Granted Patent B2

US 12,286,597 · App. 17/629,435 · Granted Apr 29, 2025

Inventors: Simeon Sauer (Heidelberg, DE); Daniel Keck (Ludwigshafen am Rhein, DE); Eric Jenne (Ludwigshafen am Rhein, DE); Alexander Badinski (Ludwigshafen am Rhein, DE); Miriam Angela Anna Hahkala (Ludwigshafen am Rhein, DE); Bart Blankers (Antwerp, BE); Hendrik De Winne (Antwerp, BE); Britta Carolin Buck (Ludwigshafen am Rhein, DE)

Assignee: BASF SE

C10G9/36C10G9/16C10G9/206F27D19/00G05B23/0283G06F30/27G06Q10/04G06F2119/22

Abstract

Claims (63)

1. A computer-implemented method ( 100 ) for predicting a progress of degradation in an equipment of a chemical production plant, comprising:

a) obtaining ( 110 ) a future value of at least one operating parameter of the equipment within a prediction horizon that defines a first future time period over which the progress of degradation in the equipment is predicted, wherein the at least one operating parameter has an influence on the degradation of the equipment, and

wherein the at least one operating parameter is known and/or controllable over the prediction horizon, such that the future value of the at least one operating parameter can be determined over the prediction horizon;

b) using ( 120 ) a prediction model to estimate a future value of at least one key performance indicator within the prediction horizon based on an input data set comprising the future value of the at least one operating parameter,

wherein the prediction model is parametrized or trained based on a sample set including historical data of at least one process variable and the at least one operating parameter, wherein the at least one process variable is used to determine the at least one key performance indicator; and

c) predicting ( 130 ) the progress of degradation in the equipment within the prediction horizon based on the future value of the at least one key performance indicator;

wherein the progress of degradation comprises one or more of:

a heat exchanger that suffers from a coking or other fouling process due to at least one of coke layer formation, polymerization, microbial deposits, and inorganic deposits;

a pipe where mass flow is impeded by a coking or other fouling process due to coke layer formation and/or polymerization;

a fixed bed reactor that suffers from a coking or other fouling process due to coke layer formation, polymerization, and/or deposits of solid material originating from an upstream unit operation;

a fluidized bed reactor that suffers from a coking or other fouling process due to coke layer formation, polymerization, and/or deposits of solid material originating from an upstream unit operation;

a fluidized bed reactor that suffers from a coking or other fouling process due to coke layer formation, polymerization and/or deposits of solid material originating from an upstream unit operation; and

a filter, the efficiency of which deteriorates due to polymerization and/or deposits of solid material originating from an upstream unit operation.

2. The computer-implemented method according to claim 1 , further comprising:

obtaining a value of at least one operating parameter of the equipment during the current and/or past operation of the equipment;

wherein the input data set comprises the value of the at least one operating parameter obtained during the current and/or past operation of the equipment.

3. The computer-implemented method according to claim 1 , further comprising:

obtaining at least one process variable that is measured during a current and/or past operation of the equipment;

determining a value of the at least one key performance indicator based on the at least one process variable obtained during the current and/or past operation of the equipment;

wherein the input data set further comprises the value of the at least one key performance indicator obtained during the current and/or past operation of the equipment.

4. The computer-implemented method according to claim 1 , further comprising:

repeatedly performing steps a) to c) over a further prediction horizon that defines a second future time period over which the progress of degradation in the equipment is predicted, wherein the first future time period precedes the second future time period in time.

5. The computer-implemented method according to claim 4 ,

wherein the further prediction horizon is partially overlapped with the prediction horizon; or

wherein the further prediction horizon is separate from the prediction horizon.

6. The computer-implemented method according to claim 1 ,

wherein the prediction model comprises a multiple linear regression model, optionally with regularization.

7. The computer-implemented method according to claim 1 ,

wherein the equipment comprises at least one of:

a steam-cracker furnace;

a transfer line exchanger of a steam cracker; and

an aniline catalyst.

8. An apparatus ( 200 ) for predicting a progress of degradation in an equipment of a chemical production plant, comprising:

a) an input unit ( 210 ) configured for receiving a future value of at least one operating parameter of the equipment within a prediction horizon that defines a first future time period over which the progress of degradation in the equipment is predicted,

wherein the at least one operating parameter has an influence on the degradation of the equipment, and

wherein the at least one operating parameter is known and/or controllable over a prediction horizon;

b) a processing unit ( 220 ) configured for:

using a prediction model to estimate a future value of at least one key performance indicator within the prediction horizon based on an input data set comprising the future value of the at least one operating parameter,

wherein the prediction model is parametrized or trained based on a sample set including historical data of the at least one process variable and the at least one operating parameter, wherein the at least one process variable is used to determine the at least one key performance indicator; and

predicting the progress of degradation in the equipment within the prediction horizon based on the future value of the at least one key performance indicator; and

c) an output unit ( 230 ) configured for outputting the predicted progress of degradation in the equipment

wherein the progress of degradation comprises one or more of:

a heat exchanger that suffers from a coking or other fouling process due to at least one of coke layer formation, polymerization, microbial deposits, and inorganic deposits;

a pipe where mass flow is impeded by a coking or other fouling process due to coke layer formation and/or polymerization;

a fixed bed reactor that suffers from a coking or other fouling process due to coke layer formation, polymerization, and/or deposits of solid material originating from an upstream unit operation;

a fluidized bed reactor that suffers from a coking or other fouling process due to coke layer formation, polymerization, and/or deposits of solid material originating from an upstream unit operation;

a fluidized bed reactor that suffers from a coking or other fouling process due to coke layer formation, polymerization and/or deposits of solid material originating from an upstream unit operation; and

a filter, the efficiency of which deteriorates due to polymerization and/or deposits of solid material originating from an upstream unit operation.

9. The apparatus according to claim 8 ,

wherein the input unit is configured for obtaining a value of at least one operating parameter of the equipment during the current and/or past operation of the equipment; and

wherein the input data set comprises the value of the at least one operating parameter obtained during the current and/or past operation of the equipment.

10. The apparatus according to claim 8 ,

wherein the input unit is configured for obtaining at least one process variable that is measured during a current and/or past operation of the equipment;

wherein the processing unit is configured for determining a value of the at least one key performance indicator based on the at least one process variable obtained during the current and/or past operation of the equipment; and

wherein the input data set further comprises the value of the at least one key performance indicator obtained during the current and/or past operation of the equipment.

11. The apparatus according to claim 8 ,

wherein the processing unit is configured for repeatedly performing the estimation over a further prediction horizon that defines a second future time period over which the progress of degradation in the equipment is predicted, wherein the first future time period precedes the second future time period in time.

12. The apparatus according to claim 11 ,

wherein the further prediction horizon is partially overlapped with the prediction horizon; or

wherein the further prediction horizon is separate from the prediction horizon.

13. The apparatus according to claim 8 ,

wherein the prediction model comprises a multiple linear regression model, optionally with regularization.

14. A non-transitory computer readable medium containing computer instructions stored therein for causing a computer processor to perform the steps according to claim 1 .

Assignments (4)

Priority Claims (2)

Continuity (1)

References Cited (23)