ARCHITECTURE FOR ROOT CAUSE ANALYSIS, PREDICTION, AND MODELING AND METHODS THEREFOR

• US 20130173332A1
• Filed: 12/29/2011
• Published: 07/04/2013
• Est. Priority Date: 12/29/2011
• Status: Abandoned Application

• Current Assignee: Bistel America Incorporated
• Original Assignee: Bistel America Incorporated
• Inventors: Ho, Tom Thuy, Wang, Weidong, Choi, Woon-Kyu, Han, Ji-Hoon Keith, Villareal, Gabriel Serge
• Application Number:
  US13/340,574
• Publication Number:
  US 20130173332A1
• Time in Patent Office: Days
• US Class Current: 705/7.27
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Abstract

Systems and methods for automatically and/or systematically include more data sources and/or more detailed data in the analysis, prediction, and model building. Process data may be employed to pinpoint the process parameter excursions and domain knowledge and/or expert systems may be automatically and/or systematically incorporated into the root cause analysis, the prediction and/or the model building to improve results and/or to reduce the reliance on inconsistent and expensive human experts.

Claims

1. A computer-implemented method for performing root cause analysis for a process result for material processed in accordance with a process, comprising:

providing quality and material (Q&

M) data representing process result for said material from said process;

selecting effect data that includes at least one main effect from said Q&

M data;

providing manufacturing data representing manufacturing conditions present while said material is processed in accordance with said process;

selecting causal data that includes at least one causal variable from said manufacturing data, said causal data being associated with said main effect data; and

analyzing said causal data and said effect data for analysis result, whereby root cause is derived from said analysis result.

2. The computer-implemented method of claim 1 wherein said effect data further includes related effects that are related to said at least one main effect.

3. The computer-implemented method of claim 1 wherein said Q&

M data is clustered prior to said selecting said effect data.

4. The computer-implemented method of claim 1 wherein said Q&

M data is segmented prior to said selecting said effect data.

5. The computer-implemented method of claim 1 further including validating said analysis result.

6. The computer-implemented method of claim 1 further comprising providing knowledge base for providing knowledge base data for use in at least one of said selecting said effect data, said selecting said causal data, and said analyzing.

7. The computer-implemented method of claim 1 further comprising providing external knowledge source for providing external knowledge data for use in at least one of said selecting said effect data, said selecting said causal data, and said analyzing.

8. A computer-implemented method for performing model building for use in predicting future process result for future processing of future material processed in accordance with a process, comprising:

providing quality and material (Q&

M) data representing process result from processing material similar to said future material in accordance with said process;

selecting effect data that includes at least one main effect from said Q&

M data;

providing manufacturing data representing manufacturing conditions present while said material is processed in accordance with said process;

selecting predictive data that includes at least one predictive variable from said manufacturing data, said predictive data being associated with said main effect data; and

analyzing said causal data and said effect data for analysis result, whereby at least one model is derived from said analysis result.

9. The computer-implemented method of claim 8 wherein said effect data further includes related effects that are related to said at least one main effect.

10. The computer-implemented method of claim 8 wherein said Q&

M data is clustered prior to said selecting said effect data.

11. The computer-implemented method of claim 8 wherein said Q&

M data is segmented prior to said selecting said effect data.

12. The computer-implemented method of claim 8 further including validating said analysis result.

13. The computer-implemented method of claim 8 further comprising providing knowledge base for providing knowledge base data for use in at least one of said selecting said effect data, said selecting said causal data, and said analyzing.

14. The computer-implemented method of claim 8 further comprising providing external knowledge source for providing external knowledge data for use in at least one of said selecting said effect data, said selecting said causal data, and said analyzing.

15. A computer-implemented method for performing prediction from data generated from processing material processed in accordance with a process, comprising:

providing quality and material (Q&

M) data representing process result for said material from said process;

providing manufacturing data representing manufacturing conditions present while said material is processed in accordance with said process;

selecting a prediction model from a knowledge base; and

generating said prediction using said prediction model, said Q&

M data, and said manufacturing data.

16. The computer-implemented method of claim 15 wherein said Q&

M data is clustered prior to said generating.

17. The computer-implemented method of claim 15 wherein said Q&

M data is segmented prior to generating.

18. The computer-implemented method of claim 15 further including validating said prediction.

19. The computer-implemented method of claim 15 further comprising providing, knowledge base for providing knowledge base data for use in said generating.

20. The computer-implemented method of claim 15 further comprising providing external knowledge source for providing external knowledge data for use in at least one of said selecting and said generating.