2187 results about "Raman spectroscopy" patented technology

The invention relates to a fermentation process abnormal state early warning method, system and device and a medium, and the early warning method comprises the steps: collecting fermentation process parameters in a fermentation tank in real time, and generating a physical parameter matrix; obtaining Raman spectrum data of the fermentation liquor and extracting metabolic feature vectors; fusing the physical parameter matrix with the metabolic feature vector to obtain a multi-modal data cube; constructing a metabolic network model, inputting the physical parameter matrix as a boundary condition, and generating calibrated metabolic flux distribution data; dynamically adjusting the monitoring weight coefficient of the fermentation process parameter, and generating a parameter sensitivity weight vector; inputting the multi-modal data cube and the parameter sensitivity weight vector into a space-time convolutional network, extracting time sequence features and spatial distribution features, and performing similarity matching with a preset abnormal mode library to obtain a matching result; and determining an abnormity early warning type according to a matching result with abnormity, and generating a corresponding compensation control instruction. The stability of the fermentation process is improved.

The invention provides a water quality heavy metal pollution detection method and system based on Raman spectrum. The method comprises the following steps: collecting a water sample through a water area to be detected, and scanning the water sample by adopting a Raman spectrometer to generate an original Raman spectrogram; based on the original Raman spectrogram, using a wavelet transform algorithm to perform de-noising processing, reducing background interference, using a principal component analysis technology to extract characteristic peaks, and generating a heavy metal preliminary prediction result; based on the preliminary heavy metal prediction result, constructing a heavy metal concentration prediction model by applying a partial least squares regression algorithm, performing quantitative analysis, evaluating prediction accuracy by adopting a cross validation technology, and generating a heavy metal actual concentration result; and based on the actual heavy metal concentration result, comparing with a water quality safety standard, evaluating a pollution condition, and generating a water quality heavy metal pollution detection report. The technical scheme provided by the invention has high sensitivity, can efficiently denoise and accurately predict, and provides a scientific means for monitoring and treating heavy metal pollution of water.

The invention relates to the field of Raman spectrums, and discloses a Raman spectrum nonlinear generation method driven by mixed machine learning, which is used for meeting the requirements of a modern Raman spectrum analysis technology on mixture spectrum data with wide coverage, complete types and reliable quality. Comprising the following steps: performing weighted linear combination on pure component spectrums based on a concentration ratio to generate a primary mixture spectrum; the data diversity is enhanced; generating a prediction spectrum; generator parameters are optimized through multi-level feature comparison and adversarial training of the discriminator; matching and deleting false peaks, and reconstructing physical reasonable characteristic peaks; and dynamically adjusting the intensity of the characteristic peak, and outputting high-fidelity spectrum data. According to the method, by fusing physical constraint and deep learning, the peak position precision, intensity consistency and noise robustness of the generated spectrum are remarkably improved, quantitative analysis of a complex mixture in a wide concentration range is supported, and an efficient solution is provided for Raman spectrum database construction and chemical detection.

The invention discloses a switch cabinet discharge detection method and system, and relates to the technical field of power equipment state monitoring and fault diagnose.The light intensity attenuation rate and the vibration frequency are collected through a photonic crystal fiber, the concentration of decomposed gas is detected in combination with a Raman spectrum, and a space-time joint feature matrix is generated; performing space weight distribution on the space-time joint feature matrix based on the switch cabinet structure, and inputting the space weight to an RBF-SVM (Radial Basis Function-Support Vector Machine) to generate discharge type probability distribution; based on a high-frequency energy parameter and a gas decomposition concentration parameter in the spatio-temporal joint characteristic matrix, inputting the parameters into a multiple linear regression model, calculating an insulation aging index, and judging an insulation degradation grade according to a threshold value; the photonic crystal fiber is used for collecting the light intensity attenuation rate and the vibration frequency, the Raman spectrum is combined for detecting the decomposition gas concentration to generate the space-time joint characteristic matrix, synchronous monitoring of various physical and chemical parameters in the switch cabinet is achieved, and the accuracy and comprehensiveness of recognition of different types of discharge phenomena are improved.

The invention discloses a mixed fishery medicine Raman spectrum detection method combining a data enhancement method and an RA-CTNet model. Data is expanded by combining a stoichiometric method and an experimental random error simulation method, so that the database building cost is reduced, and the model robustness is improved. In the aspect of model building, the advantages of CNN on local feature extraction and the capability of Transform on global feature modeling are fully utilized, training strategies of pre-training and transfer learning are adopted, rich feature information of a single fishery medicine is effectively utilized, the accuracy of mixed fishery medicine prediction is improved, and the prediction accuracy of the mixed fishery medicine is improved. And quantitative detection of a nanomole-level concentration mixture under a complex mixed sample is realized. Compared with the prior art, the technical scheme provided by the invention aims to detect forbidden fishery drugs in aquaculture water and realize nanomole-level concentration forbidden drug quantitative detection under a low data sample, and aims to improve the accuracy and robustness of Raman spectrum detection and quickly qualitatively and quantitatively analyze mixed fishery drugs.

The invention discloses a dynamic blood glucose monitoring and intelligent pump speed adjusting system and method, and relates to the technical field of biomedical engineering.The dynamic blood glucose monitoring and intelligent pump speed adjusting method comprises the steps that precise monitoring is conducted through a multi-mode sensing module, an enzyme electrode sensor adopts an anti-interference coating, a Raman spectrum dynamic correction algorithm is combined, and motion artifacts and temperature drift are restrained; the metabolic feature fusion calibration module is integrated with a time convolution network, time sequence modeling is carried out on diet, exercise and historical blood glucose data, an individualized metabolic parameter database is constructed, and self-adaptive signal drift compensation is achieved; the self-adaptive pump control module innovatively designs a double-layer fuzzy PID controller, a base layer generates an infusion rate according to a real-time blood glucose state and insulin activity, an optimization layer introduces an LSTM metabolism prediction model, and the slope of an infusion curve is dynamically adjusted in combination with future behavior pre-judgment; in the edge-cloud collaborative architecture, a lightweight TCN model is locally deployed to guarantee real-time control, and a cloud end optimizes a global digital twinborn model through federal learning and generates a multi-dimensional metabolic risk early warning report.

The invention discloses an automatic alignment and integrated control system and method for an optical crystal array. The automatic alignment and integrated control system comprises a quantum entanglement enhanced ultra-precise sensing array, a multi-factor coupling error prediction module, a full-link adaptive compensation execution module, a central control module and a federal learning collaborative optimization module. The sensing array is used for acquiring multi-dimensional error data such as sub-nano displacement, Raman spectrum deformation, infrared temperature rise and friction stress in real time; the prediction module is used for mining coupling characteristics between error sources based on an attention mechanism and predicting an instant alignment error and a hysteresis deformation error; the compensation execution module realizes full-link compensation through quantum traceability calibration, mechanical arm dynamic composite compensation and process parameter cooperative adjustment according to the prediction error; the central control module performs synchronous scheduling and conflict coordination; and the federated learning module realizes collaborative optimization and privacy protection of models among multiple devices. According to the invention, ultrahigh-precision and adaptive intelligent integration of the optical crystal array is realized.

The invention discloses an environment-adaptive transformer oil sample Raman spectrum detection method and related equipment, and relates to the field of optical sensing systems. The method comprises the following steps: collecting oil sample Raman spectrums and environmental parameters in multiple operation scenes, and constructing a multi-scene spectrum characteristic model and a standard fingerprint database; pre-processing and denoising parameters are adaptively set based on the environmental perception vector, and baseline correction and joint denoising are carried out on the original spectrum; scene discrimination is carried out by fusing the characteristics of peak position, peak height, peak width, integral area and the like, a scene-related component standard spectrum dictionary is generated, and the concentration and confidence of each target component are obtained by adopting constrained spectral line unmixing and quantitative calibration; and driving the fingerprint database and the model to update in combination with quality control indexes such as spectral shape relevancy and residual errors and a drift detection result. The system is composed of a Raman spectrum acquisition module, an environment monitoring module and a data processing module, and can improve the robustness and quantitative precision of Raman detection of transformer oil in a complex environment.

The invention belongs to the technical field of nondestructive testing, and discloses a gold ore and iron ore metal content detection method. The method comprises the following steps: acquiring an XRF energy spectrum by using an X-ray tube, acquiring an LIBS spectrum by using double-pulse Nd: YAG laser, and acquiring a Raman spectrum by using a semiconductor laser; performing baseline correction on the LIBS spectrum, performing Savitzky-Golay smoothing pretreatment on the Raman spectrum, and respectively extracting three types of spectrum characteristics; constructing a physical constraint network model, inputting XRF, LIBS and Raman features, and then outputting the correction content, fusion weight and LIBS dominant factors of Fe / Au elements; and finally, through a dynamic weight fusion strategy, combining XRF, LIBS fusion weights and network output parameters, calculating to obtain the content of the gold ore and the content of the iron ore. The technical breakthrough of multi-element cooperative detection and complex matrix interference suppression is realized, and the detection precision of Fe and Au is effectively improved.

The invention discloses a heparin impurity detection method and system based on a Raman spectrum. Impurities in heparin production are efficiently detected through a Raman spectrum technology, and a production process is optimized. The method comprises the following steps: firstly, obtaining original Raman spectrum data of a heparin production sample, performing quality analysis, and optimizing data to obtain parameters; extracting spectral data features, and generating a three-dimensional feature matrix; detecting abnormal spectral characteristics by using a density clustering algorithm, identifying impurities, and obtaining impurity detection data; and the impurity change trend is analyzed in combination with production timestamp data, and production process parameters are optimized. According to the method, the impurities can be accurately detected in real time, the production process is dynamically optimized, and the quality and safety of a heparin product are ensured. The system realizes efficient quality control, and has a wide application prospect, especially in the field of biological pharmacy.

The invention relates to a terahertz-Raman integrated detection system and method. The detection system comprises a fusion mainframe box and an integrated probe arranged at a sample detection end on the fusion mainframe box, a Raman spectrum module, a terahertz spectrum module, a terahertz optical module and a data analysis module are arranged in the fusion mainframe box; the Raman spectrum module is composed of a Raman laser, a Raman light filter, a Raman grating and a Raman detector which are sequentially connected through a light path; the terahertz spectrum module is composed of a terahertz femtosecond laser, a transmitting photoconductive antenna, a receiving photoconductive antenna and a terahertz detector which are sequentially connected through a light path; the data analysis module is in communication connection with the Raman detector and the terahertz detector and is used for synchronously processing data transmitted by the Raman detector and the terahertz detector. Compared with the prior art, the integrated probe synchronously collects two kinds of spectral data and carries out fusion processing on the two kinds of spectral data through the data analysis module, and the device has the remarkable effects that the device integration degree is high, the detection efficiency and accuracy are greatly improved, and the application range is wide.

The invention discloses a regional termite detection method and system based on multispectral fusion, and the method comprises the steps: carrying a multi-mode spectrum collection device through a movable detection platform, and synchronously collecting a visible light image, a near-infrared hyperspectral image and Raman spectrum data of a to-be-detected region; preprocessing and feature extraction are carried out on the modal data, and the modal data are converted to a frequency domain to obtain frequency features; based on the physical and biochemical characteristics of the termites and the nests thereof, calculating the matching degree and the credibility of each modal feature, and performing adaptive weighted feature fusion according to the matching degree and the credibility to generate comprehensive spectral features; inputting the fusion features into a pre-trained termite identification and risk assessment model to realize precise identification, positioning and threat level assessment of termite individuals, termite paths and nests; and carrying out trajectory analysis on termite activities by combining a multi-target tracking algorithm, and giving out early warning based on identification and tracking results. According to the invention, early-stage, lossless and accurate detection and active early warning of termites are realized, and the detection efficiency and reliability are significantly improved.

A platform for characterizing biomolecules, biological tissue sections, viruses, or other particles of interest in a non-invasive, high-throughput, cost-effective, and label-free manner. The platform includes a merged set of imaging modalities including and capable of interferometric microscopy and wide-field or confocal microscopy (such as, for example, a wide-field super-resolution surface enhanced Raman spectroscopy, SERS), although some aspects may be employed with data sets only received from wide-field or confocal microscopy. Related devices, systems, methods, techniques, and variations to the same are also provided.

To provide a composition for chemical mechanical polishing and a polishing method that can effectively suppress contamination of foreign matters during manufacturing and can polish the surface of a semiconductor substrate to a flat surface.SOLUTION: The composition for chemical mechanical polishing according to the present invention contains (A) abrasive grains including silica and (B) a liquid medium, in the (A) component, when the peak intensity of 490 cm-1 derived from a 4-membered ring measured by Raman spectroscopy is x and the peak intensity of 800 cm-1 derived from a multi-membered ring measured by Raman spectroscopy is y, x / y is 4.5 to 6.0, and the (A) component has at least one functional group selected from those represented by the following general formulae (1) to (4), -SO3-M+ (1), -COO-M+ (2), -NR1R2 (3), -N+R1R2R3M- (4).SELECTED DRAWING: None

The invention discloses a method and system for identifying perfluorooctanoic acid pollutants in tap water, and relates to the field of water environment new pollutant detection, and the method comprises the steps of SERS spectral signal collection, signal preprocessing, bimodal learning device construction and training verification, and concentration prediction result generation based on numerical value and image bimodal. The to-be-predicted data is put into the trained bimodal learning device for prediction and identification, and the concentration of the detection sample is output, so that batch rapid detection based on surface enhanced Raman spectroscopy and bimodal deep learning is realized, and high-precision identification and prediction based on small sample data are realized; the accurate detection result of the perfluorooctanoic acid pollutants in the tap water is obtained.

The invention provides a positive lithium supplement agent and a preparation method thereof, a positive pole piece, a battery and electric equipment. The positive electrode lithium supplementing agent comprises a lithium supplementing inner core and a carbon coating layer coating the surface of the lithium supplementing inner core, a Raman spectrogram of the positive electrode lithium supplementing agent has a G peak with a displacement interval of 1560-1580 cm <-1 >, a D peak with a displacement interval of 1350-1370 cm <-1 > and a first peak with a displacement interval of 655-675 cm <-1 >; wherein the peak intensity IG of the G peak, the peak intensity ID of the D peak and the peak intensity I1 of the 1 peak satisfy 0.85 lt; iG / IDlt; 1.25, 91t, 1.25, 91t; iG / I1lt; 50, 9lt; iD / I1lt; 50. The carbon coating layer of the positive electrode lithium supplement agent is compact and uniform and has excellent conductivity, a lithium supplement core and air can be better isolated, the environmental tolerance of the positive electrode lithium supplement agent is improved, the content of residual alkali on the surface is reduced, meanwhile, the conductivity of the positive electrode lithium supplement agent is greatly improved, and full play of the lithium supplement capacity is facilitated.

The invention discloses a tunable excited Raman spectrum microimaging method and device, and belongs to the field of spectrum detection and optical imaging. The device comprises a broadband adjustable wavelength light source, a high-resolution wavelength scanning module, a stimulated Raman signal excitation module and a stimulated Raman signal detection module. The stimulated Raman signal excitation and imaging module is used for focusing the two beams of narrow-band femtosecond pulse light which are overlapped in time and space on a sample and exciting a stimulated Raman signal, and meanwhile, moving the sample to realize spot scanning microscopic imaging; and the stimulated Raman signal detection module is used for converting the stimulated Raman scattering signal into an electric signal, demodulating the electric signal by using a lock-in amplifier, and recording spectral information by using a data acquisition card. According to the invention, the broadband tunable characteristic of the optical parametric amplifier is utilized to tune the pump light to the wavelength region of the sample absorption peak length so as to realize electron pre-resonance stimulated Raman; and a balance detection technology is combined at a detection end, so that high-sensitivity, high-resolution and high-signal-to-noise-ratio detection of stimulated Raman signals is realized.

The invention discloses a Raman spectrum fluorescence baseline correction method and device, and the method comprises the steps: collecting a time domain signal of a to-be-detected sample, and obtaining an IRF function of a to-be-detected sample collection system; pre-processing the time domain signal, and carrying out deconvolution on the pre-processed time domain signal and an IRF function to obtain a deconvolution result; fitting the second half data of the deconvolution result by using a support vector regression model to obtain a fitted curve; wherein a radial basis function is adopted as a kernel function, and hyper-parameters of the support vector regression model are optimized through a grid search and cross validation method; performing difference operation on the deconvolution result and the fitting curve to obtain a Raman attenuation curve; and windowing the Raman attenuation curve and averaging to obtain a Raman spectrum. According to the method, a fluorescence attenuation model and parameters thereof do not need to be preset, the IRF deconvolution result is processed and the time domain baseline is predicted by utilizing the characteristics of the time domain signal data and the support vector regression model, the signal-to-noise ratio of the extracted Raman signal can be greatly improved, a good effect is achieved, and the method is suitable for practical application.

The invention belongs to the technical field of biology, and particularly relates to a group of paired monoclonal antibodies for resisting H9N2 subtype avian influenza viruses and a surface enhanced Raman spectroscopy rapid detection test strip established based on the antibodies. The paired monoclonal antibody comprises a labeled antibody 1E9 and a capture antibody 3C10 which are prepared by taking hemagglutinin protein of the H9N2 subtype avian influenza virus as antigens and can be specifically combined with the H9N2 subtype avian influenza virus. According to the invention, an SERS (Surface Enhanced Raman Scattering) probe Au-coated Pt-4ATP is used as a marker and is coupled with a labeled antibody 1E9 to prepare a labeled probe, and the labeled probe is paired with a capture antibody 3C10 to establish an SERS immunochromatography test strip. The test strip has a colorimetric and Raman dual interpretation mode, can be used for qualitative and quantitative detection, has the advantages of strong specificity, high sensitivity, good repeatability and stability and the like, is simple and rapid in clinical detection operation, and provides reliable technical support for on-site rapid screening of subtype viruses.

The invention discloses a method and a system for identifying a spectrogram of a quaternary ammonium salt extracting solution in a textile, and relates to the technical field of material detection. Comprising the following steps: collecting different textile samples without quaternary ammonium salts and samples containing quaternary ammonium salts with different concentrations, determining extraction conditions, and extracting the quaternary ammonium salts to prepare a sample extracting solution; raman spectrums of all sample extracting solutions are collected, the spectrum containing the quaternary ammonium salt sample and the spectrum not containing the sample are divided into a plurality of sub-waveband areas, feature data are extracted, and the similarity is calculated. Based on the similarity change of the samples with different concentrations, defining the weight coefficient of the sub-band region; and performing similarity calculation on the spectrum of the to-be-detected textile extracting solution, and judging whether the to-be-detected textile extracting solution contains quaternary ammonium salt. And if not, further detecting by using Fourier transform infrared spectroscopy, and determining the quaternary ammonium salt concentration of the to-be-detected textile through the quaternary ammonium salt concentration prediction model. The calculation resources are reduced, and the detection precision and efficiency of the quaternary ammonium salt are improved.

A method including detecting contaminants in a water sample using a machine learning algorithm having a Laplacian operator configured to extract Raman peak data, a deep neural network, and a K nearest neighbors (KNN) cluster model. The method may include a test system having a silicon nanofiber film, a plurality of ZnO nanorods arranged in an array on the silicon nanofiber film, and a plurality of silver particles disposed on the plurality of ZnO nanorods. A water sample may be applied onto the test system, and the water sample may be measured using surface-enhanced Raman spectroscopy to generate the Raman peak data used in the machine learning algorithm.

The invention discloses a seawater corrosion environment biaxial test system and method based on Raman spectrum. The seawater corrosion environment biaxial test system comprises a biaxial in-situ loading device, a seawater corrosion environment simulation box and a Raman spectrum measuring instrument. According to the biaxial in-situ loading system coupled with the seawater corrosion environment and used for Raman spectrum measurement, simulation of a complex stress state and the seawater corrosion environment is achieved by coupling the biaxial in-situ loading equipment and the seawater corrosion environment simulation box, and meanwhile, based on the Raman spectrum measurement instrument, the measurement accuracy is further improved through data analysis. Key information such as chemical product evolution laws in the stress corrosion process is obtained in situ, and a technical foundation is laid for clarification of a corrosion failure mechanism of a material under a real deep-sea service condition.

The invention provides a Raman spectrum-based graphitization degree detection method and device, computer equipment and a medium. The method comprises the following steps: acquiring Raman data and X-ray diffraction data of multiple groups of test samples; obtaining the graphitization degree R-1 of the test sample based on the Raman data, and obtaining the graphitization degree g of the test sample based on the X-ray diffraction data; taking the graphitization degree R-1 and the graphitization degree g of the same test sample as a group of benchmarking data, performing numerical fitting based on multiple groups of benchmarking data, and constructing a function relationship between the graphitization degree R-1 and the graphitization degree g; raman data of a to-be-detected sample are obtained, the graphitization degree R-1 of the to-be-detected sample is calculated, and the graphitization degree g of the to-be-detected sample is determined according to the function relation. According to the method, the graphitization degree R-1 and the graphitization degree g of the material are associated, the graphitization degree g of the product can be directly obtained through Raman analysis, online detection of the carbon powder material is achieved, and the sorting precision of the carbon powder is improved.

The invention provides a raman peak intensity information-based genuine medicinal material structured feature selection method and system. The method comprises the following steps: scanning medicinal material slices to generate two-dimensional distribution data of chemical components; a three-dimensional feature is constructed by using dual-wavelength laser irradiation and combining Raman peak intensity difference. And identifying a plurality of concentration regions and boundary cross points thereof through spatial topology analysis, establishing a spatial correlation model, analyzing a distribution rule, and finally forming component arrangement graph structure data. Key information is screened based on genuine medicinal material features, and after a discrimination model is input, a result is output in combination with spatial and spectral features, so that accurate discrimination is realized. And selecting the structured characteristics of the genuine medicinal materials based on Raman peak intensity information. According to the method, the spatial topology and the chemical component distribution characteristics of the Raman spectrum are fused to construct the graph structured identification model, so that the accuracy and the interpretability of genuine medicinal material identification are remarkably improved.

The invention relates to an aquatic product drug residue detection method and system based on Raman spectrum. The method comprises the following steps: acquiring Raman spectrum data generated after an aquatic product sample is irradiated by laser; preprocessing the Raman spectrum data, and extracting characteristic peak data; comparing the characteristic peak data with a pre-established drug residue standard spectrum library to obtain a drug residue concentration value corresponding to the characteristic peak data; constructing a quantitative detection model by adopting a machine learning algorithm based on the characteristic peak data and the corresponding drug residue concentration values; and based on the quantitative detection model, predicting the drug residue concentration of the aquatic product. The method can be widely applied to the field of food safety, and an efficient and reliable solution is provided for detection of drug residues in aquatic products.

The invention relates to a bacterial pneumonia pathogenic bacterium identification method based on an intelligent Raman technology, which comprises the following steps: S1, setting a type label according to a gram staining characteristic classification mode or the occurrence frequency of bacterial types in bacterial pneumonia infection, and selecting a known strain according to the type label, collecting Raman spectrum data of a known strain; s2, carrying out wave number extraction, background subtraction, smooth noise reduction and normalization preprocessing on the Raman spectrum data; s3, constructing a classification model according to an AlexNet model; s4, dividing the preprocessed Raman spectrum data into a training set and a verification set, and inputting the training set, the verification set and corresponding type labels into a classification model for training to obtain a trained classification model; and S5, acquiring Raman spectrum data of detected bacteria by using a Raman spectrometer, preprocessing the Raman spectrum data, and inputting the preprocessed Raman spectrum data into the trained classification model to obtain the type of the detected bacteria. The bacteria are identified by establishing the classification model, so that the operation complexity is reduced, and the identification time is shortened.

The invention belongs to the technical field of spectral analysis, and discloses a Raman spectrum characteristic peak segmentation method based on distance vector and probability vector output. Spectral detail features are extracted through multi-scale wavelet decomposition, and a spectral multi-layer structure representation matrix is constructed; identifying a potential peak site and a hierarchical affiliation relationship thereof based on the local curvature change rate; generating an adaptive distance calculation kernel function in combination with the asymmetry index and the peak shape complexity coefficient; and calculating a distance vector of hierarchical perception and a probability vector extracted by deep learning, and constructing a joint segmentation decision function of a multi-layer peak structure. According to the method, the hierarchical relationship among the main peak, the shoulder peak and the sub-peak can be accurately distinguished, the complex conditions of peak overlapping, asymmetric peak shapes, low signal-to-noise ratio and the like are effectively processed, and the accuracy and the reliability of Raman spectrum analysis are improved.

The invention discloses a bacteria Raman spectrum chemical component cross-domain analysis method based on deep transfer learning, and belongs to the field of Raman spectrum intelligent analysis, the method comprises the following steps: collecting multi-source Raman spectrum data, and pre-processing the multi-source Raman spectrum data to obtain pre-processed spectrum data; constructing a deep transfer learning model, extracting spectral features of the preprocessed spectral data by the deep transfer learning model through a deep full-connection neural network and a multi-head self-attention mechanism, and eliminating distribution difference between devices by using adversarial transfer learning to obtain a Raman spectrum feature vector; performing nonlinear dimension reduction on the Raman spectrum feature vector to obtain a dimension-reduced low-dimensional feature matrix; based on the dimensionality-reduced low-dimensional feature matrix, a dynamic field adaptation and meta-learning fine tuning strategy is adopted to realize small sample fine tuning, and an optimized model is obtained; and outputting chemical component category judgment and concentration prediction results based on the optimized model.

The invention provides a mineralogical substance composition testing method and system based on multispectral data fusion. The method comprises the following steps: separating out a first characteristic interference signal caused by the oxidation state of an iron element and a second characteristic interference signal caused by the oxidation state of a manganese element by adopting wavelet transform in a superposition region of a Raman spectrum signal and a visible light absorption spectrum; performing spatial weighting on the intensity of the first feature interference signal and the intensity of the second feature interference signal to construct a multi-dimensional feature vector, inputting the multi-dimensional feature vector to a pre-trained residual neural network, and combining a radioactivity attenuation parameter measured by a gamma spectrometer to determine the radioactivity attenuation of the first feature interference signal and the second feature interference signal. And generating a mineralogical substance composition test result containing a mineral phase, an isomorphic substitution ratio, color cause analysis data and a radiation safety level. According to the method, the collaborative interpretation of the multispectral data and the radiation parameters can be realized, the mineral component analysis precision is improved, the color formation mechanism is synchronously analyzed, and the radioactive risk level is quantitatively evaluated.

The invention provides a tip Raman-based metal oxide nanoparticle in-situ detection method, which comprises: S1, dispersing metal oxide nanoparticles in a nanoparticle dispersion liquid, focusing laser to the tip of a nanometer tip through an objective lens, capturing a single nanoparticle by using an optical tweezers technology, and attaching the single nanoparticle to the nanometer tip; s2, focusing Raman laser on a nano needle tip-particle interface, generating a local high-temperature field through a photo-thermal near-field coupling effect, triggering a thermal chemical reaction of nano particles, and synchronously collecting a Raman spectrum; and S3, carrying out pretreatment and characteristic peak analysis on the collected Raman signal of the Raman spectrum, and determining the reaction critical temperature and the dynamic process in combination with temperature calibration data. According to the invention, capture and accurate heating of the nanoparticles are realized through photo-thermal coupling of the optical tweezers and the needle tip, and thermal chemical reaction monitoring of the nanoparticles is realized.