performing whipping and integration on the first detection signal set, the second detection signal set and the third detection signal set, so as to obtain a magnetic flux detection signal set;
in the embodiment of the invention, the whipping and integration of the first detection signal set, the second detection signal set and the third detection signal set means that the whipping is performed according to the basis of the magnetic field intensity and the time-space sequence, and all results are integrated into a set, so that the subsequent unified processing of data is facilitated.
Step S35: performing image conversion on the magnetic flux detection signals in the magnetic flux detection signal set by the magnetic flux signal image conversion model obtained by deep learning, thereby obtaining a detection magnetic flux atlas;
in the embodiment of the invention, the magnetic flux signal image conversion model obtained through deep learning is that a basic image recognition model and a basic image conversion model are established, a mass magnetic flux signal image is provided for training the basic image recognition model and the basic image conversion model, when the recognition and conversion deviation of the two models reaches the standard error range, the two models accord with corresponding work at present, the two models are integrated and packaged into a whole, and the Torons test is performed to ensure the packaging qualification, so that the magnetic flux signal image conversion model is formed.
Step S36: matching the detected magnetic flux patterns in the detected magnetic flux patterns according to the conventional magnetic flux patterns, and summarizing the detected magnetic flux patterns with the matching smaller than a detection threshold value, so as to obtain a screening magnetic flux pattern set;
in the embodiment of the invention, the matching of the detected magnetic flux patterns in the detected magnetic flux patterns according to the conventional magnetic flux pattern set means that two groups of images are matched according to a trained deep-learning image matching model, so that the detected magnetic flux patterns which do not match with each other are obtained;
the detection threshold is a matching pair threshold of a deep-learning image matching model, and artificial dryness can be performed to improve the application range of the model.
Step S37: classifying and marking the magnetic field intensity of the screening magnetic flux patterns in the screening magnetic flux patterns, so as to obtain a classified magnetic flux pattern set, carrying out convolution identification on the classified magnetic flux patterns in the classified magnetic flux pattern set through region matching convolution check of image matching degree, and carrying out special region extraction, so as to obtain a magnetic flux change pattern set;
in the embodiment of the invention, the classifying and marking of the magnetic field intensity of the screening magnetic flux patterns means that the marking information of the screening magnetic flux patterns is further iterated and the screening magnetic flux patterns obtained under the condition of different intensities in the same time and space can be distinguished by classifying according to the magnetic field intensity from the new marking.
In one embodiment of the present specification, step S3 includes the steps of:
performing spectrum conversion on the magnetic flux change atlas, thereby generating a magnetic variable waveform atlas;
classifying magnetic field intensity of the magnetic variable waveform atlas, so as to obtain a first intensity magnetic variable waveform atlas, a second intensity magnetic variable waveform atlas and a third intensity magnetic variable waveform atlas;
and respectively carrying out space integration on the first intensity magnetic variable waveform spectrum set, the second intensity magnetic variable waveform spectrum set and the third intensity magnetic variable waveform spectrum set, so as to obtain a first intensity waveform spectrum space set, and uniformly marking and integrating the second intensity waveform spectrum space set and the third intensity waveform spectrum space set into the waveform spectrum space set.
According to the embodiment, through carrying out the wave conversion on the magnetic flux change atlas, the internal structure of the sample and the form and composition of the substance can be displayed more intuitively, so that the display of the sample measurement information is improved, the magnetic variable waveform patterns detected by the magnetic fields with different intensities are classified and spatially integrated, three groups of sample waveform patterns under the condition of different intensities are formed, the integration of the subsequent sample information and the error reduction are facilitated, and the measurement precision of the sample is further improved.
In the embodiment of the invention, the spectrum conversion of the magnetic flux change atlas refers to the spectrum conversion of the magnetic flux change atlas through an information conversion model obtained by deep learning, so that the properties and characteristics contained in the sample can be further known by changing different angles, the spatial integration of the magnetic variable waveform atlas refers to the spatial ordering of the magnetic variable waveform atlas according to the time sequence and the spatial time sequence of magnetic flux detection signals, and then the stacking combination is performed, so that the discrete magnetic variable waveform atlas is changed into a set with a certain spatial rule.
In one embodiment of the present specification, step S4 includes the steps of:
acquiring a waveform map mapping color data set, performing color mapping on waveform maps in a waveform map space set according to the waveform map mapping color data set, so as to obtain color maps, classifying according to marked magnetic field intensity, and performing space stacking according to the space sequence in the waveform map space set, so as to obtain three color stacking three-dimensional models;
fusing the three color stacking three-dimensional models according to a preset fusion denoising algorithm, so as to obtain a color three-dimensional space model;
And reconstructing the virtual space model of the color three-dimensional space model to obtain an initial three-dimensional space model, and constructing fixed-point coordinates of the initial three-dimensional space model to obtain a final three-dimensional space model.
According to the embodiment, the color mapping is carried out through the color information degree waveform patterns corresponding to various types of information, so that the internal structure composition of a sample can be intuitively displayed, the software can conveniently identify the information on the waveform patterns, a preliminary three-dimensional model is formed by stacking the color patterns, the three-dimensional model formed by stacking the color patterns obtained by measuring different magnetic field intensities is fused, the purpose of noise reduction is achieved, the initial three-dimensional model is formed by reconstructing the virtual space model of the color three-dimensional model, the more ideal and more intuitive space model is provided for research personnel according to the actual situation, the coordinate construction is carried out on the initial three-dimensional model, the information on the model is conveniently positioned, and the observation and locking of a demand area and information display are facilitated.
In the embodiment of the invention, the waveform map color data set refers to rendering different colors of waveform information under different conditions, wherein one color corresponds to one waveform information only, a set formed by color information corresponding to all waveforms is called a waveform map color data set, the color mapping of the waveform map in the waveform map space refers to coloring the waveform map according to the corresponding relation between the colors in the waveform map color data set and the waveforms, the spatial stacking through the spatial sequence in the waveform map space refers to stacking the waveform map according to the spatial relation to form a shape similar to a spatial three-dimensional model, the fusion of three color stacked three-dimensional models according to a preset fusion denoising algorithm refers to extracting information of the three color stacked three-dimensional models, and then fusing the obtained information to form the color three-dimensional space model, the fixed point coordinate construction of the initial three-dimensional space model refers to the selection of one point as an initial coordinate zero point of a space rectangular coordinate system, and the horizontal and vertical extension according to the initial coordinate zero point to establish the space rectangular coordinate system.
In one embodiment of the present disclosure, three color stacked three-dimensional models are fused according to a preset fusion denoising algorithm, where a fusion denoising calculation formula of the preset fusion denoising algorithm is specifically the following calculation formula:
wherein K is denoted as a noise reduction fusion parameter, t is denoted as a time of one intensity measurement of nuclear magnetic resonance, a is denoted as a magnetic field intensity of the first intensity signal, b is denoted as a magnetic field intensity of the second intensity signal, c is denoted as a magnetic field intensity of the third intensity signal, θ is denoted as an opposite impact interference magnetic field intensity, β is denoted as a magnetic flux penetration weight of the measured sample property, and g is denoted as a bias adjustment term.
In this embodiment, a fusion denoising calculation formula for calculating a denoising fusion parameter K is used to calculate a comparison between the magnetic field intensities of a first intensity signal, a second intensity signal, and a third intensity signal using the magnetic field intensity a, b, and cThe relation between the magnetic field intensity and the generated noise point are calculated and analyzed, the influence of the magnetic fields with different intensities on the sample measurement data is fully considered, the interference of external conditions on the sample measurement result is reduced, and the magnetic field intensity theta of opposite impact interference and the magnetic flux penetration weight beta of the measured sample attribute are utilized to pass >And performing calculation so as to further reduce the magnetic field interference of the external magnetic field to the current environment.
In one embodiment of the present specification, step S5 includes the steps of:
step S71: obtaining standard proportion, and performing space measurement on the final three-dimensional space model according to the standard proportion so as to generate model basic data;
step S72: acquiring a conventional detection data set, performing conventional threshold screening on model basic data according to the conventional detection data set, and extracting the model basic data when the matching degree of the model basic data and conventional detection data in the conventional detection data set is smaller than the conventional threshold, so as to acquire an abnormal data set;
step S73: according to the abnormal data in the abnormal data set, carrying out directional measurement on the area where the abnormal data is located, thereby obtaining directional measurement data;
step S74: abnormal data condition matching information is obtained, abnormal information matching is conducted on the directional measurement data according to the abnormal data condition matching information, and an abnormal area is locked, so that an abnormal data information set is obtained.
According to the embodiment, the final three-dimensional space model is subjected to space measurement through the standard proportion, various attribute characteristics of a standard real sample are facilitated, the authenticity and the reliability of data are improved, conventional detection data matching selection of model basic data is facilitated, labeling and identification of an abnormal area are improved, the effectiveness of data generated by a measurement result is improved, the abnormal area is subjected to directional measurement, the accuracy of the data of the abnormal area is ensured, the accuracy of the data measurement is improved, and information matching is performed on abnormal conditions, so that research personnel can intuitively know the abnormality generated by the sample, the workload of research personnel is reduced, and the working efficiency is improved.
In the embodiment of the present invention, as described with reference to fig. 4, a detailed step flow diagram of step S5 in fig. 1 is shown, and in this example, the method includes the following steps:
step S71: obtaining standard proportion, and performing space measurement on the final three-dimensional space model according to the standard proportion so as to generate model basic data;
in the embodiment of the invention, the standard proportion refers to the ratio of the three-dimensional space model to reality, and the spatial measurement of the final three-dimensional space model according to the standard proportion refers to the expansion or reduction of the measured data according to the standard proportion, so that the measured data has more authenticity.
Step S72: acquiring a conventional detection data set, performing conventional threshold screening on model basic data according to the conventional detection data set, and extracting the model basic data when the matching degree of the model basic data and conventional detection data in the conventional detection data set is smaller than the conventional threshold, so as to acquire an abnormal data set;
in the embodiment of the invention, the conventional detection data set refers to a set of all ideal data or qualified data areas of a sample, and the conventional threshold value screening of the model basic data refers to screening of data information which does not meet the specification or requirement in the sample;
The conventional threshold value is a data information matching dividing line which is obtained through deep learning and meets the requirement under the line most, manual intervention can be performed, and the numerical value of the conventional threshold value is set, so that the application scene of the conventional threshold value is improved.
Step S73: according to the abnormal data in the abnormal data set, carrying out directional measurement on the area where the abnormal data is located, thereby obtaining directional measurement data;
in the embodiment of the present invention, the directional measurement of the area where the abnormal data is located refers to directional measurement of abnormal information of the area where the abnormal information exists.
Step S74: acquiring abnormal data condition matching information, carrying out abnormal information matching on the directional measurement data according to the abnormal data condition matching information, and locking an abnormal region, thereby acquiring an abnormal data information set;
in the embodiment of the invention, the abnormal data condition matching information refers to information data sets which are obtained by summarizing abnormal conditions according to historical accumulation and match the abnormal information with the abnormal conditions and are used for screening possible abnormal conditions of the current previous abnormal information, so that an improved reference is provided for research personnel.
In one embodiment of the present specification, step S6 includes the steps of:
and carrying out edge judgment on the abnormal data information in the abnormal data information set according to a preset abnormal edge judgment formula, so as to obtain abnormal region edge information, and marking the abnormal region edge information to the final three-dimensional space model, so as to generate a measurement result space model.
According to the method, the device and the system, the abnormal data information is subjected to edge judgment through the preset abnormal edge judgment formula, the range of the abnormal area can be effectively obtained, the abnormal situation is held, the abnormal area edge information is marked to the final three-dimensional space model, the size and the direction of the abnormal area can be known through cleaning of the research personnel, and the research personnel can quickly find an effective solution.
In the embodiment of the invention, the edge judgment of the abnormal data information in the abnormal data information set refers to the judgment of the edge information through the abnormal edge judgment weight, and the abnormal area and the normal area are sequentially segmented so as to facilitate the observation and study of the abnormal area by a research and development personnel, and the marking of the abnormal area edge information to the final three-dimensional space model refers to the marking of the abnormal area edge information on the final three-dimensional space model.
In one embodiment of the present specification, edge determination is performed on abnormal data information in the abnormal data information set according to a preset abnormal edge determination formula, wherein the preset abnormal edge determination formula is specifically the following calculation formula:
/>
wherein: l is denoted as an abnormal edge determination weight, γ is denoted as a magnetic flux intensity change rate of the measurement magnetic field, α is denoted as a magnetic flux penetration weight of a sample property of the abnormal region, β is denoted as a magnetic flux penetration weight of the measurement sample property, σ is denoted as a magnetic flux penetration weight in air, and μ is denoted as a deviation adjustment term.
In the present embodiment, an abnormal edge determination formula for calculating an abnormal edge determination weight L is calculated by using the magnetic flux intensity change rate gamma of the measured magnetic field, the magnetic flux penetration weight alpha of the sample property of the abnormal region and the magnetic flux penetration weight beta of the measured sample propertyCalculating, wherein the influence of different objects on the magnetic field is different from the influence of the magnetic field on different material properties, so that the edge of the object is divided into different weights, the edge division precision of an abnormal region is improved by fully considering various conditions, and the magnetic flux penetration weight beta of the measured sample property and the magnetic flux penetration weight sigma in the air are used for- >And calculating, thereby reducing the deviation value.
In one embodiment of the present specification, a magnetic variable measurement system for a nuclear magnetic resonance apparatus, the system comprising:
a processor, and
at least one memory electrically connected to the processor, wherein the memory stores a computer program for executing the magnetic variable measurement method for nuclear magnetic resonance apparatus according to any one of the above.
According to the embodiment, the measurement accuracy of the nuclear magnetic resonance apparatus is improved through the combination of software and hardware, a series of data obtained through measurement is processed in multiple directions, information hidden behind the data is further mined, the measurement accuracy and range are improved, research personnel can fully know information of all aspects of a sample, and a solid data base is provided for research and development.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. The magnetic variable measuring method for the nuclear magnetic resonance apparatus is characterized by comprising the following steps:
step S1: acquiring a magnetic flux conventional signal set of a nuclear magnetic resonance instrument, performing image editing on the magnetic flux conventional signal set and performing spatial ordering, thereby acquiring a conventional magnetic flux atlas;
step S2: acquiring a magnetic flux detection signal set, performing image editing on the magnetic flux detection signal set to acquire a detection magnetic flux atlas, and performing special area identification and screening on the detection magnetic flux atlas according to a conventional magnetic flux atlas to acquire a magnetic flux change atlas;
step S3: performing spectrum conversion on the magnetic flux change atlas to generate a magnetic variable waveform atlas, and performing spatial integration on the magnetic variable waveform atlas to obtain a waveform atlas spatial set;
step S4: performing space modeling according to the waveform map space set so as to generate an initial three-dimensional space model; then, constructing fixed-point coordinates of the initial three-dimensional space model, so as to obtain a final three-dimensional space model;
step S5: directional measurement is carried out on the final three-dimensional space model, so that directional measurement data are obtained, and locking is carried out on the directional measurement data, so that an abnormal data information set is obtained;
Step S6: marking the abnormal data information in the abnormal data information set to the final three-dimensional space model, so as to generate a measurement result space model;
step S7: counting the measurement results of the abnormal data information set so as to generate measurement result data, integrating the measurement result space model with the measurement result data, and marking the measurement result space model as a magnetic variable measurement result;
step S2 comprises the steps of:
step S31: the first detection transmits a first intensity signal to the surrounding environment for early detection, and receives the first intensity signal, so as to obtain a first detection signal set;
step S32: the second detection transmits a second intensity signal to the surrounding environment for medium-term detection, and receives the second intensity signal, so that a second detection signal set is obtained;
step S33: transmitting a third intensity signal to the surrounding environment for post detection and receiving the third intensity signal, thereby obtaining a third detection signal set;
step S34: the first detection signal set, the second detection signal set and the third detection signal set are whipped and integrated, so that a magnetic flux detection signal set is obtained, wherein the magnetic field intensity of the first-intensity signal is larger than that of the second-intensity signal, and the magnetic field intensity of the second-intensity signal is larger than that of the third-intensity signal;
Step S35: performing image conversion on the magnetic flux detection signals in the magnetic flux detection signal set by the magnetic flux signal image conversion model obtained by deep learning, thereby obtaining a detection magnetic flux atlas;
step S36: matching the detected magnetic flux patterns in the detected magnetic flux patterns according to the conventional magnetic flux patterns, and summarizing the detected magnetic flux patterns with the matching smaller than a detection threshold value, so as to obtain a screening magnetic flux pattern set;
step S37: classifying and marking the magnetic field intensity of the screened magnetic flux patterns in the screened magnetic flux patterns, so as to obtain classified magnetic flux patterns, convolutionally identifying the classified magnetic flux patterns in the classified magnetic flux patterns through regional matching convolution check of image matching degree, and extracting a special region, so that a magnetic flux change pattern is obtained.
2. The method of measuring a magnetic variable for a nuclear magnetic resonance apparatus according to claim 1, wherein the step S1 comprises the steps of:
step S21: transmitting a first intensity signal to the surrounding environment for preliminary detection, and receiving the first intensity signal so as to obtain a magnetic flux conventional signal set of the nuclear magnetic resonance instrument;
step S22: performing image conversion on the magnetic flux normal signals in the magnetic flux normal signal set through the magnetic flux signal image conversion model obtained through deep learning, so as to obtain a discrete magnetic flux image set;
Step S23: acquiring a detection spatial sequence, and performing spatial sequence ordering on the discrete magnetic flux images in the discrete magnetic flux image set according to the detection spatial sequence, so as to acquire a sequential magnetic flux image set;
step S24: sequential magnetic flux images in the sequential magnetic flux image set are sequentially encoded to obtain an image code, and the image code is marked into the sequential magnetic flux image to obtain a conventional magnetic flux image set.
3. The method of measuring a magnetic variable for a nuclear magnetic resonance apparatus according to claim 1, wherein the step S3 comprises the steps of:
performing spectrum conversion on the magnetic flux change atlas, thereby generating a magnetic variable waveform atlas;
classifying magnetic field intensity of the magnetic variable waveform atlas, so as to obtain a first intensity magnetic variable waveform atlas, a second intensity magnetic variable waveform atlas and a third intensity magnetic variable waveform atlas;
and respectively carrying out space integration on the first intensity magnetic variable waveform spectrum set, the second intensity magnetic variable waveform spectrum set and the third intensity magnetic variable waveform spectrum set, so as to obtain a first intensity waveform spectrum space set, and uniformly marking and integrating the second intensity waveform spectrum space set and the third intensity waveform spectrum space set into the waveform spectrum space set.
4. The method of measuring a magnetic variable for a nuclear magnetic resonance apparatus according to claim 1, wherein the step S4 comprises the steps of:
acquiring a waveform map mapping color data set, performing color mapping on waveform maps in a waveform map space set according to the waveform map mapping color data set, so as to obtain color maps, classifying according to marked magnetic field intensity, and performing space stacking according to the space sequence in the waveform map space set, so as to obtain three color stacking three-dimensional models;
fusing the three color stacking three-dimensional models according to a preset fusion denoising algorithm, so as to obtain a color three-dimensional space model;
and reconstructing the virtual space model of the color three-dimensional space model to obtain an initial three-dimensional space model, and constructing fixed-point coordinates of the initial three-dimensional space model to obtain a final three-dimensional space model.
5. The method for measuring magnetic variables for nuclear magnetic resonance apparatus according to claim 4, wherein the three color stack three-dimensional models are fused according to a preset fusion denoising algorithm, wherein the fusion denoising calculation formula of the preset fusion denoising algorithm is specifically the following calculation formula:
wherein K is expressed as a noise reduction fusion parameter, < > >Time expressed as one intensity measurement of nuclear magnetic resonance, +.>Magnetic field strength, denoted first strength signal, ">Magnetic field strength, denoted second strength signal, ">Magnetic field strength, denoted third intensity signal, ">Represented asOpposite impact interference magnetic field intensity->Magnetic flux penetration weight expressed as a property of the measured sample,/->Represented as a bias adjustment term.
6. The method of measuring a magnetic variable for a nuclear magnetic resonance apparatus according to claim 1, wherein the step S5 comprises the steps of:
step S71: obtaining standard proportion, and performing space measurement on the final three-dimensional space model according to the standard proportion so as to generate model basic data;
step S72: acquiring a conventional detection data set, performing conventional threshold screening on model basic data according to the conventional detection data set, and extracting the model basic data when the matching degree of the model basic data and conventional detection data in the conventional detection data set is smaller than the conventional threshold, so as to acquire an abnormal data set;
step S73: according to the abnormal data in the abnormal data set, carrying out directional measurement on the area where the abnormal data is located, thereby obtaining directional measurement data;
step S74: abnormal data condition matching information is obtained, abnormal information matching is conducted on the directional measurement data according to the abnormal data condition matching information, and an abnormal area is locked, so that an abnormal data information set is obtained.
7. The method of measuring a magnetic variable for a nuclear magnetic resonance apparatus according to claim 1, wherein the step S6 comprises the steps of:
and carrying out edge judgment on the abnormal data information in the abnormal data information set according to a preset abnormal edge judgment formula, so as to obtain abnormal region edge information, and marking the abnormal region edge information to the final three-dimensional space model, so as to generate a measurement result space model.
8. The method according to claim 7, wherein the edge determination is performed on the abnormal data information in the abnormal data information set according to a preset abnormal edge determination formula, wherein the preset abnormal edge determination formula is specifically the following calculation formula:
wherein: />Expressed as abnormal edge decision weight, +.>Expressed as the rate of change of the magnetic flux strength of the measuring magnetic field,/->Magnetic flux penetration weight of sample property expressed as abnormal region, +.>Magnetic flux penetration weight expressed as a property of the measured sample,/->Expressed as the flux penetration weight in air, < >>Represented as a bias adjustment term.
9. A magnetic variable measurement system for a nuclear magnetic resonance apparatus, comprising:
a processor, and
At least one memory electrically connected to the processor, wherein a computer program is stored in the memory, and the computer program is used for executing the magnetic variable measurement method for nuclear magnetic resonance apparatus according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310309167.5A CN116297620B (en) | 2023-03-27 | 2023-03-27 | Magnetic variable measurement method and system for nuclear magnetic resonance apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310309167.5A CN116297620B (en) | 2023-03-27 | 2023-03-27 | Magnetic variable measurement method and system for nuclear magnetic resonance apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116297620A CN116297620A (en) | 2023-06-23 |
| CN116297620B true CN116297620B (en) | 2023-09-26 |
Family
ID=86799491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310309167.5A Active CN116297620B (en) | 2023-03-27 | 2023-03-27 | Magnetic variable measurement method and system for nuclear magnetic resonance apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116297620B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4300095A (en) * | 1979-08-22 | 1981-11-10 | Rockwell International Corporation | Self excited saturatable core magnetic field detection apparatus |
| WO1994005964A1 (en) * | 1992-08-28 | 1994-03-17 | Oswald Richard K | A magnetic field position transducer for two or more dimensions |
| JPH07287025A (en) * | 1994-04-18 | 1995-10-31 | Mitsubishi Electric Corp | Magnetic sensor and signal detection plate |
| JP2003334174A (en) * | 2002-05-22 | 2003-11-25 | Hitachi High-Technologies Corp | Biomagnetic field measuring instrument |
| WO2022006917A1 (en) * | 2019-07-05 | 2022-01-13 | 深圳市安测健康信息技术有限公司 | Artificial intelligence-based lung magnetic resonance image recognition apparatus and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008053369A2 (en) * | 2006-08-23 | 2008-05-08 | Bio Aim Technologies Holding Ltd. | Three-dimensional electromagnetic flux field generation |
-
2023
- 2023-03-27 CN CN202310309167.5A patent/CN116297620B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4300095A (en) * | 1979-08-22 | 1981-11-10 | Rockwell International Corporation | Self excited saturatable core magnetic field detection apparatus |
| WO1994005964A1 (en) * | 1992-08-28 | 1994-03-17 | Oswald Richard K | A magnetic field position transducer for two or more dimensions |
| JPH07287025A (en) * | 1994-04-18 | 1995-10-31 | Mitsubishi Electric Corp | Magnetic sensor and signal detection plate |
| JP2003334174A (en) * | 2002-05-22 | 2003-11-25 | Hitachi High-Technologies Corp | Biomagnetic field measuring instrument |
| WO2022006917A1 (en) * | 2019-07-05 | 2022-01-13 | 深圳市安测健康信息技术有限公司 | Artificial intelligence-based lung magnetic resonance image recognition apparatus and method |
Non-Patent Citations (1)
| Title |
|---|
| MRIL-P型核磁共振测井仪探头磁场数值模拟;胡法龙;王成蔚;庄东志;肖立志;;测井技术(第05期);424-427 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116297620A (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110069972A (en) | Automatic detection real world objects | |
| CN109284786B (en) | SAR image terrain classification method for generating countermeasure network based on distribution and structure matching | |
| CN109446925A (en) | A kind of electric device maintenance algorithm based on convolutional neural networks | |
| CN105678076B (en) | The method and device of point cloud measurement data quality evaluation optimization | |
| CN105738915B (en) | Three-dimensional radar measuring method and device | |
| CN108492298A (en) | Based on the multispectral image change detecting method for generating confrontation network | |
| CN104899448B (en) | A kind of self-adapting compensation method of the static localization scheme of Ensemble Kalman Filter | |
| CN105046046B (en) | A kind of Ensemble Kalman Filter localization method | |
| CN108052914A (en) | A kind of forest forest resource investigation method identified based on SLAM and image | |
| CN108959713A (en) | Target range and face positional shift measurement method based on convolutional neural networks | |
| CN105488541A (en) | Natural feature point identification method based on machine learning in augmented reality system | |
| CN108280433B (en) | Identification method and system for gold mine under planting covered area | |
| CN112084860A (en) | Target object detection method and device and thermal power plant detection method and device | |
| Yang et al. | Linking persistent scatterers to the built environment using ray tracing on urban models | |
| CN110941933A (en) | Complex electromagnetic environment fidelity evaluation model and method based on similar theory | |
| Fernandez et al. | Cosmic filaments from cosmic strings | |
| CN116297620B (en) | Magnetic variable measurement method and system for nuclear magnetic resonance apparatus | |
| CN111664867B (en) | Target tracking result evaluation method, device, equipment and storage medium | |
| CN111563532B (en) | Unknown target identification method based on attribute weight fusion | |
| JP2021154935A (en) | Vehicle simulation system, vehicle simulation method and computer program | |
| CN112464513A (en) | RQD based on photogrammetry and RQD inversiontOptimal threshold t solving method | |
| CN115184563B (en) | Chemical workshop field data acquisition method based on digital twinning | |
| CN115883812A (en) | Multi-sensor cooperative station distribution method based on particle swarm optimization | |
| Daudt et al. | Learning to understand earth observation images with weak and unreliable ground truth | |
| CN109993727A (en) | A kind of method for detecting change of remote sensing image based on deep learning |
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 |