Embodiments of the present disclosure provide functionality for creating a sustainable dynamic reduced-order model (SDROM) for operating a real-world industrial process. The model is based upon a reduced order model (ROM) trained using data obtained from simulations performed using a first-principles model (FPM) of the real-world industrial process. The trained ROM is divided into multiple-input, single-output (MISO) sub-models, which are partitioned into component terms for incorporation of respective gain factors. The SDROM is deployed online to operate the real-world industrial process with one or more optimization objectives and the SDROM is periodically calibrated and validated using historical operation data.

A system and method for managing operation of electrical devices includes a control module that monitors status of multiple sources of electrical power to one or more electrical devices and electrical usage of the one or more electrical devices that receive electricity from the source of electrical power. The operation of the one or more electrical devices is managed using a machine learning model that forecasts status of the at least one source of electrical power and generates operational rules for the one or more electrical devices from historical values of control parameters of the one or more electrical devices, the status of the source of electrical power, and the electrical usage of the one or more electrical devices. The system may optimize renewable energy utilization, power grid stabilization, cost of electrical power usage, and the like.

A method of predicting plant data in a system generates prediction data based on a plant prediction model and for detecting anomalies of the plant by comparing the prediction data with measurement data. The method can provide precise prediction data in a normal state even though the measurement data contains data in an anomalous state. Anomaly/fault prediction accuracy is enhanced by providing precise prediction data in the normal state. An apparatus using the method includes a plant modeling unit for generating a plant prediction model based on k-nearest neighbors (k-NN) by modeling a plant based on measurement data of multiple tags; and a prediction data generating unit for measuring similarity between the plant prediction model and the measurement data, determining a parameter k value based on the similarity, and generating plant normal state prediction data based on the determined parameter k value and the measured similarity.

Machines can be controlled using advanced control systems that implement an automated version of singular spectrum analysis (SSA). For example, a control system can perform SSA on a time series having one or more time-dependent variables by: generating a trajectory matrix from the time series, performing singular value decomposition on the trajectory matrix to determine elementary matrices; and categorizing the elementary matrices into groups. The elementary matrices can be automatically categorized into the groups by: generating one or more w-correlation matrices based on spectral components associated with the time series, determining w-correlation values based on the one or more w-correlation matrices; categorizing the w-correlation values into a predefined number of w-correlation sets, and forming the groups based on the predefined number of w-correlation sets. The control system can then generate a predictive forecast using the groups and control operation of a machine using the predictive forecast.

A method for operating a plurality of wind turbines, in which a first current estimated wind value is derived from operating parameters of a first wind turbine, and in which a second current estimated wind value is derived from operating parameters of a second wind turbine. A prediction model is applied to derive, from the first current estimated wind value and the second current estimated wind value, a wind prediction, applicable to a future time point, for a third wind turbine. The wind prediction is processed in a controller, in order to generate a control signal for the third wind turbine that is effective before the future time point. The invention additionally relates to an associated control system. The loading for particular wind turbines can be reduced in that the wind conditions are predicted for a future time point.

A building system includes building equipment operable to consume one or more resources and a control system configured to generate, based on a prediction model, predictions of a load on the building equipment or a price of the one or more resources for a plurality of time steps in an optimization period, solve, based on the predictions, an optimization problem to generate control inputs for the equipment that minimize a predicted cost of consuming the resources over the optimization period, control the building equipment to operate in accordance with the control inputs, monitor an error metric that characterizes an error between the predictions and actual values of the at least one of the load on the building equipment or the price of the one or more resources during the optimization period, detect an occurrence of a trigger condition, and in response to detecting the trigger condition, update the prediction model.

A method may include obtaining first ambient condition data corresponding to a first building in a first location. The method may further include obtaining a set of ice dam models. The method may further include predicting, based at least in part on the set of ice dam models, an ice dam formation on the first building. The method may further include obtaining a heating profile. The heating profile may be based at least in part on the first ambient condition data. The method may further include adjusting, based on the heating profile, a heating device of the first building.

A method for controlling an electric drive system and the electric drive system. The method includes: measuring an external variable; estimating a control variable for a current sampling step with a mathematical model; predicting a control variable for a future sampling step for each of a plurality of candidate voltage vectors selected for the future sampling step; and calculating a cost function, and identifying a primary voltage vector giving a minimum, where the cost function is defined as a deviation between the predicted stator flux and the reference stator flux. The method further includes: predefining a lookup table giving a correlation between a nonzero voltage vector and a voltage vector group including four candidate voltage vectors, where the plurality of candidate voltage vectors is selected referring the lookup table. The electric drive system includes motor, power converter, and controller, and configured to perform the method.

A method for predicting a remaining useful life of a bearing involves obtaining a plurality of sets of actual inspection data from the bearing. The method involves obtaining an estimated wear rate from a physics based model of the bearing. The method further involves adjusting the estimated wear rate based on the plurality of sets of actual inspection data to compute an actual wear rate. The method also involves computing a calibration parameter based on the actual wear rate. The method further involves predicting a remaining useful life of the bearing based on the calibration parameter.

A system for use in a wellbore can include a computing device including a processing device and a memory device that stores instructions executable by the processing device. The instructions can cause the processing device to generate a predicted value of a parameter associated with a well environment or a wellbore operation. The instructions can also cause the processing device to determine a tuning factor for adjusting the predicted value based on historical data. The instructions can also cause the processing device to apply the tuning factor to the predicted value to generate a tuned predicted value. The instructions can further cause the processing device to generate an interface for display that includes a data point associated with the tuned predicted value plotted on a graph.