292 results about "Linear model" patented technology

The invention relates to the technical field of industrial mechanism models, in particular to a shock absorber performance optimization control method based on model fusion, which comprises the following steps: extracting a low-frequency disturbance state variable and inputting the variable-topology industrial mechanism model to generate a nominal reference state trajectory; utilizing a depth state observation network fused with energy passivity constraint to calculate a non-linear model mismatch compensation amount and an adaptive weighting parameter; performing dynamic fusion on the nominal reference state trajectory and the compensation amount based on the adaptive weighting parameter to generate a generalized state estimation value; and executing dynamic multi-objective optimization based on the generalized state estimation value, and generating mixed mode control input acting on an execution end. According to the invention, through adaptive fusion of a mechanism model and a data driving method, physical consistency, calculation real-time performance and robustness of a control process are considered.

The invention discloses a hydraulic engineering operation and management cooperative control system based on digital twinning, and the system comprises the following steps: a data assimilation module which collects observation station, remote sensing and meteorological data and assimilates the data to obtain an assimilation estimator; the dictionary and lifting module is used for generating a lifting variable sequence according to hydrodynamic force prior; the structure identification and uncertainty module is used for identifying a lifting linear model and recursively predicting uncertainty under the constraints of conservation, monotonicity, dissipation and spectral radius; the terminal security module constructs a positive invariant terminal security set according to a support function; the opportunity constraint module is used for setting a total out-of-limit probability budget and generating an opportunity constraint substitution set; the Koopman rolling optimization module is used for solving the control sequence and executing the first control quantity; and the online updating and correcting and deformation and verification module is used for executing residual error triggering low-rank correction, projection return and support surface parameter online deformation. According to the invention, risk-controllable and stable and efficient collaborative scheduling is realized.

The ELM-based frequency safety constraint linearization optimization scheduling method comprises the following steps: establishing a fire-wind-light multi-energy complementary frequency dynamic response model, and deducing a time domain analytical expression of a frequency safety index by taking a frequency maximum change rate and a frequency maximum deviation as the frequency safety index of a system; considering a frequency lowest point security constraint and a frequency maximum change rate security constraint, and establishing a frequency security constraint-containing optimization scheduling model; a maximum bearable disturbance power linearization mapping method based on ELM is provided, nonlinear frequency security constraints are converted into a series of linear constraint sets, and linearization processing of the frequency security constraints is achieved; and piecewise linearization is carried out on quadratic terms in the established objective function containing the frequency security constraint optimization scheduling model, the overall model is converted into a mixed integer linear model, and a Gurobi solver is used to solve the linearly processed model. The scheduling method can ensure that the system frequency is safe and stable, so that the established optimal scheduling model gives consideration to both economy and frequency safety.

The invention belongs to the field of near-inertia internal wave modeling, and particularly relates to a near-inertia internal wave modeling method based on a reverse echo observation array, which comprises the following steps: arranging a reverse echo measurement device array in an observation area, and acquiring echo signals from the seabed to the sea surface; performing data cleaning and band-pass filtering on the signals, and extracting near-inertia internal wave signals; calculating the depth and the relative vorticity of a mixed layer by combining historical temperature-salinity data; calculating a wind input energy flux by using the wind stress data; calculating a net level energy flux by adopting a boundary integration method; judging whether the boundary energy flux influence is smaller than a threshold value or not, and if not, adjusting array layout; and finally establishing a multivariable linear model containing wind energy input, mixed layer depth, relative vorticity and energy flux. According to the method, the temporal-spatial resolution and prediction precision of near-inertia internal wave modeling are effectively improved, the problems that in a traditional method, the boundary effect is remarkable, and multi-factor comprehensive modeling is insufficient are solved, and the method is suitable for long-term efficient monitoring of a large-range marine environment.

A method and apparatus for video coding are disclosed. According to the method for the decoder side, encoded data associated with a current block comprising a first-colour block and a second-colour block are received. An inherited model parameter set is determined from a previously coded block coded in a first CCLM related mode, wherein the inherited model parameter set comprises a first scaling parameter associated with the first CCLM related mode. A final inherited model parameter set is derived if an update value for the inherited model parameter set is determined, where the final inherited model parameter set is determined based on the first scaling parameter and the update value. Then, the encoded data associated with the second-colour block are decoded using prediction data based on an updated CCLM related model associated with the final inherited model parameter set. A method and apparatus for the encoder side are also disclosed.

The invention discloses a rapid progression type nasopharyngeal carcinoma risk prediction method based on an artificial neural network, and relates to the field of medical informatics crossing. The invention provides a rapid progressive nasopharyngeal carcinoma risk prediction method based on an artificial neural network, and aims to solve the problem that a rapid progressive nasopharyngeal carcinoma patient is difficult to recognize in time by depending on TNM staging and experience judgment in the prior art. According to the method, historical case data collection, missing value filling and standardization preprocessing, core feature determination through feature screening, class imbalance correction, feature coding and feature matrix construction are sequentially carried out, an artificial neural network model is trained and optimized under a cross validation framework, and performance and threshold values are determined on a validation set. During clinical application, patient features are input, and the model outputs a rapid progress risk probability and a risk level. Compared with a conventional staging or linear model, the method can improve the prediction accuracy, and achieves the early recognition and individualized treatment of a high-risk patient.

A video signal decoding device comprises a processor, wherein the processor predicts a sample of a chroma component corresponding to a sample of a luma component of a current block on the basis of the sample of the luma component, and predicts the current block on the basis of a predicted value of the sample of the chroma component. The predicted value of the sample of the chroma component is obtained using a linear equation, and the linear equation may include a term for a gradient value of the sample of the luma component.

The invention provides a three-coordinate measuring machine adaptive dynamic error compensation method, and relates to the field of three-coordinate measuring machines, and the method comprises the steps: obtaining multi-source state data of a three-coordinate measuring machine, and calculating a real-time dynamic error, the state data comprising a motion state, a dynamic response and environment disturbance data; based on the real-time dynamic error, using a recurrent neural network to construct a virtual measuring machine model, and performing offline training to obtain an initial error prediction model; and acquiring real-time error feedback data, and performing fine adjustment on the initial error prediction model by using an incremental learning algorithm and a sliding time window mechanism to obtain a prediction model capable of dynamically evolving and aging adaptive parameters. The method is used for overcoming the defect that in the prior art, a linear model or a fixed compensation parameter is difficult to accurately describe and compensate all dynamic errors sometimes.

The invention relates to the field of nonlinear system modeling, and particularly provides a global linear modeling method and system for a nonlinear system based on Lie derivative and sparse recognition, a terminal and a medium, and the method comprises the steps: obtaining an explicit nonlinear kinetic equation of a target system, calculating the Lie derivative of a state variable or an output variable of the system based on the kinetic equation, constructing a candidate observation function library directly associated with the physical mechanism of the system; performing screening and dimension reduction on the candidate observation function library by adopting a sparse recognition method to obtain a low-dimensional observation function set; and on the basis of the screened observation function and system operation data, a finite-dimensional global linear model of the target system in the dimension raising observation space is obtained through identification by using a data driving algorithm. According to the method, the online solving efficiency and the control real-time performance are improved, and efficient and reliable multi-target collaborative optimization control of systems such as a wind driven generator is realized.

The invention relates to the technical field of process control, in particular to an injection molding process optimization method and device, computer equipment and a storage medium, and the method comprises the following steps: obtaining stress signals of four tie bars of an injection molding machine, calculating a total mold locking force, and preprocessing the stress signals through temperature compensation and moving average filtering; real-time mold cavity pressure is calculated based on a mold filling stage linear model, a pressure maintaining stage quadratic function model and a cooling stage exponential attenuation model triggered by an injection molding machine control signal; generating a standard curve template with a confidence interval according to the characteristic parameters of the qualified sample, and dynamically updating the standard curve template; and comparing the current pressure curve with a standard template output quality judgment result in real time, and triggering automatic parameter adjustment to form closed-loop control. The device and the method have the effect of solving the problems of high cost, poor compatibility and difficulty in maintenance when the pressure of the die cavity is directly measured.

The invention relates to the technical field of power system modeling and simulation, in particular to a load model identification error analysis method, device and equipment and a storage medium, and the method comprises the steps: obtaining the prediction output and the measurement output of a preset load model, and building a target function based on the error between the prediction output and the measurement output; decomposing the measurement output to obtain an actual output and a noise component of a preset load model; and based on the objective function and the actual output, establishing a linear model between the identification error of the preset load model and the noise component through a first-order approximation method, and performing linear regression according to the linear model to obtain an analysis result of the identification error. Therefore, by constructing the theoretical model of the load model identification error, the problems that the identification error is difficult to predict, the data processing strategy selection lacks theoretical guidance and the like in related technologies are solved, and a theoretical basis is provided for selecting an optimal load modeling data processing strategy.

The invention discloses a brake chamber pressure estimation method and a brake chamber pressure sensor redundancy check method of a vehicle air pressure brake-by-wire system, and the method comprises the steps: carrying out the brake chamber pressure estimation according to a variable time constant inertia link pressure estimation model by using time constant initial values obtained through calibration in different brake modes; then, the forgetting factor is automatically adjusted by using the braking mode information; and finally, carrying out wheel state observation according to a random linear model of dynamic model parameter estimation formed by a variable time constant inertial link pressure estimation model and a wheel motion state differential equation, carrying out model parameter identification by adopting an augmented least square method with a forgetting factor, carrying out self-learning, and continuously correcting a time constant. And the corrected time constant is input into a variable time constant inertial link pressure estimation model for continuous iterative optimization, and brake chamber pressure estimation is continued.

The invention discloses a low-voltage power distribution network topology perception and electricity stealing detection method and system, and relates to the technical field of power distribution network anomaly detection, and the method comprises the steps: receiving measurement data and topology connection relation data, generating a residual equation based on the measurement data, the topology connection relation data and a Kirchhoff voltage law, and obtaining a power distribution network topology perception and electricity stealing detection result; performing approximate fitting on a pre-established linear model based on the measurement data to obtain a line impedance parameter initial value; performing impedance fitting on a pre-established nonlinear least square model based on the line impedance parameter initial value to obtain a reference line impedance parameter; acquiring a distortion data set under electricity stealing simulation, performing approximate fitting and impedance fitting to obtain a current line impedance parameter, calculating a Mahalanobis distance according to the reference line impedance parameter and the current line impedance parameter, and when the Mahalanobis distance is greater than a preset threshold value, judging that the line has an electricity stealing behavior, and if the Mahalanobis distance is greater than the preset threshold value, judging that the line has an electricity stealing behavior. Otherwise, the electricity stealing behavior does not exist, and the detection accuracy of electricity stealing is improved.

The application provides a method for predicting the operation time of a ship T-beam welding robot based on machine learning, comprising: obtaining the weld seam meters of multiple types of weld seams planned by T-beam welding robot offline programming software, and recording a data set of actual operation time thereof; dividing the data set into a training set and a test set according to the time dimension; performing normalization processing on the weld seam meters of different weld seam types; using a gradient descent method to solve and construct a linear model of multiple types of weld seams; setting hyperparameters and initial values of model variables; training the model; visualizing the output of the result to evaluate the model; predicting the operation time of a new ship section sample data on the model; constructing a linear model function of multiple types of weld seams through the characteristics of section weld seam sample data, training the weight values of each weld seam type in the model affecting the operation time, and predicting the operation time of a new section in a robot welding station, which can be applied to a robot ship manufacturing workshop and improves the accuracy of operation time prediction of the ship manufacturing workshop.

The application discloses a nearshore disaster-bearing body disaster-causing path tracing method based on digital-analog experiments, relates to the technical field of ocean dynamic disaster simulation, determines the ocean dynamic disaster characteristics of a nearshore research area, integrates multi-source historical disaster data, real-time monitoring data and disaster-bearing body background data, and constructs a time-space correlation database; based on a three-dimensional ocean and a third-generation sea wave model, a nearshore storm surge-sea wave coupling numerical model is established and verified. Through the construction of the storm surge-sea wave coupling numerical model, the present application comprehensively considers the nonlinear interaction of multiple disasters, introduces an energy conservation equation to quantify the generation, transmission and dissipation process of disaster energy, solves the limitations of traditional single-disaster linear models, and combines the real-time feedback of the three-dimensional dynamic model of the disaster-bearing body to form a closed energy-damage correlation mechanism, significantly improves the tracing accuracy of the disaster chain propagation path, and ensures that the identification of key nodes and dominant paths is more consistent with physical reality.

This invention discloses a multi-round adaptive data sharding method for building a learning index. Based on the current linear model prediction, it actively introduces empty slots to adjust the position of newly added data to the model. This accelerates data writing, repairs breaks between data shards, reduces the number of shards, and thus reduces index space overhead. This invention solves the technical problems of high learning index space overhead in existing top-down construction methods due to the large number of models, and low access efficiency in existing bottom-up construction methods due to the compact data shards lacking empty slots and requiring external buffers to support dynamic loads. It also addresses the technical problem of increased shard number and index space overhead in existing bottom-up construction methods when the error threshold is small due to the low linearity of large amounts of data.

The invention discloses a power system frequency intensity quantitative evaluation method, system, equipment and medium considering DC frequency limit control nonlinear characteristics, and belongs to the technical field of power systems and automation thereof, and the method comprises the steps: constructing a common-mode frequency model of a DC-synchronous machine system, and simplifying a high-order nonlinear system into a second-order linear model; the method comprises the following steps of: dividing frequency response into three stages according to a trigger condition of direct current frequency limit control, and respectively establishing an analytical model of each stage; and defining a frequency intensity index and a critical value based on the maximum frequency offset, and evaluating the frequency intensity margin of the system. The accuracy of the analysis method and the strength evaluation is verified through simulation. According to the method, a common-mode frequency model is established, a uniform-structure approximate synchronous machine and other equipment are adopted to dynamically analyze a frequency track under the influence of an FLC dead zone and amplitude limiting in stages, and the maximum offset characteristic is accurately obtained; meanwhile, a frequency intensity index and a critical value are defined, and quantitative evaluation and margin analysis of the frequency intensity are achieved.

The present disclosure provides a chroma block prediction method and a device. The method includes: parsing a bitstream to obtain first indication information; downsampling a first luma block by a first filter when a value of the first indication information is a first value or by using a second filter when a value of the first indication information is a second value, to obtain a second luma block; obtaining a plurality of chroma samples and a plurality of luma samples; obtaining linear model coefficients based on the plurality of chroma samples and the plurality of luma samples; and obtaining a prediction value of the current chroma block based on the second luma block and the linear model coefficients.

The invention relates to the technical field of digital soil mapping, and particularly discloses a soil organic carbon global and local integrated modeling method considering spatial heterogeneity. According to the method, global linear, global nonlinear and local spatial heterogeneity relationships are respectively captured through a mixed linear model, a support vector machine and a multi-scale geographically weighted regression model, a KAN-Transform architecture is utilized to generate a spatial adaptive integrated weight, and Bayesian optimization is combined to improve prediction precision. The problem that a traditional single model or integration method is insufficient in depicting complex spatial relations is effectively solved.

The application relates to the technical field of inductive synchro technology, and discloses an inductive synchro temperature self-adaptive compensation method, device and equipment, wherein the method comprises the following steps: determining initial linear coefficients of an initial linear model; acquiring a current environment temperature and a current measurement angle of the inductive synchro, and determining initial iteration parameters of the initial linear model according to the current environment temperature and the current measurement angle; iteratively updating the initial linear coefficients according to the initial iteration parameters to obtain target linear coefficients, wherein data format conversion is performed in each iteration updating process, and the next iteration is performed according to the conversion result; updating the initial linear model based on the target linear coefficients to obtain an updated target linear model, and determining a measurement angle compensation value of the inductive synchro according to the target linear model. The application can realize high-precision and self-adaptive real-time temperature compensation of the inductive synchro in a hot vacuum environment, and simultaneously adapt to the hardware design and reliability requirements of an aircraft.

This application provides a video image component prediction method and apparatus, and a computer storage medium. The method may include: acquiring a reference value set of a first image component of the current block; determining multiple first image component reference values ​​from the reference value set of the first image component; performing a first filtering process on the sample values ​​of the pixels corresponding to the multiple first image component reference values ​​respectively to obtain multiple filtered first image reference sample values; determining the image component reference value to be predicted corresponding to the multiple filtered first image reference sample values; determining the parameters of a component linear model based on the multiple filtered first image reference sample values ​​and the image component reference value to be predicted; performing a mapping process on the reconstructed value of the first image component of the current block according to the component linear model to obtain a mapping value; and determining the predicted value of the image component to be predicted of the current block based on the mapping value.

The invention discloses an RGB-LED spectrum closed-loop system for colorimetry teaching and a color matching method. The system comprises a multi-source input module, a spectrum database module, a dynamic modeling module, an optimization algorithm engine module, a duty ratio calculation module, a PWM driving module and a closed loop verification module. The system is provided with a multi-source input interface, target color coordinates can be obtained, and chromaticity conversion of RGB input is supported; on the basis of the constructed high-precision linear model, solving a normalized strength ratio under constraints by combining an optimization algorithm engine and taking minimization of chromatic aberration as a target; calculating an actual PWM duty ratio according to the actual PWM duty ratio; meanwhile, a spectral irradiation sensor is integrated to collect a mixed color spectrum in real time, actual color coordinates are calculated, and an offset connecting line with an arrow between a target point and an actual point is dynamically drawn in a chromaticity diagram, so that a set of complete visual teaching tool is formed. Compared with a manual color matching scheme, the color mixing precision and the color matching efficiency are greatly improved, and the teaching requirements of colorimetry can be better met.

In one embodiment, a video codec receives a local luminance compensation (LIC) linear model generated using samples of two adjacent, different blocks, which is a linear model of local luminance compensation (LIC), which is a linear model of local luminance compensation (LIC) generated using samples of the two adjacent, different blocks of samples of the two adjacent, different blocks of samples of the two adjacent, different blocks of samples. The linear model includes a scaling factor and a y-axis intercept. The video codec adjusts the linear model by applying an offset to adjust a scaling factor (or slope) of the linear model. The scaling factor or y-axis intercept of the adjusted linear model may be tailored to remain within a prescribed range. The offset may be selected from a set of predefined values for a syntax element signaled in a bitstream. The applied offset may be inherited from a previously encoded location. When a current block is encoded by bidirectional prediction, the linear model may be one of a first and a second linear model used to generate a predictor of the current block.

The application discloses a multi-power unit high-speed train control method, and relates to the technical field of train control.The method comprises the following steps: performing stress analysis on a multi-power unit high-speed train to determine a high-speed train dynamics model; determining a discrete-time nonlinear model based on the high-speed train dynamics model; constructing control force and control force change rate constraints; converting the discrete-time nonlinear model to obtain a dynamic linearization data model; designing a parameter estimation algorithm and an adaptive extended state observer; designing a discrete-time terminal sliding mode function and a hyperbolic curve type reaching law; determining a data-driven terminal sliding mode control scheme based on the dynamic linearization data model, the parameter estimation algorithm, the adaptive extended state observer, the discrete-time terminal sliding mode function and the hyperbolic curve type reaching law; and performing tracking control operation on the multi-power unit high-speed train by using the data-driven terminal sliding mode control scheme.The application improves the control precision of high-speed train operation while reducing the sliding mode chattering.

This invention discloses a method for calculating needle-free injection depth based on energy analysis, comprising the following steps: Step 1, obtaining the jet process parameters during a single needle-free injection, and calculating the initial peak jet power and the total jet energy of this injection; Step 2, calculating the initial injection depth based on the initial peak jet power using a preset initial depth linear model; Step 3, calculating the diffusion depth increment based on the total jet energy using a preset diffusion depth linear model; Step 4, calculating the predicted maximum injection depth based on the sum of the initial injection depth and the diffusion depth increment. This invention decomposes the injection process into two stages: initial impact and subsequent diffusion, and establishes linear prediction models for each stage based on the jet energy parameters, thereby achieving reliable and accurate calculation and prediction of the injection depth for large-volume needle-free injections.

The invention discloses an online parameter identification and hysteresis compensation method for a piezoelectric positioning platform. The method comprises the following steps: S1, signal acquisition: acquiring an input signal u (t) and an output signal y (t); s2, filtering processing: constructing a filtering variable and a regression vector phi (t) by using a filtering technology; s3, auxiliary variable calculation: solving an auxiliary regression matrix M (t), a vector N (t) and a vector R (t); s4, estimation error information extraction: constructing a parameter approximate estimation error vector E (t); s5, parameter estimation updating: updating an estimation vector according to a parameter estimation adaptive law based on a preset time-space obstacle function; and S6, hysteresis compensation: realizing hysteresis compensation based on a feedback linearization strategy. According to the method, the asymmetric dynamic hysteresis nonlinear model for accurately describing the piezoelectric positioning platform can be established, online parameter identification and real-time hysteresis compensation are realized for parameter perturbation possibly generated by a system under an uncertain working condition, and the positioning precision of the piezoelectric positioning platform in the ultra-precision positioning field is effectively improved.

The present application relates to the field of postharvest storage quality control of fruits and vegetables, and particularly relates to a fruit and vegetable postharvest weight loss rate prediction method and system based on sliding window correction. The method first uses the weighted average weight loss rate of a small number of time points in the early storage period to establish an initial linear model; then a time sliding window is constructed for local linear fitting when new observations are observed, and a dynamic correction factor is adaptively calculated according to the prediction error to update the weight loss rate slope and intercept in real time, so as to continuously correct the long-term trend. The system includes data acquisition, preprocessing and weighting calculation, initial modeling, sliding window fitting, dynamic correction and prediction output modules. Compared with the fixed parameter model, the present application significantly improves the determination coefficient, reduces the root mean square error and the average absolute error on various fruits and vegetables, and has high precision, strong adaptability and good engineering application prospect.

This invention discloses a multivariate time series forecasting method based on prediction domain transformation and dual-path fusion. A time series forecasting model, PDT, is proposed. It utilizes data-adaptive prediction domain transformation to project the time series onto the energy-concentrated optimal latent space for prediction. A dual-path architecture is designed to simultaneously achieve efficient extrapolation of dominant linear trends and capture complex nonlinear dynamics. A masked channel dependency strategy and a lightweight linear encoder are used to adaptively fusion and filter inter-variable dependencies and deeply extract intra-channel features, respectively. The proposed time series forecasting model significantly solves the problem of insufficient nonlinear expressive power of traditional linear models and enhances noise resistance and computational efficiency in high-dimensional multivariate scenarios, comprehensively improving the prediction accuracy and robustness of the model in multivariate time series forecasting tasks.

The invention particularly relates to a direct force carrier landing control method based on predefined time active disturbance rejection control, and belongs to the technical field of aviation. Aiming at the problems of high landing accident rate and large wake flow disturbance influence of a shipboard aircraft, uncertain convergence of a traditional control method and the like, the method comprises the following steps: firstly, establishing a six-degree-of-freedom nonlinear model, an aerodynamic force and an aerodynamic moment model of the shipboard aircraft, and fusing the wake flow disturbance influence; constructing a torque control channel and a direct force control channel, and converting the torque control channel and the direct force control channel into a control-oriented model; and then designing PTADRC-based attitude angle, angular rate and track angle control laws, and realizing total disturbance estimation and compensation through PTESO. Simulation verification shows that the method has no overshoot and no steady-state error tracking instruction in the predefined time, is high in anti-interference capability, can guarantee the stability and accurate control of the landing attitude of the shipboard aircraft, and remarkably reduces the landing risk.

The invention relates to a POD secondary manifold lower chamber flow field nonlinear model order reduction method based on anchor point optimization, and the method comprises the steps: obtaining a two-dimensional lower chamber computational fluid mechanics model as a full-order model, and building a snapshot matrix according to the full-order model; carrying out POD order reduction on the snapshot matrix, and calculating a POD reconstruction error matrix and a secondary manifold coefficient matrix of the snapshot matrix; determining an anchor point, and calculating a quadratic manifold modal matrix at the anchor point according to the POD reconstruction error matrix and the quadratic manifold coefficient matrix; according to the secondary manifold modal matrix at each anchor point, obtaining a secondary manifold modal matrix at the test point; and according to the quadratic manifold modal matrix at the test point, calculating an approximate snapshot of the POD quadratic manifold nonlinear reduced-order model at the test point. According to the method, the representative anchor points are introduced into the parameter sampling space, so that self-adaptive calculation of the secondary manifold modal matrix is realized, and the approximation precision of the reduced-order model is improved.