公开(公告)号：US20230177422A1

公开(公告)日：2023-06-08

申请号：US17541119

申请日：2021-12-02

Applicant: Johnson Controls Tyco IP Holdings LLP

Inventor： Jonathan D. Douglas ,  Kirk H. Drees ,  Tyler A. Smith

IPC: G06Q10/06 ,  G06Q10/10 ,  G16H50/80 ,  G06Q50/20

CPC classification number: G06Q10/06312 ,  G06Q10/1095 ,  G06Q50/20 ,  G16H50/80

Abstract: A building system for a school building, the building system including one or more memory devices storing instructions thereon that, when executed by the one or more processors, cause the one or more processors to receive attendance data indicating whether occupants of the school building are present or absent from the school building, determine, based on the attendance data, an infection risk level of at least one of the school building, a space of the school building, or one or more of the occupants to being infected with an infectious disease present in a population, and perform one or more operations for causing the infection risk level to be reduced in the school building.

公开(公告)号：US20230139152A1

公开(公告)日：2023-05-04

申请号：US17972454

申请日：2022-10-24

Applicant: Johnson Controls Tyco IP Holdings LLP

Inventor： Tyler A. Smith ,  Jonathan D. Douglas ,  Kirk H. Drees ,  Neuman Leverett ,  Brian Estill

IPC: F24F11/49 ,  F24F11/56

Abstract: A system can operate to receive building data for a plurality of buildings from one or more data sources. At least one building of the buildings can include building equipment. The system can operate to generate scores based on the building data for the buildings, the scores can indicate a level of potential building improvements for the buildings. The system can operate to select the building of the buildings based at least in part on the scores. The system can operate to perform an operation based at least in part on the score to generate data to improve control of the environmental condition of the building.

公开(公告)号：US11573540B2

公开(公告)日：2023-02-07

申请号：US16725999

申请日：2019-12-23

Applicant: Johnson Controls Tyco IP Holdings LLP

Inventor： Young M. Lee ,  Zhanhong Jiang ,  Viswanath Ramamurti ,  Sugumar Murugesan ,  Kirk H. Drees ,  Michael James Risbeck

IPC: G05B13/02 ,  G06N3/08 ,  G06N3/04 ,  F24F11/30 ,  G05B13/04 ,  F24F11/63

Abstract: Systems and methods for training a reinforcement learning (RL) model for HVAC control are disclosed herein. A calibrated simulation model is used to train a surrogate model of the HVAC system operating within a building. The surrogate model is used to generate simulated experience data for the HVAC system. The simulated experience data can be used to train a reinforcement learning (RL) model of the HVAC system. The RL model is used to control the HVAC system based on the current state of the system and the best predicted action to perform in the current state. The HVAC system generates real experience data based on the actual operation of the HVAC system within the building. The real experience data is used to retrain the surrogate model, and additional simulated experience data is generated using the surrogate model. The RL model can be retrained using the additional simulated experience data.

公开(公告)号：US20230034809A1

公开(公告)日：2023-02-02

申请号：US17965345

申请日：2022-10-13

Applicant: Johnson Controls Tyco IP Holdings LLP

Inventor： Young M. Lee ,  Zhanhong Jiang ,  Viswanath Ramamurti ,  Sugumar Murugesan ,  Kirk H. Drees ,  Michael James Risbeck

IPC: F24F11/64 ,  F24F11/47 ,  G05B13/04 ,  G05B13/02

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.

公开(公告)号：US11525596B2

公开(公告)日：2022-12-13

申请号：US16725961

申请日：2019-12-23

Applicant: Johnson Controls Tyco IP Holdings LLP

Inventor： Young M. Lee ,  Zhanhong Jiang ,  Viswanath Ramamurti ,  Sugumar Murugesan ,  Kirk H. Drees ,  Michael James Risbeck

IPC: G05B13/04 ,  G05B13/02 ,  F24F11/64 ,  F24F11/47

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.

公开(公告)号：US20220113045A1

公开(公告)日：2022-04-14

申请号：US17558909

申请日：2021-12-22

Applicant: Johnson Controls Tyco IP Holdings LLP

Inventor： Timothy C. Gamroth ,  Michael J. Wenzel ,  Mohammad N. ElBsat ,  David S. Eidson ,  James Burke ,  Kirk H. Drees ,  Thomas M. Seneczko

IPC: F24F11/00 ,  F24F11/64 ,  F24F11/46 ,  F24F11/72 ,  F24F8/10 ,  F24F3/14 ,  G16H40/20 ,  G16H50/30 ,  G05B19/042 ,  F24F11/39 ,  F24F11/61 ,  G05B13/04

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.

公开(公告)号：US20220011731A1

公开(公告)日：2022-01-13

申请号：US17483078

申请日：2021-09-23

Applicant: Johnson Controls Tyco IP Holdings LLP

Inventor： Michael J. Risbeck ,  Kirk H. Drees ,  Jonathan D. Douglas

IPC: G05B19/042 ,  F24F11/70 ,  F24F11/47 ,  F24F11/64 ,  F24F11/52 ,  F24F8/10

Abstract: A controller for heating, ventilation, or air conditioning (HVAC) equipment that is operable to affect an environmental condition of a building is configured to obtain predictive models that predict values of a carbon emissions control objective and another control objective as a function of control decision variables for the HVAC equipment. The controller executes an optimization process using the predictive models to produce sets of optimization results corresponding to different values of the control decision variables, the carbon emissions control objective, and the other control objective. The controller selects from the sets of optimization results based on the values of the carbon emissions control objective and the other control objective. The controller operates the HVAC equipment to affect the environmental condition of the building in accordance with the values of the control decision variables corresponding to a selected set of the optimization results.

公开(公告)号：US20210364181A1

公开(公告)日：2021-11-25

申请号：US17393138

申请日：2021-08-03

Applicant: Johnson Controls Tyco IP Holdings LLP

Inventor： Michael J. Risbeck ,  Kirk H. Drees ,  Jonathan D. Douglas

IPC: F24F11/47 ,  F24F11/52 ,  F24F11/64 ,  F24F8/10

Abstract: A heating, ventilation, or air conditioning system (HVAC) design and operational tool includes one or more processors and memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations including obtaining a dynamic temperature model and a dynamic infectious quanta model for one or more building zones, determining an infection probability, and performing a plurality of simulations for a plurality of different equipment configurations using the dynamic temperature model, the dynamic infectious quanta model, and the infection probability to generate results. The operations include generating, using the results of the plurality of simulations, at least one of design including one or more recommended design parameters data or operational data including one or more recommended operational parameters for the HVAC system and initiating an automated action using at least one of the design data or the operational data.