When we perform an orthogonal table experiment, it would take a very long time if the order of experiment is not properly done. Please see the following material.
Click here for material → QE11
p.1: When the molding cylinder temperature is used as the control factor, the temperature increase/decrease is the rate-determining factor. Suppose it takes 1 minute to raise 1°C and 5 minutes to lower 1°C. When assigning cylinder temperatures to column A, there are only two levels, so it takes 25 minutes to increase the temperature from 175 to 200°C only once. In the case that you assign cylinder temperatures to column C, if you carry out the experiments in sequence from Experiment 1, it would take a total of 775 minutes to change the temperature each time.
p.2: The left side is a reprint of p.1. You can change the order of the experiment, so we will put together levels 1, 2 and 3. The time required for heating twice is 25 minutes, and then you can save a lot of time. As described above, it is possible to efficiently carry out orthogonal array experiments by giving priority to factors requiring time to change settings and setting the experiment order. In order to perform an orthogonal table experiment certainty and efficiency, it is better to create an 'experiment instruction' in advance. If you fill in the yellow cells on the 'Cover' sheet, this content will be automatically copied to the expt.1 to expt.18 sheets. When you conduct experiments for each row, it is easier to experiment by looking at the gray conditions on the corresponding sheet in each row.
Experiment instruction file → experiment instruction