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 t
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.
대표청구항▼
1. A method for optimizing a batch process system operating in at least one mode of operation, wherein the batch process system having successive cycles of operation in the at least one mode of operation, the method comprising: detecting an event associated with a cycle of operation of the batch pro
1. A method for optimizing a batch process system operating in at least one mode of operation, wherein the batch process system having successive cycles of operation in the at least one mode of operation, the method comprising: detecting an event associated with a cycle of operation of the batch process system operating in a first mode of operation by obtaining data associated with current operation of the batch process system;determining, using one or more processors, whether the obtained data associated with the cycle of operation satisfies steady state criteria,wherein determining whether the data associated with the cycle satisfies the steady state criteria comprises: selecting an offset, the offset is a transient period in which no data is recorded, obtaining data following the offset, and determining whether the data following the offset from the event satisfies the steady state criteria,wherein determining whether the data following the offset from the event satisfies the steady state criteria comprises: separating the cycle into a first cycle portion and a second cycle portion, averaging a first set of data associated with the first cycle portion, averaging a second set of data associated with the second cycle portion, and determining whether the average of the first set of data and the average of the second set of data are within a predetermined tolerance of an overall average, wherein the overall average is the average of all data including the first set of data and the second set of data;generating, using one or more processors, optimization targets for the first mode of operation based on the obtained data; andapplying control signals comprising the optimization targets, using one or more processors, for a subsequent cycle of operation of the batch process system, when the batch process system is operating in the first mode of operation during a subsequent cycle of operation. 2. The method of claim 1, wherein the event comprises a drum change event, wherein the drum change event includes switching operation from one drum to another drum. 3. The method of claim 1, wherein the event comprises an online spalling transition event. 4. The method of claim 1, wherein the offset is selected based on a time period of transient behavior in previous cycles operating in the first mode of operation. 5. The method of claim 1, wherein the offset is about 90 minutes. 6. The method of claim 1, wherein determining whether the data following the offset associated with the cycle satisfies the steady state criteria further comprises comparing a maximum value and a minimum value to the overall average. 7. The method of claim 1, wherein the control signals further comprise optimized values for control variables. 8. The method of claim 1, wherein the optimization targets comprise at least one of a reflux flow rate, a pumparound flow rate, an overhead temperature, and overhead product specification, and a bottom product specification. 9. The method of claim 1, further comprising: detecting a second event associated with a second cycle operating in the first mode of operation;determining that data associated with the second cycle satisfies the steady state criteria;adjusting the optimization targets for the first mode of operation based on the data associated with the second cycle; andapplying second control signals comprising the adjusted optimization targets for a subsequent cycle in the first mode of operation. 10. The method of claim 1, further comprising: detecting a second event associated with a second cycle operating in the first mode of operation;determining that data associated with the second cycle does not satisfy the steady state criteria; andapplying the control signals comprising the optimization targets, without adjusting the optimization targets based on the data associated with the second cycle, for a subsequent cycle in the first mode of operation. 11. An apparatus for optimizing a batch process system having at least one operating mode, wherein the batch process system having successive cycles of operation in the at least one mode of operation, the apparatus comprising: at least one sensor configured to monitor the system to obtain data associated with the operation of the system during a cycle of operation and detect an event associated with a cycle operating in a first mode of operation; andat least one processor operatively connected to the at least one sensor,wherein the at least one processor determines whether or not the event associated with the cycle operating in the first mode of operation is operating in a steady state based upon a determination whether data associated with the cycle satisfies steady state criteria,wherein the determination whether the data associated with the cycle satisfies the steady state criteria comprises: selecting an offset, the offset is a transient period in which no data is recorded, obtaining data following the offset, and determining whether the data following the offset from the event satisfies the steady state criteria,wherein determining whether the data following the offset from the event satisfies the steady state criteria comprises: separating the cycle into a first cycle portion and a second cycle portion, averaging a first set of data associated with the first cycle portion, averaging a second set of data associated with the second cycle portion, and determining whether the average of the first set of data and the average of the second set of data are within a predetermined tolerance of an overall average, wherein the overall average is the average of all data including the first set of data and the second set of data, andwherein the at least one processor generates optimization targets for the first mode of operation based on the data;a database for storing the optimization targets generated by the at least one processor; anda controller configured to apply control signals comprising the optimization targets for a next cycle of operation of the batch process system operating in the first mode of operation.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (32)
Li, Tong; Wang, Justin Jian, Advanced control system for steam hydrocarbon reforming furnaces.
Nguyen, Anh T.; Emigholz, Kenneth F.; Woo, Stephen S.; Vercher, Stephen D.; Orsak, Steven M.; Alagappan, Perry, Application of abnormal event detection (AED) technology to polymers.
Alagappan, Perry; Emigholz, Kenneth F.; Worden, Kevin R.; Woo, Stephen S.; Nguyen, Anh T., Application of abnormal event detection technology to delayed coking unit.
Bhat Naveen V. (Houston TX) Braden William B. (Houston TX) Heckendoorn Kent E. (Houston TX) Graettinger Timothy J. (Bethel Park PA) Federowicz Alexander J. (Pittsburgh PA) Dubose Paul A. (Chapel Hill, Control system using an adaptive neural network for target and path optimization for a multivariable, nonlinear process.
Nakane Rintaro (Yokohama JPX) Egawa Jiro (Yokosuka JPX), Image forming apparatus having a function that automatically adjusts a control standard value for controlling image qual.
Ismail Ashraf A.,CAX ITX H3Z 1V1 ; Van De Voort Frederick R.,CAX ITX H9X 2V1 ; Pinchuk David,CAX ITX H4X 1C1, Method and apparatus for continuous oil monitoring and treatment.
Wallman P. Henrik (Berkeley CA), Minimum time, optimizing and stabilizing multivariable control method and system using a constraint associated control c.
Zombo Paul J. ; Seth Brij B. ; Hultgren Kent G. ; Burke Michael A., On-line monitor for detecting excessive temperatures of critical components of a turbine.
Kern, Kenneth C.; Steven Kern,; Charles, George P.; Sullivan, Christopher F.; Sullivan, Andrew D.; Shiel, Howard H.; Righi, John M.; Hayes, Michael A.; Mason, Daniel H., Process unit monitoring program.
Emigholz,Kenneth F.; Wang,Robert K.; Woo,Stephen S.; McLain,Richard B.; Dash,Sourabh K.; Kendi,Thomas A., System and method for abnormal event detection in the operation of continuous industrial processes.
Heavner, III, Louis W.; Sharpe, Jr., Joseph H.; Eryurek, Evren; Kavaklioglu, Kadir, System and method for detecting an abnormal situation associated with a heater.
Hansen Paul L. ; Kuczma Paul D. ; Palsson Jens O.,SEX ; Simon Jonathan S., Technique for controlling DCSS condensate levels in a Kalina cycle power generation system.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.