MULTIVARIATE DETECTION OF ABNORMAL CONDITIONS IN A PROCESS PLANT

• US 20080082302A1
• Filed: 09/28/2007
• Published: 04/03/2008
• Est. Priority Date: 09/29/2006
• Status: Active Grant

• Current Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Original Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Inventors: Hamad, Ahmad, Samardzija, Nikola
• Granted Patent: US 7,937,164 B2
• Time in Patent Office: Days
• US Class Current: 703/2
• CPC Class Codes: G05B 23/021 adopting a different treatment of each operating region or a different mode of the monitored system, e.g. transient modes; different operating configurations of monitored system
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
• CPC Class Codes: G05B 23/0245 based on a qualitative model, e.g. rule based; if-then decisions
• CPC Class Codes: Y10S 715/965 for process control and configuration

Abstract

Methods and systems to detect abnormal operations in a process of a process plant include collecting on-line process data. The collected on-line process data is generated from a plurality of dependent and independent process variables of the process, such as a coker heater. A plurality of multivariate statistical models of the operation of the process are generated using corresponding sets of the process data. Each model is a measure of the operation of the process when the process is on-line at different times, and at least one model is a measure of the operation of the process when the process is on-line and operating normally. The models are executed to generate outputs corresponding to loading value metrics of a corresponding dependent process variable, and the loading value metrics are utilized to detect abnormal operations of the process.

Claims

1. A system for facilitating detection of an abnormal operation of a process in a process plant, the system comprising:

a data collection tool adapted to collect on-line process data from a process within the process plant, wherein the collected on-line process data is representative of an operation of the process when the process is on-line and wherein the collected on-line process data is generated from a plurality of process variables of the process including one or more independent process variables and one or more dependent process variables dependent upon at least one of the one or more independent process variables;

an analysis tool comprising a multivariate statistical analysis engine adapted to generate a first representation of the operation of the process based on a first set of the collected on-line process data generated from the plurality of process variables of the process, wherein the first representation of the operation of the process is adapted to be executed to generate a first outcome related to a dependent process variable, and wherein the multivariate statistical analysis engine adapted to generate a second representation of the operation of the process based on a second set of the collected on-line process data generated from the plurality of process variables of the process, wherein the second representation of the operation of the process is adapted to be executed to generate a second outcome related to the dependent process variable; and

a monitoring tool adapted to determine changes in the process based on the first and second outcomes related to the dependent process variable.

2. The system of claim 1, wherein the monitoring tool is adapted to analyze a change between the first and second outcomes related to the dependent process variable to detect an abnormal operation of the process.

3. The system of claim 1, wherein the first and second outcomes related to the dependent process variable comprise two of a plurality of outcomes related to the dependent process variable generated from corresponding representations of the operation of the process based on different sets of the collected on-line process data generated from the plurality of process variables of the process, wherein the monitoring tool is adapted to monitor a trend in the plurality of outcomes to detect an abnormal operation of the process.

4. The system of claim 1, wherein the first set of the collected on-line process data is representative of a normal operation of the process when the process is on-line and operating normally, wherein the first outcome comprises a baseline outcome related to the dependent process variable, and wherein the second set of the collected on-line process data is representative of a monitored operation of the process when the process is on-line and operating.

5. The system of claim 4, wherein the monitoring tool is adapted to compare the second outcome to the baseline outcome to detect an abnormal operation of the process.

6. The system of claim 1, wherein the multivariate statistical analysis engine is adapted to perform a principal component analysis on the first set and second set of the collected on-line process data to generate corresponding first and second loading matrices each representing the operation of the process, wherein the first and second outcomes related to the dependent variable each comprise a loading value metric of the dependent variable generated from a component of the corresponding loading matrix, wherein the component corresponds to loading values corresponding to the dependent variable.

7. A method of facilitating detection of an abnormal operation of a process in a process plant, the method comprising:

collecting on-line process data from a process within the process plant, wherein the collected on-line process data is representative of an operation of the process when the process is on-line and wherein the collected on-line process data is generated from a plurality of process variables of the process including one or more independent process variables and one or more dependent process variables dependent upon at least one of the one or more independent process variables;

generating a first multivariate statistical representation of the operation of the process based on a first set of the collected on-line process data generated from the plurality of process variables of the process;

generating a first outcome related to a dependent process variable from the first multivariate statistical representation;

generating a second multivariate statistical representation of the operation of the process based on a second set of the collected on-line process data generated from the plurality of process variables of the process;

generating a second outcome related to a dependent process variable from the second multivariate statistical representation; and

determining the presence of an abnormal operation based on the first and second outcomes related to the dependent process variable.

8. The method of claim 7, wherein determining the presence of an abnormal operation comprises analyzing a change between the first and second outcomes related to the dependent process variable to detect an abnormal operation of the process.

9. The method of claim 7, wherein the first and second outcomes related to the dependent process variable comprise two of a plurality of outcomes related to the dependent process variable generated from corresponding representations of the operation of the process based on different sets of the collected on-line process data generated from the plurality of process variables of the process, wherein determining the presence of an abnormal operation comprises monitoring a trend in the plurality of outcomes to detect an abnormal operation of the process.

10. The method of claim 7, wherein the first set of the collected on-line process data is representative of a normal operation of the process when the process is on-line and operating normally, wherein the first outcome comprises a baseline outcome related to the dependent process variable, and wherein the second set of the collected on-line process data is representative of a monitored operation of the process when the process is on-line and operating.

11. The method of claim 10, wherein determining the presence of an abnormal operation comprises comparing the second outcome to the baseline outcome to detect an abnormal operation of the process.

12. The method of claim 7, wherein generating the first multivariate statistical representation comprises performing a principal component analysis on the first set of the collected on-line process data to generate a first loading matrix representing the operation of the process at a first time, and

wherein generating the second multivariate statistical representation comprises performing a principal component analysis on the second set of the collected on-line process data to generate a second loading matrices representing the operation of the process at a second time,

wherein the first and second outcomes related to the dependent variable each comprise a loading value metric of the dependent variable generated from a component of the corresponding loading matrix, wherein the component corresponds to loading values corresponding to the dependent variable.

13. A method of facilitating detection of an abnormal operation of a process in a process plant, the method comprising:

collecting on-line process data from a process control system within the process plant, wherein the data is representative of an operation of the process when the process is on-line, and wherein the collected on-line process data is generated from a plurality of dependent and independent process variables of the process comprising a first data space having a plurality of dimensions, wherein a dependent process variable describes the behavior of the process and an independent process variable affects the behavior of the process;

generating a plurality of models of the operation of the process using a plurality of corresponding sets of the collected on-line process data generated from the process variables of the process, wherein each model comprises a measure of the operation of the process when the process is on-line at different times within a second data space having fewer dimensions than the first data space and at least one model comprises a measure of the operation of the process when the process is on-line and operating normally;

generating one or more outputs from each model of the operation of the process, wherein each output relates to a corresponding dependent process variable; and

determining the presence of an abnormal operation based on a comparison of the outputs from the models.

14. The method of claim 13, wherein generating a plurality of models comprises performing a multivariate statistical analysis to represent the operation of the process based on the corresponding set of the collected on-line process data generated from the process variables of the process.

15. The method of claim 14, wherein performing a multivariate statistical analysis comprises performing a principal component analysis on the corresponding sets of the collected on-line process data to represent the operation of the process in a loading matrix defining a subspace of the first data space.

16. The method of claim 15, wherein determining the presence of an abnormal operation comprises monitoring changes in the loading matrices as compared to the loading matrix of the operation of the process when the process is on-line and operating normally.

17. The method of claim 13, wherein determining the presence of an abnormal operation comprises monitoring changes in the outputs of the models as compared to the output of the model of the operation of the process when the process is on-line and operating normally, wherein the outputs from the models comprise a loading value metric of the corresponding dependent process variable.

18. A system for facilitating detection of an abnormal operation of a process in a process plant, the system comprising:

a data collection tool adapted to collect on-line process data from a process within the process plant, wherein the collected on-line process data is representative of an operation of the process when the process is on-line and wherein the collected on-line process data is generated from a plurality of dependent and independent process variables of the process comprising a first data space having a plurality of dimensions, wherein a dependent process variable describes the behavior of the process and an independent process variable affects the behavior of the process;

an analysis tool adapted to generate a plurality of models of the operation of the process using a plurality of corresponding sets of the collected on-line process data generated from the process variables of the process, wherein each model comprises a measure of the operation of the process when the process is on-line at different times within a second data space having fewer dimensions than the first data space and at least one model comprises a measure of the operation of the process when the process is on-line and operating normally, and wherein the analysis tool is adapted to execute each of the plurality of models to generate one or more outputs from each model of the operation of the process, wherein each output relates to a corresponding dependent process variable; and

a monitoring tool adapted to compare the outputs from the models to determine the presence of an abnormal operation of the process.

19. The system of claim 18, wherein the analysis tool comprises a multivariate statistical analysis engine adapted to generate representations of the operation of the process based on the corresponding set of the collected on-line process data generated from the process variables of the process.

20. The system of claim 19, wherein the multivariate statistical analysis is adapted to perform a principal component analysis on the corresponding sets of the collected on-line process data to represent the operation of the process in a loading matrix defining a subspace of the first data space.

21. The system of claim 20, wherein the monitoring tool is adapted to monitor changes in the loading matrices as compared to the loading matrix of the operation of the process when the process is on-line and operating normally and to use the comparison to determine the presence of an abnormal operation of the process.

22. The system of claim 18, wherein the monitoring tool is adapted to monitor changes in the outputs of the models as compared to the output of the model of the operation of the process when the process is on-line and operating normally and to use the comparison to determine the presence of an abnormal operation of the process, wherein the outputs from the models comprise a loading value metric of the corresponding dependent process variable.

23. A system for facilitating detection of an abnormal operation of a coker heater, the system comprising:

a first analysis tool comprising a multivariate statistical engine adapted to perform a principal component analysis to generate a plurality of representations of the operation of the coker heater using a plurality of corresponding sets of collected on-line process data generated from one or more dependent process variables that describe the behavior of the coker heater and one or more independent process variables that affect the behavior of the coker heater, wherein the collected on-line process data is representative of an operation of the coker heater when the process is on-line, wherein each representation comprises a measure of the operation of the coker heater when the coker heater is on-line at different times, and at least one representation comprises a measure of the operation of the coker heater when the coker heater is on-line and operating normally, wherein the first analysis tool is adapted to execute each of the plurality of models to generate one or more outputs from each model of the operation of the coker heater, wherein each output relates to a corresponding dependent process variable; and

a second analysis tool adapted to compare the outputs from the models to determine the presence of an abnormal operation of the coker heater.

24. The system of claim 23, wherein the multivariate statistical engine is adapted to perform a principal component analysis to generate loading matrix based on the corresponding sets of the collected process data, wherein the loading matrix comprises a space of interrelated loading values related to the process variables, and wherein the loading matrix is calculated as:

P=[p₁, p₂, . . . , p_a],

wherein;

a comprises the number of principal component vectors, and

p_i=[p_i,1, . . . , p_i,k, p_i,k+1, . . . , p_i,n]^T comprises a loading vector for i=1, . . . , a

wherein;

k comprises the number of independent process variables the multivariate statistical engine,

n comprises the total number of dependent and independent process variables input to the multivariate statistical engine,

wherein the first p_i,1, . . . , p_i,k components of p_i comprise loading values corresponding to the independent variables in the set of the collected process data, and the p_i,k+1, . . . , p_i,n components comprise loading values corresponding to the dependent variables in the set of the collected process data, and wherein the loading matrix comprise a loading value metric for each dependent variable in the set of the collected process data, wherein the loading value metric is calculated as;

$z_j=\sqrt{\underset{i=1}{\overset{a}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>\frac{p_{i,j}^2}{{\mathrm{\sigma <br><br>}}_i^2}}$

wherein j=k+1, . . . , n, and σ

_i comprises the i^th Eigenvalue in a diagonal matrix D of the representation.

25. The system of claim 23, wherein the one or more independent variables comprise one or more independent variables selected from the group consisting of:

a temperature of pass matter at a position before a heating element of a conduit of the coker heater, a flow rate of each pass within the coker heater, a total flow rate of pass matter, a temperature of pass matter at a position after the heating element of the conduit of the coker heater, a flow rate of product material from the coker heater, and a final temperature of product material from the coker heater,

wherein the one or more independent variables comprise one or more dependent variables including an exit temperature of a pass within the coker heater, and

wherein the abnormal condition comprises coking in a tube pass of the coker heater.