Exxonmobil Research and Engineering Company

Exxonmobil Technology and Engineering Company

Mobil Oil Corporation

Apostolos T Georgiou

Jitendra V Kadam

Onur Onel

Frederick J Krambeck

Helen S Wellons

Michael G Tribo

Kiran R Sheth

Christopher W Graham

J Douglas Kushnerick

Benjamin J Ohran

Constantinos Bokis

Yunfei Chu

Howard D Franklin

Weimen Li

Joshua L Pulsipher

Peter J Hanratty

Tu Ching Cheng

Tyler A Soderstrom

Howard Franklin

Methods and systems for performing transient processes may include: providing a path and path thresholds for an operational condition as a function of progress of a transient process based on historical data of previously performed transient processes; performing the transient process in a chemical reactor using operational parameters; measuring the operational condition of the transient process as a function of the progress of the transient process; and adjusting one or more of the operational parameters during the progress of the transient process to maintain the operational condition within the path thresholds.

Methods and systems for performing transient processes

A method of monitoring and controlling an industrial process includes capturing images of a non-sensible process condition of the industrial process with an image capture device, receiving the images of the non-sensible process condition with a computer system, and converting each image into a corresponding numeric value with a machine learning model stored in and operable by the computer system. The corresponding numeric value is then received and compared to a predetermined numeric value for the non-sensible process condition with a closed-loop controller, and an actuator operates with the closed-loop controller to adjust operation of the industrial process when the corresponding numeric value fails to match the predetermined numeric value or is outside of a defined threshold near the predetermined numeric value.

Systems and methods of monitoring and controlling an industrial process

Systems and methods for optimizing a system operating in a first mode of operation include detecting an event associated with a cycle in a first mode of operation. When the cycle ends (i.e., when another event is detected), steady state criteria is applied to determine whether data associated with the cycle satisfies the steady state criteria. Optimization targets can be calculated based on the data associated with the cycle. Control signals including the optimization targets can be applied to a next cycle operating in the first mode of operation to improve process performance.

Real time optimization of batch processes

The invention provides a method and means of predicting, in near real-time, the detailed chemical composition of major streams in a refinery, including those downstream from the crude distillation column. The dynamically updated feed characterizations can be derived in near real time from an assay database of current crude diet, RTO information about upstream refinery units and various analyzer inputs. The chemical compositions of each stream are stored and updated in a plant wide database. A broad range of property calculations can be ascertained, either automatically or on demand, from the compositional information. An application permits users, such as operations, planning and engineering personnel, to access the database directly or indirectly (e.g., on line). This information is then used by each user to further optimize the operation of a given refinery unit and/or the plant as a whole.

Prediction of stream composition and properties in near real time

A component mapper is provided in connection with a process wherein a fluid stream having multiple physical components is modeled as a plurality of pseudo-components. Each physical component has a boiling point, and each pseudo-component has a pre-defined boiling point and includes all physical components from the fluid stream having approximately the pre-defined boiling point. Each pseudo-component in the model of the fluid stream has a varying pre-defined property and a varying amount. A plurality of sub-pseudo-components are defined for each pseudo-component such that the pseudo-component is replaceable therewith. Each sub-pseudo component has the pre-defined boiling point of the pseudo-component, a pre-defined value for the pre-defined property, and a varying amount. For each pseudo-component, a current value of the pre-defined property and a current amount of the pseudo-component are obtained, and a current amount for each sub-pseudo-component of the pseudo-component is then calculated. The pre-defined value of the pre-defined property and the calculated current amount for each sub-pseudo-component of each pseudo-component are then utilized in a real-time optimization process. In one embodiment of the present invention, the pre-defined property is density, and the amount is percentage weight and percentage volume.

Component mapper for use in connection with real-time optimization process

Growing community of inventors

Reston, VA, United States of America

Apostolos T Georgiou