A Systematic Approach to Planning for a Designed Industrial

# With this background we reduce the risks of naive

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: hould be avoided. With this background, we reduce the risks of naive empiricism and duplication of effort. For the CNC-matching problem introduced earlier, we have the guide sheet shown in Figure 3. 3. RESPONSE VARIABLES As mentioned previously, items 4-8 on the guide sheet are most conveniently handled using the supplementary sheets. The first one is for response variables, as shown in Table 2. Response variables come to mind easily for most experimenters, at least superficially; they know what outcomes they want to change-a strength, a failure TECHNOMETRICS, FEBRUARY 1993, VOL. 35, NO. 1 rate, a concentration, or a yield. What makes a good response variable? The answer to this question is complex. A complete answer is beyond the scope of this article, but some guidelines can be given. A response variable 1. Is preferably a continuous variable. Typically, this will be a variable that reflects the continuum of a physical property, such as weight, temperature, voltage, length, or concentration. Binary and ordinal variables have much less information content-much as the raw values are more informative than histograms that have wide bins. Note that being continuous with respect to a control variable may be important. If a response variable has, perhaps, a steep sigmoidal response to a control variable, it is effectively binary as that variable changes. For example, PLANNING FOR A DESIGNED INDUSTRIAL 5 EXPERIMENT l.Experlmenter’s Name and Organlratlon: John Smith, Brief Title of Experiment: CNC Machining Study Process Eng. Group 2. Objectives of the experiment (should be unbiased, specific, measurable, and of practical consequence): For machined titanium forgings, quantify the effects of tool vendor; shifts in a-axis, xaxis, y-axis, and z-axis; spindle speed; fixture height; feed rate; and spindle position on the average and variability in blade profile for class X impellers, such as shown in Figure 4. 3. Relevant background on response and control variables: (a) theoretical relationships; (b) expert knowledge/experience; (c) previous experi...
View Full Document

## This document was uploaded on 02/12/2014.

Ask a homework question - tutors are online