Adaptive predictive expert control procedure or system, called ADEX, that implements a control strategy in which an adaptive predictive expert controller, called ADEX controller, uses in its adaptive predictive domains a predictive adaptive model that dynamically relates the output of the process to be controlled with an integral function of the control signal that is applied to the process, instead of dynamically relating said process output with the signal that is applied to the process as conventional ADEX controllers of the prior art do. In this way, the output of said ADEX controller is an integral function of the control signal. From this integral function said control strategy uses a differential operator to calculate the real control action that is applied to the process.

Method for predictive control of a system having subsystems. The method includes providing signal injections relating to performance of the system. The signal injections include various operational controls for the system or its subsystems. Response signals corresponding with the signal injections are received, and a utility of those signals is measured. Based upon the utility of the response signals, data relating to operational controls is modified to optimize performance of the system via its subsystems.

A control device includes a first controller configured to generate a first operation amount for the device on the basis of an output fed back from the device and a target value, a predicted output generator including a learned model which is machine learned so as to generate a predicted output from the device on the basis of the output fed back from the device and the first operation amount, a second controller configured to generate a second operation amount for the device on the basis of the predicted output and the target value, an integrated operation amount generator configured to generate an integrated operation amount which is an operation amount for the device on the basis of the first operation amount and the second operation amount.

Various embodiments of the teachings herein include a method for controlling an integrated energy system. The method may include: determining the topological structure of an integrated energy system, the topological structure representing devices of the integrated energy system and connection attributes between the devices; determining general models of the devices and a connector model corresponding to the connection attributes; connecting the general models by means of the connector model so as to form a simulation model of the integrated energy system; training the simulation model; and generating a control command of the integrated energy system on the basis of the trained simulation model.

A method for controlling a system by a controller comprises accepting a current state of the system and selecting, using a trained function of the current state, a solver from a set of solvers. The method further comprises solving an optimal control optimization problem using the selected solver to produce a current control input, such that for at least some different control steps, the predictive controller solves a formulation of the optimal control optimization problem with different solvers having different accuracies, requiring different computational resources, or both and submitting the current control input to the system thereby changing the current state of the system.

A system for controlling building equipment determines a degradation factor for a first asset of the building equipment by comparing a design curve for the first asset and operational data for the first asset. The design curve includes a plurality of data points that define an operation of the first asset. The system generates an operational curve for the first asset by derating the design curve based on the degradation factor and operates the building equipment based on the operational curve.

The present disclosure describes a method of controlling a manufacturing system using multivariate time series, the method comprising: recording data from one or more devices in the manufacturing system; storing the recorded data in a data storage as a plurality of time series, wherein each time series has a first recorded value corresponding to a first time and a final recorded value corresponding to an end of the time series; interpolating, within a first time window, missing values in the plurality of time series using a Bayesian model, wherein the missing values fall between the first and end time of the respective time series; storing the interpolated values as prediction data in a prediction storage, wherein the interpolated values include the uncertainty of each interpolated value; loading the recorded data that fall within a second time window from the data storage; loading prediction data from the prediction storage that fall within the second time window and for which no recorded data are available; optimizing the parameters of the Bayesian model using the loaded recorded data and the prediction data; predicting, using the Bayesian model, values for each of the time series for which loaded recorded and prediction data are not available; storing the predicted values as prediction data in the prediction storage, wherein the prediction values include the uncertainty of each prediction value; and adjusting one or more of the devices that generate the recorded data based on the prediction data within the second time window.

A wire disconnection prediction device includes: a data acquisition part configured to acquire data relating to machining of a workpiece in a state where a wire is not disconnected during machining of the workpiece by a wire electric discharge machine; a preprocessing part configured to create, machining condition data of a condition relating to a machining condition commanded in machining of the workpiece, machining member data relating to a member used in the machining, and machining state data during machining of the workpiece, as state data indicating a state of the machining; and a learning part configured to generate, based on the state data created by the preprocessing part, a learning model indicating correlation between the state data and the state where the wire of the wire electric discharge machine is not disconnected.

Embodiments provide functionality to control real-world mechanical systems through the creation and deployment of machine learning models. An embodiment creates the machine learning model by extracting (i) an indication of efficiency and (ii) values of operational characteristics of one or more devices from one or more characteristic curves. Each characteristic curve corresponds to a respective device of one or more devices, in a mechanical system, functioning at a given speed. A training data set is created by determining efficiency and values of the operational characteristics for the mechanical system functioning with multiple combinations of the one or more devices operating at each of a plurality of speeds using the extracted indication of efficiency and extracted values of the operational characteristics. In turn, the machine learning model is trained with the created training dataset. Training configures the machine learning model to predict efficiency of the mechanical system based on operating data.

A measurement sensor is integrated with a control object so that a position separated from a processing object by the control object along a target trajectory is a measurement point. A control device includes: a first generator that generates a first command position of the control object on a plane; a first control part that generates a first operation amount using a model predictive control; a second generator that generates a second command position of the control object on an orthogonal axis that is orthogonal to the plane; and a second control part that generates a second operation amount using the model predictive control. The second generator generates the second command position so that the distance between the control object and the surface of an object is constant, based on the measurement result of the measurement sensor and the first command position.