Innovation and R&D

How to Double the Speed of New Product Development?

About 1700 words, Reading Time 6-10 minutes.

Are you a Practicing Scientist or Engineer? An R&D Manager? Do you work in R&D, Manufacturing or Engineering? Would you like to Double the Speed of New Development?

You can. If, you can make Quantitative Predictions in One Minute or Less.

In this article, I will share a tool that can be used on most problems by R&D scientists and engineers. If you have a limited budget or resources here is one tool that can give you the biggest bang for the buck. But be careful, your scientists and engineers will become very good in using this tool, and their market value will go up significantly too!

Do you wish that there was a proven scientific method/tool for solving technical problems in:

  1. Product Development and
  2. Process Improvement 
  3. Manufacturing Tech Support
  4. Customer Product Use Tech Support?

A method, a tool that can be applied again and again, on different types of problems, in different industries, and with high success rate? The tool is called Design of Experiments, DOE for short. Using DOE scientists can predict product and process performance quantitatively in one minute or less. More importantly, it permits efficient knowledge transfer from product/process R&D to Manufacturing and from Application R&D to Customers.

Why Use Design of Experiments in R&D for Product/Process Development/Improvement?

Using Statistical Methods in the design of experiments and data analysis, you, an R&D scientist, can readily attain benefits like these:

  • A 20 to 70% reduction in problem-solving time
  • A 50% reduction in R&D costs related to testing, machine time, labor, and materials, and,
  • A 200 to 300% increase in the value, quality, and reliability of the information generated.

If you can achieve these types of results on your research projects you will be a hero in your R&D manager’s eyes. Your market value will increase dramatically. And that is a significant achievement.

Why use Design of Experiments for Manufacturing?

Being a hero in R&D may not be enough. You also need to and want to develop high credibility with your peers in Manufacturing. For that you need to package your know-how with know-why to make their jobs in manufacturing easier.

Here is what they need:

  • What is an optimum formulation?
  • How does the optimum change if changes are made to the recipe or process variables
  • Which variable(s) is the machine or process sensitive to?
  • For consistent performance, what are the tolerances for these variables?
  • How does one design an effective troubleshooting guide for this product/process?

On any industrial research project, you need answers to all these questions to turn the know-how over to manufacturing in production mode. Where people with less expertise, can produce the same high quality product again and again, easily.

If you can do that, you are liked by R&D, and you are loved by Manufacturing. And, oh yes, you will also get lots of accolades from Senior Executives.

Two DOE Examples from Industry:

Let me illustrate the power of DOE with two examples I worked on.

  • A Fridel-Craft alkylation project involving mono, di and tri alkylated amines with several byproducts. With 9 experiments (yes, 9!)in a three liter laboratory reactor involving Reaction Ratio, Temperature and Catalyst Concentration, we helped Manufacturing improve productivity from 550 lbs/hour to 770 lbs/hour.
  • Scaled up an Oxy-vent-Recycle Process from an 1-inch laboratory reactor to 18-foot diameter, over 70 feet tall, fluid-bed reactor.  We increased ethylene efficiency from 94% to 98% with final optimization at plant scale using 20 well designed DOE and confirmatory experiments.

Here are some questions for R&D scientists:

Are you constantly struggling to answer these questions on your key projects?

  • Which experiments do I run?
  • How do I analyze data?
  • What are the key relationships?
  • What is the optimum?
  • Will quality be consistent?
  • Is this the best I can do?

Is your R&D Manager constantly putting pressure on you to:

  • Reduce time to market by 20 to 50%?
  • Develop custom products quickly?
  • Develop better products faster?
  • Improve R&D productivity?
  • Retain and rapidly reuse knowledge?
  • Ease technology transfer?
  • Would you like to learn the basics of a real scientific method that works?
  • Would you like to know how to convert the real scientific method into a simple, effective, systematic formula that quickly helps you discover what works and what doesn’t?

Learn statistical science of the Design of Experiments and you can answer these questions quickly and efficiently most of the time. Sometimes you will quickly find out that the goal is not achievable with the problem as stated, and new breakthrough thinking is needed. Good news is that you will find that out very quickly and cost effectively using DOE, and you will have saved resources that you can use for breakthrough thinking.

Design of Experiments (DOE) has been used extensively by DuPont, Dow, BF Goodrich, (where I worked for 15 years), and others for over 40 years.

In early Sixties, Genichi Taguchi introduced a version of DOE, known as Taguchi methods in Japan. They were introduced to the USA in the early Eighties. One key reason for the success of Toyota, Sony, Honda, and Cannon in the world market is the extensive use of these types of statistical methods in both product and process development.

In 1969, while at Graduate School in USA studying Chemical Engineering, I read about an interesting seminar announcement: “Applied Statistics for Industrial Product Development.” A visiting faculty member was going to talk about a statistical and mathematical approach to product development and optimization. I was intrigued. I attended the seminar and it changed my focus, my career and professional life. The visiting faculty member introduced us to the use of Design of Experiments, empirical modeling, and how to use this approach to reduce laboratory experimental effort by 50% and more. My first reaction was, “Wow, I can apply these methods to most of my chemical technology related problems.” Well, I enrolled and picked up another graduate degree, in applied statistics with a thesis in the Design of Experiments.

Now I have over 40 years of industrial experience in the use of Design of Experiments (DOE) to solve tough industrial problems, assisted scientists and engineers in applying DOE on more than 750 industrial projects, and trained nearly a thousand scientists, engineers and executives in DOE.   Through these efforts I

If you use these techniques on five problems within one year, you will easily double your success rate!

have developed a simplified framework to learn and use DOE. Just remember the acronym “D.E.P.L.O.Y.  DOE.”

D E P L O Y DOE Framework

Create  Text Table and Diagram See original

So, let us get started.

Here is mantra for real success in new product development:  “Fail fast, fail frequently, fail frugally, but fruitfully.”

Type the mantra in big bold letters, like a banner. Hang it on your wall. This is contrary to what you may have heard, but it is the real truth. Edison experimented with the light bulb filament materials over 400 times and failed. His answer, "I know what does not work."

Why do you want to “Fail fast, fail frequently, fail frugally, but fruitfully?”

The answer is simple. Technological problem solving is very difficult; it takes lot of time and effort, more than you realize.

The brute force Edisonian approach won’t work.

You have to be smart.

Design of Experiments, DOE for short, is the smart scientific way to learn.

Still not convinced? Let me explain, with a real example.

Enter your text here... missing? cf. original

Here is a simple industrial problem. We would like to develop an optimum recipe for a cheesecake.

Let's brainstorm and make a list of the recipe and process variables that may be important for baking a cheesecake. Here is a good list to start.

Insert Table here - Developing a New Cheesecake

Enter your text here... missing? cf. original

We have identified eight recipe and process variables. A pastry chef with considerable expertise in baking cakes probably will add a few variables to our list. But, let us assume for now that this list is adequate. Let us assume a scientist wants to consider each input variable at three levels.

Here are a couple of questions:

What is the probability of finding the optimum if you run 100 experiments ad hoc? ____

How many experiments do we need to run to find the optimum recipe? _____

Using DOE we can an optimum recipe in 20 to 40 experiments, about a month’s work, and answer all the questions that Manufacturing may ask!

So crank up your Product Development engines... Let us speedup new product development and growth rates. And let the fun begin!

References:

There are many excellent books on Design of Experiments. Unfortunately, most of these are highly mathematical. Here are a few of my favorites.

  1.  Box, Hunter and Hunter, Statistics for Experimenters: Design, Innovation, and Discovery
  2. Box and Draper, Empirical Model-Building and Response Surfaces
  3. Draper and Smith, Applied Regression Analysis
  4. Myers and Montgomery, Response Surface Methodology: Process and Product Optimization Using Designed Experiments
  5. Montgomery, Design and Analysis of Experiments
  6. Ryan, Modern Experimental Design
  7. Diamond, Practical Experiment Designs: for Engineers and Scientists
  8. Mukul Mehta One Minute DOE EBook v3.05, A 65 page easy to read introduction to DOE.
  9. Mukul Mehta, Test Program Design and Statistical Analysis of Test Data, p 599-609, Engineered Materials Handbook, Volume 2 Engineering Plastics, ASM International, USA A ten page article, provides a very quick overview.


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

Want to learn more?

Check out these articles below

>