Step 4 experiment run for each of the four trials of

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

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: by using the Taguchi method. Robust Design Example (cont’d) •  Step 2: Select control Parameters: –  Four control parameters (with L9 orthogonal array, i.e., three levels) •  Step 2: Select noise parameters •  Three noise parameters (with L4 orthogonal array, i.e., two levels) Robust Design Example (cont’d) •  Step 3: Experiment design –  Conduct four experiments for each run in L9 (e.g., run 2 in L9 is executed four Omes to include the noise matrix.) –  The first trial condiOon: a new can of paste, water rinse, and horizontal spray –  The last trial condiOon: a can of paste opened one year ago, a chlorocarbin cleaning agent, and horizontal spray for cleaning. •  Step 4: Experiment run –  For each of the four trials of each run, measure a response that represents the objecOve funcOon that we are ahempOng to opOmize: •  Shear strength of the solder joint measured at room temperature. Parameter Design (cont’d) •  Two commonly used orthogonal arrays. (a)  L4 deals with three control factors at two levels. A total of 4 runs of DOE is needed. (b) L9 array considers four control factors each at three levels. A total of 9 runs of DOE is needed. Robust Design Example (cont’d) •  Step 5: Results analysis –  For four trials, average the strength measurements and determine the standard deviaOon. For example, for run 2, we have •  Step 5: Results analysis •  In the robust design, the appropriate response parameter is the S/N raOo. Which type to use here? Robust Design Example (cont’d) •  Step 5: We obtain the following parameter matrix. Robust Design Example (cont’d) •  Step 5: Determine the average response for each of the four control parameters at each of its three levels. •  Step 5: The average S/N raOos are plohed against test level for each of the four control parameters. Robust De...
View Full Document

This note was uploaded on 02/26/2012 for the course 650 486 taught by Professor Zou during the Fall '11 term at Rutgers.

Ask a homework question - tutors are online