Day: September 25, 2008

The Return of Henry Yennie–and Gustav


Now that Hurricane Gustav has blown out of the picture, it’s time to catch up with Henry Yennie, of the Louisiana State Department of Mental Health.  I reported earlier on Henry’s decision evaluation study of evacuation plans for the City of New Orleans.  The questions he was trying to answer with Palisade Corporation’s Monte Carlo software were how many school buses would be needed in case of the city had to clear out ahead of a major storm and when and where residents would need access to them.

When Gustav was headed directly for New Orleans and classified as a Category 4 storm, people in the city started to evacuate even before they were given orders to do so.   The storm began to test Henry’s risk analysis results when official evacuation began and the school buses started up.  Fortunately Gustav veered southwest of the city and lost power before it made landfall.

The evacuation of the city turned out to be a valuable dress rehearsal, and according to Henry proved the value of the Monte Carlo simulation in decision making under uncertainty.  “You’ll be interested to know,” he writes,” that the modeling we did with @RISK to estimate the number of evacuees from New Orleans a few months ago turned out to be almost exact….I think we were off by several hundred or less.” And he jokes, “Weird…wish I could say it was because I knew what I was doing!”

SixSigmaIn demonstrates how Monte Carlo Simulation is used in Tolerance analysis

Recently, Franco Anzani of SixSigmaIn Team and Marco Manara of Casappa S.p.A. worked together on a Six Sigma tolerance analysis project where they used Palisade Corporation’s @RISK 5.0. The model represents a tolerance analysis study performed to solve a potential assembly issue in a gear pump typically used in forklifts and low noise emission machines.

The model simulates the potential gap distribution in the pump and predicts the potential percentage of scraps, depending on both the nominal value and the variation (due to the machining capability) of the parameters.

@RISK 5.0 has been used to find the optimal combination of nominal design values and process variation to minimize the scrap percentage.

A combined optimization of the two responses has been performed, and an advanced 3D view of the simulated data has been added.
Download a free trial of @RISK or the Tolerance Analysis Model.