Visit the Product Innovations Archive at
www.moderncasting.com
MetaCause Links Problems With Causes Buyers of metal castings specify the
New Product
products they want, not the processes used to make them. And according to Hathibelagal Roshan, president of MetaCause, Fox Point, Wis., metalcast-
ers have long had no easy method of determining the link between the two. But MetaCause’s Self Learning Data Analysis Software solves that problem. “MetaCause identifies the relation-
ship (positive, negative or no rela- tionship) and strength of relationship between process variables and product specifications,” Roshan said. The MetaCause Studio 2008 software
package is designed to analyze data using advanced pattern recognition techniques to discover process opti- mization opportunities from historical production data. The software analyzes inputted production information (e.g. melting, molding and casting process data) and delivers a report on optimal process settings and settings to avoid. It discovers main effects and interactions among factors so users can adjust one or more parameters at the same time to reduce casting defects. MetaCause employs a patented tech-
nique to deliver results that are more accurate than standard statistical tech- niques like regression analyses, as the techniques used make no assumptions or simplifications about the data or its conditions. It reads and interprets the full data set and can accurately char- acterize patterns from noisy data sets. Production data is entered into Meta-
Metalcasters input production information into a spreadsheet (above), and the Metacause Studio software analyzes the data to deliver a report on optimal process settings and settings to avoid (below).
Cause through spreadsheets provided with the software. MetaCause then generates an HTML report showing the factors which affect the quality of the manufactured component. MetaCause does not analyze one
process factor at a time; it analyzes data from all factors and response from the data set, isolating the effect of each fac- tor on each response by removing the noise generated by other factors. For example, in the analysis of a
high performance nickel-based alloy, MetaCause would determine the optimal settings for the alloy’s chemical composi- tion (i.e. the optimal settings for tantalum, nitrogen and oxygen) and settings det- rimental for the chemical composition (e.g. molybdenum below 1.76%). The software also indicates the interactions between process variables that have an effect on products. Sometimes main effects are weak and may not influence results on their own, but two weak main effects can come together to produce a strong interaction.
MC For more information, visit
www.metacause.com. MODERN CASTING / July 2010 45
PRODUCT INNOVATIONS
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60