16 results about "Diffusion gradient" patented technology

The invention relates to the technical field of cable joint diagnosis, in particular to a cable joint abnormity early warning method and system, and the method comprises the steps: carrying out the feature extraction of infrared thermal image data and acoustic vibration data, and obtaining a multi-modal feature data set; quantifying the coupling correlation degree between the hot spot diffusion gradient and the vibration frequency component according to the multi-modal characteristic data set to obtain a regional thermal vibration coupling anomaly index; calculating a regional defect risk score according to the regional defect type distribution; obtaining a modal fusion weight distribution value based on the regional defect risk score and the regional thermal vibration coupling anomaly index; performing weighted fusion on the infrared thermal image feature data and the acoustic vibration feature data according to the modal fusion weight distribution value to obtain a regional defect coupling feature vector; and obtaining the defect probability of the cable joint according to the regional defect coupling feature vector, and carrying out graded early warning according to the defect probability of the cable joint. According to the method, the infrared thermal image and the acoustic vibration data are fused, so that accurate early warning of the abnormity of the cable joint is realized.

The application provides a pipeline leakage detection method based on multi-modal feature fusion, and relates to the field of pipeline leakage detection. The pipeline leakage detection method based on multi-modal feature fusion comprises the following steps: acquiring an acoustic signal in a pipeline, determining an acoustic fingerprint energy spectrum in the pipeline based on the acoustic signal; acquiring a thermal image in the pipeline, determining a thermal diffusion gradient in the pipeline based on the thermal image; acquiring a pressure signal in the pipeline, determining a fluctuation entropy in the pipeline based on the pressure signal; using a confidence function, respectively mapping the acoustic fingerprint energy spectrum, the thermal diffusion gradient and the fluctuation entropy into confidence values; fusing the confidence values corresponding to the acoustic fingerprint energy spectrum, the confidence values corresponding to the thermal diffusion gradient and the confidence values corresponding to the fluctuation entropy, and determining a detection result of whether the pipeline leaks. Through the above method, the false positive rate of pipeline leakage detection is reduced.

This invention relates to the field of medicinal material identification technology, specifically to a method and system for identifying the authenticity of medicinal materials based on AI vision. The method includes the following steps: iteratively generating candidate images and comparing them with images of genuine medicinal material slices, adjusting the generation logic based on the comparison results. This invention constructs a latent vector mapping relationship consistent with the visual features of images of genuine medicinal material slices, combines image reconstruction errors for anomaly extraction, and enhances the perception of adulteration locations. The pixel-by-pixel reconstruction error method can locate areas with slight deviations in shape or color, and based on this, extracts the thermal decay curve of the isotopic infrared image sequence. Through time constant fitting calculation, it completes a quantitative modeling of the thermal conductivity characteristics in space, and further calculates the spatial gradient of the thermal decay time constant, realizing the quantification of the boundary strength of the material's thermal diffusion behavior, forming a thermal anomaly diffusion gradient map, providing physical property basis for subsequent multi-spectral fusion.

The utility model discloses a diffusion gradient film shell which comprises a sampler shell assembly, the sampler shell assembly comprises a base, a threaded column fixed on the base, a protective cover matched with the threaded column, a conical cover connected with the protective cover, and a filter membrane, a diffusion layer and an adsorption layer which are arranged between the threaded column and the protective cover. According to the utility model, the sampler shell assembly is arranged to form a threaded connection structure, so that the sampler shell does not need to be pried open when the adsorption film is recycled, the effect of repeated utilization can be achieved through simple methanol water cleaning, experimental resources are effectively saved, experimental wastes are reduced, and the experimental cost is reduced. And the structural design of the octagonal base is convenient to apply force to screw, the shell can be set into different colors, and the shells with the same color form one group, so that the marking is convenient.

The invention relates to the field of image processing, in particular to an industrial gas leakage detection method based on infrared thermal imaging, which comprises the following steps of: acquiring video streams by using a plurality of infrared thermal imagers, and constructing a gas basic geometric voxel grid through a background difference and view cone intersection method; thirdly, the sight line penetration depth and a statistical variable coefficient are calculated, and adaptive normalized radiation feature mapping based on statistical moments is constructed so as to solve errors caused by traditional homogeneous hypothesis; then, measuring and calculating a three-dimensional form compactness factor, generating a heterogeneous space density field weight in combination with the relative depth, and fitting a real diffusion gradient; and finally, calibrating a physical mapping coefficient by using single-point sensor data, and performing integral calculation on the real-time mass flow in combination with a three-dimensional optical flow method. According to the invention, the complex density gradient in the gas can be effectively reduced, and high-precision three-dimensional visual display and quantitative flow monitoring of gas leakage are realized.

The invention provides a pipeline leakage detection method based on multi-modal feature fusion, and relates to the field of pipeline leakage detection. The pipeline leakage detection method based on multi-modal feature fusion comprises the following steps: acquiring an acoustic signal in a pipeline, and determining a voiceprint energy spectrum in the pipeline based on the acoustic signal; obtaining a thermodynamic image in the pipeline, and determining a thermal diffusion gradient in the pipeline based on the thermodynamic image; acquiring a pressure signal in the pipeline, and determining a fluctuation entropy in the pipeline based on the pressure signal; respectively mapping the voiceprint energy spectrum, the thermal diffusion gradient and the fluctuation entropy into confidence values by using a confidence function; and fusing the confidence value corresponding to the voiceprint energy spectrum, the confidence value corresponding to the thermal diffusion gradient and the confidence value corresponding to the fluctuation entropy, and determining a detection result whether the pipeline leaks or not. Through the method, the false alarm rate of pipeline leakage detection is reduced.

The invention discloses a magnetic resonance center frequency determination method and device, a storage medium and a terminal. A first frequency spectrum corresponding to the first signal and a second frequency spectrum corresponding to the second signal are determined, the first signal is a magnetic resonance signal collected under the zero diffusion gradient magnetic field, and the second signal is a magnetic resonance signal collected under the diffusion gradient magnetic field; a plurality of effective wave crests in the first frequency spectrum and the second frequency spectrum are identified, diffusion coefficients corresponding to the effective wave crests are calculated, and the effective wave crests are wave crests corresponding to the human tissue components; and determining the center frequency of the magnetic resonance system based on the signal intensity, the frequency and the diffusion coefficient of each effective wave crest. Through the magnetic resonance signals of the zero diffusion gradient and the applied diffusion gradient magnetic field, the effective peak diffusion coefficient is analyzed in combination with the spectrum, the peak of each component is identified, and the center frequency is determined accordingly, so that the limitation of empirical judgment or analysis based on spectrum characteristics is overcome, and the identification accuracy of the magnetic resonance center frequency in a complex signal environment is improved.

The invention discloses a gap feature filling method. The filling method comprises the following steps: at a first temperature, introducing a halogen group-containing surface reaction inhibitor, so that the halogen group-containing surface reaction inhibitor is reversibly adsorbed on active sites of gap characteristics to form a passivation layer; adjusting a deposition region of the introduced first precursor and / or second precursor in the gap feature via the barrier of the passivation layer; and in response to the deposition film morphology in the gap feature reaching the preset morphology, raising the temperature to a second temperature to remove the passivation layer. By executing the steps, the deposition reaction activity of a specific region in the gap feature on the surface of the substrate can be selectively and reversibly inhibited, the film forming defect of diffusion gradient can be fundamentally compensated, and a film layer with uniform height and excellent shape retention can be deposited in a high aspect ratio structure; and in the process of recovering the deposition reaction activity of the specific area, the operation is convenient, and damage or cross contamination cannot be caused to a substrate interface.

The application discloses a diffusion-weighted magnetic resonance spectrum parallel acquisition and reconstruction method. The method comprises the following steps: adding a pair of diffusion gradients in a single voxel spectrum sequence to obtain a single voxel diffusion-weighted magnetic resonance spectrum sequence; performing point-by-point summation on single-band radio frequency pulses at each voxel position of interest to obtain multi-band radio frequency pulses; obtaining a multi-voxel diffusion-weighted magnetic resonance spectrum signal through the single voxel diffusion-weighted magnetic resonance spectrum sequence and the multi-band radio frequency pulses; obtaining a sensitivity map of each channel of a receiving coil; separating and reconstructing the multi-voxel diffusion-weighted magnetic resonance spectrum signal according to the sensitivity map; and finally obtaining a separated and reconstructed multi-voxel diffusion-weighted magnetic resonance spectrum signal. The application can simultaneously measure diffusion-weighted magnetic resonance spectrum signals of multiple voxels of a human body, and obtain a signal-to-noise ratio and an apparent diffusion coefficient equivalent to those of a single voxel diffusion-weighted magnetic resonance spectrum signal, thereby saving at least half of the scanning time.

Systems and methods are provided for producing diffusion-weighted images of a subject using a magnetic resonance imaging (MRI) system. The method includes performing a stimulated echo preparation module using non-selective radio-frequency (RF) pulses designed to induce a stimulated echo, performing an acquisition module that includes a multi-slice acquisition of MR data in the presence of diffusion gradients, and reconstructing the diffusion-weighted images of the subject from the MR data.

The invention relates to the technical field of medicinal material identification, in particular to a medicinal material authenticity identification method and system based on AI vision, and the method comprises the following steps: generating a candidate image through iteration, comparing the candidate image with a pure medicinal material decoction piece image, and adjusting the generation logic according to the comparison result. According to the method, the potential vector mapping relation consistent with the visual features of the pure medicinal material decoction piece image is constructed, anomaly extraction is performed in combination with the image reconstruction error, the perception of the doping position is enhanced, and the form or color slight deviation area can be positioned based on the image pixel-by-pixel reconstruction error mode, so that the accuracy of the extraction is improved. And extracting a thermal attenuation curve of the same-position infrared image sequence on the basis, completing quantitative modeling of heat conduction characteristics in space through fitting calculation of time constants, further calculating a space gradient of thermal attenuation time constants, realizing quantification of material thermal diffusion behavior boundary strength, and forming a thermal anomaly diffusion gradient map. And a physical character basis is provided for subsequent multi-map fusion.

The present application relates to the technical field of sediment / soil two-dimensional monitoring, in particular to a preparation method of a composite film for synchronous detection of sediment pollutants and environmental factors. The composite film is designed based on a planar photoelectrode (PO) and a thin film diffusion gradient balance principle. The preparation process includes designing and synthesizing three kinds of fluorescent sensing materials, namely PtTFPP@PSAN, HPTS(ODA)3@PSPVP and BBS@PVDCAN, and two kinds of DGT adsorption materials, namely Nano-ZrO and Nano-Chelex. In the preparation process of the sensing film, the three kinds of fluorescent sensing materials are embedded and fixed in the bottom layer by polyurethane hydrogel D4, and the DGT adsorption materials are embedded and fixed in the surface layer by polyurethane hydrogel D4. With the aid of the sensing film, based on the fluorescent analysis principle, the fluorescence intensity image of the composite film at the sediment or soil contact interface can be obtained in real time, and the DO and pH two-dimensional refined distribution information can be converted through the scale. Then, the composite film is further processed, and the fine distribution information of phosphorus, heavy metals and other pollutants is obtained through thin film color development, laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS) and other fine imaging methods.

The present application relates to the technical field of cable joint diagnosis, and particularly relates to a cable joint abnormality early warning method and system, which comprises feature extraction on infrared thermal image data and acoustic vibration data to obtain a multimodal feature dataset; according to the multimodal feature dataset, a coupling correlation degree between a thermal spot diffusion gradient and a vibration frequency component is quantified to obtain a regional thermal-vibration coupling abnormality index; a regional defect risk score is calculated according to a regional defect type distribution; a modal fusion weight distribution value is obtained based on the regional defect risk score and the regional thermal-vibration coupling abnormality index; the infrared thermal image feature data and the acoustic vibration feature data are weighted and fused according to the modal fusion weight distribution value to obtain a regional defect coupling feature vector; a cable joint defect probability is obtained according to the regional defect coupling feature vector, and a hierarchical early warning is performed according to the cable joint defect probability. The present application realizes accurate early warning of cable joint abnormalities by fusing infrared thermal image data and acoustic vibration data.

The invention discloses a wake diffusion gradient-based underwater moving target positioning method, which comprises the following steps of: obtaining an activated sensor set, constructing an interior point judgment strategy to obtain a sensor interior point set, and extracting wake diffusion gradient feature vectors by utilizing principal component analysis; selecting an optimal reference sensor node through a time-space double-weight index function to obtain a reference point, orthogonally projecting the sensor node in a point set in the sensor to an axial straight line, and obtaining a projection point position to construct a wake diffusion gradient profile function; after direction disambiguation of a wake flow diffusion gradient vector is realized based on a wake flow diffusion gradient profile function, a disturbance intensity critical point is defined, and an isosceles triangle wake flow diffusion area representing the wake flow position direction and scale of the underwater moving target is obtained according to the disturbance intensity critical point through interpolation fitting and least square ellipse fitting algorithms. Aiming at the problem that the adaptability of the traditional acoustic, optical and magnetic detection method in a complex underwater environment is limited, the invention provides a new way for positioning an underwater moving target based on wake flow characteristics.

The application discloses a water-sediment interface research device based on a thin film diffusion gradient, and has the characteristics that the device comprises a simulation tank and a passive sampler; the simulation tank is provided with an opening at one end, and a sediment layer and a liquid layer are sequentially arranged in the tank body from bottom to top; the passive sampler comprises a sampler back plate, a sampling recess is arranged on the surface of the sampler back plate, a hand-held device is arranged at one end of the sampler back plate, and a stabilizer is arranged at the other end of the sampler back plate; the stabilizer is used for vertically placing the sampler in the simulation tank, so that the sampling recess can be in contact with the sediment layer and the liquid layer at the same time; a DGT film layer assembly is detachably attached in the sampling recess; the DGT film layer assembly comprises a binding gel layer, a diffusion gel layer and a filter layer from bottom to top in sequence; the passive sampler further comprises a sampler front plate, a sampling port is arranged on the sampler front plate, and the sampling port is used for accommodating the sampling recess; and the sampler front plate can be closed with the sampler back plate, so as to fix the DGT film layer assembly.