Optimize Product/Process Performance

Lesson 6: Optimize Product/Process Performance

Consider a simple example. 

We would like to find optimum Backing conditions, Baking Temperature and Baking Time to get a desired Bulk Density between 1.15 and 1.3 and desired Moisture % between 40% and 50%.  How would we find the optimum conditions?

One possible approach is to use a contour plot. We generate a contour plot of Bulk Density and Moisture %, as a function of Baking Temperature and Baking Time. See figure below.

In the above contour plot the light brown diamond shape shows the desired optimum region. If we look closely a 345 degree F bake Temperature and 35 Minutes Bake Time is an optimum.

But wait.

What about the other responses, Particle Size, Color, Weight, and Cost?

Should we draw 4 more contour plots?

For these four contour plots which Control-variables-pairs  should we select? 

A little bit of math, which I would skip, will show that we need to look at (8 x 7/2) x (6 x 5/2) = 420 pair-wise contour plots are possible.  Hmmm ... too much work, too many options. A visual approach will not work!

We need to use a different approach.

As Albert Einstein, would say:

We cannot solve our problems with the same thinking, that we used, when we created them. We need to think in a higher plain.

Here is a set of optimums.  The second column, "moisture_max" shows optimum conditions for Maximizing Moisture. First column lists the Responses and Control Variables values corresponding to that optimum.

Notice you cannot obtain these type of results using contour plots.  FReD, the bot, thinks in a higher plain!

That concludes this short lesson. Lesson 6: Optimize for Product/Process Performance.

About Author

Mukul Mehta


Mukul Mehta has over 40 years of proven industrial experience in chemical , polymer, and plastics industry. Worked as a Sr. Manager, Statistics and Computer Aided Research for BF Goodrich Chemical, a Fortune 500 company, and then as a software entrepreneur, promoted "quantitative, predictive modeling in one minute or less as a mantra for R&D and New Product Development." Many multi-million dollar successes for dozens of Corporate R&D clients in chemical and pharma industry. Trained over 750 R&D chemists, engineers and managers to Speedup New Product Development through statistical design of experiments.

{"email":"Email address invalid","url":"Website address invalid","required":"Required field missing"}
>