Factors in Taguchi designs

In This Topic

Control factors and noise factors
Using noise factors to identify optimal control factor settings
What is a signal factor?

Control factors and noise factors

A Taguchi design has two types of factors: control factors and noise factors.

Control factors: Control factors are process or design parameters that you can control.; Examples of control factors are equipment settings, material used to manufacture the product, or product design features.
Noise factors: Noise factors are process or design parameters that are difficult or expensive to control during manufacturing.; Examples of noise factors are ambient temperature or humidity.

Consider a cake mixture manufacturer who wants to optimize cake flavor under various conditions. The manufacturer wants to determine control factors that reduce the effect of noise factors on cake flavor.

Control factors, which are in the manufacturer's control include cake mixture ingredients.
Noise factors, which are out of the manufacturer's control, include the air temperature and humidity while the consumer is making the cake.

Using noise factors to identify optimal control factor settings

In Taguchi designs, noise factors are factors that cause variability in the performance of a system or product, but cannot be controlled during production or product use. You can, however, control or simulate noise factors during experimentation. You should choose noise factor levels that represent the range of conditions under which the response should remain robust.

Common types of noise factors are:

External: Environmental factors, customer usage, and so on.
Manufacturing variations: Part-to-part variations.
Product deterioration: Degradation that occurs through usage and environmental exposure.

During experimentation, you manipulate noise factors to force variability to occur, then from the results, identify optimal control factor settings that make the process or product resistant, or robust to variation from the noise factors. Control factors are those design and process parameters that can be controlled.

For example, a printer manufacturer wants to optimize printer performance. One noise factor is different paper types. During experimentation, the manufacturer tests several paper types to determine control factors that reduce the effect of paper type on printer performance.

Compounding noise factors is a strategy in which you group the noise factor levels into combinations that you anticipate will produce extreme response values. Because estimating the effects of individual noise factors is not the primary goal, compounding is a useful way to reduce the amount of testing. For example, if you have three noise factors, each with two levels, you could have eight different combinations of settings to test. Instead, you could group noise factors into two overall settings – one setting in which the noise factors levels increase the response values and the other setting in which the noise factors levels decrease the response values.

What is a signal factor?

A signal factor is a factor, with a range of settings, that is controlled by the user during use. A signal factor is present in a dynamic Taguchi design, but is not present in a static Taguchi design. In a dynamic response design, the quality characteristic operates along a range of values and the goal is to improve the relationship between a signal factor and an output response. In a static response design, the quality characteristic of interest has a fixed level.

For example, the amount of deceleration is a measure of brake performance. The signal factor is the degree of depression on the brake pedal. As the driver pushes down on the brake pedal, deceleration increases. The degree of pedal depression has a significant effect on deceleration. Because no optimal setting for pedal depression exists, it is not logical to test it as a control factor. Instead, engineers want to design a brake system that produces the most efficient and least variable amount of deceleration through the range of brake pedal depression.