Controlling a discrete-type manufacturing process with a multivariate model
Described are methods, systems, and a computer-readable storage medium for controlling a discrete-type manufacturing process (e.g., an injection molding process) with a multivariate model. Data representing process parameters, operating parameters, or both of the manufacturing process are received. The received data is compared with a multivariate model that approximates the manufacturing process to provide a result. Upon the result of the comparing satisfying a condition, one or more values for a set of operating parameters for the manufacturing process are determined. When the one or more determined values for the set of operating parameters satisfies a criterion, at least one operating parameter of the manufacturing process is updated.
1. A computer-implemented method for optimizing an injection molding process, the method comprising:
receiving data measured after at least a portion of the injection molding process, the data representing process parameters, operating parameters, or both of the injection molding process;
approximating a current state of the injection molding process with a multivariate model that is generated using the received data to represent past or present values of one or more dependent variables;
predicting an expected state of the injection molding process with the multivariate model that is generated using the received data to represent future values of the one or more dependent variables;
comparing the approximated injection molding process with the predicted injection molding process to provide a result, the result comprising at least one of a predicted score value, a multivariate statistic, or both;
upon the result of the comparing satisfying a condition, determining one or more values for a set of operating parameters for the injection molding process that optimizes an objective function by adjusting one or more manipulable variables based on the future values of the one or more dependent variables; and
dynamically optimizing the objective function during the injection molding process by updating at least one operating parameter of the injection molding process when the one or more determined values for the set of operating parameters satisfies a criterion.
2. The method of claim 1 , wherein the set of operating parameters comprises ideal operating parameters of the injection molding process.
3. The method of claim 1 , wherein updating comprises communicating one or more of the determined values to a tool of the injection molding process.
4. The method of claim 1 , wherein updating comprises setting at least one operating parameter of a machine associated with the injection molding process.
5. The method of claim 1 , wherein the condition comprises a trend in a multivariate analysis of the injection molding process.
6. The method of claim 1 , wherein the condition is satisfied if the predicted score value, the multivariate statistic, or both exceeds one or more threshold functions.
7. The method of claim 1 , wherein the multivariate statistic comprises at least one of a score, a Hotelling's T 2 value, a DModX value, a residual standard deviation value, or any combination thereof.
8. The method of claim 1 , wherein the multivariate statistic comprises a principal components analysis or partial least squares analysis.
9. The method of claim 1 , wherein the objective function includes values of controllable parameters of the injection molding process.
10. The method of claim 9 , wherein dynamically optimizing the objective function comprises minimizing the objective function.
11. The method of claim 10 , wherein the objective function is a quadratic function.
12. The method of claim 1 , wherein the process parameters are not directly configurable during the injection molding process.
13. The method of claim 1 , wherein the process parameters represent the one or more manipulable variables, and the one or more manipulable variables are associated with the operating parameters.
14. The method of claim 13 , wherein the operating parameters are user-configurable.
15. The method of claim 1 , wherein values of the process parameters comprise values observed outside of a mold, within one or more cavities of the mold, or both.
16. The method of claim 1 , wherein the injection molding process is a discrete-type manufacturing process.
17. The method of claim 1 , further comprising:
detecting at least one fault condition of the injection molding process; and
filtering the received data associated with process parameters of the injection molding process in response to detecting the at least one fault condition.
18. The method of claim 17 , wherein the at least one fault condition comprises a fault state or a trend towards a fault state.
19. The method of claim 17 , wherein filtering comprises at least one of disregarding a portion of the received data or removing a portion of the received data.
20. The method of claim 17 , wherein the at least one fault condition is detected based at least in part on a fault detection model.
21. The method of claim 20 , wherein the fault detection model is based on a default model.
22. The method of claim 1 , further comprising:
detecting at least one fault of the injection molding process; and
modifying the multivariate model based at least in part on the detected fault.
23. The method of claim 1 , further comprising:
generating the multivariate model that approximates the injection molding process.
24. The method of claim 1 , further comprising updating the multivariate model based at least in part on the received data.
25. The method of claim 24 , wherein updating the multivariate model comprises modifying values in the multivariate model or generating a new multivariate model.
26. The method of claim 1 , wherein the one or more manipulable variables are associated with at least one of environmental changes, material changes, process setpoint changes, deterioration of at least one process tool of the injection molding process, temperature changes of the mold, or any combination thereof.
27. The method of claim 1 , wherein the received data represents data measured after completion of a cycle of the injection molding process.
28. A method for optimizing a discrete-type manufacturing process with a multivariate model, the method comprising:
providing a closed-loop controller;
representing the manufacturing process with the multivariate model;
comparing, with a data comparison module, an approximated manufacturing process with an expected manufacturing process to provide a result, comprising at least one of a predicted score value, a multivariate statistic, or both, the data comparison module comprising an approximation portion and a prediction portion, wherein the comparing comprises;
approximating, with the approximating portion, the current state of the manufacturing process with the multivariate model that is generated using received data to represent past or present values of one or more dependent variables; and
predicting, with the prediction portion, the expected state of the manufacturing process with the multivariate model that is generated using the received data to represent future values of the one or more dependent variables;
determining, with a solver module, at least one control action for the manufacturing process based on an output of the data comparison module; and
dynamically optimizing an objective function during the manufacturing process by updating a set of operating parameters of the manufacturing process based on the at least one control action determined by the closed-loop controller.
29. A computer readable product, tangibly embodied in a non-transitory machine readable storage device operable to cause a data processing apparatus in communication with an injection-molding apparatus to:
receive data measured after at least a portion of the injection molding process, the data representing process parameters, operating parameters, or both of the injection molding process;
approximate a current state of the injection molding process with a multivariate model that is generated using the received data to represent past or present values of one or more dependent variables;
predict an expected state of the injection molding process with the multivariate model that is generated using the received data to represent future values of the one or more dependent variables;
compare the approximated injection molding process with the expected injection molding-process to provide a result, the result comprising at least one of a predicted score value, a multivariate statistic, or both;
determine, upon the result satisfying a condition, one or more values for a set of operating parameters for the injection molding process that optimizes an objective function; and
dynamically optimize the objective function during the injection molding process by updating at least one operating parameter of the injection molding process when the one or more determined values for the set of operating parameters satisfies a criterion.
30. A system for optimizing an injection molding process, the system comprising:
data acquisition means for receiving data measured after at least a portion of the injection molding process, the data representing process parameters, operating parameters, or both of the injection molding process;
data approximation means for approximating a current state of the injection molding process with a multivariate model that is generated using the received data to represent past or present values of dependent variables;
data prediction means for predicting an expected state of the injection molding process with the multivariate model that is generated using the received data to represent future values of dependent variables;
data comparison means for comparing the approximated injection molding process with the expected injection molding process to provide a result, the result comprising at least one of a predicted score value, a multivariate statistic, or both;
process logic means for determining, upon the result of the comparing satisfying a condition, one or more values for a set of operating parameters for the injection molding process that optimizes an objective function by adjusting one or more manipulable variables based on the future value of the one or more dependent variables; and
process control means for dynamically optimizing the objective function during the injection molding process by updating at least one operating parameter of the injection molding process when the one or more determined values for the set of operating parameters satisfies a criterion.
31. A system for optimizing a discrete-type manufacturing process, the system comprising:
a data processing module in communication with the manufacturing process, the data processing module configured to:
receive data measured after at least a portion of the manufacturing process, the data representing process parameters, operating parameters, or both of the manufacturing process;
approximate a current state of the manufacturing process with a multivariate model that is generated using the received data to represent past or present values of one or more dependent variables;
predict an expected stated of the manufacturing process with the multivariate model that is generated using the received data to represent future values of the one or more dependent variables;
compare the approximated manufacturing process with the expected manufacturing process; and
determine at least one of a predicted score value, a multivariate statistic, or both;
a solver module configured to:
receive the at least one of the predicted score value, the multivariate statistic, or both; and
generate, upon the predicted score value, multivariate statistic, or both satisfying a condition, a set of operating parameters for the manufacturing process based on an optimized objective function that associates values of configurable parameters of the manufacturing process and the one or more dependent variables; and
a controller module configured to dynamically optimize an objective function during the manufacturing process by updating at least one operating parameter of the manufacturing process.