Buckman Laboratories International, Inc.

Narasimha M Rao

John Carter

Arun Kumar Raju Ganesan

Ryan Carli

Steven R Hatch

William A Von Drasek

A system and method is provided for correction of sensors in an industrial process. A first sensor provides first data corresponding to measured variables for at least one respective process component, which are further aggregated in data storage with corresponding contextual tags comprising time series identifiers. For a given sample from the industrial process, at least the first data having a corresponding time series identifier are obtained for comparison with second data collected via a second sensor and which comprises measured variables corresponding to the at least one respective process component from the given sample. A feedback signal is selectively generated based on a determined error between the collected first data and the collected second data corresponding to the given sample, and may in an embodiment be used for automatically calibrating the first sensor. The feedback signal may further or alternatively be used to prompt interventions in the first sensor.

System and method for retroactive and automated validation or corrective action with respect to online sensors

Systems and methods are disclosed herein for contextual data analysis and proactive intervention in industrial plant processes. Each of multiple data streams in an industrial plant are mapped to a common hierarchical data structure, wherein the data streams correspond to respective values or states associated with unit operations, assets, and process streams in the plant. The mapped data streams define hierarchical process relationships between subsets of the unit operations, assets, and process streams. Real-time data is collected to populate at least one level of the hierarchical data structure for certain data streams, wherein future outcomes are predicted for downstream operations based on the collected real-time data for at least one data stream, and at least one other data stream having a defined hierarchical process relationship therewith. Upon ascertaining that predicted future outcomes correspond to issues requiring intervention, output signals are generated based thereon for operator alerts and/or automated control.

Growing community of inventors

Collierville, TN, United States of America

Narasimha M Rao