Earlier in the week, Yili Hong, a PhD student from Iowa State, gave an applied statistics seminar in our department about predicting transformer lifetimes. Our power system depends on having transformers up and working. Being able to predict transformer lifetimes (both individually and collectively) is useful for forecasting maintenance and installation. When looking at the data, it was clear that there are different types of transformers, and these classifications were important for making meaningful predictions. Although I didn’t understand some of the statistical techniques and bootstrapping algorithms applied, not being a statistician, I found a few things very interesting. First, there are transformers that were installed in the 1930’s still working in the United States! The old transformers have longer anticipated lifetimes than the new ones. (Their lifetimes were modeled using a Weibull distribution with beta=2 vs. beta=6. Statisticians, discuss amongst yourselves). This is incredibly depressing. We live in a world where everything is disposable. Even our necessary infrastructure.
December 6, 2008
transformers, more than meets the eye
By Laura Albert
This entry was posted on Saturday, December 6th, 2008 at 1:07 pm and posted in Uncategorized. You can follow any responses to this entry through the RSS 2.0 feed.
Search Punk Rock OR:
- I had 3 kids before tenure ✅ I write a blog, not just journal pubs, and use social media ✅ I make time to talk to… twitter.com/i/web/status/1… 1 day ago
- I had three children pre-tenure, including one child in grad school. I finished my PhD, got tenure, and was promo… twitter.com/i/web/status/1… 1 day ago
- Dr. Janis Terpenny, the chair of Penn State’s ISYE department, is talking about Thoughtful Purposeful Leadership.… twitter.com/i/web/status/1… 1 day ago
- RT @csl_UWMadison: A big thank you to meriko borogove for sharing your experiences with the members of the CSL lab and the College of Engin… 2 days ago
- RT @kellyperil: At a panel where rock star @UWMadison professors talk about why they frequently respond to reporters looking for sources, @… 2 days ago
- I'm going to be on an @UWMadisonMedia panel about interacting with the media as an expert in two hours. https://t.co/ytzMWeMPaR 2 days ago
Tagsanalytics art aviation blogs cheese coloring computing conferences cooking coupons criminal justice data decision analysis disasters education elections emergencies environmentalism & natural living finance football analytics grand challenges graph theory health healthcare higher education holidays homeland security humanitarian invited talks lightning lottery march madness marketing math programming mip MODA Olympics optimization ORMS blog-off OR publications PhD phd student advice pirates podcast and video Poisson politics probability public policy publishing queuing recipe risk communication science communication science fair secretary problem slidecasts social justice social networking sports star wars stochastic processes stopping problems teaching teaching with technology traffic Transportation TSP twitter vampires weather werewolves women work-life balance writing zombies