1641results about "Analysis using nuclear magnetic resonance" patented technology

A method for material detection is described. The method may include extracting, from a material database, a resonance frequency for the target material. The method may further include comparing an application type to entries in a scan database. The scan database may store pre-defined scanning patterns and corresponding application types. The method may include extracting, from the scan database, a scan sequence for the application type. Also, the method may include instructing a gimbal to follow positions in the scan sequence. The method may also include transmitting into an environment an RF signal when the gimbal is at the positions in the scan sequence. The method may further include receiving a response signal from the environment. The method may include analyzing the response signal for resonance characteristics that indicate a presence of the target material. Additionally, the method may include generating a haptic feedback when the target material is detected.

Embodiments include a system for material detection and identification. The system may include an RF transmit device configured to transmit into an environment an RF signal at a resonance frequency. The system may also include an RF receiver device configured to receive a response signal from the environment. The system may further include a communication device connecting the RF transmit device and the RF receiver device. The communication device may include a control module. The system may include a geolocation device. The control module may be configured to receive geolocation data from the geolocation device, analyze the response signal for resonance characteristics that indicate a presence of a material, and identify the material to a user when the presence of the material is indicated by the resonance characteristics. Methods for material detection and identification are also described. Methods may involve obtaining geolocation data.

The invention discloses a nuclear magnetic T2 spectrum correction method for a shale reservoir, and relates to the field of object detection, and the nuclear magnetic T2 spectrum correction method for the shale reservoir comprises the following steps: 1, determining the gas logging porosity, saturated water porosity and main mineral components of the shale reservoir; compared with the prior art, the method disclosed by the invention has the beneficial effects that a drying-saturated water-centrifugal two-dimensional nuclear magnetic resonance experiment is carried out, and signals of crystal water, clay bound water and hydroxyl in a sample are preliminarily identified; through inversion of organic matter signals in the dry sample, signals of movable water are further determined; the relation between the difference value among the gas logging porosity, the saturated water porosity and the nuclear magnetic porosity and different mineral contents is discussed, and particularly the remarkable influence of iron-containing minerals on the porosity difference value is discussed; by eliminating the influence of diffusion relaxation caused by the magnetic susceptibility difference, the T2 spectrum correction method based on the mineral magnetic susceptibility is established, and the T2 spectrum accuracy obtained through nuclear magnetic resonance measurement is improved.

The invention relates to a metabolic marker for diagnosing diabetic secondary osteoporosis and application of the metabolic marker, and belongs to the technical field of biological medicine. The method comprises the following steps: firstly, screening out obviously different metabolites between osteoporosis (DOP) and osteoporosis-free groups (DM) in diabetic patients; and secondly, screening out significant difference metabolites between the primary osteoporosis patient and the healthy control group, and excluding the intersection of the two groups of difference metabolites to obtain metabolites which exclude the influence of the primary osteoporosis. Metabolic markers, namely cytosine nucleotide, ketoglutaric acid and triethylamine, are obtained through further screening, and when the three metabolic markers are independently used, AUCgt; the AUC during combined use is 0.99, so that the limitation that the sensitivity of the traditional bone mineral density detection on the osteoporosis recognition in the diabetic population is insufficient is effectively made up.

The invention provides a nuclear magnetic resonance and image intelligent bimodal unfrozen water dynamic identification method and system, and belongs to the technical field of frozen soil engineering and geophysical exploration, and the method comprises the steps: sealing a frozen soil sample in a nuclear magnetic sample tube, and achieving the gradient cooling of the sample in a preset low temperature range through temperature control; scanning by using a nuclear magnetic resonance technology to obtain transverse relaxation time T2 spectrums and nuclear magnetic images of the frozen soil sample at different temperature nodes; after image preprocessing is carried out on the nuclear magnetic image, a temperature-signal intensity curve in the nuclear magnetic image is automatically extracted by utilizing an image recognition technology; carrying out integral calculation on a liquid water signal in the T2 spectrum, and dynamically calculating the content of the unfrozen water at each temperature based on a nuclear magnetic signal intensity formula; according to the method, a pore-fracture co-evolution matrix is constructed, accurate analysis of unfrozen water dynamic and pore evolution in the freezing and thawing process is realized, the method is suitable for hydrothermal coupling characteristic analysis of Qinghai-Tibet soil in a complex freezing and thawing environment, and reliable technical support is provided for stability evaluation of frozen soil engineering.

The invention relates to the technical field of rock sample oil-water saturation determination based on a nuclear magnetic technology, and provides a shale sample oil-water saturation intelligent determination method based on a two-dimensional nuclear magnetic technology, and the method comprises the following steps: collecting volumes, echo signals and signal-to-noise ratios of a preset number of rock samples; marking a target rock sample and a comparison rock sample, and determining a volume influence comprehensive interference degree and a noise amplification coefficient of a target echo signal; obtaining a denoised target echo signal according to the target echo signal, the volume of the rock sample corresponding to the target echo signal and the noise amplification coefficient of the echo signal; according to experiments of rock sample two-dimensional nuclear magnetic oil-water distribution, pore attributes and the like, a two-dimensional nuclear magnetic T1-T2 map is divided into an invalid pore area and an effective pore area of a rock sample corresponding to the two-dimensional nuclear magnetic T1-T2 map and an oil-water distribution area of the effective pore area, a fluid close to reservoir oil-water distribution is adopted to recover a two-dimensional nuclear magnetic spectrum of the rock sample, and the oil-water content corresponding to a nuclear magnetic signal is extracted; and obtaining a rock sample oil-water saturation determination result based on the nuclear magnetic technology.

A method for material detection may include extracting, from a material database, a resonance frequency for the target material. The method may further include comparing an application type to entries in a scan database. The scan database may store pre-defined scanning patterns and corresponding application types. The method may include extracting, from the scan database, a scan sequence for the application type. Also, the method may include instructing a gimbal to follow positions in the scan sequence. The method may also include transmitting into an environment an RF signal when the gimbal is at the positions in the scan sequence. The method may further include receiving a response signal from the environment. The method may include generating a haptic feedback to indicate a directionality or a proximity to the target material. The method may include analyzing the response signal for resonance characteristics that indicate a presence of the target material.

Provided is a method for determining huff and puff fluid volumes in multi-scale spaces of shale oil reservoirs, including the following steps: rock sample pretreatment; porosity stress sensitivity testing; high pressure hg injection testing and nuclear magnetic resonance testing benchmarking; online nuclear magnetic resonance testing; data processing and analysis. Firstly, a changing law of multi-scale spaces of shale oil reservoirs with an effective stress is characterized through a pore stress sensitivity measurement and online nuclear magnetic resonance measurement combined experiment, and then the huff and puff fluid volumes of multi-scale spaces of shale oil reservoirs under a condition of a certain stimulated reservoir volume are calculated. A usage amount of a fracturing fluid for a fracturing horizontal well in the shale oil reservoir is determined from the perspective of giving full play to the imbibition replacement role of micro-nano pores.

The invention belongs to the technical field of shale oil development and research, and discloses a shale oil mobility evaluation method based on a two-dimensional nuclear magnetic resonance experiment, which comprises the following steps: dividing an oil-containing shale sample harvested by a closed coring well into three parts which are respectively marked as a sample 1, a sample 2 and a sample 3; carrying out a TOC determination experiment on the sample 1 to obtain the TOC content of the sample; carrying out a step-by-step pyrolysis experiment on the sample 2 to obtain the contents of the sample S1-1 and the sample S2-2; calculating to obtain a shale oil mobility evaluation factor which is marked as FMO; carrying out a two-dimensional nuclear magnetic resonance experiment on the sample 3 before and after centrifugation to obtain the movable oil content of the sample before and after centrifugation, calculating to obtain the percentage of two-nuclear magnetic resonance movable oil, and recording the percentage as MO2D-NMR; and shale oil mobility evaluation is realized through analysis of the relationship between MO2D-NMR and FMO. According to the method provided by the invention, nondestructive testing of the sample can be realized in the two-dimensional nuclear magnetic resonance experiment process, the loss of light hydrocarbon can be reduced to the greatest extent, and the mobility evaluation precision of shale oil is effectively improved.

The invention discloses a CO2-EGR visual monitoring method based on nuclear magnetic resonance. The CO2-EGR visual monitoring method aims at solving the problem that dynamic observation of the pore scale gas drive process is insufficient in the traditional technology. Multi-sequence nuclear magnetic resonance monitoring is synchronously executed, a T2 spectrum is obtained through a CPMG sequence to analyze CH4 content changes, a layered T2 spectrum is generated through an SE-SPI sequence to represent axial fluid distribution, a one-dimensional frequency signal is collected based on a GR-HSE sequence to track a displacement leading edge in real time, and fluid migration visualization is achieved in combination with an HSE overall imaging sequence. The system integrates a gas injection unit, a high-pressure-resistant nuclear magnetic holder, a back pressure controller and a data acquisition module, and is hermetically connected through a high-pressure-resistant pipeline to form a closed-loop experiment system. According to the method, displacement front recognition, displacement process in-situ analysis and quantitative characterization of the displacement efficiency in the non-intrusive CO2-EGR process are achieved for the first time, the CO2-EGR visualization bottleneck is broken through, and a scientific basis is provided for optimizing gas injection parameters and improving the natural gas recovery rate and the carbon sequestration efficiency.

The invention discloses a microscopic crack dynamic in-situ characterization method, and relates to the technical field of crack in-situ detection. According to the method, a plurality of hardened cement paste bodies are soaked in a sulfate solution, the porosity development trend of the hardened cement paste bodies is obtained through a nuclear magnetic resonance test and a mercury injection test in the soaking process, a test sample and a test sample are prepared after soaking is finished, and the crack propagation length of the test sample is measured through a scanning electron microscope. According to the distance gradient between the sampling angle of the test sample and the exposed surface, space coordinates of crack cracking are converted into a time process along the center axis of the test sample, a delay microscope is established on the microscale, and the test sample is scanned by using X-ray computed tomography equipment in a matched mode; a crack propagation animation image is formed based on a crack form between adjacent X-ray tomography slices, and a crack development process is obtained by continuously capturing high-resolution images, so that omission of time information is avoided, and in-situ detection of microscopic cracks in a hardened cement paste sample is realized.

The invention belongs to the technical field of honey analysis, and particularly relates to a method for analyzing characteristic chemical components of Qinling Mountain medium-peak honey. The analysis method comprises the following steps: obtaining different extraction layers, and carrying out mass spectrometry on each layer of sample; constructing a molecular network by mass spectrum data through a GNPS platform, and comparing the mass spectrum data with a database to obtain primary identification; unmatched nodes predict the skeleton by using an NAP tool to obtain a secondary result; then fractions are separated, and an unknown structure is deduced by combining an SMART technology with nuclear magnetism; and finally, synthesizing the three types of results to determine the characteristic chemical components of the honey. Compared with a single chromatography-mass spectrometry technology, the analysis method provided by the invention not only realizes data visualization, but also reduces the dependence of chemical component identification on a database to a certain extent, and provides reference for rapid characterization of chemical components in a honey crude extract or fraction.

The invention provides a shale oil pyrolysis adsorption oil and free oil correction method based on a nuclear magnetic experiment, and belongs to the field of exploration and development of unconventional oil and gas fields. According to the method, on the basis of a shale rock physical experiment and a shale nuclear magnetic resonance experiment, the occurrence space and content of adsorbed oil are determined by using multi-state nuclear magnetic resonance experiments such as original sample, saturated oil, washing oil and different temperatures, so that a nuclear magnetic adsorbed oil model is constructed, and the content of the adsorbed oil is determined by further combining a different-temperature-order parallel crushed sample lithologic pyrolysis experiment-nuclear magnetic combined measurement experiment. The content of the free oil and the content of the adsorbed oil are calculated through the two-dimensional nuclear magnetism T1-T2 spectrum semaphore, the content of the free oil and the content of the adsorbed oil are compared and analyzed, the difference between the nuclear magnetism adsorbed oil and the pyrolysis adsorbed oil is matched with a free hydrocarbon curve to achieve adsorbed oil correction, and the free oil and the adsorbed oil are obtained.

The invention belongs to the technical field of engineering material detection, and particularly discloses an asphalt mixture dynamic water stability comprehensive detection system which comprises a standard test piece preparation module, a dynamic load loading module, a diffusion behavior analysis module, a sealing failure verification module and a water stability evaluation module. A detection area is limited through closed sealing treatment, a staged progressive increase dynamic load is applied to simulate an actual working condition, a three-dimensional moisture diffusion map is constructed to analyze diffusion behavior parameters, and a dynamic water stability grade evaluation result is generated in combination with an intelligent matching algorithm. According to the method, edge water seepage interference can be effectively avoided, the moisture diffusion process is accurately monitored, the performance of the asphalt mixture is comprehensively evaluated, and a scientific basis is provided for pavement structure design and material optimization.

The invention discloses a method and equipment for evaluating the sensitivity of shale porosity to the pH value of a well-entering fluid, and the method comprises the steps: obtaining a plurality of groups of experimental data of a shale sample, the experimental data comprising a first initial porosity and a first pH value of the well-entering fluid corresponding to the shale sample; a three-dimensional response curved surface model of the porosity increment, the initial porosity and the pH value is constructed according to the experimental data, the initial porosity comprises the first initial porosity, and the pH value comprises the first pH value; according to the three-dimensional response curved surface model, the target initial porosity of the target shale and the target pH value of the well entering fluid corresponding to the target shale, the target porosity increment of the target shale is predicted; and evaluating the sensitivity of the target shale to the second pH value according to the target porosity increment. According to the technical scheme provided by the invention, the porosity increment of the target shale can be predicted, and the sensitivity of well entering fluids with different pH values can be quantitatively evaluated based on the porosity increment.

Disclosed in the present invention is a method for dynamically measuring water content of an emulsified oil, comprising: (1) on-site calibration: performing oil-water separation on an emulsified oil, respectively measuring M(n)oil and M(n)water, and calculating a hydrogen index of the oil, i.e., HIoil=M(n)oil / M(n)water; (2) real-time measurement: dividing a fluid in an emulsified oil pipeline into n layers in a direction perpendicular to the flow direction of the fluid, using a magnetic resonance probe to perform layer-by-layer scanning, collecting the maximum amplitude M(n) of FID on each layer, and calculating water content η(n) on each layer according to M(n)=η(n)×M(n)water / n+[1-η(n)]M(n)water×HIoil / n; and (3) calculating dynamic water content according to η=η(1)×S(1)+η(2)×S(2)+…+η(n)×S(n), wherein n is an integer selected from 2-15. In this way, a rapid, green and non-intrusive test of the water content of the emulsified oil is realized.

The invention provides a method for determining microcosmic characteristic influence factors of a shale reservoir. The method comprises the steps of rock core observation, sampling and experiment, and lithofacies type division according to rock core observation and experiment results; performing characteristic evaluation on different types of lithofacies, and determining favorable lithofacies types; analyzing reservoir microscopic characteristics of different types of lithofacies; and according to an analysis result, determining factors influencing the microscopic characteristics of the reservoir. According to the method, favorable lithofacies and reservoir microscopic feature analysis can be comprehensively and effectively carried out, the evaluation accuracy is improved, and the accuracy is improved by 40% and reaches 90%; the working efficiency is improved, invalid work is avoided, the workload of two persons in 10 days is reduced to be completed by one person in 10 days, and lithofacies evaluation and reservoir microscopic feature influence factor analysis can be efficiently completed.

The invention provides a denoising method for a magnetic resonance spectrum based on Transform, and relates to the technical field of signal processing and artificial intelligence, and the method comprises the steps: firstly obtaining a noisy free induction decay signal (FID) and a corresponding label signal, constructing a training data set, converting the signal into a frequency domain signal through fast Fourier transform, and carrying out the amplitude normalization; a real part and an imaginary part of a frequency domain signal are respectively projected to a high-dimensional feature space, and are respectively sent to a multi-head self-attention mechanism-based multi-layer Transform encoder through two channels, so as to capture the global correlation of a long sequence. And the coded output is separated and decoded, a real part and an imaginary part are recovered respectively, and a denoised complex frequency domain signal is obtained through combination. In the training process, a complex mean square error is used as a loss function, and dynamic learning rate scheduling and an early stop mechanism are combined to improve convergence stability and model training efficiency.

Described herein are systems and techniques for improving an accuracy of determinations made using data sensed in a wellbore or in a laboratory. Nuclear magnetic resonance (NMR) sensing devices may be used to collect data in a wellbore or lab. NMR sensing devices include a magnet (e.g., a permanent magnet or electromagnet) that provides a magnetic field that aligns the spins of protons / nuclei in substances near the NMR sensing device. The magnetic field strength provided by the magnet of the NMR sensing device affects the sensitivity of the NMR sensing device and affects frequencies that the NMR sensing device effectively uses when the NMR sensing device operates. Systems and techniques of the present disclosure may measure concentrations of lithium in brine deposits when identifying particular brine deposits that include sufficient lithium concentrations to justify extracting lithium from those particular brine deposits.

A system and method for modeling one or more characteristics of a molecule using a quantum device implemented on quantum hardware is disclosed. Through control, via modulation, of coupling strengths between qubits on the quantum device and a comparison to an experimentally-measured nuclear magnetic resonance spectrum, J-coupling values may be deduced. These J-coupling values may then be used to recover the molecular structure of the given molecule. The control of coupling strengths may take place through an iterative process until convergence to the one or more characteristics is reached. In some embodiments, such a process may be implemented as part of a quantum computing service. In such cases, the quantum hardware may be local to the quantum computing service, or may be outsourced to a quantum hardware provider.

The invention belongs to the technical field of biological medicine, and particularly relates to application of a metabolic marker combination in diagnosis of gastric cancer. According to the method, specific metabolites in plasma or tissue of a gastric cancer patient are accurately quantified and analyzed through a targeted metabonomics technology, an optimal metabolic marker combination is developed through machine learning, and a novel non-invasive, efficient and accurate gastric cancer detection method is provided.

The invention relates to the technical field of water flooding gas reservoirs, in particular to a rock core displacement fluid saturation testing method and a testing device thereof.The method comprises the steps that S1, the original formation pressure and temperature of a gas reservoir are obtained; s2, obtaining a rock core, and testing physical property data of the rock core; then carrying out nuclear magnetic testing on the rock core; s3, saturating the rock core with formation water, and then carrying out nuclear magnetic testing; s4, carrying out gas drive water seepage test on the rock core according to the data in the S1, and obtaining the drive water quantity; s5, performing nuclear magnetic test on the depleted rock core; s6, obtaining the irreducible water saturation of the depleted rock core according to the nuclear magnetic test results of the steps S2, S3 and S5; s7, the total irreducible water saturation of the rock core is obtained according to the rock core physical property data, the displacement water amount and the irreducible water saturation of the rock core after exhaustion; the device comprises a drying oven, a first container, a second container, a core holder, a confining pressure pump, a displacement pump, a back pressure assembly, a receiving container and an electronic balance. The accuracy of fluid saturation determination can be improved.

The present invention belongs to the technical field of oil and gas exploration and development. Disclosed are a nuclear-magnetic-resonance-based method and system for characterizing the degree of miscibility of CO2 flooding. The method comprises: on the basis of a slim tube method, testing the minimum miscible pressure of crude oil of a target oil reservoir and CO2 (S101); on the basis of the minimum miscible pressure, conducting CO2 oil displacement experiments using cylindrical cores, collecting, in real time, two-dimensional weighted nuclear magnetic resonance images and multi-component T2 spectra of a fluid in the cores varying over time and space, synchronously collecting an outlet-end fluid, and conducting a chromatographic test to obtain chromatographic test data (S102); and on the basis of the two-dimensional weighted nuclear magnetic resonance images, the multi-component T2 spectra and the chromatographic test data, performing dynamically-changing qualitative and quantitative characterization on the degree of miscibility, so as to obtain qualitative and quantitative characterization results of the degree of miscibility of CO2 and the crude oil (S103).

The invention relates to a method and a device for determining the flow characteristic of CO2 in a porous medium and the distribution rule of CH4 in a pore space. The method comprises the following steps: (1) pretreating a sample; (2) system connection and air tightness inspection; (3) vacuumizing the system; (4) temperature control; (5) CH4 saturation and pressure stabilization; (6) displacement experiment and data acquisition; (7) monitoring outlet gas; and (8) data processing. The problem that in existing CO2 geological sequestration and enhanced gas production research, due to the fact that in-situ visualization of the pore size cannot be achieved, a microscopic displacement mechanism is unclear is solved, and the method aims at providing scientific basis and technical support for efficient exploitation of natural gas and effective geological sequestration of CO2.

The embodiment of the invention discloses a scanning NV probe microscope which comprises an atomic force microscopy system used for detecting surface topography information of a sample and an optical detection magnetic resonance system used for detecting surface magnetic field distribution information of the sample, and the atomic force microscopy system comprises a vibration arm and a diamond probe. The optical detection magnetic resonance system comprises an NV color center, a transition excitation light path and a fluorescence detection light path; a sample to be scanned and the transition excitation light path are respectively positioned on two opposite sides of the diamond probe, and the transition excitation light path and the fluorescence detection light path are positioned on the same side of the diamond probe; a first metal coating film is arranged on one side, close to the sample, of the diamond probe and is used for blocking surface fluorescence of the sample. According to the scanning NV probe microscope provided by the embodiment of the invention, the metal coating is arranged at the bottom of the diamond probe to block stray fluorescence from the surface of the sample, so that the problems of low magnetic field imaging signal-to-noise ratio and limited measurement precision of the existing scanning NV probe microscope are solved.

In a general aspect, orientation information is used to generate a unique code. In some aspects, orientation information is extracted from an object. The object includes multiple elements, and the orientation information indicates the relative spatial orientations of the respective elements. The orientation information can be extracted, for instance, by a scanner system that detects the elements. A unique code is generated for the object based on the orientation information. In some examples, the elements are diamond particles that each have one or more color centers, and the orientation information is extracted by detecting the color centers.

The invention belongs to the technical field of nuclear magnetic resonance detection, and particularly relates to a method for detecting fluorine ions in an ion exchange membrane and application of the method. The method comprises the following steps: (1) soaking an ion exchange membrane to prepare a sample, winding the sample on a bar, and loading the sample into the bottom of a nuclear magnetic tube in a screw-in manner; the shape of the sample is a polygon, the polygon has a symmetrical structure, and the number of edges is not less than 4; (2) putting the nuclear magnetic tube prepared in the step (1) into a nuclear magnetic resonance spectrometer, selecting a pulse sequence, tuning, shimming, adjusting nuclear magnetic resonance test parameters, and collecting signals; the nuclear magnetic resonance test parameters comprise: 90-degree pulse width is 9-15 [mu] s; and the power is 20-55W. The pulse width of a nuclear magnetic sample obtained by adopting a specific sample preparation method at 90 degrees is 9-15 microseconds; under the power of 20-55W, < 19 > F in a bulk phase of the ion exchange membrane can be detected, and a powerful support is provided for detecting and analyzing structural information in the bulk phase of the ion exchange membrane.

The invention provides a tight sandstone gas reservoir formation water division method based on mercury intrusion and online nuclear magnetic resonance, and relates to the field of gas reservoir formation water production, and the method specifically comprises the following steps: obtaining a tight sandstone core standard rock sample; cutting the rock core into two sections, and performing a high-pressure mercury injection experiment on the first section of the rock core; and scanning the nuclear magnetic resonance signal T2 spectrum curve of the rock core in the completely saturated water state and the area of the nuclear magnetic resonance T2 spectrum curve. And carrying out gas drive and nuclear magnetic scanning experiments. And sequentially increasing the displacement pressure differences to obtain a nuclear magnetic resonance correction curve under different displacement pressure differences. And drawing a water saturation and displacement pressure difference relation curve, and defining the critical pressure difference of different types of formation water production according to the curve form and the slope change rule. And processing the data to obtain the formation water production rule of the tight sandstone gas reservoir in different states. According to the technical scheme, the problem that in the prior art, the critical output pressure difference and the dynamic output rule of various types of formation water in different pore diameter ranges cannot be quantitatively represented is solved.

The invention provides a method for analyzing tobacco leaf moisture migration characteristics based on an LF-NMR technology, and belongs to the technical field of electric digital data processing. The method comprises the following steps: carrying out standardized sample pretreatment, measuring a moisture state through low-field nuclear magnetic resonance, establishing a moisture migration dynamic model, calculating a moisture diffusion coefficient matrix, constructing a moisture loss prediction model, adjusting migration parameters by applying a moisture diffusion optimization function, and analyzing whole-leaf moisture distribution by applying a neural network model of a multi-scale attention mechanism. And carrying out different temperature gradient experiments, analyzing the moisture migration difference between the main vein and mesophyll tissues, verifying the accuracy of the prediction model and the like, thereby realizing accurate quantitative analysis on the migration dynamic characteristics of the tobacco leaf moisture in different microstructures. According to the method, the low-field nuclear magnetic resonance technology, the moisture diffusion theory and deep learning are combined, the migration characteristic of moisture in the tobacco leaf microstructure is accurately recognized, and a scientific basis is provided for tobacco leaf curing process optimization.

The invention discloses a method and device for testing moisture migration in the frost heaving and thaw collapse process of fiber cement soil based on low-field nuclear magnetic resonance, and relates to the field of cement soil testing engineering.The method comprises the steps that T2 spectrums of the whole freezing process and the whole thawing process of a fiber cement soil sample are obtained; inverting a three-dimensional moisture distribution diagram of the whole freezing process and the whole melting process of the fiber cement soil sample according to the T2 spectrum; and determining moisture migration conditions of the whole freezing process and the whole melting process of the fiber cement soil sample according to the three-dimensional moisture distribution diagrams of the whole freezing process and the whole melting process of the fiber cement soil sample. According to the method, T2 spectrum data is mapped to a three-dimensional space position on the basis of a nuclear magnetic resonance (NMR) signal gradient positioning technology, and a pixel-level three-dimensional moisture distribution diagram of a fiber cement soil sample is obtained by performing data inversion on a T2 spectrum, so that pixel-level moisture migration conditions in the freezing process and the melting process of the fiber cement soil are visualized.