62 results about "Chemometrics" patented technology

The invention discloses a Raman spectrum joint classification and quantification method based on a prior fusion double-flow network, and belongs to the technical field of spectral analysis and chemometrics. The method comprises the following steps: acquiring Raman spectrum original data, and preprocessing to obtain standardized spectrum data; raman spectrum prior information is extracted, and a prior information double-flow network containing classification and quantitative flow sub-networks is constructed; standardized data and prior information are input, classification preheating-combined fine tuning training is adopted, conflict is relieved by combining dynamic weighting and PCGrad, and samples are expanded through a physical consistency strategy synchronously; processing unknown samples by using the trained network, and outputting categories and component contents; according to the method, weak peak information is mined through double-flow architecture and cross-flow attention, derivative noise is suppressed, classification-quantification performance is balanced through double-task optimization, and small sample overfitting is solved through physical expansion; on a polycyclic aromatic hydrocarbon data set, classification and regression indexes are superior to those of a traditional method, the low-concentration / weak-peak scene precision and robustness are better, and the engineering application prospect is good.

A medication assurance system for verification of both the medication and the patient is disclosed. A portable spectrometer is used to obtain a light spectrum of the medication. A subject identification or biometric device is used to identify the patient. A controller coupled to the portable spectrometer and the subject identification device identifies the medication by performing a chemometric analysis of the light spectrum. Based on the medication identified and the patient identified, the controller can determine if the medication is to be taken by the patient.

The present application relates to the field of on-line analysis of material chemical composition, and discloses an on-line monitoring process for the composition of a lead frame electroplating solution, comprising: calculating the concentration of the electroplating solution by conventional monitoring of the spectrum; calculating a spectrum entropy index based on the degree of deviation of the real-time spectrum from a pre-established statistical baseline model, and comparing the spectrum entropy index with a pre-set failure trigger threshold; starting a dynamic calibration step only when the spectrum entropy index exceeds the pre-set failure trigger threshold, the dynamic calibration step generating a model error vector by comparing the physically real differential spectrum with the model virtual differential spectrum through injection of a standard pulse, and correcting the chemometrics model using the model error vector, so that the present application realizes on-demand calibration, ensures real-time accuracy of the model, and reduces the consumption of the standard.

The invention relates to a white tea quality discrimination method and related equipment. The method comprises the following steps: acquiring ultraviolet-visible diffuse reflection spectrum data of a white tea sample to be detected; wherein the wavelength range of the spectral data covers an ultraviolet region to a near-infrared short wave region; performing first pretreatment on the spectral data, and performing production place authenticity judgment on the white tea sample to be detected by adopting a chemometrics method based on the spectral data subjected to the first pretreatment and the first characteristic wavelength set to obtain a production place authenticity judgment result; and when the authenticity discrimination result of the production area is a pure material in the target production area, carrying out second pretreatment on the spectral data, and carrying out grade discrimination on the white tea sample to be detected by adopting a chemometrics method based on the spectral data subjected to the second pretreatment and the second characteristic wavelength set to obtain a grade discrimination result. According to the method, the discrimination cost of the white tea quality is reduced, and the discrimination accuracy is improved.

The invention provides a calibration curve establishment method based on multi-weight parallel fitting in liquid chromatogram data management software, relates to the cross technical field of a chemometrics algorithm and chromatographic data analysis, and aims to establish and implement a full-automatic technical process of parallel fitting-automatic evaluation-intelligent decision making. According to the invention, the establishment of the correction curve is converted from a process depending on user experience and manual trial and error into a technical optimization process which is automatically completed by the system and based on objective quantitative indexes. According to the method, the data processing efficiency can be improved, the subjectivity and complexity of human intervention can be reduced, and better fitting results can be obtained under different given data sets through comprehensive comparison and automatic optimization of multiple models, so that the accuracy, the reliability and the automation level of liquid chromatogram quantitative analysis are remarkably improved.

The invention relates to an intelligent grading and quantitative nondestructive testing method for cornu cervi pantotrichum decoction pieces, which is used for training an artificial intelligence recognition model by means of machine learning and the like to realize quick and high-throughput quality grading of cornu cervi pantotrichum. Meanwhile, through bioinformatics and chemometrics analysis means, spectral characteristics of the cornu cervi pantotrichum decoction pieces at all levels are extracted, association of the characteristics, physicochemical properties and spectral characteristics of the cornu cervi pantotrichum decoction pieces is established, a scientific basis is provided for quantitative prediction of the quality of the cornu cervi pantotrichum decoction pieces through infrared spectroscopy, and then lossless intelligent grading and quantitative grading of the cornu cervi pantotrichum decoction pieces are achieved. According to the nondestructive testing method established through multi-data fusion, the problem that traditional quality grading of the cornu cervi pantotrichum decoction pieces depends on subjective experience is solved, and the quality of the cornu cervi pantotrichum decoction pieces can be rapidly and accurately evaluated.

The invention discloses a full-automatic Raman spectrum baseline correction method and system, and the method comprises the steps: introducing a deep learning algorithm on the basis of chemometrics, recognizing peak and background regions in a spectrogram through a weight output model based on deep learning, and outputting an initial weight vector; and then adaptively optimizing a smoothness parameter based on a multi-index evaluation strategy, finally performing dynamic weighted iteration by adopting a more robust dynamic iteration reweighted penalty least square method algorithm to fit a background curve, and outputting a final corrected baseline. The method can solve the problems that in an existing Raman spectrum baseline correction method, parameters need to be manually adjusted, balance between peak intensity information reserving and noise interference removing is difficult to obtain, the processing speed is low and the like, baseline correction of the Raman spectrum is achieved on the premise that the reliable peak position and intensity of the Raman spectrum peak are obtained, and the method is suitable for large-scale popularization and application. The method has a supporting effect on qualitative and quantitative analysis of Raman spectrum, is high in operation speed, and can be used for processing large-scale data.

The application discloses a kind of material evaluation methods, pharmaceutical compositions and application of sophora fruit products.It is specific, disclose a kind of material evaluation methods of sophora fruit products, it includes the following steps: S1, using liquid chromatography, the fingerprint of the sophora fruit product of different processing time is established, and common characteristic peak is extracted;S2, the hemostatic effect of sophora fruit product of different processing time is determined;S3, according to the characteristic peak data of the sophora fruit product of different processing time and its hemostatic effect data, statistical analysis is carried out by chemometrics method, and the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect of the hemostatic effect

The application belongs to the technical field of food safety, and particularly relates to a volatile organic compound detection device based on olfactory visualization technology and a detection method thereof. The device comprises a fixed frame structure, a control module is arranged above the fixed frame structure, a detection platform is arranged below the fixed frame structure, a pipette and an image acquisition device and a sensor control device are respectively arranged above both sides of the detection platform, and the control module is connected with the pipette, the image acquisition device and the sensor control device. The control module is used for controlling the pipette, the image acquisition device and the sensor control device to operate in the detection platform area. The application can prepare a color-sensitive sensor printed with a metal porphyrin, obtain volatile gas of an organic compound, and cause a coordination reaction with the volatile gas. Image data before and after the reaction of the volatile gas with the organic compound is detected and analyzed through the image acquisition device, and corresponding chemometrics methods are combined, so that rapid quantitative analysis of the organic gas can be realized.

The application discloses a detection method for carbonation depth of cement-based materials, comprising the following steps: placing mud test pieces into a rapid carbonation test box to perform rapid carbonation to different carbonation ages; testing dielectric constants of the cement test pieces of different carbonation ages from top to bottom along the carbonation depth direction, taking the depth value as the carbonation depth I based on the dielectric constant when the dielectric constant changes greatly; testing the carbonation depth II of the cement test pieces of the carbonation age by adopting a phenolphthalein method; fitting two groups of data by adopting a chemometrics method according to the obtained carbonation depth I and the carbonation depth II, and establishing a fitting equation of the carbonation depth I and the carbonation depth II; and then realizing rapid and efficient detection of the carbonation depth of the cement test pieces. The test method is simple and convenient without damaging the test pieces, the detection result is relatively accurate, and a new thought is provided for rapid detection of the carbonation depth of cement-based materials.

This invention relates to a method for compressing GC-HRMS fingerprint data, specifically for metabolomics analysis of plant, food essential oils, or biological samples. The method includes three steps: extraction of EICs, column isometry, and row isometry, which converts the data into an equal-row, equal-column matrix comparable to the original data, and then combines this with classical chemometric methods. This method overcomes the drawbacks of existing GC-HRMS fingerprints, such as their massive size and complexity, and is also applicable to LC-HRMS data. While the data compression method may sacrifice m / z accuracy, the peak intensities corresponding to each m / z range can be placed in their appropriate dictionary positions, ensuring accurate m / z readings in subsequent mass spectrometry. After row isometry, the retention time remains unchanged compared to the original data. Compared to existing ROI techniques, this data compression method offers significantly faster processing speeds.

Disclosed are a THz-TDS system (S), a sample preparation and chemometric-based analysis method that enables the determination of quality control, adulteration and authenticity of all organic substances and materials, especially samples with high water content.

This invention proposes a method for rapid determination of the content of Phellodendron amurense charcoal slices processed at different temperatures using near-infrared spectroscopy. Near-infrared spectroscopy is used to collect spectral information of Phellodendron amurense charcoal slices processed at different temperatures. Background interference is eliminated through preprocessing methods such as baseline correction, standard normal variable transformation, multivariate scattering correction, and first derivative. Combined with competitive adaptive reweighted sampling, CARS combined with iterative retention of information variables, and iterative combination optimization, a partial least squares regression quantitative prediction model is established. This model achieves accurate prediction of the content of five key components: 5-O-FQA, 3-O-FQA, berberine, berberine, and berberine, with prediction correlation coefficients all exceeding 0.90. This invention combines spectral information with chemometric methods to establish a digital content prediction model based on near-infrared spectroscopy for online monitoring of the Phellodendron amurense charcoal slice processing process. It has the advantages of objectivity, speed, non-destructive nature, and reliability, effectively solving the technical problem of lack of objectivity in existing technologies based on human judgment.

The invention provides a tobacco leaf raw material spectrogram data management method and system and a storage medium. The tobacco leaf raw material spectrogram data management method comprises the steps of S1, obtaining initial spectrogram data of tobacco leaf raw materials; s2, classifying and managing the initial spectrogram data according to preset spectrogram data types to obtain target spectrogram data; and S3, performing data analysis processing on the target spectrogram data to generate an analysis result corresponding to the tobacco leaf raw material. The invention aims to provide core technical support for design and implementation of a tobacco scientific research big data management system. According to the method, spectrogram sources and formats are investigated, spectrogram data are classified, deep analysis mining is performed according to the classified spectrogram data in combination with multiple chemometrics algorithms, a foundation is laid for centralized storage, efficient retrieval, unified management and safe sharing of the spectrogram data and other scientific research data, the tobacco scientific research efficiency can be improved, and the tobacco scientific research efficiency can be improved. And powerful support is provided for industry scientific and technological innovation and decision making.

This invention discloses a method for wheat grain quality detection and functional gene analysis based on hyperspectral imaging technology, belonging to the field of agricultural testing technology. The method includes: extracting hyperspectral indices; measuring wheat grain quality indicators as manual measurements; assigning weight coefficients to each quality indicator to digitize the wheat quality phenotype; extracting characteristic wavelengths to establish predictive models for each indicator and wheat quality values; performing GWAS on hyperspectral indices and chemical indicators as phenotypic traits with genotypes to screen SNP loci, conduct co-location analysis, obtain candidate genes, and perform functional verification. This invention, through hyperspectral technology combined with chemometric modeling, is suitable for real-time monitoring during wheat quality breeding and processing; by combining spectral phenotype with GWAS gene mining, it overcomes the limitations of traditional quality detection that only serves phenotypic screening, forming a closed loop of "non-destructive detection - gene localization," providing targeted genes for wheat quality improvement.

The invention relates to the technical field of metal surface treatment and intelligent monitoring, and discloses an intelligent monitoring management system in a NiP binary alloy preparation process. The method comprises the following steps: acquiring ultraviolet-visible-near-infrared full-spectrum scanning data of a plating solution sample, constructing a three-dimensional absorption spectrum matrix, generating a separated spectral feature vector by utilizing principal component analysis, carrying out simultaneous quantitative analysis on multiple components based on a Lambert-Beer law and a chemometrics principle, and predicting a byproduct accumulation rate in combination with a recurrent neural network. Real-time monitoring and intelligent management of by-products in the NiP chemical plating process are achieved, and the technical problem that traditional single-wavelength detection is insufficient in selectivity is solved.

The present application belongs to the technical field of cross of spectrum analysis and artificial intelligence, specifically to a Raman spectrum quantitative modeling closed-loop optimization method and system based on a large language model, wherein the method comprises: constructing a historical task memory bank containing a spectrum state vector; extracting spectrum quality, baseline, spectral peak, sample distribution and other features of a new task to construct a state vector; respectively retrieving successful and failed memories based on a weighted comprehensive distance; generating a candidate modeling process using a large language model; performing verification and discriminating failure modes based on rules; generating improved actions constrained by spectroscopy and chemometrics rules; iteratively optimizing until passing the deployment checklist; and finally packaging as a spectrum workstation deployment package. The present application converts expert experience into reusable structured knowledge, realizes automatic closed loop from data to deployment, reduces the modeling threshold, and improves the model reliability and interpretability.

The present application belongs to the field of health wine quality evaluation, and particularly relates to a quality evaluation method and application of health wine with liver damage reduction function, which is based on GC-MS and LC-MS technology to establish a content detection method of various chemical components in health wine, combines chemometrics to distinguish health wines of different quality grades and screen differential markers of health wines of different quality grades, more comprehensively and objectively explores chemical components of health wines of different quality grades, and provides a reference for health wine quality control.

The invention belongs to the technical field of intelligent control, and discloses a multi-element material control system and method based on quantum sensing. The method comprises the following steps: acquiring an original quantum sensing signal through a quantum sensor mounted at a preset position, and preprocessing the original quantum sensing signal to obtain preprocessed data; performing inversion on the preprocessed data based on a chemometrics model to obtain a multivariate component prediction vector; constructing a digital twinborn body, updating the digital twinborn body according to the multivariate component prediction vector, and obtaining an updated global material twinborn state; calculating based on the multivariate component prediction vector and a preset target component formula to obtain component deviation, and performing composite optimization control in combination with the updated global material twinning state to obtain a composite control quantity; according to the method, the multi-element material component information can be obtained in real time and with high precision, the control strategy can be dynamically adjusted based on the component deviation, the limitation of traditional mechanical control is thoroughly eliminated, and the multi-element material component control precision and the product percent of pass are remarkably improved.

The invention relates to a method for rapidly predicting the content of aflatoxin B1 in corn, and belongs to the technical field of near infrared spectrum analysis. According to the method, a prediction model containing multi-branch convolution and an attention mechanism is constructed by utilizing potential relevance among material components, local and global features are captured at the same time through multi-scale convolution branches, and an ECA attention module is introduced into each branch to enhance channel importance, strengthen key information extraction and reduce redundancy; performing weighted fusion on the three branch features through a feature fusion network to adjust the contribution of each branch in overall prediction; and further feature extraction and dimension reduction are carried out on the fused features in combination with convolution and pooling operations in the feature extraction network. Compared with traditional stoichiometric modeling methods such as PLSR and SVR, the method has the advantages that the complex nonlinear relation between the near infrared spectrum and the chemical components can be effectively captured, the prediction precision and robustness of the model are remarkably improved, and rapid, lossless and high-precision detection of the aflatoxin B1 content in the corn is achieved.

The present application relates to a kind of methods for screening anti-inflammatory, antioxidant active compounds from natural Chinese herbal medicine wormwood based on spectrum-effect relationship, the method establishes the method for the common characteristic peak of the fingerprint chromatogram of wormwood extract ultra-high performance liquid chromatography.By grey correlation analysis, Pearson bivariate correlation analysis method and partial least square regression analysis etc. chemometrics method establishes the spectrum-effect relationship of wormwood anti-inflammatory, antioxidant activity, to screen the anti-inflammatory, antioxidant active compounds in wormwood.The analysis result shows that compound chlorogenic acid, isochlorogenic acid A, isochlorogenic acid C is the main anti-inflammatory, antioxidant active compound in wormwood extract.The present application provides scientific and effective method for the research of the medicinal material basis of wormwood and quality control, and provides reference for the development and utilization of wormwood.

The invention discloses a wheat grain quality detection and functional gene analysis method based on a hyperspectral imaging technology, and belongs to the technical field of agricultural detection. The method comprises the following steps: extracting a hyperspectral index; determining a wheat grain quality index as an artificial measurement value; a weight coefficient is given to each quality index, and the wheat quality phenotype is digitalized; extracting a characteristic wavelength, and establishing a prediction model of each index and a wheat quality value; gWAS, SNP site screening and co-localization analysis are performed on the hyper-spectral index and the chemical index as phenotypic characters and genotypes respectively, and candidate genes are obtained and subjected to functional verification. The method combines a hyperspectral technology with chemometrics modeling, and is suitable for real-time monitoring in wheat quality breeding and processing processes; the spectrum phenotype is combined with GWAS gene mining, the limitation that traditional quality detection only serves phenotype screening is broken through, a'nondestructive testing-gene positioning 'closed loop is formed, and a target gene is provided for wheat quality improvement.

The present application relates to a kind of urban inland river sewage intelligent detection method, comprising the following steps: 1) preparation standard sewage sample, obtain multiple sewage samples with different indicators and different index data;2) the near infrared spectrum data of all sewage samples is collected and pretreated, form near infrared spectrum data set, and be divided into training set and test set;3) construct sewage index quantitative detection model based on convolution neural network, sewage index quantitative detection model is trained and tested by training set and test set;4) collection actual water sample and divide into two parts, respectively by chemometrics and the sewage index quantitative detection model established to predict its key index data, by comparing to verify the accuracy and reliability of the model established;5) using the sewage index quantitative detection model obtained to detect the urban inland river water quality to be detected.The method is conducive to improving the speed and accuracy of urban inland river water quality detection.

Disclosed herein is a system and method are provided for rapid, high-throughput phenotyping of nutritional traits in plants using mid-infrared (MIR) spectroscopy and chemometric modeling. One or more processors control MIR sensors to capture spectral images of plant material, which are analyzed using a chemometric model, such as partial least squares regression, to determine characteristics including protein, fatty acids, dietary fiber, starch, resistant starch, sulfur-containing amino acids, and digestibility. The method supports non-destructive analysis with minimal sample preparation and is applicable to a wide range of plant species and biological materials. Results can be stored in a local or cloud database and visualized through a graphical user interface. The chemometric models may be trained and validated using K-fold cross validation and can include spectral preprocessing and interpolation filters. This enables rapid, cost-effective nutritional analysis to support plant breeding, food quality assessment, and industrial applications.

The invention provides a method for rapidly detecting the content of total flavonoids in ginkgo biloba extract based on ultraviolet spectrum, which comprises the following steps: taking a ginkgo biloba extract sample, and treating by adopting an ultrasonic-assisted extraction method to prepare flavone extract liquor; scanning the flavone extracting solution by using an ultraviolet-visible spectrophotometer to obtain ultraviolet absorption spectrum data of the flavone extracting solution in a characteristic wavelength range; and inputting the obtained ultraviolet absorption spectrum data into a pre-generated general flavone content prediction model, and directly outputting to obtain the content value of general flavone in the ginkgo leaf extract. According to the method, interference of coexisting substances in a traditional ultraviolet method is effectively overcome through a chemometrics algorithm, detection is completed within a few minutes, and the accuracy of the method is equivalent to that of a high performance liquid chromatography. The method is easy and convenient to operate, low in cost, high in efficiency and particularly suitable for rapid quality control and raw material screening in the production process of the ginkgo leaf extract.

The invention relates to the technical field of traditional Chinese medicinal materials, in particular to a detection method for a dual-wavelength fingerprint spectrum of dried pears and a control characteristic chromatogram of the dried pears, and the detection method comprises the following steps: determination of high performance liquid chromatography conditions: detection wavelengths are 280 nm (0-25 min) and 350 nm (26-90 min); preparing a mixed reference substance solution; preparing a dried pear test solution; establishing a dried pear control characteristic spectrum; detecting the quality of the dry pear sample to be detected; and analyzing the quality of the dried pears in combination with a chemometrics analysis method. The dual-wavelength fingerprint spectrum detection method provided by the invention can be used for comprehensively and effectively detecting main chemical components of the dried pears, a scientific evaluation method is provided for quality control of the dried pears, and the method can provide a scientific basis for subsequent development of dried pear medicinal and edible decoction pieces.

The invention belongs to the technical field of traditional Chinese medicine detection, and particularly relates to a method for rapidly determining the content of one or more heavy metals in gastrodia elata tubers through laser-induced breakdown spectroscopy. The method for rapidly determining the content of one or more heavy metals in gastrodia elata tubers through laser-induced breakdown spectroscopy comprises the following steps: S1, pretreating a gastrodia elata sample, and preparing a tablet as a to-be-detected sample; s2, establishment of initial spectral data: detecting the tablet prepared in the step S1 by adopting a laser-induced breakdown spectroscopy instrument, and collecting the spectral data; s3, measuring heavy metals in the gastrodia elata sample; s4, preprocessing the initial spectral data, and establishing a gastrodia elata heavy metal element content prediction model according to the heavy metal content data of the gastrodia elata sample in combination with a chemometrics method. The detection method provided by the invention can accurately and efficiently realize rapid quantitative detection of the heavy metal elements in the gastrodia elata sample.

The invention discloses a copper-based nano-enzyme, a colorimetric sensing array and application of the copper-based nano-enzyme and the colorimetric sensing array, and belongs to the technical field of nano-material preparation. The copper-based nano-enzyme is prepared through a simple coprecipitation method, and sheet-shaped nano-enzyme (the molar ratio is 1: 55. 3) or circular-ring-shaped nano-enzyme (the molar ratio is 1: 6.176) with regular morphology can be prepared respectively by accurately regulating and controlling the molar ratio of metal salt to 2-methylimidazole. A four-channel colorimetric sensing array is constructed on the basis of the two nano enzymes, and high-selectivity distinguishing and quantitative detection of seven phenolic acids such as ferulic acid and chlorogenic acid are realized by capturing differential absorbance signals generated by catalytic oxidation of TMB (tetramethylbenzidine) under the wavelengths of 370 nm and 652 nm and combining chemometrics methods such as linear discriminant analysis (LDA). The method is simple and convenient to operate, high in sensitivity and strong in anti-interference capability, and is successfully applied to detection and distinguishing of phenolic acids in actual traditional Chinese medicine samples.

The application discloses a kind of carbon metering algorithm verification methods for multi-source heterogeneous data fusion, including collecting the multi-source heterogeneous data of preset computing power center, based on physical and statistical mixed construction high-fidelity simulation test environment, generate test case data stream, the test case data stream is pretreated;Dynamic operating condition generator generates dynamic operating condition signal based on physical model, based on space-time scheduling strategy dynamic injection preset anomaly on dynamic operating condition signal to the high-fidelity simulation test environment;The dynamic operating condition signal includes load fluctuation, fuel switching transient, start-stop process;Theoretical carbon emission calculation model based on material balance and chemical metrology obtains theoretical reference value, three-dimensional consistency analysis is carried out to the output value of measured carbon metering algorithm and the theoretical reference value, and comparison data is obtained;The three-dimensional is internal logic, abnormal response and trend rationality;According to the comparison data, construct multi-source heterogeneous fusion carbon metering verification model, input the data to be verified into the multi-source heterogeneous fusion carbon metering verification model, and output verification result.

The application discloses a laser-induced breakdown spectroscopy element quantitative analysis method based on machine learning optimization, belongs to the technical field of cross of spectroscopy analysis, chemometrics and machine learning, and comprises the following steps: collecting one-dimensional spectrum data of a sample and calibrating and matching, and dividing a training set and a test set; performing SNV normalization, baseline correction and smoothing pretreatment on the spectrum; constructing a PLSR linear base learner, determining optimal latent variable parameters and outputting a prediction result; building a 1D-CNN nonlinear base learner and outputting a prediction result; calculating sample distribution deviation and prediction divergence to generate a gating weight; taking the minimum training set RMSE as a target to search for an optimal gating form and parameters, and completing fusion; and fixing parameters to infer the test set, and outputting a prediction result, an evaluation index and a gating weight. The laser-induced breakdown spectroscopy element quantitative analysis method based on machine learning optimization improves the problems of insufficient LIBS quantitative generalization ability and low fusion interpretability of existing LIBS.