Statistical Process Control (SPC) is a system for monitoring, controlling, and improving a process through statistical analysis. It has many aspects, from control charting to process capability studies and improvement. Nonetheless, the over-all SPC system of a company may be broken down into four basic steps: 1) measuring the process; 2) eliminating variances within the process to make it consistent; 3) monitoring the process; and 4) improving the process. This four-step cycle may be employed over and over again for continuous improvement.

Bulk of SPC concepts in use today were developed based on the premise that the process parameter being controlled follows a normal distribution. Any SPC practitioner must be aware that the parameter must first be confirmed to be normal before being subjected to analysis concepts based on normal behavior. Thus, any discussion on SPC must be preceded by a discussion of what a normal distribution is. 

The Normal Distribution

The normal distribution (see Fig. 1), normal curve, or bell-shaped curve, is probably the most recognized and most widely-used statistical distribution.  The reason for this is that many physical, biological, and social parameters obey the normal distribution. Such parameters are then said to behave 'normally' or, more simply, are said to be 'normal.'  The semiconductor industry has many processes that output data or results that comprise a normal distribution.  As such, it is important for every process engineer to have a firm grasp of what a normal distribution is.

Aside from the fact that the normal distribution is frequently encountered in our day-to-day lives, the mathematics governing normal behavior are fairly simple.  In fact, only two parameters are needed to describe a normal distribution, namely, the mean or its center, and the standard deviation (also known as sigma) or its variability. Knowing both parameters is equivalent to knowing how the distribution looks like.

The normal distribution is bell-shaped, i.e., it peaks at the center and tapers off outwardly while remaining symmetrical with respect to the center.  To illustrate this in more tangible terms, imagine taking down the height of every student in a randomly selected Grade 5 class and plotting the measurements on a chart whose x-axis corresponds to the height of the student and whose y-axis corresponds to the number of students.

Figure 1. The Normal Distribution

<Proceed to Next Page>

HOME

Copyright © 2003-2005 SiliconFarEast.com. All Rights Reserved.