Method and system of determining and visualizing dependencies between industrial process parameters

• US 20100033486A1
• Filed: 06/30/2009
• Published: 02/11/2010
• Est. Priority Date: 07/01/2008
• Status: Abandoned Application

• Current Assignee: CAPEE GROUP AB
• Original Assignee: CAPEE GROUP AB
• Inventors: Dahlen, Karl Erik Vilhelm
• Application Number:
  US12/459,306
• Publication Number:
  US 20100033486A1
• Time in Patent Office: Days
• US Class Current: 345/440.200
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs

Abstract

A method is provided of determining and visualizing dependencies between industrial process parameters with a minimum of mouse clicks.

Claims

1. A method for visualizing mathematical dependencies between industrial response process parameters on a computer with a minimum of user interactions, comprising:

a. defining an initial data set (10) for a data source (1) using a library of displays (3) presenting data associated with process parameters (14) that contain graphical representation (14) of the process parameters (12), the initial data set (10) containing time-based process parameter data;

b. defining a suitable data import time range (7);

c. marking data on an interactive data chart to trigger an explanation algorithm (20) and display an explanation algorithm result (21); and

d. validating the explanation algorithm result (21).

2. The method according to claim 1, further comprising displaying the explanation algorithm result in a list in explanation degree order and where ranked list items (2) correspond to explaining process parameters.

3. The method according to claim 1, further comprising basing the explanation algorithm (20) on multivariate linear regression.

4. The method according to claim 1, further comprising basing the explanation algorithm (20) frequency analysis (eg Fast Fourier Transform).

5. The method according to claim 1, wherein the interactive graphical chart (53) is a time based line chart.

6. The method according to claim 1, wherein the interactive graphical chart (53) is an x/y chart.

7. The method according according to claim 1, wherein the interactive graphical chart (53) is a bar chart.

8. The method according to according to claim 1, wherein the execution of the explanation algorithm (20) is triggered by the event of a user executing a selection of data in an interactive graphical chart (53).

9. The method according to claim 1, wherein the explanation algorithm result (21) is displayed, without a computer mouse click, when the mouse is near, or over a graphical representation (14) of process parameters (12).

10. The method according to claim 1, wherein a filter control window (25) containing interactive filters for process parameters (12) is used by the explanation algorithm (20) such that a user can further filter/limit the time points with process data in the analysis data set (18) by setting minimum and maximum ranges.

11. The method according to claim 1, further comprising using an interactive line chart (15) where a user can select a displayed process parameter, which is represented in the interactive line chart (15) with a curve, and a time adjustment by moving the curve along a time line on the interactive line chart, and by that time adjusting corresponding data in the analysis data set (18).

12. The method according to claim 1, wherein the initial analysis data set (10) is automatically updated with new data from data sources (1) when new data is available.

13. The method according to claim 9, further comprising moving a mouse over a ranked list item (22) in a window with resultant output displayed as a ranked list (54), and a detailed explanation result window (60) display characterized by containing detailed information about the explanation algorithm result (21) associated with the ranked list item (22) and associated explaining parameter and response parameter.

14. The method according to claim 13 wherein the detailed explanation result window (60) contains at least a line chart displaying a response parameter and an explaining parameter (28) with the response parameter and the explaining parameter associated to a ranked list item (22)

15. The method according to claim 13 wherein the detailed explanation result window (60) contains at least a graphical x/y chart displaying a response parameter and an explaining parameter (28) with the response parameter and the explaining parameter associated to a ranked list item (22).

16. The method according to 11, further comprising an automatic calculation of the time adjustment that gives the best explanation degree between a process parameter and a response parameter.

17. The method according to claim 11 wherein a time adjustment control (62) in a detailed explanation result window (60) is characterized by showing an explanation degree at different time adjustments between a response process parameter and an explaining parameter.

18. The method according to claim 17 wherein a detailed relation graph (61) is time adjusted according to user interaction with the time adjustment control (62).

19. The method according to claim 18 wherein a user interaction with the time adjustment control (62) executes a time adjustment to the analysis data set (18) that results in an update of the explanation algorithm result (21) according to the updated time adjusted analysis data set (18).

21. A computer-readable medium having stored therein instructions that, when executed by a computer, cause the computer to perform the method of claim 1.

20. A system for visualizing mathematical dependencies between industrial response process parameters on a computer with a minimum of user interactions, comprising:

a. a defined initial data set (10) for a data source (1) having a library of displays (3) presenting data associated with process parameters (14) and containing graphical representation (14) of the process parameters (12), the initial data set (10) containing time-based process parameter data;

b. a defined suitable data import time range (7);

c. means for marking data on an interactive data chart to trigger an explanation algorithm (20) and display an explanation algorithm result (21); and

d. means for validating the explanation algorithm result (21).