161 results about "Discriminant model" patented technology

The invention discloses a tank equipment sealing micro-leakage intelligent early warning and positioning method, which comprises the following steps of: deploying acoustic sensors, vibration sensors, gas concentration sensors, temperature and humidity sensors and the like aiming at different positions of a tank to realize multi-mode original signal acquisition; various signals are standardized and corrected through denoising, normalization and structural difference mapping, and the influence of the environment and the material structure on the signals is compensated; extracting multi-dimensional feature parameters, and carrying out space-time weighted fusion by adopting an attention mechanism to generate feature vectors marked by confidence; according to the method, a self-learning anomaly recognition algorithm is combined, a judgment model is continuously optimized through transfer learning and online sample accumulation, micro-leakage anomaly judgment is achieved, accurate positioning of a tank leakage source point is executed based on a physical propagation model, and the sensitivity and the self-adaptive capacity of micro-leakage detection are improved; and leakage identification and positioning requirements in a complex environment and a dynamic working condition can be effectively met.

The invention provides an HCG and LH test paper identification method and system based on optical characteristics and a storage medium. The method comprises the following steps: firstly, collecting and generating a reflectivity curve of a test paper detection area and a quality control area; secondly, extracting a reflection characteristic value of a curve in a detection area for test paper validity verification, and entering a core identification stage if the test paper is qualified; preliminary judgment is carried out by calculating a similarity deviation value of a quality control area curve and an HCG / LH standard curve, when the deviation is significant, a preliminary recognition result is generated and enters a cross validation link, and a result is confirmed by comparing a reflection characteristic value with a dynamic threshold range; when the similarity deviation is not obvious or the cross validation is not passed, starting a pre-trained discrimination model to perform final arbitration; by constructing a quadruple judgment mechanism of validity verification, preliminary recognition, cross validation and model arbitration, the operation complexity and misjudgment risk of manual test paper type selection are overcome, and the automation degree of the detection process and the accuracy and reliability of the recognition result are improved.

The invention relates to the cross technical field of signal processing and artificial intelligence, in particular to a multi-source noise removal method and system based on DAE, and the method comprises the steps: 1, carrying out the data collection and feature extraction of multi-source noise and pure signals; step 2, constructing a de-noising recognition knowledge base based on feature analysis; step 3, constructing a deep denoising auto-encoder model based on a knowledge base; step 4, hierarchical training and optimization guided by a mixed loss function of the deep denoising model; step 5, denoising processing of a target signal and output evaluation based on a discrimination model; according to the invention, noise data in multiple fields such as electromagnetism, remote sensing and biological signals are integrated, a dynamic mixing strategy and a data enhancement technology are adopted, a training set which highly simulates a real environment is constructed, and a unique cross-scene adaptation module can perform adaptive adjustment according to signal characteristics of different application scenes; the problem that a traditional method is poor in scene adaptability is solved.

The invention provides a cutting tool wear state identification and residual life prediction method based on a digital twinning technology, and relates to the technical field of intelligent tool health. The method comprises the following steps: constructing a cutting process physical model consistent with a machine tool-tool-workpiece system and process parameters, generating a virtual monitoring signal and a virtual degradation track, and comparing the virtual monitoring signal and the virtual degradation track with actually measured data of a multi-source sensor to form virtual-real synchronous monitoring residual features; constructing a likelihood function based on the residual error, and jointly calibrating cutter individual and material parameters through Bayesian updating to obtain an updated digital twinborn model accurately matched with the current working condition; on this basis, a corrected state discrimination model is constructed, stable recognition of the tool wear state is achieved, a random degradation process model is adopted for quantitative prediction of wear evolution and residual life, and the accuracy and robustness of tool health monitoring and life prediction are effectively improved.

The invention discloses a liquid qualification detection system and method, and belongs to the technical field of intelligent detection and data analysis, multi-dimensional response signals of to-be-detected liquid under excitation of different frequencies are obtained, and a multi-dimensional response data set containing optical, acoustic, electrical and thermal physical channels is constructed; extracting a liquid component behavior characteristic spectrogram through a multi-modal characteristic fusion module; a liquid qualification judgment model is constructed based on a clustering enhanced convolutional neural network and a multi-scale attention mechanism, and classification prediction of the liquid qualification state is realized; further combining confidence coefficient calculation with historical sample database comparison, performing adaptive calibration on a prediction result, and outputting a detection result and a risk level; if the detection result is unqualified or the risk level exceeds the threshold value, an alarm mechanism is automatically triggered, and abnormal feature parameters are marked; the method has the advantages of high detection precision, high response speed, high anomaly recognition capability, excellent traceability and the like, and is suitable for scenes of liquid quality control, environment detection, biological sample analysis and the like.

The invention provides a cross-omics sparse feature selection system and method based on hierarchical causal modeling, and the system comprises a data input and preprocessing module which is used for receiving multi-omics original data of a multivariate sample; the hierarchical causal structure learning module is connected with the data input and adaptive preprocessing module and is used for constructing a cross-omics hierarchical causal topology; the causal-oriented sparse feature selection module is connected with the hierarchical causal structure learning module; and the model retraining and integration module is used for constructing a three-layer weighted integration discrimination model based on the screened markers, optimizing the fusion weight of each layer through a gradient descent algorithm, and outputting a final prediction result. According to the method, the protein-metabolism biological hierarchy relationship and serum-urine complementary information are fully utilized, and the method has good generalization ability and can be widely applied to marker mining and prediction modeling of cancers, metabolic diseases and the like, so that the accuracy and reliability of precise medical treatment are improved.

The invention discloses a smart city public facility supervision method based on the Internet of Things, and the method comprises the steps: carrying out the multispectral collection and space marking of a surface block of a to-be-detected circuit board, and achieving the standardized preprocessing and physical feature extraction of multi-label high-dimensional pixel data; according to the method, material spectral features and surface texture data are combined, a clustering analysis and supervision discrimination model is used for accurately discriminating the type of a block material, material attributes and multi-spectral features are fused, and pixel-level thickness prediction and dynamic adaptive correction are realized through a machine learning model. The system can automatically monitor drifting of the material and the mapping relation, and performs real-time optimization on the mapping model based on periodic calibration data.

The invention provides an attack technology and tactical identification method oriented to honey array linkage. The method comprises the following steps: coding according to malicious sample data and associated TTP labels, and constructing a training data set; constructing an interpretable discrimination model for binary classification modeling to obtain a behavior triggering weight vector and an offset item of the malicious sample; extracting dominant trigger rules to construct a mapping inference rule base; obtaining alarm data, extracting a behavior clue based on a preset standard behavior dimension set, converting the behavior clue to obtain a trigger identifier, and mapping the alarm data into an alarm behavior vector; constructing a prediction TTP label set of the alarm behavior vector and recording a trigger path; and encapsulating the behavior semantic data, constructing an execution strategy response rule set, performing mapping in the execution strategy response rule set according to the behavior semantic data to obtain an execution strategy, and adjusting honey array deployment according to the execution strategy. By applying the method, accurate identification and transparent reasoning of the potential TTP in the attack activity can be constructed and realized, and linkage scheduling of a defense system is supported.

The invention relates to the field of vulnerability evaluation of extreme rainfall induced mass landslide, in particular to an extreme rainfall mass landslide vulnerability evaluation method fusing diffusion generation and interpretable learning, which comprises the following steps: firstly, constructing a multi-dimensional factor data set, and realizing rasterization preprocessing; secondly, establishing a feature response analysis module, identifying main control factors of landslide occurrence and eliminating redundant variables; then, a denoising diffusion probability model is introduced, and an enhanced balance sample library is constructed; then, carrying out landslide probability prediction based on a multi-algorithm fusion integrated discrimination model, and outputting a grid-level landslide occurrence probability; and finally, minimizing intra-class variance and maximizing inter-class variance by using a natural breakpoint method, determining an optimal grading threshold set, and realizing landslide susceptibility grade division and spatial mapping output. Under the extreme rainfall condition, the method can effectively characterize the susceptibility zoning influence of the mass-occurring landslide flow slip catastrophe process, and achieves high-precision landslide susceptibility evaluation.

The invention provides an urban built-up area air quality space-time evolution and exposure risk prediction method, and relates to the technical field of electrical digital data processing.The space-time evolution method comprises the steps that a to-be-monitored target area is discretized into a cubic sampling domain, an execution flight path of an unmanned aerial vehicle is planned, and a sparse data set containing five-dimensional features is constructed; executing iterative up-sampling operation, and converting the sparse data set into a dense feature point set covering a sampling domain; calculating a pollutant transmission flux vector of each node in the dense feature point set, constructing a weighted reverse tracking vector pointing to a suspected source, and constructing a three-dimensional traceability probability cone in combination with turbulence intensity; extracting a centroid offset coefficient and an axial dispersion, and identifying an emission working condition label of the pollution source through an emission working condition ternary discrimination model; executing multi-source probability field superposition fusion, and determining an estimation coordinate of a pollution source; and executing forward space-time diffusion simulation based on the estimated coordinates, and outputting a three-dimensional risk early warning graph.

The invention relates to a multi-modal zero-speed integrated navigation method based on OpenCV binocular recognition, which comprises the following steps: constructing a multi-modal zero-speed discrimination model through heterogeneous data fusion of a binocular camera and an inertial measurement unit, realizing rapid extraction of optical flow features by using a CUDA acceleration module of OpenCV, and eliminating transmission delay in combination with a high-precision timestamp synchronization technology; a zero-speed judgment algorithm based on a dynamic weight fusion rule is designed, combined decision making is carried out on the angular speed variance of the gyroscope, the acceleration module value statistics and the binocular optical flow displacement, and the zero-speed misjudgment rate is reduced to 3.2% from 25% of a traditional method; meanwhile, a Kalman filtering model is adopted, speed / attitude dual observation constraints are injected in a zero-speed interval, inertial device zero offset and visual scale drift are compensated synchronously, and the orientation precision error lt after 3-minute rapid alignment is achieved; 6 '.

The invention discloses a method for analyzing component difference between Maotai-flavor yeast and yeast-making wheat by using non-targeted metabonomics. The method comprises the following steps: S1, pre-treating a sample; s2, detecting each sample by adopting the combination of an ultra-high performance liquid chromatograph and a quadrupole time-of-flight mass spectrometer; s3, acquiring original data, performing peak extraction, peak alignment and normalization by adopting metabonomics data analysis software, and evaluating the overall difference and intra-group variation among sample groups by adopting principal component analysis; constructing a grouping discrimination model through discriminant analysis of an orthogonal partial least square method; determining differential metabolites of the two groups of samples by taking variable projection importance (VIP) greater than 1 and statistical significance P less than 0.01 as a primary screening standard and combining a secondary screening standard that the difference multiple log2FC greater than 2 is up-regulated and the difference multiple log2FC less than-2 is down-regulated; s4, performing compound structure and category annotation on the screened differential metabolites through a metabolome database; and performing pathway enrichment analysis by adopting a statistical test method, and determining a core metabolic pathway enriched by the differential metabolites.

The application discloses a polymer electrolyte molecular structure formula generation method, system, device and medium, and belongs to the technical field of lithium batteries. The polymer electrolyte molecular structure formula generation method comprises the following steps: obtaining a performance data set and a molecular structure formula data set of a polymer electrolyte; constructing a discriminant model by using the performance data set; constructing a generative model by using the molecular structure formula data set; training the generative model based on the discriminant model; if a molecular structure design task is received, generating a plurality of new molecular structure formulas of polymer electrolytes by using the trained generative model, and screening the new molecular structure formulas of polymer electrolytes by using the discriminant model to obtain a molecular structure formula meeting the molecular structure design task. The application can automatically generate a molecular structure formula of a polymer electrolyte, and improve the generation efficiency and effectiveness of the molecular structure formula.

The present application relates to the technical field of speech processing, which can be applied to business scenarios such as financial technology and medical health, and discloses a data tracing method and device based on collaborative training, equipment and medium, comprising: obtaining an initial intermediate feature representation output by a generation model and a discrimination model, generating speech data and inputting the discrimination model to produce a discrimination loss, updating the generation model based on the discrimination loss to obtain a traceable intermediate feature representation, generating an updated intermediate feature representation using the updated generation model, generating training speech data and inputting the training speech data and real data into the discrimination model to obtain an updated discrimination model, and using the updated discrimination model to discriminate and output a detection result of whether the input speech data is generated by the generation model when receiving the input speech data. The present application trains the generation model and the discrimination model collaboratively, so that the generation model outputs speech embedded with traceable features, while improving the discrimination model's ability to reject unknown sources, thereby reducing waveform disturbance and accurately determining the source.

This invention discloses a multi-task behavioral-EEG synchronous monitoring method for schizophrenia screening, relating to the field of schizophrenia screening. The method includes: designing a multi-task temporal loading paradigm based on clinical screening needs; simultaneously collecting EEG signals and behavioral data of subjects during the execution of the multi-task temporal loading paradigm, and preprocessing the collected raw data; extracting multidimensional features from the preprocessed data, wherein the multidimensional features include EEG feature groups, behavioral feature groups, and time-varying feature groups; constructing a multimodal fusion discriminant model, inputting the multidimensional features into the multimodal fusion discriminant model, and outputting a baseline risk probability and a schizophrenia risk index. The advantages of this invention are: achieving efficient, accurate, and objective screening of the core cognitive dimensions of schizophrenia, effectively improving the sensitivity and specificity of screening.

The application relates to the field of extreme rainfall-induced group landslide susceptibility evaluation, in particular to an extreme rainfall group landslide susceptibility evaluation method fusing diffusion generation and explainable learning, which comprises the following steps: firstly, a multidimensional factor dataset is constructed to realize grid pretreatment; secondly, a feature response analysis module is established to identify main control factors of landslide occurrence and remove redundant variables; then, a denoising diffusion probability model is introduced to construct an enhanced balanced sample library; next, a landslide probability prediction is carried out based on an integrated discriminant model of multi-algorithm fusion, and a grid-level landslide occurrence probability is output; finally, the natural breakpoint method is used to minimize intra-class variance and maximize inter-class variance, so that an optimal grading threshold set is determined, and landslide susceptibility grading and spatial mapping output are realized. Under the condition of extreme rainfall, the application can effectively represent the susceptibility partition influence of group landslide flow slide catastrophe process and realize high-precision landslide susceptibility evaluation.

This invention discloses a method and system for delineating soil contaminated areas. The method includes: generating a first pollution feature layer by fusing historical pollution data and remote sensing spectral features, and generating a second pollution concentration layer based on an anisotropic pollution diffusion model; analyzing whether pixel spectral features indicate pollution using a trained discriminant model, and marking pixels as core, suspicious, or clean pixels based on concentration exceeding the standard; determining the diffusion correlation between suspicious areas and adjacent core areas by calculating boundary migration feature similarity; merging highly correlated areas according to pollution diffusion fusion rules based on the correlation results to form pollution diffusion areas; and finally optimizing, aggregating, and classifying all contaminated areas based on preset rules to generate a final soil contaminated area delineation map with risk levels. This invention achieves automated and high-precision identification and delineation of soil contaminated areas.

The invention relates to a part boxing feasibility discrimination method based on a graph neural network, and the method comprises the steps: S1, receiving the size information of a to-be-discriminated container, and the size information of all to-be-boxed parts; s2, constructing container nodes and part nodes; s3, generating feature representations of container nodes and part nodes; s4, establishing container part edges for connecting the container nodes and the part nodes respectively, and generating feature representations of the container part edges; s5, respectively establishing part edges connected with any two part nodes, and generating feature representation of each part edge based on the size information of the corresponding two parts; and S6, inputting the heterogeneous graph containing the container nodes, the part nodes, the container part edges and the part edges into the trained discrimination model to obtain a discrimination result. Compared with the prior art, the method has the advantages that the discrimination efficiency can be greatly improved under the condition that the high discrimination accuracy is guaranteed, and the like.

This invention discloses a control method, system, device, and medium for air switches with intelligent anti-false tripping and conditional automatic reclosing functions. Belonging to the field of air switch control technology, the invention includes: collecting multi-source heterogeneous data from the air switch; processing the collected data to obtain a fused feature vector and quality score; performing feature extraction and fusion operations on the fused feature vector to obtain a dimensionality-reduced fused state feature vector; inputting the dimensionality-reduced fused state feature vector into a discrimination model to determine the tripping cause, and performing a reclosing operation after determining the delay time according to a delay mechanism; performing multi-source verification before executing the reclosing operation; initiating a delayed retry mechanism when the reclosing conditions are not yet met; and entering a blocking state when the number of consecutive retries reaches a threshold and reclosing is still unsuccessful; and recording the entire process data to construct a knowledge base. This invention significantly reduces the risk of false closing and improves the safety and continuity of power restoration.

The application discloses a kind of based on electronic nose's insect tea species identification method, belong to insect tea aroma detection technical field.The method includes: selecting training set and test set insect tea sample;Through the optimal parameter of single factor test screening carries out sample pretreatment and electronic nose detection, obtains sensor response characteristic value;Application principal component analysis (PCA) constructs category distribution model, obtains PCA distinction diagram;Application discriminant function analysis (DFA) constructs category discriminant model;Test set sample characteristic value is projected into PCA distinction diagram, and it is input DFA model to obtain discriminant result, and carries out visual verification.The method of the application is simple in operation, result is objective and reliable, can realize the accurate identification of different plant raw materials insect tea, and the overall accuracy reaches 91.84% by 49 unknown samples verification.

The application provides a method for identifying attack technology and tactics facing the linkage of honeycomb, comprising: encoding and constructing a training data set according to malicious sample data and associated TTP labels; constructing an interpretable discriminant model for binary classification modeling to obtain the behavior trigger weight vector and bias term of the malicious sample; extracting explicit trigger rules to construct a mapping inference rule library; obtaining alarm data, extracting behavior clues based on a preset standard behavior dimension set and converting to obtain a trigger identifier, mapping the alarm data into an alarm behavior vector; constructing a prediction TTP label set of the alarm behavior vector and recording the trigger path; packaging behavior semantic data, constructing an execution strategy response rule set, mapping the behavior semantic data in the execution strategy response rule set to obtain an execution strategy, and adjusting the deployment of the honeycomb according to the execution strategy. The method can construct and realize the accurate identification and transparent inference of the potential TTP in the attack activity, and support the linkage scheduling of the defense system.

The invention provides a fluid-structure interaction multi-physics field prediction method for an offshore wind plant. According to the method, any Lagrangian-Euler mapping is introduced, a computational domain containing a structure and fluid is expressed as a deformation computational grid dynamically evolved along with structural vibration or free interface change, time sequence prediction is conducted on a grid displacement field through a first generator, and then the computational grid is updated; efficient prediction of fluid field or multi-physical field state variables is achieved through a second generator; moreover, a discrimination model is introduced in a prediction model training stage, and combined constraint is carried out on statistical consistency and physical rationality of a prediction result in combination with a physical constraint loss function. According to the decoupling prediction method, the moving boundary calculation precision is improved by adding physical constraints, so that the prediction precision is improved, powerful technical support can be provided for key links of offshore wind power engineering, and the decoupling prediction method can be applied to optimization of structural design, fine evaluation of the operation state and prospective prediction and early warning of extreme environment working conditions.

The application relates to the field of biological medicine, and particularly discloses application of saliva TP17, TP47 and TP15 specific antibodies in preparation of an auxiliary diagnostic product for neurosyphilis. Based on specific antibody immunoglobulin G (IgG) of Treponema pallidum in saliva, combined detection of saliva TP17 / IgG, TP47 / IgG and TP15 / IgG outputs a risk value of neurosyphilis of a subject, or a four combined Logistic regression discriminant model is constructed by combining serum TRUST titers, and the subject is stratified into a low-risk or high-risk group based on a preset judgment threshold, so that the comprehensive recognition capability for neurosyphilis is improved. The saliva is used as a detection sample, and the application has the advantages of non-invasiveness, convenience, easy popularization, repeatable collection and the like, and can be used for early screening, auxiliary diagnosis and clinical path management of neurosyphilis.

The invention discloses an end-to-end prediction method for the dust removal efficiency of a wet dust collector, and the method comprises the steps: firstly obtaining an actual pressure fluctuation signal, dividing the actual pressure fluctuation signal into a plurality of intervals according to the size of the dust removal efficiency, and selecting actual pressure fluctuation signal segments corresponding to the actual dust removal efficiency in different intervals through the actual pressure fluctuation signal corresponding to the actual dust removal efficiency; respectively converting the signal segments in different intervals into images by adopting two conversion methods; fusing the images by adopting different image feature fusion methods to form an image data set; a set network model is adopted to train different image data sets of each interval, then different initial discrimination models are formed, discrimination weights of the different initial discrimination models in each interval are dynamically calculated according to accuracy rates of the different initial discrimination models in each interval, performance advantages of each model in a specific interval are utilized to the maximum extent, and the discrimination accuracy of the different initial discrimination models in the specific interval is improved. And a dust removal efficiency fusion prediction model is obtained, so that high-precision and high-robustness dust removal efficiency monitoring is realized.

The invention relates to a method and device for judging whether an artificial CO2 gas cap is formed or not for an oil reservoir with a stratigraphic dip angle, and is applied to the oil reservoir with the stratigraphic dip angle. The method comprises the following steps that the CO2-crude oil capillary force gradient, the CO2 gas phase pore pressure gradient, the CO2 gas buoyancy force gradient and gravity gradient difference data of a target oil reservoir in the stratum direction of the CO2 injection well construction position are obtained; calculating a dimensionless numerical value formed by the artificial gas cap of the target oil reservoir based on a pre-constructed mechanical discrimination model for the dimensionless number of the artificial gas cap; and judging whether the dimensionless numerical value is greater than a first threshold value or not, if so, determining that the target oil reservoir artificial gas cap is formed, and if not, determining that the target oil reservoir artificial gas cap is not formed. The method can solve the problem that mechanical action mechanisms and conditions formed by the artificial gas cap of the oil reservoir with the dip angle are incomplete, imperfect and indefinite, and can conveniently judge whether the artificial gas cap can be formed by gas injection of the oil reservoir with the dip angle.

This invention discloses a method and system for water hammer protection and control in large-scale drip irrigation networks based on pressure feedback, relating to the field of drip irrigation water hammer prevention and control technology. The method includes: constructing the drip irrigation network topology using GIS digital modeling technology and marking the locations of water hammer protection devices; collecting network water condition data through sensor arrays, and constructing a network water condition dataset after preprocessing; calculating the water hammer risk coefficient of each network segment using a covariance matrix discriminant model based on the network topology and water condition dataset, selecting a set of risky network segments, solving the pre-control action parameters of the adjustable water hammer protection device using a particle swarm optimization algorithm, and issuing the device for execution after verification through steady-state and transient joint hydraulic simulations, thereby predicting and preventing water hammer occurrence and ensuring steady-state network pressure. This invention achieves accurate identification and efficient control of water hammer risk in large-scale drip irrigation networks, reduces water hammer protection energy consumption, and ensures stable operation of large-scale drip irrigation networks.

The invention belongs to the technical field of quality evaluation of traditional Chinese medicinal materials, and provides a poria cocos medicinal material quality evaluation method based on an intelligent sensory technology, which comprises the following steps: S1, data acquisition: respectively acquiring tactile, visual, olfactory and gustation data of different poria cocos samples by using a texture analyzer, a color photometer, an electronic nose and an electronic tongue; s2, model establishment: carrying out data fusion on the tactile, visual, olfactory and taste data of the different poria cocos samples, and establishing a production place identification model or an authenticity identification model or a grade discrimination model by adopting PLS-DA; s3, sample detection: inputting tactile, visual, olfactory and taste data of a to-be-detected poria cocos sample into the production place identification model, the authenticity identification model or the grade identification model, and judging the type, authenticity or grade of the production place according to a model prediction result. The method can distinguish poria cocos from different producing areas, and provides a scientific basis for quality control and producing area identification of poria cocos.

The invention provides a sedimentary subfacies and microfacies quantitative identification method, and the method comprises the steps: S1, constructing a sedimentary subfacies and sedimentary microfacies database, and determining a sea or lake plane evolution process; s2, establishing a sedimentary concept model, and extracting a data set of virtual well lithology, sedimentary subfacies and sedimentary microfacies; s3, carrying out logging curve forward modeling simulation on the lithology of the virtual well; s4, establishing a discrimination model based on a support vector machine supervision algorithm; s5, verifying the accuracy of the discrimination model; and S6, carrying out sedimentary subfacies and sedimentary microfacies combined judgment on a to-be-evaluated well by utilizing the judgment model to obtain a sedimentary subfacies and sedimentary microfacies judgment result. Batch, efficient and accurate identification of sedimentary subfacies and microfacies of multiple types of clastic rocks can be carried out, the method has important application value for prediction of clastic rock reservoir distribution rules and remaining oil, and meanwhile, favorable technical support is provided for construction of intelligent oil fields and geological large databases.

The application discloses a sheep meat tracing method based on mineral fingerprint characteristics and belongs to the technical field of food tracing detection. The method takes the longissimus dorsi muscle of Yemule Baiyang, Kazakh sheep and Turpan black sheep in northern Xinjiang as samples, determines the content of 28 kinds of mineral elements by using an ICP-MS method, screens ten kinds of elements B, Na, Mg, V, Zn, As, Rb, Sr, Mo and Ag based on Wilks' Lambda criterion, and constructs a stepwise linear discriminant model, wherein the discriminant accuracy of model back substitution and cross validation reaches 100%. The method has strong pertinence, high precision and good stability, can quickly and accurately identify three kinds of characteristic sheep meat, and provides a reliable technical means for Xinjiang northern characteristic sheep meat origin tracing, variety identification, brand protection and market supervision.

The invention discloses an electric energy meter internal fault discrimination method and system based on fusion image recognition, and relates to the field of electric energy metering, and the key points of the technical scheme are that the method comprises the steps: obtaining global image data in an electric energy meter, and carrying out the mask processing of the global image data, and obtaining the local image data of each function module of the electric energy meter; inputting the global image data and the local image data into the initialized convolutional neural network in parallel, and outputting a prediction result; a loss value between a prediction result and a real result is calculated by adopting a loss function obtained by weighted summation of order likelihood loss, graph regular loss, comparison loss, consistency loss and total variation regular loss, and back propagation is carried out based on the loss value to obtain a gradient of network parameters; the network parameters of the initialized convolutional neural network are updated according to the gradient until the maximum training frequency is reached, and a fault discrimination model in the electric energy meter is output; and performing fault discrimination on the acquired to-be-discriminated electric energy meter image based on the fault discrimination model.