An operation condition setting support device supporting setting of an operation condition of a plant includes a state value acquirer acquiring state values representing states of controlled devices during operation of the controlled devices, a predictor estimating predicted values for the respective state values at a predetermined future time point based on the respective state values acquired by the state value acquirer, and a notifier, in a case where an index calculated based on a difference between each of the state values at the predetermined time point acquired by the state value acquirer and each of the predicted values at the predetermined time point or a later time point than the predetermined time point estimated by the predictor or a change ratio of the difference satisfies a predetermined condition, providing notification of the case.

A control mechanism scheduler for a water resource infrastructure receives operating data and disturbance data, the operating data describing infrastructure components of the water resource infrastructure, the disturbance data comprising a disturbance signal describing a disturbance expected to disturb the water resource infrastructure. The control mechanism scheduler generates classes for disturbance signals, generates simulations of the water resource infrastructure, and generates schedules of setpoints for control mechanisms actuable to control the infrastructure components of the water resource infrastructure in accordance with approaching a predetermined objective.

A system and computer-implemented method are provided for training a dynamics model to learn the dynamics of a physical system. The dynamics model may be learned to be able to infer a future state of the physical system and/or its environment based on a current state of the physical system and/or its environment. The learned dynamics model is inherently globally stable. Instead of learning a dynamics model and attempting to separately verify its stability, the learnable dynamics model comprises a learnable Lyapunov function which is jointly learned together with the nominal dynamics of the physical system. The learned dynamics model is highly suitable for real-life applications in which a physical system may assume a state which was unseen during training as the learned dynamics model is inherently globally stable.

Systems and methods of managing an electricity distribution grid, including receiving a layout of at least one electricity distribution grid coupled to at least one power distributor facility, each grid having at least two electrical power nodes, collecting data for at least one consumer of the electricity distribution grid, assigning a dynamic consumer value to each of the at least one consumer according to predefined attributes, determining aggregated power consumption values for each electrical power node, wherein for each electrical power node the aggregated power consumption values are received for all consumers assigned thereto, and allocating resources of the at least one power distributor facility, from the first electrical power node to the second electrical power node, if the difference between the compared consumer values exceeds a predetermined threshold.

A powered balancing mobility device that can provide the user the ability to safely navigate expected environments of daily living including the ability to maneuver in confined spaces and to climb curbs, stairs, and other obstacles, and to travel safely and comfortably in vehicles. The mobility device can provide elevated, balanced travel.

A cardboard sheet manufacturing system includes an information editing unit storing production state information, operation state information, and warping state information as acquisition information in a storage unit, the information editing unit deleting, in a case where the stored acquisition information includes prescribed information to be deleted, the information to be deleted from the storage unit and outputting the acquisition information stored in the storage unit as editing information. The system also includes an editing information storage unit storing the editing information output from the information editing unit, a prediction model calculation unit calculating a prediction model of the warping state based on the editing information stored in the editing information storage unit; and a control table update unit updating a target value of a control value of a control element in the cardboard sheet manufacturing apparatus, based on the prediction model.

A device for controlling an industrial system comprises an input block and a reference value predicter. The reference value predicter includes a disturbance predicter, a state predicter, and a model parameter predicter. A model updater updates the model of the industrial system based on the predicted state and the predicted parameters. A one-prediction-step calculator of the reference value predicter calculates a prediction step based on the predicted disturbances and the model of the system. The device further includes a matrix updater and a linear solver that includes a memory structure such that each row of Jacobian and gradient matrices may be processed in parallel, a pivot search block that determines a maximum element in a column of the Jacobian and gradient matrices, and a pivot row reading block. Moreover, the device further includes a solution updater that updates the solution for an iteration step and controls the iteration process and an output block that sends a solution to the industrial system.

Methods for control of post-design free form deposition processes or joining processes are described that utilize machine learning algorithms to improve fabrication outcomes. The machine learning algorithms use real-time object property data from one or more sensors as input, and are trained using training data sets that comprise: i) past process simulation data, past process characterization data, past in-process physical inspection data, or past post-build physical inspection data, for a plurality of objects that comprise at least one object that is different from the object to be fabricated; and ii) training data generated through a repetitive process of randomly choosing values for each of one or more input process control parameters and scoring adjustments to process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments.

A method for controlling energy usage of one or more building devices associated with a building space including determining, by the one or more processing circuits based on a simulation, penalties associated with the one or more varied operating values of the one or more building devices, wherein the penalties indicate user behavior that causes energy inefficiency of the one or more building devices, and selecting, by the one or more processing circuits, one or more optimal operating values from the varied one or more operating values based on one or more future environmental conditions and a number of the penalties associated with each of the one or more varied operating values.

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.