Abstract: Computer-implemented methods and structures deploy a heating ventilation and air conditioning (HVAC) energy optimization program. A standard operating control platform (OCP) is deployed in an energy optimization control engine (EOCE) computing system communicatively coupled to a plurality of HVAC components via a building automation system (BAS). An energy optimization portal (EOP), which receives from the EOCE computing system a first data set identifying the plurality of HVAC components, a second data set including operational control parameters for each of the plurality of HVAC components, and a third data set including measured operations data associated with each of the plurality of HVAC components. The EOP generates an energy optimized operating control platform based on the first, second, and third data sets, which is automatically communicated from the EOP to the EOCE computing system.

Abstract: A controller for controlling an energy discharge from an energy saving device to a power grid. The system includes decision logic to implement a local response responsive to events currently occurring in a power grid and in addition remote commands sent from a remote location.

Abstract: An energy management system is configured to calculate a percentage of satisfied based on the report data for each of the plurality of buildings; create, for each of the plurality of buildings, a plan for operating each of the air-conditioning facilities based on the percentage of satisfied and a predetermined target percentage of satisfied; calculate a first energy consumption amount based on the first piece of data; calculate a second energy consumption amount based on the second piece of data, the third piece of data, and the fourth piece of data, the second energy consumption amount being obtained when the each of the air-conditioning facilities is operated after a lapse of a predetermined time period; and control, when the first energy consumption amount is larger than the second energy consumption amount, the operation of the each of the air-conditioning facilities so as to achieve the second energy consumption amount.

Abstract: A building management system (BMS) for filtering a fluid within a building is shown. The system includes one or more sensors configured to measure one or more characteristics of a first fluid within an air duct of the BMS and measure one or more characteristics of a second fluid after the second fluid has been filtered. The system further includes a pollutant management system configured to receive data from the one or more sensors and control a filtration process. The filtration process selects a filter of a plurality of filters based on at least one of a level of the one or more characteristics of the first fluid or the one or more characteristics of the second fluid.

Abstract: A device such as a smart thermostat is provided for controlling heating and cooling systems. The device is operable to execute an energy control program to control the heating and a cooling systems based upon different control strategies: a first control strategy that compares the at least one temperature setpoint in the programming schedule to the current measured dry bulb temperature to determine whether to engage or disengage the heating and a cooling systems, and a second control strategy that compares the at least one temperature setpoint in the programming schedule to a normalized humidex temperature to determine whether to engage or disengage the heating and a cooling systems, the normalized humidex temperature being the current measured dry bulb temperature modified by historical humidity values to provide an indicator of thermal comfort within the premise.

Abstract: Systems and methods for training a reinforcement learning (RL) model for HVAC control are disclosed herein. Simulated experience data for the HVAC system is generated or received. The simulated experience data is used to initially train the RL model for HVAC control. The HVAC system operates within a building using the RL model and generates real experience data. A determination may be made to retrain the RL model. The real experience data is used to retrain the RL model. In some embodiments, both the simulated and real experience data are used to retrain the RL model. Experience data may be sampled according to various sampling functions. The RL model may be retrained multiple times over time. The RL model may be retrained less frequently over time as more real experience data is used to train the RL model.

Abstract: An occupancy tracking device configured to identify devices connected to an access point over a predetermined time period. The device is further configured to populate entries in a device log for the identified devices. The device is further configured to determine a predicted occupancy level and to control a Heating, Ventilation, and Air Conditioning (HVAC) system based on the predicted occupancy level.

Abstract: A state determination device acquires data on an industrial machine, extracts data used for processing related to machine learning from the acquired data, out of the acquired data, according to an extraction condition for extracting the data, and executes the processing related to the machine learning using the extracted data.

Abstract: There is provided a substrate processing system, including: a plurality of substrate processing apparatuses; a first control part installed in each of the plurality of substrate processing apparatuses and configured to transmit a first apparatus data from each of the plurality of substrate processing apparatuses; a second control part configured to receive the first apparatus data from each of the plurality of substrate processing apparatuses, generate a priority data of each of the plurality of substrate processing apparatuses based on the first apparatus data, and transmit the priority data to the first control part; and a display part configured to display the priority data thereon.

Abstract: A thermal state of a plurality of zones of the building is updated according to a building thermal model and information received from temperature sensors of the building. Predicted occupant counts for an upcoming plurality of time slots for each of the plurality of zones are updated using actual occupancy counts for each of the plurality of zones. A misprediction type distribution for the upcoming plurality of time slots for each of the plurality of zones is updated, the misprediction type distribution indicating misprediction for true negatives, false positives, false negatives, and true positives. A total misprediction cost expectation is updated according to the predicted occupant counts and the misprediction type distribution. HVAC power for each of the plurality of zones is determined to optimize occupant thermal comfort weighted according to the predicted occupant counts while minimizing the total misprediction cost expectation. HVAC operation is controlled per the HVAC power.

Abstract: Mold lock is remediated by performing a layer-by-layer, two-dimensional analysis to identify unconstrained removal paths for any support structure or material within each two-dimensional layer, and then ensuring that aligned draw paths are present for all adjacent layers, all as more specifically described herein. Where locking conditions are identified, a sequence of modification rules are then applied, such as by breaking support structures into multiple, independently removable pieces. By addressing mold lock as a series of interrelated two-dimensional geometric problems, and reserving three-dimensional remediation strategies for more challenging, complex mold lock conditions, substantial advantages can accrue in terms of computational speed and efficiency.

Abstract: Methods and apparatus to adjust operation of a fluid flow control assembly are disclosed. An example safety valve controller apparatus includes comparator circuitry to compare a current measurement to at least one of a first threshold associated with a first flow setting of a fluid flow control assembly or a second threshold associated with a second flow setting of the fluid flow control assembly, and determine a first drive signal associated with the first flow setting or a second drive signal associated with the second flow setting in response to satisfying a respective one of the first or second thresholds, and current modulating circuitry to determine a third drive signal based on the current measurement, the third drive signal to modulate the flow setting of the fluid flow control assembly between the first and second flow settings.

Abstract: Some implementations provides a system to implement a safety control at an oil and gas facility, the system comprising: one or more motor control centers, each comprising a network interface, and a programmable logic controller (PLC), wherein each motor control center is configured to monitor and control one or more field devices coupled thereto, and wherein a plurality of field devices are dispersed at the oil and gas facility; and a safety instrumented system (SIS) in communication with the one or more motor control centers through the network interface thereof, wherein each motor control center is configured to communicate with the SIS without an interposing relay, and wherein the SIS comprises control elements configured to implement the safety control at the oil and gas facility based on communication with each motor control center through the network interface thereof.

Abstract: A method of controlling a gas furnace system includes determining a first pressure in a conduit coupled to a draft inducer from signals output by a pressure transducer positioned to sense a pressure within the conduit with a motor of the draft inducer in a stopped condition. A first status of the pressure transducer is determined based at least in part on the first pressure. The motor of the draft inducer is controlled to increase a speed of the motor from the stopped condition in response to a call for heat when the first status does not indicate that the pressure transducer is unreliable, and the motor is maintained in a stopped condition when the first status indicates that the pressure transducer is unreliable.

Abstract: An information processing apparatus incudes a schedule determination unit configured to determine a schedule of an operating status for causing a temperature of an air-conditioned space of each of a plurality of load-side units to reach a specified set temperature at a specified set time, based on a learning model representing an input-output relationship between input data indicating an influencing factor of a thermal load of each of the load-side units and output data indicating the thermal load.

Abstract: An occupancy tracking device configured to identify devices connected to an access point over a predetermined time period. The device is further configured to populate entries in a device log for the identified devices. The device is further configured to determine a presence value for each device that indicates an amount of time that a device was present during the predetermined time period. The device is further configured to identify entries that are associated with a presence value that is less than a presence threshold value and to associate the entries with a user device classification. The device is further configured to identify clusters for the entries that are associated with a user device classification, to determine a predicted occupancy level based on the number of clusters that are identified, and to control a Heating, Ventilation, and Air Conditioning (HVAC) system based on the predicted occupancy level.

Abstract: Systems and methods for training a reinforcement learning (RL) model for HVAC control are disclosed herein. Simulated experience data for the HVAC system is generated or received. The simulated experience data is used to initially train the RL model for HVAC control. The HVAC system operates within a building using the RL model and generates real experience data. A determination may be made to retrain the RL model. The real experience data is used to retrain the RL model. In some embodiments, both the simulated and real experience data are used to retrain the RL model. Experience data may be sampled according to various sampling functions. The RL model may be retrained multiple times over time. The RL model may be retrained less frequently over time as more real experience data is used to train the RL model.

Abstract: A method for visualizing process data in which a process control system controls and monitors an industrial technology plant, wherein the process control system automatically triggers a process alarm if the process data fulfills a trigger condition such a corresponding alarm message is transferred to an alarm system for output to an operator, triggered process data alarms are archived as a history, such that by selecting a process data item and specify a display period by the operator the alarm system simultaneously requests the history of the selected process data item process alarms assigned to a process object for the display period, where the alarm system outputs a time sequence of the process data item as a graphic and presents process data points in the graphic in an encoding that specifies for each process data point the highest priority with which process alarms have occurred during the acquisition period.

Abstract: A system includes a controller with processors configured to execute an auto-correlation module embodied in one or more sets of program instructions stored in memory. The auto-correlation module is configured to cause the processors to receive one or more patterned wafer geometry metrics, receive wafer characterization data from one or more characterization tools, determine a correlation between the one or more patterned wafer geometry metrics and the wafer characterization data, generate a ranking of the one or more patterned wafer geometry metrics based on the determined correlation, construct a composite metric model from a subset of the one or more patterned wafer geometry metrics based on the ranking of the one or more patterned wafer geometry metrics, generate one or more composite wafer metrics from the composite metric model, and generate a statistical process control output based on the one or more composite wafer metrics.

Abstract: A building control system has a controller including a processing circuit configured to transition between multiple discrete operating states by executing state transitions, generate an adaptive user interface including a representation of the multiple discrete operating states and the state transitions therebetween, and automatically learn one or more learned behaviors or preferences of the user. The processing circuit is also configured to retrieve, from a descriptive text database, a description of a selected operating state or selected state transition based on the one or more learned behaviors or preferences of the user, the descriptive text database storing multiple different descriptions of the selected operating state or selected state transition, and update the adaptive user interface to provide the description of the selected operating state or selected state transition retrieved from the descriptive text database based on the one or more learned behaviors or preferences of the user.