Loss Function
Model introduced by Dr. Genichi Taguchi
used to approximate the financial loss for any particular deviation in a
product using the best specification target and for the amount of variation
in any process.
The model argues that there is an increasing loss (both for producers
and for society at large), which is a function of the deviation or
variability from the best or perhaps target value of a parameter.
The greater the deviation from target, the greater is the loss. The notion
that loss is dependent on variation is very well established in some
design theories, and at a technique level is associated with the
assistance and the cost related to
dependability.
Formulas:
Loss at a point: L(x) = k*(x-t)^2
k = loss coefficient
x = measured value
t = target value
Average Loss of a sample set: L = k*(s^2 + (pm - t)^2)
s = standard deviation of sample
pm = process mean
Total Loss = Avg. Loss * number of samples
The Taguchi methodologies are sometimes
linked with moderately limited aspects of design,
example, single piece parts, rather than very complicated products,
procedures and/or services. Some professionals will also argue that the
net results of the Taguchi methodology may not always offer enhanced
design resolutions than what could achieved by using standard methods.
You can find more information at Leeds
Metropolitan University, and for an example chart visit Universität
Magdeburg.
