Intro to Design of Experiments

Quick reference

• 00:04 Hello, I'm Ray Sheen.
• 00:06 Design of experiments is a very powerful technique for
• 00:09 determining the design of a new system or process.
• 00:12 We have an entire course on this topic, but
• 00:15 I wanna take a few minutes now to introduce DOE to you.
• 00:20 Let me start with the whole concept of experimental design as compared to
• 00:23 theoretical design.
• 00:25 The design process is an inquiry process.
• 00:28 Its goal is to discover a new or better mousetrap.
• 00:30 It's about creating a positive change for the customer.
• 00:34 Either with a new or improved product or service.
• 00:37 Experimental design does that inquiry through a set of experiments.
• 00:41 It tries something and based upon the result, it tries something else.
• 00:45 This may continue for numerous tests or
• 00:47 experiments until a design a deemed acceptable.
• 00:51 The goal of experimental design is to gather enough actual data, that a model or
• 00:55 formula can be created that explains how things work.
• 00:59 This is in contrast to theoretical design that starts with a formula.
• 01:03 It creates a theoretical design concept and
• 01:05 then builds it to confirm that the theoretical performance can be achieved.
• 01:09 One of the outcomes of experimental design is the y
• 01:12 equals f(x) equation that we've discussed earlier.
• 01:16 Now there are a lot of different systems and methods for
• 01:19 doing experimental design work.
• 01:21 But they seemed to fall into two categories, organized inquiry and
• 01:25 disorganized inquiry.
• 01:27 Most designers use disorganized inquiry.
• 01:30 They eat too much and get indigestion and that keeps them awake all night.
• 01:33 And sometime during the night as they're thinking about the most recent Star Wars
• 01:37 movie, they get an idea of something that they wanna try.
• 01:40 And next day they set about trying it.
• 01:42 Well, DOE does not rely on midnight inspirations.
• 01:46 It is organized inquiry.
• 01:49 So let's look at the theory behind the designs of experiments, or
• 01:52 as it's commonly called, DOE.
• 01:54 The DOE approach is to first quantify the relationships between factors and
• 01:59 output performance for the product to system.
• 02:02 It analysis the different combinations using statistical techniques
• 02:05 to quantify the relationships.
• 02:07 Once those relationships had been determined,
• 02:09 the design can then be optimized for the key performance matrix.
• 02:13 Since we have an entire course on DOE, this module will just discuss the concept.
• 02:17 To create this model, the various process or product factors and
• 02:20 the characteristics are divided into several subsets.
• 02:23 One of these is controllable factors.
• 02:26 These will be studied to provide insight into how to use them
• 02:29 to manage process performance.
• 02:31 Another category is variable uncontrolled factors.
• 02:35 These are often environmental factors like temperature, humidity, time of day,
• 02:39 or common cause process variation.
• 02:42 The third category is discrete uncontrolled factors.
• 02:46 Many times, the analysis will be made to determine if these discrete factors should
• 02:49 be controlled or uncontrolled.
• 02:51 These factors could be which suppliers' material are used ,or
• 02:55 which location does the processing?
• 02:57 These are often determined by system boundaries or constraints.
• 03:01 The fourth category is the set of system performance or response parameters.
• 03:05 For DOE to work, there must be at least one measurable parameter.
• 03:09 It's even better if that response is variable, but
• 03:12 it can work with a discreet factor.
• 03:14 We can actually use DOE in two modes.
• 03:17 One is to help further isolate a problem in analysis mode and
• 03:20 the other is a design mode for a new system or process.
• 03:24 Let's look at the problem solving one first.
• 03:27 If one of the output or response factors is the problem condition,
• 03:31 DOE can tell us which factors or combinations of controlled and
• 03:34 uncontrolled factors will create the problem condition.
• 03:38 In this case, we can use DOE to establish expectations about process capability.
• 03:44 Which you should recall, is the ability of the process to reliably deliver
• 03:47 outputs that are within the customer's specifications.
• 03:50 In other words, DOE will tell us if the process will always be creating some
• 03:54 results that are out of tolerance.
• 03:56 That will set us up for a discussion with stakeholders about realistic expectations.
• 04:02 The DOE can also be used to show which factors have a positive,
• 04:05 negative, or nil effect on the problem's condition.
• 04:09 In addition to using DOE for analysis, DOE can be used to create a new design.
• 04:14 To create a new normal as part of the improved stage in
• 04:17 your lean six sigma project.
• 04:19 Remember we said that DOE creates the model describing how all the factors,
• 04:23 both controllable and uncontrollable, work together to generate the product or
• 04:26 system response.
• 04:27 It explains the behaviors and allows us to predict the performance for
• 04:32 different sets of input factors.
• 04:34 A great aspects of DOE is that most of the DOE analysis methods will analyze both
• 04:38 primary effects and combination effects.
• 04:42 When working with complex systems, many times the most important factors are based
• 04:46 upon the interplay of two or three factors, rather than on a single one.
• 04:50 So through the use of DOE, we can design the system and
• 04:53 determine the best set of controls to drive system performance.
• 04:57 We can also determine the allowable tolerances for
• 04:59 those controls, that will ensure that we get acceptable process performance.
• 05:04 And we can tell the stakeholders what are the realistic expectations on performance,
• 05:08 based upon the factors that they wanna control.
• 05:12 This analysis can be used to illustrate the effect of common cause variation and
• 05:16 what it will take the change that variation.
• 05:19 By understanding the factors and how they contribute,
• 05:21 the team can explain to stakeholders what is needed to resolve the problem.
• 05:26 They can create several solutions with different control factors and tolerances.
• 05:30 Stakeholders can then evaluate the cost and benefits of each.
• 05:33 DOE will help you to understand and get control of factors
• 05:37 contributing to common cause variation that is part of your problem.
• 05:42 Now it's a powerful technique, but it's not needed on every project.

Lesson notes are only available for subscribers.