Case studies, complete with data, that cover a wide range of applications of DOE in engineering and science. The collection is ideal for teachers and students of DOE. It is also useful for those who want to learn more about the power of DOE methods or who are looking for research ideas.
By way of example, this article lays out a strategy for design of experiments (DOE) that provides maximum efficiency and effectiveness for development of a robust system. It broadens the scope of a prior article (Anderson and Whitcomb 2014) that spelled out how to right-size multifactor tests via statistical power-calculations—a prerequisite for DOE success.
Without mixture design of experiments, chemists would have taken twice as long to develop the extremely biostable HOCUT 8000 coolant and been lucky to achieve its same levels of performance in extending sump life and eliminating the need for costly sump-side additives. Here's an inside look at how they did it.
Engineers at a major medical device manufacturer used RSM to successfully model a key process for their flagship product. The RSM model then became the foundation for development of robust specifications to ensure quality at six-sigma levels.
Optimizing the formulation of a new metalworking fluid required assessing multiple additives. Houghton International used design of experiments (DoE) to develop — in half the time required by the company's previous methods — a line of multi-metal cutting fluids that handle steel, cast iron, aluminum and cast aluminum.
Design of experiments (DOE) is the design of any task that aims to describe or explain the variation of information under conditions that are hypothesized to reflect the variation. This article describes how DOE helps in developing a new specialty chemical product.
In this application, a supplier of industrial equipment wanted to market an existing product to companies producing ethanol from corn. There was anecdotal evidence indicating that the device increased ethanol yield. However, prior to marketing the device the company wanted to find the best operating conditions and determine what performance ethanol producers could expect from the product. Researchers performed a design of experiments (DOE) that quantified the effects of three key factors, singly and in combination, on sample preservation. The sample preservation method recommended by the DOE functioned well for ethanol plants across the Midwest.
An industrial equipment supplier made great improvements to their corn-ethanol measurement process using DOE.
Researchers worked to fine-tune the conditions that best promote peptide bond formation in an uncatalyzed aqueous phase reaction. We felt that we should be able to obtain a better yield than our initial 20% and had a hunch that one or more interactions between variables might be playing a role that was obscured by the OFAT (one factor at a time) method.
Because interactions abound in the coatings industry, the multifactor and multicomponent test matrices provided by the design of experiments (DOE) approach is very appealing. However, carrying out DOE correctly requires that runs be randomized whenever possible to counteract the bias that may be introduced by time-related trends, such as aging of materials, increasing humidity, and the like. But what if complete randomization proves to be inconvenient or impossible? In this case, a specialized form of design called “split plot” becomes attractive, because of its ability to effectively group hard-to-change (HTC) factors. A split plot accommodates both HTC factors and those factors that are easy to change (ETC).