A building management system is provided. The building management system includes a database, a trust region identifier configured to perform a cluster analysis technique to identify trust regions, and a regression model predictor configured to utilize a regression model technique to calculate a regression model prediction. The building management system further includes a distance metric calculator configured to calculate a distance metric, an artificial neural network model predictor configured to utilize an artificial neural network model technique to calculate an artificial neural network model prediction, and a combined prediction calculator configured to determine a combined prediction based on the distance metric, the regression model prediction, and the artificial neural network model prediction.

A hybrid machine-learning and simulation-based system provides forecasting for an energy system. The system predicts day-ahead and real-time supply and demand, and prices of energy, and generates inputs to an optimization algorithm performed by an Independent System Operator (ISO) that affects behavior of electricity generators and electricity consumers to improve the economic efficiency of electricity grids, and reduce harmful emissions.

A method for controlling a variable refrigerant flow (VRF) system includes applying a time window to sensor data associated with the VRF system, the sensor data including input data points and having a first resolution, wherein applying the time window to the sensor data isolates a subset of the input data points; applying a timing weight to one or more input data points in the subset of the input data points to generate corrected data points having a second resolution higher than the first resolution; creating a virtual sensor and mapping the corrected data points to an output of the virtual sensor; and controlling the VRF system based on an output of the virtual sensor. The use of virtual sensors with a higher resolution than corresponding physical sensors in this manner allows for existing physical sensors to be used while improving performance of the VRF system.

A control system includes an electronic control unit including a feedback controller and a reference governor. The feedback controller is configured to determine a value of control input such that a value of control output approximates a target value. The reference governor is configured to calculate, with a prediction model, a predicted maximum value of an overshoot amount of the control output that overshoots from the target value. The prediction model is derived assuming that an n-th delay (n is a natural number) occurs in a response of the control output. The reference governor is configured to calculate the target value by correcting the provisional target value of the control output based on the predicted maximum value so as to increase a degree of satisfaction of a constraint condition with regard to the control output.

A control circuitry includes a propulsor trim prediction circuitry and an output circuitry. The propulsor trim prediction circuitry is configured to generate a predicted proprotor nacelle trim value based on an aircraft velocity and a pitch attitude deviation from a reference. The output circuitry is configured to output a proprotor nacelle command based on the predicted proprotor nacelle trim value. The proprotor nacelle command is configured to cause an adjustment in a nacelle angle of a proprotor of an aircraft.

A building management system (BMS) for heating, ventilation, or air conditioning (HVAC) parameters in a building. The BMS includes one or more processing circuits including one or more memory devices coupled to one or more processors. The one or more processors query a training data storage and receive training data, institute a policy with a machine learning engine and train the policy using the training data, receive temperature, pressure, and humidity (TPH) sensor data from one or more sensors, determine a fault based on the TPH sensor data, provide the TPH sensor data and the fault to the policy of the machine learning engine and output a corrective action to resolve the fault, and generate a work order for a user based on the TPH sensor data, the determined fault and the corrective action.

A building management system for monitoring and controlling HVAC parameters in a building includes one or more processing circuits configured to initialize a predictive model for predicting temperature, pressure, and humidity within a target area and an adjacent area of the building, receive target area data from a target area sensor array configured to measure temperature, pressure, and humidity of the target area, receive adjacent area data from an adjacent area sensor array configured to measure temperature, pressure, and humidity of the adjacent area, execute the predictive model based on the target area data and the adjacent area data to generate a prediction of future temperature, pressure, and humidity within the target area, and control operation of HVAC equipment to maintain the temperature, pressure, and humidity of the target area within a compliance standard.

Centralized controllers for a photovoltaic-enabled distribution grid are described herein. Photovoltaic cells may generate electricity that may be supplied to the distribution grid, which may experience unexpected abnormal power loads. The controllers utilize photovoltaic inverters connected to the photovoltaic cells to optimize the performance of the grid by absorbing or injecting reactive power. These controllers are particularly efficient in handling unexpected abnormal power loads.

A computing system receives historical data. The historical data comprises physical actions taken in an experiment in a physical environment. The experiment comprises user-defined stages. The historical data comprises a recorded outcome, according to user-defined performance indicator(s) related to the user-defined stages, for each physical action taken in the experiment. The system generates, by a discrete event simulator, a computing representation of a simulated environment of the physical environment. The simulated environment comprises processing stages. The system obtains simulation data. The simulation data comprises simulated actions taken by the discrete event simulator. The simulation data comprises a predicted outcome, according to user-defined performance indicator(s) related to the processing stages, for each simulated action taken by the discrete event simulator. The system validates accuracy of the discrete event simulator at predicting the recorded outcome in the experiment. The system trains a computing agent according to a sequential decision-making algorithm.

A system comprises active magnetic emitters positioned within an area, passive magnetic emitters configured to be moved within the area, a magnetic field detector configured to measure a strength and direction of a magnetic field within the area, and a processor in communication with the magnetic field detector. The passive magnetic emitters are configured to be integrated in, coupled to, or secured to at least one tracked object or tracked subject within the area. The processor is configured to evaluate at least one change in the measured strength and direction of the magnetic field end send a signal to a visual effect actuator or visual effects display to initiate a visual effect based on the at least one change. A method and computer program product relating to the system is also provided.