-
公开(公告)号：US20230147522A1
公开(公告)日：2023-05-11
申请号：US17454590
申请日：2021-11-11
CPC分类号： G05B13/0265 , G06T7/0004 , G06T7/10 , F01K1/16 , F01K1/20
摘要： A method may include obtaining, from a camera device, thermal image data for a steam area of a plant facility. The steam area may include a steam trap for a steam network. The method may further include obtaining plant steam data regarding the steam trap. The method may further include determining pixel data regarding the steam trap using the thermal image data and an image segmentation process. The method further includes determining various temperature values across the steam trap using the pixel data. The method may further include determining predicted steam trap data using the temperature values, the plant steam data, and a machine-learning model. The method may further include transmitting a command that adjusts one or more parameters of the steam network based on the predicted steam trap data.
-
公开(公告)号：US20230080357A1
公开(公告)日：2023-03-16
申请号：US17477076
申请日：2021-09-16
IPC分类号： G05B19/418
摘要： A method may include obtaining acquired process data regarding a plant process that is performed by a plant system. The method may further include obtaining from a process model, simulated process data regarding the plant process. The method may further include determining drift data for the process model based on a difference between the acquired process data and the simulated process data. The drift data may correspond to an amount of model drift associated with the process model. The method may further include determining whether the drift data satisfies a predetermined criterion. The method further includes determining, in response to determining that the drift data fails to satisfy the predetermined criterion, a model update for the process model.
-
公开(公告)号：US20240242113A1
公开(公告)日：2024-07-18
申请号：US18154674
申请日：2023-01-13
摘要： Systems and a method are disclosed. The method includes collecting observed input data and observed output data from a data-generating system; determining reduced order observed output data; simulating reduced order simulated output data; performing a quality check; splitting the observed input data into a first observed input data group and a second observed input data group; training a first machine learning model; generating inferred input data with the first machine learning model; training a second machine learning model with the observed input data, the inferred input data, and the observed output data; and generating inferred output data with the second machine learning model. The method further includes adding noise to the inferred input data and the inferred output data to create synthetic input data and synthetic output data; and designing soft sensors based on the synthetic input data and the synthetic output data for deployment in an operational plant.
-
-
搜索结果
3 条记录 (耗时 0.012 秒)
