44 results about "Linear correlation analysis" patented technology

The invention provides a fault self-diagnostics method for multi-sensor system, which includes the following steps: firstly, carrying out linear analysis to the information obtained from each sensor of the multi-sensor system having relativity output, and then comparing corresponding relativity and setting threshold value to realize sensor array fault self-diagnostics of the multi-sensor, wherein, as the number of the sensor having relativity output is two, fault-diagnostics of the sensor system can be realized thereby providing alarm information; as the number of the sensor having relativity output is three, fault-diagnostics of the sensor system can be realized thereby providing alarm information and isolating the fault to guarantee normal operation of the system. The effects of the invention are that self-diagnostics, alarm and fault-isolation for the sensor are realized and single system for monitoring sensor operation status is saved thereby simplifying the system configuration and increasing stability of the self-diagnostics system through using the relativity between the information measured by each sensor in the multi-sensor system and using multi-channel measuring signal.

The invention relates to a method for judging abnormal electricity consumption behaviors of users based on an EEMD method. The method comprises the following steps of S1, carrying out cluster on electrical loads of the users by adopting a self-organizing map neural network method; S2, selecting one cluster from the clustering results of the step S1 at random and selecting any user in the cluster at random to obtain load data on any two identical time periods; S3, decomposing data in the step S2 into an IMF component and residual trend terms by adopting an empirical mode decomposition method; S4, carrying out linear correlation analysis on load residual terms of the two time periods respectively to obtain rho1 and rho2; S5, analyzing the rho1 and the rho2. The method for judging the abnormal electricity consumption behaviors of the users based on the EEMD method enables power supply enterprises to detect the abnormal behaviors in the electricity consumption process of the users, corresponding measures can be taken, and better services can be supplied to the users.

The present invention discloses a method for evaluating the coupling relationship between the collision waveform and the restraint system property, and overcomes the problem that the CAE simulation technology has huge calculation amount and is time-consuming when the coupling relation between the vehicle body structure and the occupant restraint system is studied. The method comprises: 1. establishment of the occupant response surface based on the single-degree-of-freedom model: 1) defining shape parameters of a dual trapezoidal wave and a trilinear constraint stiffness curve, 2) solving the occupant response surface with the single-degree-of-freedom model, and 3) respectively averaging the response surface in the X and Y directions; 2. correlation analysis of occupant response and collision waveform parameters: 1) carrying out supplementary definition on the collision waveform parameters, and 2) extracting the correspondence between basic parameters of the collision waveform and the Av from the occupant response surface, and carrying out linear correlation analysis; and 3. evaluation of the coupling relation between the collision waveform and the restraint system property: 1) establishing the comprehensive evaluation index alpha of the collision waveform, 2) establishing the comprehensive evaluation index beta of the restraint system, and 3) establishing ao of the comprehensive evaluation index of the collision waveform and the restraint system.

The invention discloses a line transformation relation abnormity judgment method based on correlation between electric quantity and line loss. The line transformation relation abnormity judgment method includes a data acquisition module which is used for acquiring electric quantity information, a data processing module which is used for analyzing correlation between electric quantity and line loss, and a data display module which is used for displaying abnormal line transformation relations, wherein the data acquisition module, the data processing module and the data display module are sequentially connected. The line transformation relation abnormity judgment method utilizes power consumption, voltage, current and other data of a line and a transformer provided by a power consumption information acquisition system, and utilizes a big data analysis technology and a transformer area line loss non-linear correlation analysis method to construct the line transformation relation error correction model independent of the local communication relation and find out the line transformation relation with statistical errors, so as to improve the accuracy of topological information of the power transmission line and provide technical guidance for conducting line transformation relation on-site troubleshooting, so that the calculation precision of line loss is improved, and technical support is provided for lean marketing management.

The embodiment of the invention provides a covert fault troubleshooting method and apparatus of a 4G base station. The method comprises the following steps: obtaining relevant dimensionality data, andintegrating the relevant dimensionality data to obtain a data index set; obtaining a correlation coefficient between index items of the data index set based on a linear correlation analysis method, and performing dimensionality reduction on the data index set according to the correlation coefficient to obtain a dimensionality reduction data set; and inputting the dimensionality reduction data setinto a trained fault positioning model to obtain a fault identification result. According to the covert fault troubleshooting method and apparatus of the 4G base station provided by the embodiment ofthe invention, the AI machine learning technology is imported, the incidence relation between deep factors of various covert faults of the 4G base station are mined to form an intelligent covert fault troubleshooting model to achieve automatic identification and diagnosis of problems.

The invention relates to the technical field of motor control, in particular to a variable frequency motor dynamic adaptive control method and system based on multi-parameter analysis. The method comprises the following steps: collecting a multi-dimensional electrical operation monitoring parameter flow of a variable frequency motor, carrying out multi-parameter nonlinear correlation analysis and parameter topological correlation reconstruction, and constructing a multi-dimensional feature topological correlation network; a variable frequency motor multi-working-condition travel history database is obtained, multi-working-condition disturbance transient response analysis is carried out, multi-modal behavior prediction evolution is carried out based on the multi-dimensional feature topological association network, and a dynamic multi-modal behavior prediction engine is constructed; and acquiring multi-part electromagnetic sensing parameters of the motor, and performing abnormal electromagnetic intensity fluctuation detection and abnormal part power loss calculation to obtain abnormal part power loss characteristics. The self-adaptive real-time parameter motor control is realized, the energy efficiency of the motor is improved, the maintenance frequency and cost are reduced, and the full-life-cycle optimal control of the motor is realized.

The invention discloses an estuary dam geometrical morphology measuring method. The method includes the following steps that firstly, a prototype geologic model is determined according to measuring region geological data, a physical model is established according to the similarity theory of sedimentary physical simulation, an experimental scheme is designed accordingly, an experiment is carried out on the basis of the experimental scheme and the sedimentation process is controlled; secondly, the sedimentation result is researched through a section cutting method, the position of an estuary dam is determined, length and width data of the estuary dam and the extended distance of the lake shoreline are measured, a planar distribution diagram of the estuary dam is drawn, and thickness data of the estuary dam are measured in combination with the section; thirdly, linear correlation analysis is conducted on the obtained length-thickness and length-width data of the estuary dam; fourthly, modern sedimentation estuary dam length and width data measured on the basis of satellite photos are obtained, statistical analysis is conducted on the modern sedimentation estuary dam length and width data, and a research area estuary dam length-width empirical formula is established by synthesizing water tank simulation and modern sedimentation measuring results. The method has the advantage of being capable of guiding exquisite configuration anatomy of a work area estuary dam and can be widely applied to the technical field of reservoir description.

The invention discloses a method and a device for quantitatively distinguishing massive sandstones of the main body of a phase control sand body structure. The method comprises: dividing small layersand taking the comprehensive logging interpretation result as the object of the sand body structure research; performing linear correlation analysis on specified parameters and shale content, selecting top N items with better correlation as the basis of the comprehensive index method, and obtaining the threshold value of the specified parameters according to different log series values and core measured data corresponding to massive sandstones and bedding sandstones; determining a weight coefficient corresponding to each specified parameter; performing data standardization processing on top Nspecified parameters, and calculating the comprehensive index for the parameters after the data standardization processing, in which a weight based on the shale content is used as a coefficient and the directly / inversely proportional relationship of electrical characteristic of the massive sandstones is used as a basis; calculating the smoothness of the comprehensive index through a variance formula and a variation formula. According to the method and the device for quantitatively distinguishing the massive sandstones of the main body of the phase control sand body structure, the massive sandstones can be accurately identified to guide the fine exploration and development of lithological oil-gas reservoir.

The invention provides a method for measuring factors affecting rhizosphere soil amino acid availability. The method comprises the steps that typical zonal soil is collected for sample pretreatment comprising screening and grinding, the soil is placed into an artificial greenhouse for culturing plants, labeled amino acid is added, the soil plant sample treatment is performed to measure the physicochemical property of the soil, linear correlation analysis is carried out on the physicochemical property of the soil and the amino acid absorptive amount, and the main soil factors affecting the soil amino acid biological validity are researched. The method is easy to implement, the factors affecting the amino acid biological availability significantly can be found from complex factors through correlation detection, and a method foundation is provided for researching and controlling amino acid biological availability.

The invention relates to a power grid accurate unit load prediction method and system based on deep learning. The method comprises the following steps: acquiring operation monitoring parameters and equipment environment parameters of electric equipment in a power grid area; dynamic voltage feature extraction is carried out on the operation monitoring parameters of the electric equipment in the power grid area, and voltage fluctuation trend feature data and multi-level load curve features are generated; performing nonlinear correlation analysis on the voltage fluctuation trend characteristic data and the multi-level load curve characteristics according to the equipment environment parameters to generate load-environment deep nonlinear correlation data; identifying power grid area electric equipment to obtain power grid area electric equipment nodes; based on the load-environment deep nonlinear associated data, carrying out accurate unit clustering division on power grid area electric equipment nodes, and constructing a power grid unit load characteristic network; a precision unit type is generated based on the plurality of grid precision units. According to the invention, accurate power grid load prediction is realized.

The invention discloses a reservoir parameter prediction method based on an improved Transform. The reservoir parameter prediction method comprises the following steps: collecting logging data and corresponding rock core lithologic data; preprocessing the logging data through a rock core homing method; selecting an input logging characteristic curve through Pearson linear correlation analysis, and carrying out standardization processing on the input logging characteristic curve; the method comprises the following steps of: improving a Transform by using a TransBlock multi-head attention mechanism and a Real-LN residual structure, and performing feature extraction on a training sample by using a TransBlock algorithm obtained after improvement to form a TransBlock feature model; and obtaining a reservoir parameter prediction result from the to-be-detected data through the TransBlock feature model. According to the method, the problems of less data and insufficient generalization ability in reservoir parameter prediction are solved by improving Transformer, the prediction performance and generalization adaptation ability of the model are improved through limited logging data and hidden correlation between the logging data, and the accuracy of reservoir parameter prediction is remarkably improved.

The invention provides a method for rapidly identifying shallow lake sediment pollution layering information through shallow cutting. The method comprises the following steps of: scanning by a shallow cutting device, collecting a columnar sample, analyzing the columnar sample and linear correlation, and finally drawing a contour map to obtain a sediment pollution layering result. According to the method for rapidly identifying the shallow lake sediment pollution layering information through shallow cutting, on the basis of shallow cutting scanning and columnar sample pollutant determination, linear correlation analysis of the water content and the pollutant content of the sediment in each layer is added, so that the pollution layering information of the sediment in the lake is rapidly identified through shallow cutting.

The invention discloses an efficient control method for realizing optical network construction on the basis of linear correlation analysis, and belongs to the technical field of communications. According to the method, multi-dimensional optimized decomposition is carried out on optical access network hotspots by adopting linear correlation of feature vectors, and the most suitable construction models are matched to satisfy the construction demands of the hotspots. According to the method, linear matching of the optical access network hotspots and the construction optimized models is newly provided, an approximation set is found, a Bayesian network is constructed to carry out decision judgement, and the optimum construction models are selected to realize the efficient construction of the hotspots.

The invention discloses a calculation method for quickly determining phreatic water level fluctuation characteristics. The calculation method comprises the following steps: determining a target analysis area of phreatic water level fluctuation characteristics; collecting rainfall data and phreatic water level monitoring well actual measurement data in an administrative region where the target analysis region is located; constructing a coordinate system; drawing a point diagram on a coordinate system according to the collected sum; carrying out linear correlation analysis on the drawn point graph to obtain a linear correlation linear equation; calculating a correlation coefficient R of the linear correlation linear equation to verify whether the linear correlation linear equation is established or not; and determining the submersible water level burial depth or elevation of the target analysis area by utilizing the linear correlation linear equation and the rainfall data of the target analysis area so as to analyze the submersible water level fluctuation characteristics of the target analysis area. The method has the advantages that the fluctuation characteristics of the phreatic water level can be quickly determined, and a basis is provided for evaluating migration of pollutants in underground water and investigating the environment of a polluted site.

The invention discloses a dimension reduction and correlation analysis method suitable for large-scale data, and the method comprises the steps: projecting high-dimensional data to a Fourier domain, and converting a solving feature vector problem of linear correlation analysis into a meaningful Fourier domain basis; because the Fourier domain basis is predefined and the characteristic value distribution of the data is ordered, accelerating training by inputting the training samples in batches until the required Fourier basis is stable and ordered; determining the number of Fourier bases and aprojection matrix, and multiplying the projection matrix by the high-dimensional data set to obtain a low-dimensional data set so as to facilitate rapid processing of data. According to the data dimension reduction method, on the basis of fast Fourier transform and correlation analysis, noise and redundant information in a high-dimension data set can be removed, unnecessary operation processes indata processing are reduced, and the running speed and the memory use efficiency in data dimension reduction calculation are improved.

The invention is suitable for the technical field of power grid monitoring, and relates to a method for analyzing abnormal power utilization based on LTU and multi-dimensional data, a medium and a terminal, and the method comprises the steps: building a power grid relation model; the method comprises the following steps: connecting an ammeter and LTU equipment into a master station, and collecting electric energy indicating value data and topology identification data in a specific time period; matching and comparing the topology identification data with the power grid relation model, automatically correcting a related power grid hierarchical membership relation, putting user electricity meters of which the topology relation cannot be identified into a preset power grid relation user electricity meter pool, and putting related monitoring points into a preset power grid relation monitoring point pool; accounting the loss rate data of each monitoring point; carrying out linear correlation analysis; aggregating to obtain a characteristic information matrix of each pre-dispatching power grid relation monitoring point and a pre-dispatching power grid relation user electric meter; carrying out multi-dimensional data fusion analysis and correction topology linkage iteration; and obtaining an abnormal electricity user roster. The method is simple in process and convenient to operate, and effectively improves the analysis accuracy of the abnormal power consumption of the transformer area.

The invention provides a method and device for clustering the states of a blast furnace. The method comprises the steps that process parameters of the states of the blast furnace are collected and preprocessed; state feature data of the process parameters is extracted; the state feature data of the process parameters is subjected to linear correlation analysis, and the linear correlation result between the state feature data is determined; when it is determined that the linear correlation result shows linear independence, a K-means algorithm is utilized for clustering the state feature data, and the clustering result of the states of the blast furnace is acquired; and thus, the states of the blast furnace are precisely divided according to the clustering result, and correlation analysis of operation and indexes can be carried out conveniently so that a blast furnace superintendent can grasp the current state of the blast furnace to precisely guide blast furnace operation.

The present invention relates to a method and system for accurate unit load prediction of a power grid based on deep learning. The method includes the following steps: acquiring operation monitoring parameters of power consumption equipment and equipment environment parameters in a power grid area; extracting dynamic voltage characteristics from the operation monitoring parameters of power consumption equipment in the power grid area to generate voltage fluctuation trend characteristic data and multi-level load curve characteristics; performing non-linear correlation analysis on the voltage fluctuation trend characteristic data and multi-level load curve characteristics according to the equipment environment parameters to generate load-environment deep non-linear correlation data; identifying power consumption equipment in the power grid area to obtain power consumption equipment nodes in the power grid area; performing accurate unit clustering division on the power consumption equipment nodes in the power grid area based on the load-environment deep non-linear correlation data to construct a power grid unit load characteristic network; and generating accurate unit types based on multiple accurate power grid units. The present invention realizes accurate power grid load prediction.

The invention discloses a noninvasive method for determining iron content in brain tissue. The method comprises the steps of performing whole brain magnetic susceptibility imaging on participator with magnetic resonance instrument, and storing amplitude image in obtained image data; measuring average signal intensities of caudate nucleus, putamen, globus pallidus, thalamus, red nucleus, substantia nigra, frontal lobe white matter and medulla oblongata in brain region of each participator, and dividing with the average signal intensity of medulla oblongata as internal reference respectively, to obtain relative amplitude signal intensity data; performing normal distribution conversion on the obtained relative amplitude signal intensity data, performing Pearson linear correlation analysis with brain region iron content distribution data of population of same age group published by autopsy research, and fitting to obtain a simple relation equation according to correlation analysis result. The method can non-invasively accurately estimate iron content in brain, only needs measurement and calculation on a simple third-party image processing software during measurement, and needs no special workstation.

Embodiments of the present invention provide a method and device for diagnosing hidden faults of a 4G base station. The method includes: acquiring relevant dimension data, integrating the relevant dimension data to obtain a data index set; and obtaining the data index based on a linear correlation analysis method According to the correlation coefficient between the index items of the set, reduce the dimension of the data index set according to the correlation coefficient to obtain a dimension-reduced data set; input the dimension-reduced data set into the trained fault location model to obtain the fault identification result. The embodiment of the present invention provides a method and device for diagnosing hidden faults of 4G base stations, which introduces AI machine learning technology, and forms an intelligent hidden fault troubleshooting model by mining the correlation between various deep-level factors of hidden faults of 4G base stations. , to realize the automatic identification and diagnosis of problems.

The invention discloses a system and a method for detecting the level of cortisol in urine and application, and relates to the technical field of detection of the level of cortisol in urine. The detection system comprises a 24h urocortisol related data and urocortisol correlation analysis module. Wherein the 24-hour urocortisol related data and urocortisol correlation analysis module is based on a monitored 24-hour urocortisol level value after a patient takes hydrocortisone acetate, a 24-hour urocortisol related data level value before and 1 hour after the patient takes hydrocortisone acetate at 8 o'clock in the morning, and a 24-hour urocortisol related data level value before and 1 hour after the patient takes hydrocortisone acetate at 4 o'clock in the afternoon; and performing multivariate linear correlation analysis to obtain a linear relation. The urine cortisol level is calculated according to the linear relational expression, the treatment effect of hormone drugs, especially hydrocortisone acetate, on hypopituitary function can be accurately monitored, and the phenomenon that in the prior art, all urine within 24 h is collected and then cortisol detection is conducted, so that the result is not accurate is avoided.

The present invention discloses a method and system for detecting damage caused by important corn pests based on drone patrol. First, a two-dimensional map model is constructed, and initial image data of corn fields is obtained through drone inspections to identify pest types, quantities and damage symptoms, and at the same time evaluate the damage caused by them. Subsequently, sub-regions are fused based on the insect distribution and loss impact analysis, and changes are monitored over multiple cycles to generate insect distribution and loss impact change data. Sub-regions with linear correlation are marked using linear correlation analysis and association rule information is generated, and insect distribution and loss impact data are predicted based on the LSTM model. Finally, a prevention and control plan is generated based on the predicted data. Through the present invention, accurate insect distribution and loss impact prediction and analysis can be achieved, providing data support for subsequent information-based pest control.

The invention discloses a processing method for accurately interpolating and extending the hydrological characteristics of a design station, and aims to provide a processing method for the hydrological characteristics of a design station closer to the real value. It includes the following steps: (1) simple linear correlation analysis; (2) complete linear correlation analysis; (3) partial value calculation; and (4) physical numerical calculation of complete linear correlation. The invention is applicable to the processing of hydrological characteristics of design stations in the technical field of hydrology and water resources.

The invention discloses a method for researching correlation between sweet substances in rose essential oil and a sensor based on an electronic nose, and belongs to the technical field of tobacco flavor detection.The method comprises the following steps that firstly, main sweet substances in the rose essential oil are added into cigarettes, and the content of the sweet substances in the rose essential oil is determined by combining sensory rating and grey correlation degree analysis; screening out aroma substances and other sensory qualities which are remarkably related to the sweetness; preparing solutions with different concentration gradients from the screened aroma substances remarkably related to the sweet feeling, scoring the odor intensity and testing the electronic nose to respectively obtain original response data values of the sensor to the aroma substances, and establishing linear correlation analysis through SPSS software to obtain the original response data values of the sensor to the aroma substances. Finally, finding out the electronic nose sensor with the strongest correlation with the sweet substances as WLSGF / A, wherein the correlation between the rose oxide and the WLSGF / A is the best; according to the method, mathematical statistics is combined with sense organs and the electronic nose, so that objective and efficient evaluation of the sweet aroma is realized.

The invention provides a regional wind power modeling method, which comprises the following steps: acquiring historical power generation powers of a plurality of wind power plants in a set region, performing linear correlation analysis and clustering processing on the wind power plants in the region based on the historical power generation powers, and determining a plurality of equivalent wind power plants in the set region; according to each equivalent wind power plant, establishing an edge density function of each equivalent wind power plant by using an orthogonal series method; and according to the edge density function of each equivalent wind power plant, establishing a wind power joint probability model of a set area by using a Pair-Copula function method. Through the method, the calculation number of the wind power plants in the region is reduced, the modeling dimension is reduced, the influence of the random variable boundary effect is avoided, and the probability modeling accuracy of the generated power correlation of the wind power plants is improved.

The present invention is applicable to the field of power grid monitoring technology, and relates to a method, medium, and terminal for analyzing abnormal power consumption based on LTU and multidimensional data, including: establishing a power grid relationship model; connecting the electric meter and LTU equipment to the main station, collecting electric energy indication data and topology identification data for a specific time period; matching and comparing the topology identification data with the power grid relationship model, automatically correcting the relevant power grid hierarchical affiliation, placing the user electric meter for which the topological relationship cannot be identified into a pre-adjusted power grid relationship user electric meter pool, and placing the relevant monitoring points into a pre-adjusted power grid relationship monitoring point pool; calculating the loss rate data of each monitoring point; performing linear correlation analysis; aggregating to obtain the characteristic information matrix of each pre-adjusted power grid relationship monitoring point and pre-adjusted power grid relationship user electric meter; performing multidimensional data fusion analysis and correcting topology linkage iteration; and obtaining a list of abnormal power users. The present invention has a simple process and is easy to operate, and effectively improves the accuracy of abnormal power consumption analysis in the substation area.

The invention discloses an MD / QM / CSM method for extracting representative conformation of a beta-CD subject-object system. The method comprises the following steps: (1) calculating a topological structure and RESP charges of a host molecule; (2) calculating topological structures and RESP charges of guest molecules; (3) constructing an initial conformation of a subject-object compound; (4) screening dominant conformations of the host-guest compound, the host molecules and the guest molecules; (5) carrying out ECD calculation on the dominant conformation of the subject-object compound, and comparing with an ICD experiment to determine the accuracy of the screening structure; (6) calculating inclusion free energy of dominant conformations of the subject-guest compound, the subject molecules and the guest molecules by adopting a QM / CSM method, and performing linear correlation analysis on a calculated value and an experimental value. According to the method, the representative conformation of the subject-guest compound system can be accurately extracted, an accurate structural model is provided for calculation of the inclusion free energy, meanwhile, the inclusion free energy and the solvent effect in vacuum are calculated, calculation of the inclusion free energy of the subject-guest system is more perfect, and guidance is provided for experiments.

According to an application of MT-ND6 as a new target in metabolic syndrome diagnosis and treatment drugs, expression of the MT-ND6 gene in peripheral blood leucocytes of type 2 diabetes patients and livers of obese mice is remarkably reduced, meanwhile, methylation level of the MT-ND6 gene is remarkably increased, linear correlation analysis shows that the methylation level of the MT-ND6 gene is in negative correlation with expression of mRNA of the MT-ND6 gene, and in positive correlation with insulin resistance index HOMA-IR, glycosylated hemoglobin content and serum triglyceride level, and knock-down of the MT-ND6 can cause mitochondrial dysfunction, increase liver lipid droplet accumulation and reduce insulin sensitivity, indicating that the MT-ND6 gene is closely related to metabolic syndrome. The invention provides a new target for clinical diagnosis and treatment of metabolic syndrome and complications thereof, and has important application value.

The invention discloses a machine learning-based early accelerated aging diagnosis method for a ternary lithium ion battery. The method comprises the steps that 17 aging feature parameters representing the health state of the ternary lithium ion battery are extracted from a discharge capacity-voltage curve, a discharge IC curve and a discharge DV curve of the ternary lithium ion battery; then, a new combinatorial algorithm is utilized to accurately diagnose accelerated aging of the ternary lithium ion battery in an early stage, firstly, important features are selected through a random forest, then, linear correlation of the important features is reduced through linear correlation analysis, and finally, accelerated aging is judged through a logistic regression model. Accurate early diagnosis of accelerated aging of the ternary lithium ion battery is realized, so that whether accelerated aging of the ternary lithium ion battery occurs or not is judged in the early stage, and important information is provided for health state management and health state evaluation of the lithium ion battery.

The invention discloses an efficient control method for realizing optical network construction on the basis of linear correlation analysis, and belongs to the technical field of communications. According to the method, multi-dimensional optimized decomposition is carried out on optical access network hotspots by adopting linear correlation of feature vectors, and the most suitable construction models are matched to satisfy the construction demands of the hotspots. According to the method, linear matching of the optical access network hotspots and the construction optimized models is newly provided, an approximation set is found, a Bayesian network is constructed to carry out decision judgement, and the optimum construction models are selected to realize the efficient construction of the hotspots.