Failure cause diagnostic device for injection molding machine

Patent metadata

Field	Value
Publication number	US-10618202-B2
Application number	US-201615223108-A
Country	US
Kind code	B2
Filing date	Jul 29, 2016
Priority date	Jul 31, 2015
Publication date	Apr 14, 2020
Grant date	Apr 14, 2020

Abstract

A failure cause diagnostic device of the present invention receives input of internal and external state data on injection molding machines and diagnoses failure cause of the injection molding machines by means of a machine learning device. An internal parameter of the machine learning device is obtained by performing machine learning using the state data obtained from the injection molding machines subject to failure cause and the state data obtained from the injection molding machines free of failure cause.

First claim

The invention claimed is:

1. A failure cause diagnostic device configured to determine a cause of failure of at least one injection molding machine, the device comprising a machine learning device configured to
receive internal and external state data from the at least one injection molding machine, during a failure state and a non-failure state of the at least one injection molding machine,
register a correlation among the internal and external state data in advance to identify primary and secondary causes of the failure state,
perform machine learning on the internal and external state data to obtain an internal parameter of the machine learning device,
set a state variable based on the internal and external state data at a predetermined time and a target variable based on a prediction of the failure state after a predetermined time period, and
predict that the failure state of the injection molding machine occurs after the predetermined time period from the predetermined time.

2. The failure cause diagnostic device according to claim 1 , wherein the internal and external state data include a load on a driving unit of the injection molding machine, frequency response of axes, resin pressure, clamping force, alarming history, machine operation history, process monitoring data for each molding cycle, molding conditions, and/or quality information on a molded article and information on the occurrence of failure cause.

3. The failure cause diagnostic device according to claim 1 , further configured to predict the failure cause of the injection molding machine using the state data based on the result of the machine learning.

4. The failure cause diagnostic device according to claim 3 , further configured to identify state data causative of failure cause among the state data in response to predicting the occurrence of the failure cause.

5. The failure cause diagnostic device according to claim 3 , further configured to calculate the correlation between the state data and the occurrence of failure cause in response to predicting the occurrence of the failure cause.

6. The failure cause diagnostic device according to claim 3 , further configured to calculate an adjusted value of the state data so that no failure cause occurs in response to predicting the occurrence of failure cause.

7. The failure cause diagnostic device according to claim 1 , further configured to identify state data causative of failure cause among the state data in response to causing the failure cause.

8. The failure cause diagnostic device according to claim 1 , further configured calculate the correlation between the state data and the occurrence of failure cause in response to causing the failure cause.

9. The failure cause diagnostic device according to claim 1 , further configured to calculate an adjusted value of the state data so that no more failure cause occurs in response to causing a failure cause.

10. The failure cause diagnostic device according to claim 1 , wherein the internal and external state data are input from a plurality of injection molding machines connected by a network.

11. The failure cause diagnostic device according to claim 1 , further configured to share the internal parameter of the machine learning device by a plurality of injection molding machines connected by a network.

12. A machine learning device configured to:
receive internal and external state data from at least one injection molding machine, during a failure state and a non-failure state of the at least one injection molding machine;
register a correlation among the internal and external state data in advance to identify primary and secondary causes of the failure state;
perform the machine learning on the internal and external state data to obtain an internal parameter of the machine learning device;
set a state variable based on the internal and external state data at a predetermined time and a target variable based on a prediction of the failure state after a predetermined time period; and
predict that the failure state of the injection molding machine occurs after the predetermined time period from the predetermined time.

Assignees

• Fanuc Corp

Inventors

• Maruyama Junpei

Classifications

• B29C2945/76949

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

• B29C45/768

  Detecting defective moulding conditions (B29C45/84 takes precedence) · CPC title

• B29C45/84 Primary

  Safety devices {(B29C45/7626 takes precedence)} · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• B29C37/0096 Primary

  Trouble-shooting during starting or stopping moulding or shaping apparatus (B29C66/872 takes precedence) · CPC title