AUTOMATED FAULT ANALYSIS AND RESPONSE SYSTEM

• US 20120154149A1
• Filed: 12/19/2011
• Published: 06/21/2012
• Est. Priority Date: 12/17/2010
• Status: Active Grant

• Current Assignee: Jdt Processworks Inc.
• Original Assignee: Jdt Processworks Inc.
• Inventors: Trumble, Jeffrey
• Granted Patent: US 9,069,352 B2
• Time in Patent Office: Days
• US Class Current: 340/540
• CPC Class Codes: G05B 19/41875 characterised by quality surveillance of production
• CPC Class Codes: G05B 2219/32222 Fault, defect detection of origin of fault, defect of product
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

A process for determining a root cause problem for an out-of-tolerance component manufactured by a plurality of operations performed on the component. The process can include providing manufacturing data from at least a subset of plurality of operations performed on a plurality of components and discovering an out-of-tolerance measurement on at least a subset of the plurality of manufactured components downstream from the plurality of operations. An auto-regression analysis between the out-of-tolerance measurement and the plurality of upstream operations can also be performed using the manufacturing data. A correlation between at least one of the upstream operations and the out-of-tolerance measurement can be found and the correlation can result in the identification of at least one upstream operation that is the root cause of the out-of-tolerance measurement.

Claims

1. A process for determining a root cause problem for an out-of-tolerance component manufactured by a plurality of operations performed on the component, the process comprising:

providing manufacturing data from at least a subset of the plurality of operations performed on a plurality of components manufactured by the plurality of operations;

discovering an out-of-tolerance measurement on at least a subset of the plurality of manufactured components downstream from the plurality of operations using the manufacturing data;

performing an auto-regression analysis between the out-of-tolerance measurement and the plurality of upstream operations using the manufacturing data; and

finding a correlation between at least one of the upstream operations and the out-of-tolerance measurement, the correlation identifying at least one upstream operation that is the root cause of the out-of-tolerance measurement.

2. The process of claim 1, further including sending at least one of a report and an alert related to the root cause to predefined personnel.

3. The process of claim 1, further including instantly initiating a continuous monitoring of the at least one upstream operation that is the root cause of the out-of-tolerance measurement using manufacturing data produced by the at least one upstream operation.

4. The process of claim 3, further including immediately notifying predefined personnel when the monitored upstream operation executes an out-of-tolerance operation.

5. The process of claim 4, wherein the notification is an electronic notification containing a graphical illustration of manufacturing data for the out-of-tolerance operation.

6. The process of claim 1, further including performing a statistical analysis on each of the plurality of operations using the manufacturing data for the purpose of determining an out-of-tolerance performance level for each operation.

7. The process of claim 6, wherein the statistical analysis provides a ranking of the plurality of operations with respect to which one or more operations are producing out-of-tolerance measurements on the plurality of components.

8. The process of claim 7, wherein the ranking identifies a top subset of worst-performing operations.

9. The process of claim 8, wherein the auto-regression analysis is performed between at least one of the top subset of worst-performing operations and all upstream operations for a given worst-performing operation in order to determine the root-cause operation for the given worst-performing operation.

10. The process of claim 9, wherein the root-cause operation is not one of the top subset of worst-performing operations identified by the ranking.

11. The process of claim 1, further including providing a cloud-based system for receiving and using the manufacturing data to discover the out-of-tolerance measurement on at least a subset of the plurality of manufactured components downstream from the plurality of operations;

perform the auto-regression analysis between the out-of-tolerance measurement and the plurality of upstream operations using the manufacturing data; and

find the correlation between at least one of the upstream operations and the out-of-tolerance measurement, the correlation identifying the at least one upstream operation that is the root cause of the out-of-tolerance measurement.

12. The process of claim 11, wherein the manufacturing data is provided in real-time from a manufacturing facility.

13. The process of claim 11, wherein the manufacturing data is provided in batch form from a manufacturing facility for root-cause analysis.

14. A process for determining a root cause problem for an out-of-tolerance component manufactured by moving the component from one station to a subsequent station after one or more operations are executed on the component at a particular station, the process comprising:

providing manufacturing data from at least a subset of the plurality of stations, the manufacturing data being a function of one or more operations executed on a plurality of components at a given station;

discovering an out-of-tolerance measurement on at least a subset of the plurality of manufactured components downstream from the plurality of stations;

performing an auto-regression analysis between the out-of-tolerance measurement and the plurality of upstream stations using the manufacturing data; and

finding a correlation between at least one of the upstream operations and the out-of-tolerance measurement, the correlation identifying at least one upstream station that is a source of the root cause of the out-of-tolerance measurement.