PREDICTIVE TEMPERATURE SCHEDULING FOR A THERMOSTAT USING MACHINE LEARNING

    公开(公告)号:US20220214064A1

    公开(公告)日:2022-07-07

    申请号:US17655956

    申请日:2022-03-22

    摘要: A heating, ventilation, and air conditioning (HVAC) control device configured to receive a user input for controlling an HVAC system, to determine whether the user input indicates an energy saving occupancy setting, and to identify a first plurality of time entries that are associated with a confidence level for a predicted occupancy status that is less than a predetermined threshold value in the predicted occupancy schedule. The device is further configured to modify the predicted occupancy schedule by setting the first plurality of time entries to an away status when the user input indicates an aggressive energy saving occupancy setting. The device is further configured to modify the predicted occupancy schedule by setting the second plurality of time entries to a present status when the user input indicates a conservative energy saving occupancy setting. The device is further configured to output the modified predicted occupancy schedule.

    Diagnostics of indoor unit of HVAC system based on sound signatures

    公开(公告)号:US20240344728A1

    公开(公告)日:2024-10-17

    申请号:US18299302

    申请日:2023-04-12

    摘要: A method for heating, ventilation, and air conditioning (HVAC) system diagnostics includes sending a first instruction to a thermostat to shut down an HVAC system. A user is instructed to minimize background noise. A second instruction is sent to the thermostat to turn on the HVAC system. A third instruction is sent to the thermostat to set a temperature setpoint below or above a value of a room temperature. Indoor unit sound data is captured for a second time period. The baseline sound data is subtracted from the indoor unit sound data to determine normalized indoor unit sound data. Expected sound signatures of the indoor unit are identified. The normalized indoor unit sound data is compared to the expected sound signatures. In response to determining that an expected sound signature for a blower is missing from the normalized indoor unit sound data, it is determined that the blower has failed.

    Diagnostics of HVAC system based on visual and sound signatures

    公开(公告)号:US20240344727A1

    公开(公告)日:2024-10-17

    申请号:US18299257

    申请日:2023-04-12

    IPC分类号: F24F11/38 F24F11/39 F24F11/67

    摘要: A method for heating, ventilation, and air conditioning (HVAC) system diagnostics includes, in response to determining that a triggering event has occurred, entering a filter diagnostics mode. A first instruction is sent to a thermostat to shut down an HVAC system. A user is instructed to locate and remove a filter. The filter is classified as acceptable or dirty. In response to classifying the filter as acceptable, the user is instructed to the turn on the HVAC system. In response to determining based on the triggering event that a desired mode is a cooling mode, a first value of a room temperature is determined. The user is instructed to set a temperature setpoint below the first value. A second value of the room temperature is determined. In response to determining that the second value is less than the first value, it is determined that the HVAC system operates properly.

    PREDICTIVE TEMPERATURE SCHEDULING FOR A THERMOSTAT USING MACHINE LEARNING

    公开(公告)号:US20220214065A1

    公开(公告)日:2022-07-07

    申请号:US17655960

    申请日:2022-03-22

    摘要: A heating, ventilation, and air conditioning (HVAC) control device configured to receive a user input for controlling an HVAC system, to determine whether the user input indicates an energy saving occupancy setting, and to identify a first plurality of time entries that are associated with a confidence level for a predicted occupancy status that is less than a predetermined threshold value in the predicted occupancy schedule. The device is further configured to modify the predicted occupancy schedule by setting the first plurality of time entries to an away status when the user input indicates an aggressive energy saving occupancy setting. The device is further configured to modify the predicted occupancy schedule by setting the second plurality of time entries to a present status when the user input indicates a conservative energy saving occupancy setting. The device is further configured to output the modified predicted occupancy schedule.

    PREDICTIVE PRESENCE SCHEDULING FOR A THERMOSTAT USING MACHINE LEARNING

    公开(公告)号:US20210199327A1

    公开(公告)日:2021-07-01

    申请号:US16731974

    申请日:2019-12-31

    摘要: 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.

    Diagnostics of outdoor unit of HVAC system based on sound signatures

    公开(公告)号:US20240344729A1

    公开(公告)日:2024-10-17

    申请号:US18299482

    申请日:2023-04-12

    IPC分类号: F24F11/38 F24F11/52

    摘要: A method for heating, ventilation, and air conditioning (HVAC) system diagnostics includes sending a first instruction to a thermostat to shut down an HVAC system. A user is instructed to minimize background noise. A second instruction is sent to the thermostat to turn on the HVAC system. A third instruction is sent to the thermostat to set a temperature setpoint below or above a value of a room temperature. Outdoor unit sound data is captured for a second time period. The baseline sound data is subtracted from the outdoor unit sound data to determine normalized outdoor unit sound data. Expected sound signatures of the outdoor unit are identified. The normalized outdoor unit sound data is compared to the expected sound signatures. In response to determining that an expected sound signature for a compressor is missing from the normalized outdoor unit sound data, it is determined that the compressor has failed.