NOVEL SOLUTIONS
Joining the Data Revolution
SHANNON WETZEL, SENIOR EDITOR
pass up reading “Big Data,” by Viktor Mayer-Sch- onberger and Kenneth Cukier. “Big Data” takes a nontechnical look at how the sheer amount of data openly available and economically achievable will bring about a revolutionary way the world will “live, work and think.” In the book, the authors use a lot of examples
A
from the Internet world, but the idea behind big data can still be applied to metalcasters. What the book does best is clearly explain why we make certain decisions based on data today and how that method or reasoning will change in the future. In the past, collecting and storing information was expen- sive, so the emphasis was on obtaining exact data through sampling and pinpointing the reason behind what the samples told us. Today, the vast amount of data at our disposal means we won’t get an exact rea- son and there will be a little bit of error, but because we are looking at information from thousands and even millions of points, the data can be a little messy and still be valuable. Metalcasters are starting to see this wealth of data in the multitude of measurements taken and recorded in their machinery and equipment. Measurements of temperature, moisture, vibra- tion, cycles, pressures, etc., taken often in minute intervals, bring a vast amount of new knowledge to plant personnel. This information can be and is used for predictive maintenance and quality control, but we are just on the frontier of where the data can take us. Big data can be used to better predict market fluctuations so you know when your customer will want his next part or when you can expect a big change in an order. Or it might be used to find correlations between job applicants and successful employees. Perhaps it could tell you definitively which day of the week correlates to the most efficient shift to pour a certain alloy. “A worldview we thought was made of causes is
being challenged by a preponderance of correlations,” the authors write. “T e possession of knowledge, which once meant an understanding of the past, is coming to mean an ability to predict the future.” “Big Data” is not going to speak to you directly as a metalcaster, but it may give you a vision of how this industry will be using data in the not so distant future.
42 | MODERN CASTING October 2013
fter separate meetings with a couple of very diff erent metalcasters who both were thinking about data analysis in the foundry, I couldn’t
ABRIDGED
Relevance to Metalcasters Technical Diffi culty Self-Help Fluff Profi t Booster
“Note that predictive analytics may not explain the cause of a problem, it only indicates a problem exists....T e correlations show what, not why, but as we have seen, knowing what is often good enough.”
Metalcasters’ Translation: T e vast amount of data now available can help us make deci-
sions based on patterns found in the data. For example, suppose data showed a correlation between a worker’s likelihood of properly wearing safety equipment and the type of magazines available in the breakroom. It’s a correlation you would not have predicted and the reason behind the correlation may never be known, but its value is still relevant.
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 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68