42 results about "Polynomial regression model" patented technology

The invention discloses a performance prediction and fault alarm method for a photovoltaic power station. The method comprises the following steps of: a, setting the station of the power station; b, setting the operation mode of the power station; c, judging whether required real-time data or historical data exists or not; d, predicting the performance of the power station through an experience model if the state in the step a is that a new photovoltaic power station is required to be designed and the required real-time data or historical data in the step c does not exist, and predicting the performance of the power station through a data drive performance model if the required real-time data or historical data in the step c exists; e, predicting the performance of the power station through the data drive performance model or a polynomial regression model if the photovoltaic power station in the step a is operated and the required real-time data or historical data in the step c exists, and predicting the performance of the power station through the experience model if the required real-time data or historical data in the step c does not exist; f, comparing actual performance with the predicted performance, and performing fault alarm; and g, correcting the models on line by a Kalman filtering method and returning to the step c, and otherwise, directly returning to the step e. By the method, solar energy resources can be utilized to the maximum extent, and power utilization cost can be reduced; and the accuracy of performance prediction and fault diagnosis is improved.

The embodiment of the invention provides a method for applying seismic multiattribute parameters to predicting the coal seam thickness. The method comprises: a suitable time window is selected in a three-dimensional offset data body, seismic attribute data of amplitude, frequency, and instantaneity and the like are extracted from the time window, and a seismic attribute database is established; a correlated analysis is executed on seismic attributes and coal seam thicknesses and cross-correlation analyses are further executed on the seismic attributes, so that a plurality of seismic attributes that are most meaningful are optimized as basic parameters of a coal seam thickness prediction model; with combination of known boring data, a multicomponent polynomial regression model and a BP artificial neural network model of between all the seismic attributes and the coal seam thicknesses are established by utilizing a multicomponent polynomial regression method and a BP artificial neural network method; and the models are utilized to predict coal seam thicknesses. According to the method provided in the embodiment of the invention, because multiattribute parameters are considered, obtained calculating models are perfect and realistic; an effect for prediction of the coal seam thickness is good; and credibility and accuracy are high.

A system for preventing abnormal situations in process plants is provided. A polynomial regression model is employed to predict values of a monitored variable based on measured samples of a load variable. An abnormal situation is detected when a predicted value of the monitored variable differs from a measured value of the monitored variable by more than a predetermined amount. The system employs one or more algorithms for automatically determining an optimal order or degree of the polynomial regression model.

The invention discloses a method for predicting the low-cycle fatigue life of a titanium alloy material based on the surface integrity. The low-cycle fatigue failure mode of the titanium alloy material under the pulling-pressing loading condition is considered, index parameters of the surface integrity serve as bases, a polynomial regression model is combined with a sine and cosine regression model, a predicting model for evaluating the low-cycle fatigue life of the titanium alloy material by adopting a combination of the surface roughness Ra and the maximum surface residual main stress sigmar is built, and finally a method for predicting the low-cycle fatigue life of the titanium alloy material based on the surface integrity is provided. By means of the method, the low-cycle fatigue life of the titanium alloy material can be easily, rapidly and accurately predicted, theoretical bases can be provided for reliable design of parts, practical production can be guided, and the certain engineering application value can be achieved.

The embodiment of the invention discloses an answer scoring method and device, computer equipment and a storage medium. The method comprises the following steps that obtaining an answer of a target proposition; inputting the answer into a preset scoring model, the scoring model being a calculation model for performing polynomial regression on the feature vector according to the feature vector between the answer and a standard answer, and the feature vector representing the similarity between the answer and the standard answer; and determining the score of the answer according to the output result of the scoring model. When a polynomial regression model is established, synonym expansion is carried out on the obtained training answers, and it is ensured that the same score is obtained when the same semantics are expressed by different words. In this way, the answer is scored without depending on specific keywords or sentences, the flexibility and accuracy of paper marking and scoring areimproved, and the objectivity of scoring is effectively guaranteed.

The invention discloses a performance prediction and fault alarm method for a photovoltaic power station. The method comprises the following steps of: a, setting the station of the power station; b, setting the operation mode of the power station; c, judging whether required real-time data or historical data exists or not; d, predicting the performance of the power station through an experience model if the state in the step a is that a new photovoltaic power station is required to be designed and the required real-time data or historical data in the step c does not exist, and predicting the performance of the power station through a data drive performance model if the required real-time data or historical data in the step c exists; e, predicting the performance of the power station through the data drive performance model or a polynomial regression model if the photovoltaic power station in the step a is operated and the required real-time data or historical data in the step c exists, and predicting the performance of the power station through the experience model if the required real-time data or historical data in the step c does not exist; f, comparing actual performance with the predicted performance, and performing fault alarm; and g, correcting the models on line by a Kalman filtering method and returning to the step c, and otherwise, directly returning to the step e. By the method, solar energy resources can be utilized to the maximum extent, and power utilization cost can be reduced; and the accuracy of performance prediction and fault diagnosis is improved.

The invention discloses an anti-seismic optimization design method of a building anti-seismic support-hanger. The method includes the steps: building a three-dimensional space analysis model of the building structure-anti-seismic support-hanger; selecting maximal space of the anti-seismic support-hanger and a minimum cross-sectional area of an inclined strut, and calculating maximum acceleration reaction of the anti-seismic support-hanger; calculating a floor response spectrum of a building structure, and correcting the floor response spectrum according to the maximum acceleration reaction toobtain a corrected floor response spectrum; building quadratic polynomial regression models among the maximum acceleration reaction of the anti-seismic support-hanger, the space of the support-hangerand the cross-sectional area of the inclined strut according to the corrected floor response spectrum; determining optimized design values of the space of the support-hanger and the cross-sectional area of the inclined strut. According to the method, polynomial regression models among earthquake actions of the anti-seismic support-hanger, the space of the support-hanger and the cross-sectional area and the support-hanger can be rapidly and accurately built, design parameters of the anti-seismic support-hanger are optimized, calculation result accuracy is ensured, and optimization design efficiency is greatly improved.

The invention discloses a method for calculating the gradient of a wind generation set tower. The method includes the steps that a relation expression between the gradient of the tower, the wind speed and the pitch angle is established and a superposition method is adopted for calculating the offset of the tower; when the wind speed v is smaller than or equal to 12 m / s, an adaptive least squares algorithm is adopted for fitting a function relationship between the wind speed and the gradient of the tower, and therefore the gradient of the wind generation set tower is acquired when the wind speed is zero or close to zero; an equation is solved under the operation condition that the wind speed is larger than the rated wind speed; when the inequation that 12 m / s<V<=25 m / s is satisfied, a multielement nonlinear regression analysis method is adopted for acquiring a relationship between the gradient, the wind speed and the pitch angle, a quadratic polynomial regression model is established, parameters of a multielement nonlinear regression model are estimated through a least square method, and the gradient is acquired. The method has the beneficial effects that the gradients of the wind generation set tower under different wind speed conditions can be acquired and calculation results are accurate.

The invention relates to a temperature compensation-based system time delay error correction method. According to the temperature compensation-based system time delay error correction method, a temperature measuring point is set in a precise ranging product, and temperature telemetry is acquired; temperature-pseudo range measurement is performed on the product, so that a priori value can be obtained; an n-order polynomial regression model is established to perform fitting residual analysis; when residual precision is compressed or is smaller than a predetermined threshold value with the increase of the order, the order which appears at the compression point of the residual precision or when the residual precision is smaller than the predetermined threshold value is adopted as the order of the polynomial regression model; the time delay correction coefficient of the n-order polynomial regression model is estimated according to the minimum root-mean-square criterion; and time delay correction is carried out under the temperature of the precise ranging product according to the time delay correction coefficient and the temperature telemetry which is acquired in real time. According to the temperature compensation-based system time delay error correction method of the invention, temperature telemetry acquisition is additionally realized on the product, and is adopted as a correction input factor, and therefore, ranging system errors caused by temperature change of the precise ranging product can be effectively solved. The correction method is simple and reliable and only occupies a small quantity of resources on the whole.

The invention discloses a searching method for a high-energy-efficiency neural network architecture. The searching method comprises the following steps: step 1, constructing a polynomial regression model of hierarchical operation time and power; step 2, calculating the overall energy consumption of the neural network architecture based on the operation time and power of the hierarchy; step 3, carrying out serialization on the discrete search space; and step 4, adding the energy consumption as one of search targets into a neural network architecture search process. According to the method, the high-energy-efficiency network architecture is accurately found in a machine search mode, and unnecessary search overhead is reduced. In the measurement of the energy consumption of the network architecture, the energy consumption of a specific architecture is predicted by using a polynomial regression model; in the architecture design process, the architecture meeting the requirements is automatically searched by using a machine instead of manual work, and the design process is more scientific; and a continuous search space and a search method based on gradient descent are utilized, a high-energy-efficiency target is newly added on the basis that only a high-precision neural network architecture is searched originally, and search results are optimized while search efficiency is improved.

Polynomial regression models are used to reduce errors in measurements of pseudorange between a GNSS satellite and a receiving station; for data compression by replacing a large number of measurements with a small number of coefficients of the model polynomial, optionally combined with modeling residuals; for extrapolating usefully accurate estimates of future range between the GNSS satellite and the receiving station; and for providing usefully accurate estimates of future coefficient values of the polynomial regression models themselves.

The embodiment of the invention belongs to the technical field of image processing. The invention relates to an image color real-time correction method, device and system, computer equipment and a storage medium, and the method comprises the steps: obtaining original data, carrying out data preprocessing, wherein the original data comprise original image data and standard color card data, and thestandard color card data at least comprise two pieces of gray color block data, calculating an RGB three-channel mean value of each color block included in the standard color card based on the original image data, fitting the RGB three-channel mean value of the gray color block to obtain a fitting parameter, correcting all color blocks of the standard color card by utilizing the fitting parameters, calculating correction parameters through a polynomial regression model, performing color real-time correction on the original image data based on the fitting parameters and the correction parameters, and then displaying the image data after color correction. According to the embodiment of the invention, the image color correction precision and speed can be improved.

Polynomial regression models are used to reduce errors in measurements of pseudorange between a GNSS satellite and a receiving station; for data compression by replacing a large number of measurements with a small number of coefficients of the model polynomial, optionally combined with modeling residuals; for extrapolating usefully accurate estimates of future range between the GNSS satellite and the receiving station; and for providing usefully accurate estimates of future coefficient values of the polynomial regression models themselves.

A method for the early identification of recurrences of chronic obstructive pulmonary disease comprising the following steps: measuring, with a predefined time frequency, a plurality of parameters that define the pulmonary function of a patient by means of the forced oscillation technique (FOT); calculating the trend of said plurality of parameters in a predefined time period; identifying an impending recurrence by comparing the parameters describing said trend of said plurality of parameters with predefined thresholds; where the step of calculating the trend of said plurality of parameters isachieved by calculation of an N order polynomial regression model; and the step of identifying an impending recurrence by comparing said parameters describing said trend with predefined thresholds comprises the step of comparing at least one coefficient of the N order polynomial regression with predefined thresholds.

The invention discloses a rotor structure optimization method based on central composite design, which comprises the following steps: 1, determining design variables of the rotor structure optimization, and determining the range and constraint conditions of the design variables; 2. The central composite design model is used to generate N groups of design variables, and the parameterized finite element method is used to compute the N groups of samples, and the maximum equivalent stress value corresponding to the N groups of samples is obtained as the objective function. 3. The least square method is used to fit the second-order polynomial regression model of the design variable and the objective function. 4. The fitting regression model is optimized, the initial point, initial step, acceleration coefficient, shrinkage coefficient and precision are given, the constraint conditions are set, and the axial detection movement and mode movement mode are judged by voting until the convergencecondition is satisfied, and the optimization of rotor structure is completed. The invention can quickly and accurately solve the problem of rotor structure optimization.

The invention relates to a wafer CMP material removal rate prediction method of a GMDH neural network. The method comprises the following steps: (1) obtaining a polishing sample data set after abnormal value removal; (2) analyzing samples in the polishing sample data set, and determining b effective process variables; (3) extracting the mean value, the standard deviation, the skewness and the kurtosis of each effective process variable to obtain 4 * b feature vectors; (4) screening the correlation between the 4 * b feature vectors and the corresponding MRR values, and determining m feature vectors as input feature vectors of the GMDH neural network model; (5) performing normalization processing on a data set formed by the m feature vectors to obtain a training feature set; (6) adopting a binary quadratic Volterra polynomial regression model, taking an input feature value in the training feature set as an input layer, taking a correspondingly output MRR value as an output layer, and obtaining a trained GMDH network model; and (7) inputting m characteristic values serving as inputs in a to-be-predicted sample into the trained GMDH network model, and outputting a predicted MRR value.

The invention relates to a correlation analysis method for multi-source tunneling parameters of a shield tunneling machine. The method comprises the following steps of: 1, acquiring multi-source data of the shield tunneling machine, and preprocessing the data; 2, carrying out preliminary screening of tunneling parameters based on a variance selection method; 3, analyzing a linear relation between every two parameters; 4, analyzing a nonlinear relation between every two parameters; 5, analyzing a linear relation between passive parameters and active parameters based on a multiple linear regression model; 6, analyzing a nonlinear relation between the passive parameters and the active parameters based on a polynomial regression model; and 7, carrying out model training between passive parameters and active parameters on residual parameters screened in the step 6 by utilizing a random forest algorithm, and selecting an optimal parameter combination according to feature importance. Compared with the prior art, the correlation analysis method has the advantages of being high in accuracy, more reliable, visual, high in efficiency, high in analysis capability and the like.

The invention discloses a fan output power prediction method, which comprises the following steps of: firstly, establishing a multivariate polynomial regression model based on a maximum information coefficient and multivariate polynomial regression; and then, determining a test set, and predicting the output power of the fan on the test set by using the multivariate polynomial regression model. In addition, the invention further provides a fan output power prediction system. According to the method and system, the maximum information coefficient is used for selecting the important variables influencing the output power of the fan in the process of establishing the multivariate polynomial regression model, multiple important variables are comprehensively considered, the problem that analysis is not comprehensive enough due to the fact that influence factors of the output power of the fan are analyzed manually is solved, and further, the relation between multivariable and the fan output power is modeled through a polynomial method, so that prediction of the fan output power has high accuracy and low model complexity.

The embodiment of the invention relates to the field of artificial intelligence, and discloses an end-to-end-based lane line detection method, device and equipment and a storage medium, and the method comprises the steps: obtaining a training sample set, and adding a lane line label to each sample image in the training sample set; inputting the sample image added with the lane line label into a specified depth polynomial regression model to obtain a prediction result; adjusting model parameters in a specified depth polynomial regression model according to a prediction result, and retraining the specified depth polynomial regression model to obtain a lane line detection model; and obtaining a to-be-detected image shot by a foresight shooting device of the target vehicle, and inputting the to-be-detected image into the lane line detection model to obtain a lane line of the target vehicle. In this way, the lane line can be determined more accurately and effectively, and the efficiency and the real-time performance of lane line detection are improved. The invention relates to a block chain technology, for example, image data can be written into a block chain so as to be used for scenes such as data evidence obtaining.

The invention discloses a structural damage identification method based on a step-by-step deletion model. The method comprises the following steps of obtaining a curvature modal difference between a current state and an intact state of a structure; establishing a curvature modal difference polynomial regression model; carrying out matrix processing on the regression model, and carrying out parameter estimation; deleting the curvature modal difference of a certain node, re-establishing a polynomial regression model and carrying out matrix processing, and carrying out parameter estimation; analyzing the difference of regression coefficients before and after node deletion by using MWK statistics, and searching a node set which is judged to be possibly damaged; wherein the node with the maximum MWK statistical magnitude absolute value in the possible damage node set is judged as a damage node; and deleting residual sample data of the node with the maximum MWK statistic absolute value in the damage set, and repeating the steps until all damage points are found out. According to the method provided by the invention, the parameter extraction process is suitable for a single-damage or multi-damage condition, and the technical problem of unclear damage position judgment caused by noise and measurement errors in existing power damage identification can be solved.

The invention relates to a titanium alloy constitutive relation prediction method based on machine learning, and belongs to the technical field of constitutive behavior prediction of metal materials.The prediction method comprises the following steps: obtaining and preprocessing stress-strain curves of various titanium alloys under different temperature and strain rate conditions; making a curvedata set which is independently used for training the a VAE-GAN model; constructing a prediction model part I based on the VAE-GAN model, and performing training; building a prediction model part II based on a polynomial regression model, and predicating coding of a stress-strain curve according to experimental conditions; and inputting the prediction codes into a VAE-GAN decoder, and outputting afinal prediction stress-strain curve. According to the prediction method, the change process and the failure strain of the stress of the titanium alloy material along with the strain are predicted atthe same time, the defect that a traditional constitutive model cannot predict the failure strain of the alloy material is overcome, and a new method is provided for alloy material constitutive relation prediction.

The invention provides a bank outlet blank voucher inventory usage prediction method and device, equipment and a medium. The method comprises the steps: acquiring the usage data and auxiliary data ofa blank voucher of a bank outlet; performing feature extraction according to the usage amount data and the auxiliary data to obtain feature data; respectively inputting the feature data into a plurality of pre-trained monomer prediction models to obtain corresponding prediction values; adopting a non-dominated sorting genetic algorithm with an elitist strategy to process the prediction value of each monomer prediction model to obtain a bank outlet blank voucher inventory usage prediction result, wherein the monomer prediction model is a polynomial regression model, an SVR regression model, anAdaBoost regression model, a Catboost model or a deep belief neural network model. According to the invention, by adopting the technical scheme, the inventory usage of various important blank voucherscan be accurately predicted, and the problem of shortage or overstock of one or more types of important blank voucher inventory can be avoided.

The invention relates to a method for determining a spatial interpolation model of cancer data. The method comprises the following steps: acquiring cancer data and related data of a to-be-analyzed area; the cancer data comprising cancer death rate data, the related data comprising basic geographic data, mining industry distribution data, social economic data, daily value meteorological data and PM2.5 pollution data, and the basic geographic data comprises village boundary vector data, road data, river data and topographic data; based on the cancer death rate data, the basic geographic data and the mining distribution data, determining the interpolation precision of the inverse distance weighting model, the interpolation precision of the trend surface analysis model and the interpolation precision of the common Kriging model; based on the cancer death rate data and the related data, determining the interpolation precision of the polynomial regression model and the interpolation precision of the collaborative Kriging model; and determining the model corresponding to the highest interpolation precision as an optimal spatial interpolation model. According to the scheme of the invention, the optimal cancer data spatial interpolation model can be rapidly determined, and the interpolation precision and the depicted data precision are improved.

The invention discloses an anti-seismic optimization design method of a building anti-seismic support-hanger. The method includes the steps: building a three-dimensional space analysis model of the building structure-anti-seismic support-hanger; selecting maximal space of the anti-seismic support-hanger and a minimum cross-sectional area of an inclined strut, and calculating maximum acceleration reaction of the anti-seismic support-hanger; calculating a floor response spectrum of a building structure, and correcting the floor response spectrum according to the maximum acceleration reaction toobtain a corrected floor response spectrum; building quadratic polynomial regression models among the maximum acceleration reaction of the anti-seismic support-hanger, the space of the support-hangerand the cross-sectional area of the inclined strut according to the corrected floor response spectrum; determining optimized design values of the space of the support-hanger and the cross-sectional area of the inclined strut. According to the method, polynomial regression models among earthquake actions of the anti-seismic support-hanger, the space of the support-hanger and the cross-sectional area and the support-hanger can be rapidly and accurately built, design parameters of the anti-seismic support-hanger are optimized, calculation result accuracy is ensured, and optimization design efficiency is greatly improved.

The embodiment of the present application belongs to the technical field of image processing, and relates to a real-time image color correction method, device, system, computer equipment, and storage medium. The method includes: acquiring raw data and performing data preprocessing, and the raw data includes raw image data and Standard color card data, the standard color card data includes at least two gray color block data; Calculate the RGB three-channel mean value of each color block included in the standard color card based on the original image data, and the gray color block Fitting the average value of the three channels of RGB to obtain fitting parameters; using the fitting parameters to correct all the color blocks of the standard color card, and calculating the correction parameters through the polynomial regression model; based on the fitting parameters and correction The parameter performs real-time color correction on the original image data, and then displays the color-corrected image data. The embodiments of the present application can improve the accuracy and speed of image color correction.

A search method for a high-energy-efficiency neural network architecture, including: Step 1: Construct a polynomial regression model of hierarchical running time and power; Step 2: Calculate the overall energy consumption of the neural network architecture based on the hierarchical running time and power; Step 3: Discrete Continuous search space; Step 4: Add energy consumption as one of the search objectives to the neural network architecture search process. The present invention accurately discovers high-energy-efficiency network architectures by means of machine search and reduces unnecessary search overhead. In the measurement of network architecture energy consumption, the polynomial regression model is used to predict the energy consumption of a specific architecture; in the architecture design process, machines are used instead of manual methods to automatically search for architectures that meet the requirements, making the design process more scientific; using continuous search space And the search method based on gradient descent, and on the basis of only searching for high-precision neural network architecture, a high-energy-efficiency target is added to improve search efficiency and optimize search results.

The invention provides a seven-color color separation model construction method based on a polynomial regression algorithm, which is used in a multi-color color separation method and is characterized by comprising the following steps: 1, designing a test sample set, dividing cyan, magenta, yellow, black, red, green and blue into six groups according to hue angles, performing balanced sampling according to the dot area rate of each color to generate a test sample set, and printing and outputting the Lab color value of the test sample set through a multi-color printer; 2, taking the dot area rate of each color block in the test sample set as a dependent variable, taking the Lab color value of each color block as an independent variable, and establishing a polynomial regression model; 3, conducting parameter estimation on the polynomial regression model through a total least square method, obtaining all coefficients of the polynomial regression model, so that a seven-color color separation model based on CMYKRGB is established, wherein parameter estimation of the total least square method is shown in the specification.

The invention relates to a method and a device for determining energization data for an actuator of an injection valve of a motor vehicle, wherein a control unit is supplied with input data and the control unit determines the energization data taking into account the input data, wherein the control unit Energy supply data were also determined by using a polynomial regression model (4).

The invention discloses a spatial consistency correcting method of a multi-spectral imaging system. The method comprises the following steps: measuring response values of a series of gray paper at different positions of the objective table of the multi-spectral imaging system, meanwhile, measuring a color block response value used for reflectivity reconstruction in the multi-spectral imaging system, and by means of a polynomial regression model, mapping the response values of the different gray paper at different positions to the response values of the central position by using the position information as independent variables, and meanwhile, mapping the response values of the color block used for reflectivity reconstruction to the target value by taking the position information as an independent variable. The spatial consistency precision requirement and the reflectivity reconstruction precision requirement in the multi-spectral imaging system are met at the same time, so that after spatial consistency correction is carried out, the spatial consistency chromatic aberration of the system is greatly reduced, and meanwhile, the chromatic aberration mean value of the reflectivity reconstruction is also reduced.