A system for controlling an operation of a machine subject to state constraints in continuous state space of the machine and subject to control input constraints in continuous control input space of the machine is provided. The apparatus includes an input interface to accept data indicative of a state of the machine, a memory configured to store an optimization problem for computing the safety margin of a state and action pair satisfying the state constraints and a control policy mapping the state of the machine within a control invariant set (CIS) to a control input satisfying the control input constraints, and a processor configured to iteratively perform a reinforcement learning (RL) algorithm to jointly control the machine and update the control policy.

Systems and methods for establishing relationships between building automation system components and controlling building automation system components. Data for a building automation system components may be received from the building automation system components and one or more models may be applied to the received data to determine types of the building automation system components and relationships between building automation system components. Once the types of building automation system components have been determined or identified, uniform names may be applied to the building automation system components. The received data may include, among other data, naming data and telemetry data from the building automation system components.

A method for controlling HVAC equipment for a building includes generating, based on historical building data, a discomfort tolerance defining an acceptable amount of occupant discomfort, determining a first value of an environmental condition at which the occupant discomfort is predicted to exceed the discomfort tolerance in a first direction, determining a second value of the environmental condition at which the occupant discomfort is predicted to exceed the discomfort tolerance in a second direction opposite the first direction, and controlling the HVAC equipment to maintain the environmental condition between the first value and the second value.

A method may include obtaining one or more inputs in which each of the inputs describes at least one of: a state of an autonomous vehicle (AV) or a state of an object; and identifying a prediction context of the AV based on the inputs. The method may also include determining a relevancy of each object of a plurality of objects to the AV in relation to the prediction context; and outputting a set of relevant objects based on the relevancy determination for each of the plurality of objects. Another method may include obtaining a set of objects designated as relevant to operation of an AV; selecting a trajectory prediction approach for a given object based on context of the AV and characteristics of the given object; predicting a trajectory of the given object using the selected trajectory prediction approach; and outputting the given object and the predicted trajectory.

Model-based predictive control method (MPC) for the reduction of structural load in wind turbines comprising: exclusively proposing a single internal linear model for the MPC for the entire operating range of the turbine; obtaining the adjustable parameters of the linear internal model from the experimental data previously measured in the turbine; choosing the discrete time values for the control and prediction horizons; adjusting the MPC controller and performing a practical implementation test.

There is provided a method of determining and utilizing predicted available power resources from one or more renewable power sources for one or more industrial gas plants comprising one or more storage resources. The method is executed by at least one hardware processor and comprises: obtaining historical time-dependent environmental data associated with the one or more renewable power sources; obtaining historical time-dependent operational characteristic data associated with the one or more renewable power sources; training a machine learning model based on the historical time-dependent environmental data and the historical time-dependent operational characteristic data; executing the trained machine learning model to predict available power resources for the one or more industrial gas plants for a pre-determined future time period; and controlling the one or more industrial gas plants in response to the predicted available power resources for the pre-determined future time period.

Computer-implemented methods for fault diagnosis in an industrial environment generally includes processing the plurality of sensor data values to determine a recognized pattern therefrom; retrieving at least one industrial-environment digital twin corresponding to the industrial environment, the at least one industrial-environment digital twin comprising a plurality of component digital twins, with each of the plurality of component digital twins corresponding to one of the plurality of components in the industrial environment, and wherein the at least one industrial-environment digital twin and the plurality of component digital twins are visual digital twins that are configured to be rendered in a visual manner; and rendering the at least one industrial-environment digital twin and the at least one respective component digital twin corresponding to the particular component in the client application in response to the received request and based on the operational condition of the particular component.

Accuracy of feedforward control for a wire straightener is improved. A feedback operation amount to a straightener is determined by a feedback control means based on an error between a target curvature and a straightening curvature. A feedforward compensation means determines a feedforward compensation value from a measurement value of the straightener using a prediction model. A learning means performs machine learning on the prediction model using teaching data. The learning means adds at least one combination including the measurement value and a manipulated variable when an absolute value of an error is smaller than a reference value to the teaching data.

Methods and systems are provided for optimizing a drill path from the surface to a target area below the surface. A method for operating an automated drilling program may comprise drilling to a target location along a drill path, updating a drilling path model based at least on data obtained during the state of drilling to the target location, creating a modified drill path to the target location based on at least the drilling path model in real-time as the step of drilling to the target location along the drill path is being performed, and drilling to the target location along the modified drill path.

A controller for operating building equipment of a building including processors and non-transitory computer-readable media storing instructions that, when executed by the processors, cause the processors to perform operations including obtaining a first setpoint trajectory from a cloud computation system. The first setpoint trajectory includes setpoints for the building equipment or for a space of the building. The setpoints correspond to time steps of an optimization period. The operations include determining whether a connection between the controller and the cloud computation system is active or inactive at a time step of the optimization period and determining an active setpoint for the time step of the optimization period using either the first or second setpoint trajectory based on whether the connection between the controller and the cloud computation system is active or inactive at the time step. The operations include operating the building equipment based on the active setpoint.