Systems and approaches for autotuning an injection molding machine

Patent metadata

Field	Value
Publication number	US-11225006-B2
Application number	US-201916432403-A
Country	US
Kind code	B2
Filing date	Jun 5, 2019
Priority date	Jun 29, 2018
Publication date	Jan 18, 2022
Grant date	Jan 18, 2022

Abstract

Systems and approaches for controlling an injection molding machine and a mold forming a mold cavity and being controlled according to an injection cycle. The systems and methods include analyzing a model of at least one of the injection molding machine, the mold, and a molten material to determine initial values for one or more control parameters of the injection molding machine, and executing a run of injection cycles at the injection molding machine; measuring operation of the injection molding machine during a particular injection cycle of the run of injection cycles; determining one or more operational parameters exceed a threshold; and upon determining that the one or more operational parameters exceed the threshold, adjusting the one or more control parameters for subsequent injection cycles of the run of injection cycles.

First claim

What is claimed is:

1. A method for controlling an injection molding machine and a mold forming a mold cavity, the injection molding machine being controlled according to an injection cycle, the method comprising:
analyzing a model of at least the injection molding machine and the mold, wherein the model of the injection molding machine includes an indication of a resistivity for one or more parts of the injection molding machine and the model of the mold includes data associated with historic injection cycles;
determining initial values for one or more control parameters of the injection molding machine based at least upon the resistivity for the one or parts of the injection molding machine and the mold data associated with historic injection cycles;
executing a run of injection cycles at the injection molding machine, wherein during each injection cycle of the run, the injection molding machine injects a molten material into the mold cavity according to an injection pattern;
measuring operation of the injection molding machine during a particular injection cycle of the run of injection cycles;
determining one or more operational parameters exceed a threshold; and
upon determining that the one or more operational parameters exceed the threshold, adjusting the one or more control parameters for subsequent injection cycles of the run of injection cycles.

2. The method of claim 1 , wherein determining that the one or more operational parameters exceed comprises:
comparing a value of a particular operational parameter to the threshold.

3. The method of claim 1 , wherein the one or more operational parameters include two or more operational parameters, and the method further comprises:
combining a value for two or more of the operational parameters to generate a composite metric.

4. The method of claim 3 , wherein determining that the one or more operational parameters exceed the threshold comprises:
comparing the composite metric to the threshold.

5. The method of claim 3 , wherein combining the value for the two or more operational parameters comprises:
applying a machine learning algorithm to determine the composite metric.

6. The method of claim 1 , wherein the determination that the one or more operational parameters exceed the threshold is indicative of a viscosity of the molten material or a part weight of a molded part being outside of an expected range of operation.

7. The method of claim 1 , wherein the one or more operational parameters include one or more of a steady-state error, an overshoot pressure, an undershoot pressure, and an environmental parameter.

8. The method of claim 1 , wherein the injection pattern defines one or more setpoint patterns for the one or more control parameters.

9. The method of claim 8 , wherein adjusting the one or more control parameters includes adjusting the one or more setpoint patterns included in the injection pattern.

10. The method of claim 1 , wherein adjusting the one or more control parameters includes adjusting one or more gains of a PID controller operatively connected to the injection molding machine.

11. The method of claim 1 , wherein adjusting the one or more control parameters comprises:
applying a machine learning algorithm to determine an adjustment to the one or more control parameters.

12. The method of claim 1 , wherein determining the initial values for the one or more control parameters includes:
analyzing sensor data sensed by one or more environmental sensors.

13. An injection molding system comprising:
an injection molding machine;
a mold;
a model database configured to store models for (i) the injection molding machine and (ii) the mold; and
a controller operatively connected to the model database and to the injection molding machine, the controller configured to:
analyze the model of at least the injection molding machine and the mold wherein the model of the injection molding machine includes an indication of a resistivity for one or more parts of the injection molding machine and the model of the mold includes data associated with historic injection cycles;
determine initial values for one or more control parameters of the injection molding machine based at least upon the resistivity for the one or parts of the injection molding machine and the mold data associated with historic injection cycles;
execute a run of injection cycles at the injection molding machine, wherein during each injection cycle of the run, the injection molding machine injects a molten material into a cavity of the mold according to an injection pattern;
measure operation of the injection molding machine during a particular injection cycle of the run of injection cycles;
determine one or more operational parameters exceed a threshold; and
upon determining that the one or more operational parameters exceed the threshold, adjust the one or more control parameters for subsequent injection cycles of the run of injection cycles.

14. The system of claim 13 , further comprising:
a proportional-integral-derivative (PID) controller configured to control a control parameter of the one or more control parameters, the PID controller having (i) a first gain associated with a proportional component; (ii) a second gain associated with an integral component; and (iii) a third gain associated with a derivative component.

15. The system of claim 14 , wherein to adjust the one or more control parameters, the controller is configured to:
adjust one of the first, second, or third gains of the PID controller.

16. The system of claim 13 , wherein the injection pattern defines one or more setpoint patterns for the one or more control parameters.

17. The system of claim 16 , wherein to adjust the one or more control parameters, the controller is configured to:
adjust a setpoint pattern for the one or more setpoint patterns.

18. The system of claim 13 , wherein the model database includes a model of the molten material.

19. The system of claim 18 , wherein to determine the initial values for the one or more control parameters, the controller is configured to:
analyze the model of the molten material.

20. The system of claim 13 , wherein the one or more operational parameters include two or more operational parameters, and wherein to determine the one or more operational parameters exceed the threshold, the controller is configured to:
combine a value for two or more of the operational parameters to generate a composite metric.

Assignees

• Imflux Inc

Inventors

• Burns Brian Matthew
• Altonen Gene Michael

Classifications

• B29C2945/7605

  Viscosity · CPC title

• B29C2945/76949

  using a learning system, i.e. the system accumulates experience from previous occurrences, e.g. adaptive control · CPC title

• B29C45/766 Primary

  the setting or resetting of moulding conditions, e.g. before starting a cycle · CPC title

• B29C2945/76943

  compare with thresholds · CPC title

• B29C2945/76969

  derivative and integral, i.e. PID regulation · CPC title