公开(公告)号：US20210223768A1

公开(公告)日：2021-07-22

申请号：US17222243

申请日：2021-04-05

Applicant: Johnson Controls Technology Company

Inventor： Sumant S. Khalate ,  Tushar Shripad Joshi ,  Dishant Mittal

IPC: G05B23/02 ,  G06N7/00 ,  G06F17/18 ,  G06N20/00 ,  G06N5/04

Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determining the fault diagnosis associated with the predicted fault.

公开(公告)号：US20210223769A1

公开(公告)日：2021-07-22

申请号：US17222337

申请日：2021-04-05

Applicant: Johnson Controls Technology Company

Inventor： Sumant S. Khalate ,  Tushar Shripad Joshi ,  Dishant Mittal

IPC: G05B23/02 ,  G06N7/00 ,  G06F17/18 ,  G06N20/00 ,  G06N5/04

Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determining the fault diagnosis associated with the predicted fault.

公开(公告)号：US11835945B2

公开(公告)日：2023-12-05

申请号：US17222337

申请日：2021-04-05

Applicant: Johnson Controls Technology Company

Inventor： Sumant S. Khalate ,  Tushar Shripad Joshi ,  Dishant Mittal

IPC: G05B23/02 ,  G06F17/18 ,  G06N7/01 ,  G05B17/02 ,  G06N20/00 ,  G06N5/045 ,  G06N20/10 ,  G06N5/046 ,  G06N3/02

CPC classification number: G05B23/0283 ,  G05B23/0221 ,  G05B23/0229 ,  G06F17/18 ,  G06N5/045 ,  G06N7/01 ,  G06N20/00 ,  G05B17/02 ,  G05B23/024 ,  G05B2219/2642 ,  G06N3/02 ,  G06N5/046 ,  G06N20/10

Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determining the fault diagnosis associated with the predicted fault.

公开(公告)号：US10969775B2

公开(公告)日：2021-04-06

申请号：US16014556

申请日：2018-06-21

Applicant: Johnson Controls Technology Company

Inventor： Sumant S. Khalate ,  Tushar Shripad Joshi ,  Dishant Mittal

IPC: G05B23/02 ,  G06F17/18 ,  G06N20/00 ,  G05B17/02 ,  G06N7/00 ,  G06N5/04 ,  G06N20/10 ,  G06N3/02

Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determining the fault diagnosis associated with the predicted fault.

公开(公告)号：US20180373234A1

公开(公告)日：2018-12-27

申请号：US16014556

申请日：2018-06-21

Applicant: Johnson Controls Technology Company

Inventor： Sumant S. Khalate ,  Tushar Shripad Joshi ,  Dishant Mittal

IPC: G05B23/02 ,  G06F17/18 ,  G06N7/00 ,  G06N99/00

Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determining the fault diagnosis associated with the predicted fault.