In accordance with a program, a processor obtains a plurality of manufacturing parameters and a measured value of an at least one property of an alloy material, calculates a pre-predicted value based on a first manufacturing parameter included in the plurality of manufacturing parameters using a prediction expression describing a relationship between the first manufacturing parameter, and a pre-predicted value of the property representing a roughly calculated value of a target predicted value that is a target value of the property, calculates a difference between the pre-predicted value and a measured value of the property, and trains a model using a training data set including a second manufacturing parameter and the difference, to generate a trained model that is used to predict the at least one property.

An indoor air quality control system may be implemented to control a plurality of air handling units within an industrial facility in a concerted effort to effect an overall air quality goal. A remote server analyzes sensor data, historical data, and other environmental data (e.g., predicted weather data), and uses one or more machine learning algorithms to model the behavior of air within the facility. The sensed air quality data is considered holistically to understand the overall condition of the facility and the gradient of air flows and/or contaminant flows within the 3-dimensional space. Air handling models are applied to current sensor data to generate instructions to selectively turn on/off or otherwise control components of various air handling equipment to reach an optimized air quality result. Decisions on how to control the facility are based on environmental health and safety considerations.

A system control method includes receiving a control task and randomly selecting a chromosome from an evolution pool according to the control task. The selected chromosome is decoded to obtain (N+1) ensemble policies, where the chromosome includes (N+1) gene fragments, and where N is a positive integer greater than or equal to 1. Each gene fragment can uniquely correspond to an ensemble policy, and each ensemble policy can uniquely correspond to a preset function. One ensemble policy is used for assigning a weight to a preset function that uniquely corresponds to the ensemble policy. The evolution pool can maintain two or more chromosomes. An ensemble calculation is performed according to weights assigned by the (N+1) ensemble policies to obtain an ensemble control output. A control signal is generated according to the ensemble control output, where the control signal is used for performing system control.

A building control system includes one or more processors and one or more non-transitory computer-readable media storing instructions. When executed by the one or more processors, the instructions cause the one or more processors to perform operations including using an artificial intelligence model to adjust a threshold value of a constraint based on user input provided via one or more user devices during a first time period. The user input indicates user satisfaction with an environmental condition of a building space during the first time period. The operations include using the threshold value of the constraint to operate equipment that affect the environmental condition of the building space during a second time period subsequent to the first time period.

Smart electricity monitors with unique identities placed at individual power outlets within a building communicate frequent power measurements to a service which determines, from this power usage data, which outlets are associated with occupied seats within the building. This occupancy information can be used to update an occupancy model for the building that is used to forecast the building's occupancy. Based on present occupancy, projected occupancy, and other data, in some instances, the building's thermostats can be controlled and unoccupied seats can be assigned dynamically.

A method for controlling a direct contact membrane distillation (DCMD) system, the method including modeling the DCMD system with differential-algebraic equations (DAEs), wherein the DAEs include process states {tilde over (x)}(t.sub.k) and an input state u(t.sub.k); selecting a value for the input variable u(t.sub.k) for a time t.sub.k; estimating the process states {tilde over (x)}(t.sub.k) based on the DAEs and the input state u(t.sub.k); checking that a boundedness function G applied to the process states {tilde over (x)}(t.sub.k) is smaller than a desired steady-state point ρ.sub.e; and minimizing an objective function, which depends on the process states {tilde over (x)}(t.sub.k) and the input state u(t.sub.k), to determine an updated input state u(t.sub.k+1) for a next time t.sub.k+1. The process states {tilde over (x)}(t.sub.k) include temperatures and heat flow rates.

Apparatuses, systems, and methods of physical-model based building automation using in-situ regression to optimize control systems are presented. A simulation engine is configured to simulate a behavior or a controlled system using a physical model for the controlled system. A data stream comprises data from a controlled system. A training loop is configured to compare an output of a simulation engine to a data stream using a heuristic so that a physical model is regressed in a manner that the output of the simulation engine approaches the data stream.

A method is for producing, for a hydraulic machine having an actuator, a setpoint-value trajectory satisfying predefined limitations in order to influence an output variable of the hydraulic machine. A trajectory of unlimited setpoint values is fed to a trajectory planning function, which produces the setpoint-value trajectory from the trajectory of unlimited setpoint values. In the trajectory planning function, the trajectory of unlimited setpoint values is differentiated at least twice in order to obtain a trajectory of unlimited setpoint values that is differentiated n times. In the trajectory planning function, at least one limitation is applied to the differentiated trajectory of unlimited setpoint values in order to obtain a differentiated trajectory of limited setpoint values. The differentiated trajectory of limited setpoint values is fed to a filter integrator chain in order to obtain the setpoint-value trajectory.

The present invention relates to a method for controlling power ramps with prediction in intermittent power generation plants, such as, for example, a photovoltaic solar plant, which minimizes the storage capacity required for compliance with the maximum ramp requirements for power fluctuation as well as the cycling of said storage systems, thus extending its lifespan and also reducing associated energy losses, thus reducing investment costs in the plant, such that, in order to achieve the same maximum fluctuation ramp, a minor use is made of the energy storage system.

A method for reducing and/or managing energy-related stress in an electrical system includes processing electrical measurement data from or derived from energy-related signals captured by at least one intelligent electronic device (IED) in the electrical system to identify and track at least one energy-related transient in the electrical system. An impact of the at least one energy-related transient on equipment in the electrical system is quantified, and one or more transient-related alarms are generated in response to the impact of the at least one energy-related transient being near, within or above a predetermined range of the stress tolerance of the equipment. The transient-related alarms are prioritized based in part on at least one of the stress tolerance of the equipment, the stress associated with one or more transient events, and accumulated energy-related stress on the equipment. One or more actions are taken in the electrical system in response to the transient-related alarms to reduce energy-related stress on the equipment in the electrical system.