Patent classifications
F24F2130/10
ELECTRONIC APPARATUS AND OPERATION METHOD FOR PREDICTING HVAC ENERGY CONSUMPTION USING MACHINE LEARNING
An operation method for reducing energy consumption and an electronic apparatus thereof are provided. The operation method includes obtaining, by the electronic apparatus, weather forecast information, inputting, by the electronic apparatus, the weather forecast information to an artificial intelligence model for predicting an amount of power to be consumed by a first air conditioner, and displaying, by the electronic apparatus, the predicted power consumption amount of the first air conditioner output from the artificial intelligence model, wherein the artificial intelligence model is trained to obtain correlation information between a weather condition and a power consumption amount of an air conditioner, based on a weather history and operations of a plurality of air conditioners related to the weather history, and predict the amount of power to be consumed by the first air conditioner based on the correlation information and the weather forecast information.
Predictive presence scheduling for a thermostat using machine learning
A heating, ventilation, and air conditioning (HVAC) control device configured to generate the machine learning model using the first set of weights and the second set of weights. The machine learning model is configured to output a probability that a user is present at the space based on an input that identifies a day of the week and a time of a day. The device is further configured to determine a probability that a user is present at the space for a predicted occupancy schedule using the machine learning model, to determine an occupancy status based on a determined probability that a user is present at the space, and to set a predicted occupancy status in the predicted occupancy schedule based on a determined occupancy status for each time entry. The device is further configured to output the predicted occupancy schedule.
Space conditioning based on weather information
Methods, devices, and systems for space conditioning based on weather information are described herein. One device includes a memory, and a processor to execute executable instructions stored in the memory to receive forecasted weather information, determine, based on the forecasted weather information, future weather conditions, determine based on the future weather conditions and historical setpoint data, whether conditioning of a space is expected, and generate an alert in response to conditioning of the space being expected.
METHODS OF INCREASING THE AVERAGE LIFE TIME OF BUILDING MATERIALS AS WELL AS REDUCING THE CONSUMPTION OF OTHER RESOURCES ASSOCIATED WITH OPERATING BUILDINGS
Disclosed are methods for at least approximating any one or any combination of system targets of a) reducing the average energy expenditure for keeping at least one primary compartment of a building within a desired temperature range by means of active
e air conditioning, or b) reducing temperature variations during a typical 24-hour cycle within said at least one primary compartment of said building, or c) reducing one or both of the average temperature or the peak temperature of said at least one primary compartment of said building.
The invention concerns predominantly enclosed spaces, typically buildings, which are at least exposed to directionally and temporally varying levels of solar electromagnetic radiation as well as temporally varying levels of ambient air temperature and ambient air flow velocity and direction. Such a building comprising at least one primary compartment and at least one secondary compartment, and wherein said primary compartment predominantly serves to achieve the primary purpose of the building.
The disclosed methods are furthermore at least in part based on at least one electronic controller, which is able to one or both of a) controlling means to modulate the amount of passive air flow to and from said at least one secondary compartment, and b) controlling means to modulate the amount of actively driven air flow to and from said at least one secondary compartment, and said electronic controller furthermore comprising at least one, at least partially descriptive, analytical and/or, numerical, and/or reduced order model to at least approximately compute, i.e. predict, the thermal behavior of said building, and said controller using said at least partially descriptive model to derive control signals suitable to at least approximate said at least one system target. In some embodiments the disclosed methods are at least partially incorporated in a home automation system, including optionally internet connectivity.
In some embodiments the disclosed methods are at least partially capable of increasing the typical lifetime of some components of buildings and thus reducing resources associated with maintaining at least some buildings functional.
HVAC SENSOR VALIDATION WHILE SYSTEM IS OFF
An HVAC system includes a suction-side sensor, a liquid-side sensor, an outdoor temperature sensor, and a controller. The controller determines that initial criteria are satisfied for initiating validation of the suction-side sensor and the liquid-side sensor. After determining that the initial criteria are satisfied, a suction-side property value, liquid-side property value, and outdoor temperature value are received. The controller determines whether a first validation criteria and a second validation criteria are satisfied. If both the first validation criteria and the second validation criteria are satisfied, the suction-side sensor, the liquid-side sensor, and the outdoor temperature sensor are determined to be functioning properly. Otherwise, the controller determines which one or more of the sensors are malfunctioning.
Occupancy sensing and building control using mobile devices
Apparatus, systems and methods for ascertaining the occupancy of a building are presented. The building is divided into one or more control zones which correspond to physical areas of the building associated with controllable modules, such as HVAC units, lighting, irrigation, or other environmental features such as fountains, music, video, and the like. Zone parameters define how zone devices shall react to the number of occupants located in the particular zone. A building control system detects individual mobile devices in and around the building, and determines the locations of each device by using trilateration and/or location services. The identified mobile devices act as proxies for building occupants. The locations of these devices are correlated with the locations of the zones in the building, and the building control system then adjusts the operating parameters of the zone based on the number of devices present in the zone.
Systems and methods for adaptively tuning thresholds for fault detection in buildings
A building system including one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to determine an average of a minimum half of sorted energy consumption values for a first time period and determine an average of a maximum half of sorted energy consumption values for a second time period. The instructions also cause the processor to determine a ratio of the average of the minimum half of sorted energy consumption values for the first time period to the average of the maximum half of sorted energy consumption values for the second time period, compare the calculated ratio to an adaptively tunable threshold value and activate a system responsive to the calculated ratio exceeding the adaptively tunable threshold value.
Ventilator
A ventilator (1) includes: an air supply fan (2) to supply outdoor air to a room; an air exhaust fan (3) to exhaust indoor air, out of the room; and a total heat exchanger (4) which is made with partition boards (41) being moisture-permeable flat parts and with spacer boards (42) being corrugated parts, the partition boards and the spacer boards being alternately stacked, the total heat exchanger exchanging heat between the outdoor air and the indoor air; and thereby suppresses ice formation. The ventilator (1) includes: an indoor temperature sensor (7); an indoor humidity sensor (8); an outdoor temperature sensor (6); and a control unit (5) to control operation of the air supply fan (2) and the air exhaust fan (3) on a basis of at least one state quantity estimated by substituting the indoor air temperature, the indoor air humidity, and the outdoor air temperature in a total heat exchanger model formula (51a) representing characteristics of the total heat exchanger (4).
Demand control ventilation with predictive humidity control
Systems, apparatus and methods for operating an environmental control system that delivers dehumidified outdoor air into a conditioned space through an air valve. The method includes establishing CO.sub.2 setpoints corresponding to a ventilation outdoor air flow rate and a dehumidification outdoor air flow rate, determining a humidity metric of the conditioned space, and delivering outside air to the conditioned space at the ventilation outdoor air flow rate or dehumidification outdoor air flow rate based upon the humidity metric. The outside air may be tempered with return air from the conditioned space. The dehumidification CO.sub.2 set point is determined by predicting the dehumidification CO.sub.2 set point based on the airflow quantity per occupant and the relationship of the occupant predicted water vapor emission rate and CO.sub.2 emission rate.
ENERGY MANAGEMENT AND SMART THERMOSTAT LEARNING METHODS AND CONTROL SYSTEMS
A method of HVAC system performance monitoring using a computing device connected to at least one thermostat of an HVAC system in a building includes receiving thermostat data from the thermostat, the thermostat data including temperature setpoint data, measured building temperature data, and HVAC operation data for a time period. Weather data is received from a weather service for the time period, and the thermostat data is synchronized with the weather data with respect to time. At least one machine learning model is trained using the synchronized thermostat and weather data, and performance of the HVAC system over time is monitored using the trained machine learning model.