234 results about "Regression analysis" patented technology

The invention belongs to the technical field of blasting vibration prediction, and particularly discloses a blasting vibration speed attenuation law prediction method based on regression analysis, and the method comprises the steps: laying monitoring points in multiple directions around a blasting source, synchronously collecting the geological parameters and mass point peak vibration speed of each point, and constructing a segmented propagation path; a single dominant propagation section is identified based on adjacent monitoring point data, independent influence of specific geological conditions on vibration attenuation is quantified by combining single-factor control regression analysis, decoupling modeling of geological factors and attenuation behaviors is realized, and meanwhile, a double-factor dominant propagation section is identified on the basis of quantizing the independent influence of the single geological conditions. And deducting a known effect through residual analysis to separate out an independent contribution of another geological parameter, and finally integrating a multi-factor influence function to construct a comprehensive attenuation model. Progressive modeling from single-factor decoupling to multi-factor collaboration is achieved, and the precision and physical interpretability of blasting vibration prediction in a complex heterogeneous stratum are remarkably improved.

The invention discloses an intelligent prediction method for a fracturing wellhead yield increase effect, and the method comprises the steps: carrying out the fusion collection, standardization and embedded dimension reduction of multi-source real-time and historical data, environment and geological parameters and expert experience, cooperatively extracting high-dimensional features, evaluating the uncertainty of the features through a Bayesian model, and carrying out the weighted input of a reinforcement learning architecture, thereby achieving the intelligent prediction of the yield increase effect of a fracturing wellhead. According to the method, causal reasoning and deviation correction are carried out in combination with physical and business indexes, high consistency of a strategy and a multi-target business index is realized by dynamically adjusting a reward function, and self-adaptive retraining and robust optimization of a model in extreme environments such as high noise and data missing are realized through field evaluation regression analysis of output. According to the method, the adaptability and prediction accuracy of the fracturing yield increase prediction and optimization system to complex working conditions are remarkably improved.

According to the slope geological disaster risk assessment method and system provided by the invention, the feature information of the slope object can be accurately assessed by obtaining the non-natural vibration data and combining the hidden danger description factor information of the slope object, so that the adjacent slope objects around the target slope object are considered together in the slope object set, and the risk assessment accuracy is improved. Comprehensive analysis of a target slope object is formed through slope hidden danger data features in the slope object set, and then feature extraction of important hidden dangers is carried out on the target slope object set to obtain a description vector of the target slope object set; and according to the description vector regression of the target slope object set, whether the slope object attribute of the target slope object affects the slope geological disaster risk assessment result is analyzed, the slope object attribute is used for representing the attribute affecting the hidden danger of the slope object, and the regression analysis accuracy of the attribute change of the slope object is improved. And the accuracy and confidence of evaluation are ensured.

The invention discloses a thunderstorm gale regression analysis method and system based on multi-stream parameters, and relates to the technical field of data processing. The method comprises the following steps: collecting multi-stream parameters in real time, and constructing a real-time multi-stream parameter sequence; mapping the real-time multi-flow-parameter sequence to a pre-constructed multi-flow-parameter coupling sensitivity field model, and calculating to generate a real-time convection sensitivity field; inputting the real-time convection sensitivity field into the physical consistency constraint model to generate real-time structured convection characteristics; main regression analysis under multi-flow parameter regression is executed, and a main regression result is established; and after the real-time local disturbance index is calculated, disturbance residual compensation of the main regression result is triggered, dynamic weight adjustment is carried out on the main regression result after residual compensation by utilizing seasonal phase characteristics, and a thunderstorm gale regression analysis result is output. The technical problem that thunderstorm gale prediction accuracy is insufficient in the prior art is solved, and the technical effect of improving thunderstorm gale regression analysis result accuracy is achieved.

The invention discloses a damage safety assessment method and system for a building service glass curtain wall, and the method comprises the steps: setting a plurality of damage conditions based on a glass curtain wall standard test piece, and building a function relation between the maximum panel deflection and the inherent frequency through a regression analysis method; calculating the maximum theoretical panel deflection according to specifications, substituting the maximum theoretical panel deflection into the function relationship to obtain a critical inherent frequency, and constructing a safety evaluation model according to the critical inherent frequency; and acquiring the actual inherent frequency of the curtain wall to be tested, and evaluating the damage safety state of the curtain wall according to the model. According to the invention, rapid and efficient safety assessment can be carried out on the active glass curtain wall without damaging the rubber material body, and large-area screening and regular inspection can be realized; field test provides real data, finite element simulation supplements multiple working conditions, and data accuracy and model universality are guaranteed; the obtained inherent frequency reflects the essential attributes of the structure, and the damage detection and evaluation sensitivity is high; according to the constructed evaluation model, the result is direct and reliable through comparison between a safety threshold value and actual measurement.

The invention discloses a coal type sales planning and sales time collaborative management and control method and system based on a coal enterprise, and relates to the technical field of coal sales management. Multi-source data are integrated through technologies such as a data fusion algorithm, the problems of data dispersion and different formats are solved, high-quality data support is provided for follow-up analysis, the sales trend and price fluctuation are accurately predicted by applying a long-short-term memory neural network and a regression analysis model, enterprises are assisted in optimizing sales strategies, the inventory overstock risk is reduced, and the sales quality is improved. By means of linear programming and reinforcement learning algorithms, sales tasks are dynamically adjusted in combination with real-time data, market response speed and sales efficiency are improved, scientificity and flexibility of sales management of coal enterprises are effectively improved, and market competitiveness is enhanced.

The invention provides a mountain road coal gangue slope ecological restoration method, which comprises the following steps: acquiring real-time monitoring data from a coal gangue slope through a sensor network, including weathering degree and compaction density indexes, and obtaining an initial feature set; according to the initial feature set, carrying out preliminary grouping on the side slopes by adopting a clustering analysis method, and determining a classification standard threshold value; feedback data in the restoration implementation process are obtained and compared with the preliminary groups, and the effect deviation degree is judged; if the effect deviation exceeds a preset threshold value, a classification standard threshold value is updated through a regression analysis model, and an adjusted classification system is obtained; for the adjusted classification system, extracting a corresponding repair scheme template from a database, and generating an optimization scheme version; performing virtual testing on the optimization scheme version through an analog simulation module to obtain a prediction effect index; and collecting subsequent monitoring data according to the final execution parameter, and performing iterative comparison with the prediction effect index to obtain a further adjustment signal.

A calculation method of karst underground reservoir capacity curve based on hydrogeological parameters, including the following steps: hydrogeological exploration, determination of karst underground water reservoirs scope, determination of water storage space, determination of relevant hydrogeological parameters based on hydrogeological tests, and underground reservoir capacity analysis. The invention uses the unit water permeability and the borehole line karst rate that are very easily obtained through the borehole pressure (injection) water test and combines it with a small amount of water pumping test, thereby obtaining a correlation function relationship through regression analysis between the specific yield and the karst rate that are difficult to obtain and the unit water permeability or the permeability coefficient; the underground storage capacity at the corresponding elevation is calculated according to the specific yield or the karst rate and the underground storage capacity curve is obtained, which can improve accuracy and reduce errors.

The invention relates to the technical field of forage grass drying evaluation, and particularly discloses a forage grass drying evaluation method and system based on multi-modal fusion. According to the method, a quality file containing indexes such as the moisture content, the dry matter content and the dryness grade is established for each batch of forage grass, the feed intake, the feed intake behavior and the production performance data of cattle herds are synchronously collected in the feeding period, and a multi-modal association data set is established with batch identifiers and timestamps as association keys; and obtaining response results of the ingestion performance and the production performance corresponding to different drying characteristics by adopting correlation analysis, regression analysis and statistical significance test, and dynamically correcting the forage grass drying evaluation standard according to the response results of the ingestion performance and the production performance. According to the method, the forage grass drying characteristic data is associated with the cattle herd feed intake, the feed intake behavior and the production performance data according to batches and time, the multi-mode associated data set is constructed, and the direct corresponding relation between the forage grass drying state and the actual feed intake performance and the growth effect of the cattle herd is achieved.

The invention relates to the technical field of aviation safety, in particular to a short-distance parallel runway collision risk assessment method based on influence of front and side wind, which comprises collision risk assessment, Bayesian parameter estimation, linear regression analysis, dynamic front and side wind fitting and Monte Carlo analog simulation. The problem of small sample parameter estimation is solved by introducing a Bayesian parameter estimation method, crosswind parameters are calculated by combining linear regression analysis, positive crosswind data are fitted by applying Weibull distribution, and an influence rule of positive crosswind and an initial interval on collision probability is quantified through Monte Carlo simulation. According to the short-distance parallel runway collision risk assessment method based on the influence of the positive and crosswind, on the basis of a traditional collision model, a re-flight condition is incorporated into the model, complex scenes such as crosswind and re-flight are considered, a dynamic interval adjustment model is fused, and a new collision risk model is established; the crosswind grading minimum interval standard is provided for airline companies and air traffic control operation management, and the runway safety and the airport operation capacity are improved.

The invention discloses an industrial chain electricity consumption sensitivity feature extraction method, system and device and a storage medium, and the method comprises the steps: obtaining multi-dimensional electricity consumption data, carrying out the feature extraction and dimension reduction of the multi-dimensional electricity consumption data, and mapping an original high-dimensional feature into a low-dimensional feature; carrying out regression analysis on the low-dimensional features, calculating a feature sensitivity coefficient, reversely associating original high-dimensional features, calculating the total influence degree of the original high-dimensional features on power consumption, and screening to obtain key features; based on the characteristic sensitivity coefficient and the key characteristic, the deviation degree of the low-dimensional characteristic and the normal working condition distribution is calculated, abnormity is detected according to the deviation degree, when abnormity is detected, a dynamic optimization mechanism is triggered, extraction of the electricity utilization sensitivity characteristic is achieved, and online learning and dynamic optimization requirements in a super-large scale time sequence scene are supported.

The invention provides a variable-speed vibration signal feature extraction method and system. The method comprises the following steps: acquiring vibration signal data under a variable-speed condition; preprocessing the vibration signal data; carrying out feature extraction on the preprocessed vibration signal data by adopting order analysis; optimizing the feature data by adopting a self-adaptive filtering algorithm; constructing a fault feature physical model, and performing classification or regression analysis on feature data based on a machine learning or deep learning algorithm; and inputting the optimized feature data into the fault feature physical model, and carrying out bearing fault diagnosis. According to the variable-speed vibration signal feature extraction method and system provided by the invention, an equal-angle resampling technology is adopted, the accuracy and consistency of signal analysis are ensured, and in combination with an intelligent feature extraction and mode recognition algorithm, mild, moderate and severe classification evaluation of faults such as bearing wear is realized.

This invention relates to the field of parcel delivery volume prediction technology, and discloses a method for predicting logistics parcel delivery volume based on a multi-level network architecture. The method includes: acquiring raw data and standardizing the data; constructing a multi-level network hierarchy and a multi-dimensional weighted ranking model; displaying the data in multiple dimensions; calculating the confidence interval based on the prediction model and attaching a confidence level label to each predicted value; introducing a user behavior learning model to record user click habits and query preferences, and optimizing the network display order and recommendation logic; using an integrated prediction model to fuse time series analysis, regression analysis, and machine learning prediction methods to form a combined prediction result; establishing a prediction error feedback mechanism to compare the actual delivery volume with the predicted delivery volume and optimize model parameters; and adopting a hierarchical prediction strategy. This invention provides reliable support for logistics delivery planning and resource allocation, reduces operating costs, and improves service quality.

According to various embodiments of the present invention, a regression analysis-based circuit characteristic optimization device for digital circuit design may: receive, from the outside, information about a digital circuit to be designed, and arbitrarily set a characteristic value for at least one transistor included in the digital circuit; generate a circuit characteristic regression model by mathematically modeling the characteristic of a path included in the digital circuit on the basis of the characteristic value of the transistor included in the digital circuit; obtain an initial coefficient of the circuit characteristic regression model by applying the arbitrarily set characteristic value thereto; and obtain the improved characteristic value for the at least one transistor included in the digital circuit on the basis of the circuit characteristic regression model into which the initial coefficient has been incorporated.

This invention relates to the field of intelligent driving technology for vehicles, and provides a method, system, vehicle, and storage medium for missing lane line completion. The method includes the following steps: collecting lane information to form a dataset; importing the dataset into a deep learning network model to train the network, enabling the network to predict the future trajectory of a vehicle based on the historical trajectories of surrounding vehicles; fitting the predicted trajectory of the vehicle and the lane line trajectory output by the network; performing regression analysis and matching the fitted curve of the lane line trajectory near the predicted trajectory to obtain a mathematical model of the fitted curve; obtaining the relationship between the fitted curve of the lane line and the vehicle's driving trajectory through the mathematical model; and completing the lane line based on the fitted lane line trajectory and the vehicle's position. This invention can achieve high-precision lane line completion in scenarios where lane lines are missing or blurred.

An analysis device according to the embodiment includes a creation unit and an output control unit. The creation unit arranges a line segment indicating a point that is a product of an attribute value of a regression model obtained by regression analysis by secure computation and a regression coefficient in a direction corresponding to a sign of the corresponding regression coefficient and creates a nomogram in which the point is plotted at a position corresponding to a target point on the line segment. The output control unit outputs the created nomogram.

The present application relates to the technical field of agricultural drought monitoring and precision irrigation, and particularly relates to a crop water stress diagnosis method and system based on sunlight-induced chlorophyll fluorescence, which collects crop canopy oxygen absorption band spectral data through a hyperspectral sensor, and calculates sunlight-induced chlorophyll fluorescence intensity SIF values by using a fluorescence extraction algorithm. The SIF value of a non-water-stressed crop canopy is taken as a reference canopy SIF value, the difference between the SIF value of a to-be-measured crop canopy and the reference canopy SIF value is determined, then a relative SIF water deficit index SIFWDI is generated by combining a preset formula, a regression analysis model is used to establish a mapping relationship between the SIFWDI and a soil water deficit index to output a diagnosis report, a variable irrigation decision and early warning are triggered according to a stress level, and model parameter adaptive optimization is realized through a feedback mechanism. The system realizes non-destructive, real-time and high-precision water stress monitoring and irrigation management.

A machine learning system and method for optical critical dimension measurement. From a training set of spectra and references, features are extracted and subjected to regression analysis to generate predictor variables. Using feature functions, inverse feature functions, a machine-learning predictor component and masks, a machine-learning optical critical dimension explainer is generated. A wafer is analyzed by metrology tools and the machine-learning predictor component calculates a critical dimension inference from measured spectra. Theoretical spectra are then generated by the predictor component based upon a modification of the critical dimension inference. The measured spectra are compared to the theoretical spectra and the fit of the measured spectra to the theoretical spectra is evaluated for acceptance. The results of the comparison and analysis is output in human readable form.

The application provides a model construction and verification method and nomogram for predicting the clinical prognosis of SFTS patients complicated with AP. By collecting the clinical data of SFTS patients, the independent risk factors related to adverse prognosis are screened out by using LASSO regression analysis, a multi-factor Logistic regression model is constructed, and the model is visualized by nomogram for predicting the adverse prognosis of SFTS patients complicated with AP. The model has high discrimination and calibration, and can provide an effective prediction tool for clinicians to optimize clinical decision-making.

This invention discloses a comprehensive parameter design method for the cross-section of long-span highway tunnels. Using tunnel flatness ratio and equivalent initial support strength as two variables, and with tunnel safety and economy as dual objectives, it employs numerical simulation and regression analysis to establish evaluation indicators and objective functions for flatness ratio and initial support. Based on survey results, the range of variables for flatness ratio and equivalent initial support strength is determined. Safety constraints are defined according to safety requirements. A non-dominated sorting genetic algorithm is used to perform optimization calculations within the specified variable range and constraints to obtain mutually suitable tunnel cross-section flatness ratio and equivalent initial support strength. Furthermore, the equivalent initial support strength is transformed into support form and parameters, ultimately forming the optimal initial support parameters for long-span tunnels. This method overcomes the shortcomings of traditional long-span highway tunnel design methods that only consider safety or economy as a single objective, and solves the problem of relying on manual experience to determine the optimal flatness ratio and initial support parameters.

The application discloses a driving behavior influence on energy consumption evaluation method, system, vehicle and equipment. Wherein, the driving behavior influence on energy consumption evaluation method comprises: obtaining driving data of a vehicle; obtaining driving behavior characteristic data according to the driving data; taking unit energy consumption of the vehicle as a target variable and taking the driving behavior characteristic data as an input variable, a regression analysis model between the driving behavior and the unit energy consumption is constructed, wherein the regression analysis model represents the influence relationship of different driving behaviors on the energy consumption of the vehicle; according to the parameters of the regression analysis model, the energy consumption influence weight corresponding to each type of driving behavior characteristic data is calculated, and the influence of the driving behavior on the energy consumption is evaluated according to the energy consumption influence weight. By analyzing the influence of the driving behavior on the energy consumption of the vehicle, the driving habit, the loading configuration and the driving route can be optimized, and the energy consumption and the carbon emission can be significantly reduced.

The invention relates to a hot rod effective power evaluation method based on spatial distribution characteristics of a soil body temperature field, and is suitable for permafrost region engineering. The method comprises the following steps: selecting a hot rod which works stably, arranging temperature measuring holes on a horizontal section of a vertical axis in the middle of an evaporation section according to a near field, a middle field and a far field, and obtaining soil body temperatures T at different radial distances r; based on the steady-state heat conduction theory, regression analysis is carried out on measured data, a mathematical model T = C1 * ln (r) + C2 is constructed, and a coefficient C1 is solved; and combining the heat conductivity coefficient lambda of the soil body with the effective length L of the hot rod, and calculating the effective refrigeration power of the hot rod on the soil body by utilizing a formula Q =-2pi lambda LC1. The method does not need to pre-embed a sensor, does not interfere with the operation of the hot rod, and can include the contact thermal resistance influence between the hot rod and the soil body. The method has the advantages of high measurement precision, low cost and the like, and realizes in-situ and quantitative evaluation of the actual refrigeration efficiency of the existing engineering hot rod.

The invention relates to the technical field of spectral analysis, and discloses a light intensity adaptive closed-loop adjustment system and method for spectrum monitoring, and the method comprises the following steps: presetting a light intensity target range; establishing an environment and equipment influence model based on regression analysis, and calculating and outputting a theoretical light intensity expected value; after the light source irradiates a sample, the sample absorbs light intensity, and the spectrum detector receives a light signal absorbed by the sample, processes the received light signal and outputs full-wave-band real-time light intensity original data; comparing the real-time light intensity original data with a theoretical light intensity expected value to obtain effective light intensity; and comparing the effective light intensity with a preset light intensity target range to obtain an adjustment deviation value between the target light intensity and the actual light intensity, and generating an optimization adjustment strategy. According to the method, the light intensity error caused by environment change and equipment state is dynamically predicted and eliminated through regression analysis and an error estimation function, so that more accurate effective light intensity is obtained.

This invention discloses a multi-dimensional analysis system and method for regional economic development potential, aiming to solve the problems of scattered data, single dimensions, and subjective and lagging assessments in traditional regional economic analysis. It adopts a three-layer architecture: a data layer, a model layer, and an application layer. The data layer integrates multi-source data from statistical yearbooks, government information disclosure, the internet economy, and geospatial data, forming a unified analytical foundation through standardization and outlier processing. The model layer constructs a six-core dimension indicator system, including economic scale and industrial structure, and uses entropy weighting, TOPSIS, and regression analysis to achieve quantitative assessment, supporting dynamic updates and adjustments. The application layer outputs analysis results through visualization and customizable functions. This invention achieves deep integration of multi-source data, comprehensive characterization of multi-dimensional potential, and objective, accurate, and timely assessment results, adapting to various scenarios such as government decision-making and corporate investment, providing scientific and efficient decision support for high-quality regional economic development.

Embodiments of the present disclosure are directed to a system for monitoring operating conditions of a saltwater disposal pump system, which includes a processing device that causes a controller to receive an alarm from the at least one machine that exceeds a predetermined alarm level indicative of an abnormal machine operation, receive a plurality of data from a plurality of sensors that are indicative of a current operating conditions of a saltwater disposal pump assembly, derive an expected value utilizing a statistical regression analysis, determine whether the expected value and a history of the plurality of data correlate at a point where the plurality of data exceeds the predetermined alarm level, determine whether a deviation from a predefined operating profile exceeds a predetermined machine data validation threshold value, validate the alarm, output an alert of the deviation and inhibit further operation of the saltwater disposal pump assembly.

The present application relates to the technical field of municipal pipeline detection, and discloses a full-pipe operation early warning analysis method for a sewage pipe network, comprising the following steps: S1, arranging sensors at key nodes of the sewage pipe network to collect real-time operation data of the sewage pipe network; S2, acquiring real-time meteorological data, including rainfall, rainfall intensity and other related meteorological factors; S3, performing data cleaning and standardization processing on the collected sewage pipe network data and meteorological data; S4, based on multivariate regression analysis, establishing a relationship model between flow, liquid level and full-pipe risk; S5, using a long short-term memory network to perform time series prediction to predict future flow and liquid level trends. Through time series prediction by the long short-term memory network, the early warning threshold is dynamically adjusted in combination with an adaptive algorithm, the operation state change of the sewage pipe network is realized in real time, the future flow and liquid level trends are accurately predicted, and the accuracy of early warning and the response speed to sudden full-pipe risk are improved.

The invention relates to an intelligent impact tendency evaluation method based on multitask gating mechanism coal, which belongs to the technical field of crossing of electric digital data processing and geological engineering, and comprises the following steps of: 1, collecting related data, and constructing a data set; 2, training a coal body impact tendency intelligent evaluation model based on multi-task learning by using the constructed data set, so that the model learns nonlinear mapping of a coal body microstructure and macroscopic mechanical properties; and 3, inputting particle accumulation and joint structure information of to-be-detected coal into the model trained in the step 2, carrying out regression analysis to obtain a coal impact tendency index, and judging the coal impact tendency according to a standard. According to the method, a low-cost and high-reliability intelligent solution is provided for mine dynamic disaster prevention and control, and the method has technical innovation and engineering application value.

Provided in the present invention is a grading method for evaluating the severity of the clinical symptoms of hypersplenism. In the present invention, a model for evaluating the severity of the clinical symptoms of hypersplenism is constructed by means of performing logistic regression analysis on PLT, WBC and RBC to establish a nomogram, converting regression coefficients into a visual scoring system, separately performing score assignment on the basis of primary and secondary factors, and finally constructing a total-score-based hypersplenism grading prediction model. The model in the present invention is used to evaluate the severity of the clinical symptoms of hypersplenism in patients. By means of correlation analysis of peripheral blood cell testing results of patients with hypersplenism, hypersplenism grades of the patients are evaluated, such that personalized treatment plans can be provided to the patients in a timely manner, thereby avoiding delays in treatment.

The application discloses a kind of nuclear power plant operation event trend analysis and prediction method and device, for the accuracy of existing statistical analysis method is insufficient in complex nuclear power environment, lack of multivariate nonlinear consideration and real-time analysis capability is short of etc., the application fuses deep learning and big data analysis technology, realizes event trend identification and high-risk area prediction.It includes: collecting operation log, sensor data and other multi-source event data, is stored after cleaning, standardization preprocessing;Extract the key features of event occurrence time, type, severity, etc., and construct a feature set;Through the analysis of time series data based on standardized event data extraction multi-LSTM based on standardized event data extraction multi-neural network model, identify long-term trends and periodic changes;Combined with deep learning and regression analysis, predict the probability of event occurrence and severity, locate high-risk period and area;Generate real-time warning information and provide prevention suggestions.

The invention belongs to the technical field of tumor prognosis prediction, and relates to a colorectal cancer allotropic liver metastasis prediction method and system.The method comprises the steps that colorectal adenocarcinoma cases are collected, the volume of an intra-tumor region-of-interest is delineated and automatically expanded to generate the volume of a peritumor region-of-interest, image omics characteristics are extracted through a pyradiomics packet, core omics characteristics are screened out, and the colorectal cancer allotropic liver metastasis prediction result is obtained. The method comprises the following steps: respectively constructing an intratumoral model and a peritumoral model, analyzing and integrating intratumoral and peritumoral core omics characteristics through logistic regression to form a combined radiomics model, integrating the combined radiomics model and clinical risk factors, establishing a column diagram for predicting the non-hepatic metastasis lifetime, and dividing patients into a low-risk group and a high-risk group according to a column diagram score threshold value; according to the method, LMFS prediction results of 1-5 years can be quickly output, and 0.6911 is set as a standardized risk stratification cut-off value so as to support risk stratification and personalized treatment decision of a patient.