Techniques are disclosed that enable the generation of predicted sequences of terminals using a generator model portion of a prediction model. Various implementations include controlling actuators of a robot based on the predicted sequences of terminals. Additional or alternative implementations include jointly training the generator model portion of the prediction model using a discriminator model portion of the prediction model using, for example, stochastic adversarial based sampling.

Systems and methods for model-based demand response are disclosed. An analytics server is communicatively connected to a data acquisition component and a virtual system model database. The data acquisition component is operable to acquire and transmit real-time data from a demand response (DR) power network to the analytic server. The virtual system model database is operable to provide a virtual system model of the DR power network. The analytics server is operable to generate predicted data based on the virtual system model of the DR power network and update the virtual system model in real time based on a difference between the predicted data and the real-time data. The analytics server is further operable to optimize DR output of the DR power network to a power grid.

An irrigation water optimization system based on predictive calculation of water potential of soil through web/cloud is provided. A field data collection system includes a local weather station and a soil data detection device for each area a prediction is to be obtained. Sensors of water potential in the soil detect efforts made by the crop in using available water. A neural network provides the necessary irrigation predictions based on acquired data and evapotranspiration calculated by appropriate equations. Predictions specifically refer to concerned land and allow saving water.

Computer implemented method for prediction of performances of a compressor includes modelling a CFD gas path, modelling vanes and blades as non-adiabatic solids, building a model of the rotor including at least a first rotor solid domain facing a plurality of vanes non-adiabatic solids and at least a second plurality of rotor solid domains attached to a plurality of blades non-adiabatic solids, building a model of the stator including at least a first casing solid domain attached to a plurality of vanes non-adiabatic solids and at least a second casing solid domain facing a plurality of blades non-adiabatic solids, modelling one or more solid rotor interfaces, each solid rotor interface providing an heat exchange link between a respective pair of adjacent rotor solid domains, and modelling one or more solid stator interfaces, each solid rotor interface providing an heat exchange link between a respective pair of adjacent stator solid domains.

A method for controlling a distributed power system is provided, the system including an aggregator communicatively coupled to a plurality of nodes, each of the plurality of nodes including an associated load. The method includes receiving, at the aggregator, a commanded power profile from an independent service operator, the commanded power profile including a commanded power deviation for the distributed power system, calculating, using the aggregator, a score for each of the plurality of nodes based on a current operating power of each node, selecting, using the aggregator, a subset of the plurality of nodes based on the calculated scores, and commanding, using the aggregator, each node in the subset to adjust its current power by a respective predetermined amount, the predetermined amounts determined based on the commanded power deviation.

To generate real-time or at least near real-time predictions for a process in an industrial plant, a set of neural networks are trained to create a set of trained models. The set of trained models is then used to output the predictions, by inputting online measurement results in an original space to two trained models whose outputs are fed, as reduced space inputs and reduced space initial states, to a third trained model. The third trained model processes the reduced space inputs to reduced space predictions. They are fed to a fourth trained model, which outputs the predictions in the original space.

A predicted value shaping system is provided for calculating a highly accurate control value by shaping of a predicted value. A prediction governor for calculating a control value (v) for controlling a controlled object includes: a result value acquisition unit (22) that acquires a previous target value of the controlled object, that is, a result value (r(t−1)); a predicted value acquisition unit (21) that acquires a predicted value (r (t)) obtained by predicting the target value of the controlled object (12); and a control value calculation unit (23) that calculates a control value (v(t)) for controlling the controlled object (12) by applying the result value (r(t−1)) and the predicted value (r (t)) to a predicted value shaping algorithm (G) to correct the predicted value (r̂(t). The predicted value shaping algorithm (G) uses parameters of a control model (P) of the controlled object (12).

Provided is a method and a device for computer-assisted detection of building automation parameters of a building, wherein a first building automation having first building automation parameters is determined for the building, which first building automation is based on one or more classes of respectively local parameters. The classes of local parameters include at least one first class of static building data of the building, a second class of current weather data for the location of the building, and a third class of prior building automation parameters of the building. The first building automation parameters are adapted depending on a number of classes of distant parameters of at least one predecessor building, which is situated at a location that is different from the location of the building. The number of classes of distant parameters at the location or for the location of the respective predecessor building is determined.

A system includes a controller configured to control an operation of a turbine system, and an analytics system coupled to the controller and configured to receive inputs corresponding to the operation of the turbine system, generate an operational impact factor (OIF) value based at least in part on the inputs, generate a turbine system life prediction model configured to predict an operating life of one or more components of the turbine system based at least in part on the OIF value, and provide the OIF value to the controller to perform an action based thereon.

A method, device, and system for configuring a coating machine for coating a surface of a product using a coating substance are provided. The method includes determining a value associated with one or more parameters from a plurality of parameters associated with the coating operation. The method also includes predicting a value associated with at least one attribute associable with the coating substance based on the determined value associated with the one or more parameters using a trained machine learning model. The method includes configuring the coating machine for coating the surface using the coating substance based on the predicted value associated with the at least one attribute associable with the coating substance. The method also includes initiating a coating operation at the configured coating machine for coating the surface of the product using the coating substance.