System and method for tuning process models

Patent metadata

Field	Value
Publication number	US-2016291584-A1
Application number	US-201615084237-A
Country	US
Kind code	A1
Filing date	Mar 29, 2016
Priority date	Mar 30, 2015
Publication date	Oct 6, 2016
Grant date	—

Abstract

A tuning system for improving operation of a plant. A server is coupled to the tuning system for communicating with the plant via a communication network. A computer system has a web-based platform for receiving and sending plant data related to the operation of the plant over the network. A display device interactively displays the plant data. A reconciliation unit is configured for reconciling actual measured data from the plant in comparison with a performance process model result from a simulation engine based on a set of predetermined reference or set points. The reconciliation unit performs a heuristic analysis against the actual measured data and the performance process model result using a set of predetermined threshold values.

First claim

What is claimed is:

1 . A tuning system for improving operation of a plant, the tuning system comprising:
a server coupled to the tuning system for communicating with the plant via a communication network; a computer system having a web-based platform for receiving and sending plant data related to the operation of the plant over the network; a display device for interactively displaying the plant data; and a reconciliation unit configured for reconciling actual measured data from the plant in comparison with a performance process model result from a simulation engine based on a set of predetermined reference or set points, wherein the reconciliation unit performs a heuristic analysis against the actual measured data and the performance process model result using a set of predetermined threshold values.

2 . The tuning system of claim 1 , wherein the reconciliation unit receives the plant data from the plant via the computer system, and the received plant data represents the actual measured data from equipment in the plant during a predetermined time period.

3 . The tuning system of claim 1 , further comprising an interface module configured for providing an interface between the tuning system, a database storing the plant data, and the network.

4 . The tuning system of claim 1 , further comprising a prediction unit configured for predicting a trustworthiness of a current process model of the simulation engine based on the comparison of the plant data.

5 . The tuning system of claim 4 , wherein the prediction unit calculates a trustworthiness score of the corresponding process model based on the comparison of the plant data using an analytic technique.

6 . The tuning system of claim 4 , wherein the prediction unit creates a scoring model for determining a degree of trustworthiness of the corresponding process model based on at least one plant operational parameter.

7 . The tuning system of claim 5 , wherein the trustworthiness score is weighted based on an amount of difference between the plant data and the corresponding predetermined threshold values.

8 . The tuning system of claim 6 , wherein the scoring model is updated with a weighted trustworthiness score, and the current process model is adjusted or tuned based on the scoring model.

9 . The tuning system of claim 4 , wherein the prediction unit cumulatively calculates a difference between a selected plant parameter and the corresponding performance model result during a predetermined time period to determine a fitness of a simulation related to the operation of the plant.

10 . The tuning system of claim 1 , further comprising an optimization unit configured for optimizing at least a portion of the plant based on a trustworthiness score of a plant process model.

11 . The tuning system of claim 10 , wherein the optimization unit defines an objective function as a user-defined calculation of a total cost of the operation during a particular process, including materials consumed, products produced, and utilities utilized, subject to at least one constraint.

12 . The tuning system of claim 1 , further comprising an analysis unit configured for determining an operating status of the plant based on at least one of: a kinetic model, a parametric model, an analytical tool, and a related knowledge and best practice standard.

13 . The tuning system of claim 12 , wherein the analysis unit determines a target operational parameter of a final product of the plant based on at least one of: an actual current operational parameter and a historical operational parameter.

14 . A tuning method for improving operation of a plant, the tuning method comprising:
providing a server coupled to a tuning system for communicating with the plant via a communication network; providing a computer system having a web-based platform for receiving and sending plant data related to the operation of the plant over the network; providing a display device for interactively displaying the plant data, the display device being configured for graphically or textually receiving the plant data; obtaining the plant data from the plant over the network; generating a plant process model based on the plant data for estimating plant performance expected based on the plant data; monitoring a health of the plant based on the plant process model; reconciling actual measured data from the plant in comparison with a performance process model result from a simulation engine based on a set of predetermined reference or set points; creating a scoring model for determining a degree of trustworthiness of the plant process model based on the plant data; and tuning the plant process model based on the scoring model for representing a potential performance of the plant.

15 . The tuning method of claim 14 , further comprising performing a heuristic analysis against the actual measured data and the performance process model result using a set of predetermined threshold values.

16 . The tuning method of claim 14 , further comprising detecting an error in the tuning of the plant process model based on a predetermined threshold or range.

17 . The tuning method of claim 14 , further comprising monitoring and comparing the plant process model with actual plant performance to ensure an accuracy of the plant process model.

18 . The tuning method of claim 14 , further comprising predicting an effect of an operating strategy of the plant based on the tuning of the plant process model.

19 . The tuning method of claim 14 , further comprising calculating a trustworthiness score of the plant process model based on the comparison of the plant data using an analytic technique.

20 . The tuning method of claim 14 , further comprising generating a set of reconciled plant data of the simulation engine based on the tuned plant process model.

Assignees

• Uop Llc

Inventors

• Horn Ian G
• Romatier Christophe
• Kowalczyk Paul
• Alzein Zak

Classifications

• G05B19/41865 Primary

  characterised by job scheduling, process planning, material flow · CPC title

• G05B13/04 Primary

  involving the use of models or simulators · CPC title

• G05B2219/41077

  Self tuning, test run, detect, compute optimal backlash, deformation compensation · CPC title

• G06F15/00

  Digital computers in general (details G06F1/00 – G06F13/00); Data processing equipment in general · CPC title

• G06Q10/00 Primary

  Administration; Management · CPC title