75 results about "Multivariable model" patented technology

An computer implemented apparatus and method are disclosed for defining areas of a field in which a crop or other vegetation is grown based on their selective ability to grow such vegetation through a growing season, or some shorter preselected time period. The method includes making a number of temporally separated measurements through air borne imaging of a field, registering the data to the geography of the field and each other, normalizing the data including converting the data to a vegetative index indicative to the presence of vegetation in the field, comparing the data to identify clusters of like value, and classifying the clusters and images to learn how the different field areas responded in growing vegetation through the season. With this method, the field may be segregated into a number of like areas called crop response zones which exhibit similar vegetative growth characteristics as an aid to a grower in his decision making regarding how to maximize yield in his field.

Systems and methods are provided that allow a user to monitor, diagnose, and configure a process. A user interface may be presented that displays data received from process monitors, sensors, and multivariate models. The user interface may be interactive, allowing a user to select which composite and multivariate models are displayed. The user interface and multivariate model may be constructed and updated in real time. The user interface may present various data and interfaces, such as a representation of a composite variable in a multivariate model, a representation of the contribution of process variables to the composite variable, and a representation of a subset of the process variables. The user may select a point of the composite variable for analysis, and the interface may indicate the contribution and values of process variables at the selected point. The interface may be transmitted to a remote user.

A fast and reliable technique for tuning multivariable model predictive controllers (MPCs) that accounts for performance and robustness is provided. Specifically, the technique automatically yields tuning weights for the MPC based on performance and robustness requirements. The tuning weights are parameters of closed-loop transfer functions which are directly linked to performance and robustness requirements. Automatically searching the tuning parameters in their proper ranges assures that the controller is optimal and robust. This technique will deliver the traditional requirements of stability, performance and robustness, while at the same time enabling users to design their closed-loop behavior in terms of the physical domain. The method permits the user to favor one measurement over another, or to use one actuator more than another.

A novel multivariate model for analysis of absorbance spectra allows for each wavelength or spectral region to be modeled with just enough factors to fully model the analytical signal without the incorporation of noise by using excess factors. Each wavelength or spectral region is modeled utilizing its own number of factors independently of other wavelengths or spectral regions. An iterative combinative PCR algorithm allows a different number of factors to be applied to different wavelengths. In an exemplary embodiment, a three-factor model is applied over a given spectral region. The residual of the three-factor model is calculated and used as the input for an additional five-factor model. Prior to the additional five factors being applied, some of the wavelengths are removed. This leads to a three-factor model over the first region and an eight-factor model over the second region. This analysis of residuals can be repeated such that a one to n factor model could be applied to any given wavelength, or rather any number of factors may be employed to model any given frequency or spectral region. A method of predicting concentration of a target analyte from sample spectra applies a calibration developed using the inventive PCR algorithm to a matrix of sample spectral to generate a vector of predicted concentrations for the target analyte.

The invention discloses a fault diagnosis-based rail transit vehicle bearing residual life prediction method. The method includes the following steps that: S100, multi-angle feature extraction and fusion are performed; S200, cyclostationary theory-based fault diagnosis is performed; S300, multi-variable model training is performed, so that multi-variable model-based fault isolation is realized; and S400, based on a semi-supervised algorithm, a BP neural network algorithm and a support vector regression algorithm are used in combination to perform fault diagnosis-based residual life prediction. With the fault diagnosis-based rail transit vehicle bearing residual life prediction method of the invention adopted, fault detection, fault isolation and residual life prediction at the early stage of the fault of a bearing are realized, and a basis is provided for the formulation of vehicle bearing maintenance decision making.

The invention discloses a fluidized bed boiler control and combustion optimization system. The problem that a fluidized bed boiler system is not easy to control for a long time is solved. According to a method, a control strategy of combining an advanced control algorithm and a conventional control algorithm is adopted, and continuous, economical and stable operating of the boiler system is guaranteed; multivariable model-free adaptive control is adopted, and decoupling control of the fuel quantity and the air supply quantity over the bed temperature under the variable load work condition is achieved; and a nerual network technique is adopted for building a boiler combustion prediction model, online calculation of the boiler efficiency and NOX and SOX emissions is achieved, a multi-objective optimization function is constructed according to the prediction result, a combustion self-optimization algorithm is adopted, the flue gas oxygen content and the bed temperature are optimized constantly so as to adapt to work condition changes, and a fluidized bed boiler can operate in an optimal combustion area.

The invention relates to a multi-parameter time-varying robot spraying method which comprises the following steps: firstly, establishing a free-form surface multivariable spraying model which uses flow of a spraying gun, a spraying distance and a spraying speed as model independent variables; then discretizing an original spraying path into a plurality of sections of minute sub paths, distributing initial values of time-varying spraying process parameters to each sub path and on the basis of the established multivariable spraying model, predicting distribution of an initial coating thickness; next, on the basis of a prediction result on distribution of the coating thickness, carrying out combined optimization on the time-varying process parameters to obtain the optimal process parameters on each section of sub path and finally, obtaining a multi-parameter time-varying spraying path of a surface to be sprayed. According to the method disclosed by the invention, various process parameters are used as variables; by the multivariable spraying model and a free-form surface coating thickness predicting method, the optimal process parameters on the sub paths of the discretized spraying path are obtained; dynamic optimization of the process parameters is implemented; the multi-parameter time-varying robot spraying method has the important effect of improving spraying operation efficiency, quality and safety of a robot.

An automated tuning method of a large-scale multivariable model predictive controller for multiple array papermaking machine cross-directional (CD) processes can significantly improve the performance of the controller over traditional controllers. Paper machine CD processes are large-scale spatially-distributed dynamical systems. Due to these systems' (almost) spatially invariant nature, the closed-loop transfer functions are approximated by transfer matrices with rectangular circulant matrix blocks, whose input and output singular vectors are the Fourier components of dimension equivalent to either number of actuators or number of measurements. This approximation enables the model predictive controller for these systems to be tuned by a numerical search over optimization weights in order to shape the closed-loop transfer functions in the two-dimensional frequency domain for performance and robustness. A novel scaling method is used for scaling the inputs and outputs of the multivariable system in the spatial frequency domain.

Example embodiments of the present invention relate to a multivariate modeling method, a method of fabricating semiconductors using a semiconductor fabricating facility and a multivariate model creating apparatus. Other example embodiments of the present invention relate to a method and apparatus for modeling multivariate parameters having constants and the same pattern and a semiconductor fabricating method of detecting whether a semiconductor fabricating facility is operating normally using the multivariate modeling method. In a multivariate modeling method according to example embodiments of the present invention, data of parameters are selected during a modeling period. Averages and standard deviations of the data of the parameters may be calculated. It may be determined whether the data of the parameters contain non-random data. If the data of the parameters do not contain non-random data, the data may be normalized using the averages and standard deviations of the data of the parameters. If the data of the parameters contain non-random data, random data may be added to data of a parameter containing the constants or the data similar to constants among the parameters. The data may be normalized by calculating an artificial standard deviation of the random data added data of the parameter. Characteristic values of the parameters may be analyzed from the normalized data. A model may be created based on the characteristic values.

Methods and systems for the design and implementation of optimal multivariable MPC controllers for fast-sampling constrained dynamic systems utilizing a primal-dual feasibility approach and/or a graph approach. The primal-dual feasibility approach can compute and store matrices defining constraints of quadratic programming problems in an off-line part in order to calculate vectors of Lagrange multipliers and an optimizer. Then primal-dual feasibility can be checked in an on-line part using the Lagrange multipliers and the optimizer can provide a unique optimal solution for the constrained dynamic system. The graph approach can compute and store the matrices and the vectors, and also prepare and store a structure of directed graph in off-line part. An optimizer for a given parameter vector can be determined in on-line part using the directed graph, the matrices and the vectors.

Thermomechanical pulp is an important process for producing fibrous mass used in papermaking. A two-level control strategy that stabilizes and optimizes the refining process has been developed. The Stabilization layer consists of a multivariable model predicative range controller that regulates the refiner line operations. The Quality Optimization layer provides the pulp quality control as measured by an online pulp quality (freeness, fibre length) sensor. This control startegy leverages the natural decoupling in the process. The modular design technique is able to handle multiple refiner lines that empty into a common latency chest. A global optimizer is also used to integrate and coordinate the two layers for enhanced constraint handling.

A technique for fast performance prediction of multivariable model predictive controllers (MPC) for large-scale spatially-distributed dynamic systems is provided. When operating an MPC for a two-dimensional sheetmaking process, the controller's performance can be separated into spatial performance and dynamic performance. The steady-state spatial performance for different sheet property modes is first predicted, thereafter, the dynamic performance is predicted on the basis of the steady-state actuator profiles. During the steady-state spatial performance prediction, the original MPC's cost function is approximated to be a steady-state cost function. Then the steady-state measurement profiles and the actuator profiles are calculated through the steady-state cost function. The actuator profiles in time series can be efficiently solved by minimizing the difference between the actuator profiles and the steady-state actuator profiles in the face of constraints. Finally, the model can be employed to expeditiously compute the measurement profiles in times series.

The invention discloses a multivariable-based equipment dynamic health state assessment method. A multivariable model combining the comprehensive significance-bias convolutional neural network and thedecreasing maximum entropy fuzzy clustering is utilized to perform equipment dynamic health state evaluation; the method has the advantages that the training time is shortened, the model precision and generalization ability are improved, the fault threshold can be dynamically distributed according to the environment, the real working condition of the equipment is met, and the accurate health state evaluation and life prediction of the equipment are realized.

The invention discloses a multivariable model and blind number theory-based spatial load prediction method. The method is characterized by comprising the steps of performing correlation analysis on total power loads based on numerous factors influencing changes of the total power loads, and determining main factors influencing the changes of the total power loads in the factors; by applying a multivariable analysis method, building a multivariable prediction model for predicting the total power loads by taking the main factors influencing the changes of the total power loads as input variables; establishing an index system for assessing development states of the main factors influencing the changes of the total power loads, calculating target annual values of the main factors influencing the changes of the total power loads, and predicting the total power loads by adopting the multivariable prediction model; and calculating target annual classified power load values by utilizing totalpower load prediction results, establishing a power geographic information system comprising land use information of to-be-predicted areas, and calculating out classified power load density, thereby obtaining power load values of power supply communities.

A method for a cache architecture simulation includes obtaining a first sample set for the cache architecture using a non-stationary Gaussian field model, performing a cache architecture simulation using the first sample set to produce a first set of simulation data, and fitting a first multivariate model to the first set of simulation data.

Embodiments of the present invention provide systems, apparatuses, methods, and computer program products for forecasting the future headcount of an organization by generating, validating and displaying models of the headcount of an organization or division thereof over time. In some embodiments, at least three different models are generated using stored historical headcount information, including a linear regression model, a multivariate model using macroeconomic variables, and an autoregressive moving average model. In some embodiments, for each of the foregoing types, multiple models are generated and the best model of each type is selected for use in forecasting headcount according to predetermined evaluation criteria.