|
|
|
|
|
||||||||||||||||||||
|
alarms. Features our unique chart Toolbar for chart functions. |
|
|
||||||||||||||||||||||||||||||||||||||||
|
|
FEATURES
ADDITIONAL FEATURES
REQUIRES 8 MB RAM required, 4 MB hard disk space required, Windows 95, 98, ME, XP or Windows NT 4.0 NETWORK READY - SPC/PI+ can be installed on a
network and allows for multiple access. Customers must purchase enough licenses to cover the maximum number of concurrent users. PRICE: $495.00 U.S. ($649.00 Canadian) includes one year tech support and Quick Start video tutorial . Multiple license discounts start at 10% for 2 copies and run to 50% at 25 copies. Why SPC/PI+ ? Most SPC software programs have proven to be very difficult to
use due to complexity of architecture which requires many steps to do an analysis. SPC/PI+ is remarkably simple to use. You just copy/paste or paste link in your data from any Windows application, click on a column and select
the analysis or chart that you want. SPC/PI+ creates the chart and allows you access to our unique Chart Toolbar
for a variety of simple functions, such as identifying data points, adding comments to data points, scrolling through the data, excluding points, recalculating limits and adding additional data points. Becasue our worksheets can be linked to any Windows spreadsheet or database, your charts can be updated at the touch of a button. SPC has never been simpler.
In addition, many users of SPC have been frustrated because of the inherent limitations of Shewart charts. The Average (X bar) and Range control chart developed by Walter Shewhart in 1931 is still the most popular
chart in use today, due to its simplicity and effectiveness. However, in order for the X-bar and R chart to function properly, the underlying assumptions must be valid. The observations are assumed to be normally distributed and
statistically independent. The assumption of normality is usually met because of the central limit theorem -- the distribution of sample averages tends to be normal, even if the individual observations are not. The need for the
samples to be statistically independent can be a much more serious problem, since there is no similar mechanism assuring reasonable results. The assumption of independence is usually met in manufacturing industries where discrete
components are being produced and piece to piece variation is monitored. In the process industries, however, statistical independence cannot be assumed. Inertial elements in the process frequently cause the observations to become
positively autocorrelated; that is, if X(t) is positive, it is likely that X(t+1) will also be positive. The mean of the observations also tends to meander or drift. This does not mean that the process is "out-of-control"
-- it actually represents the inherent process variation. The application of a Shewhart control chart in this case results in many false alarms, leading to expensive and fruitless searches for assignable causes. When individuals
are plotted (sample size is one) and the data is not normally distributed, the central limit theorem does not apply, and the chart will likely give misleading signals of false alarms or misses. Process Capability indices will also
be incorrect. Even if the data is normally distributed and statistically independent, a Shewhart chart of individuals will usually fail to detect a significant process shift early enough to prevent the production of defective
product. SPC/PI+ comes to the rescue with an advanced tool kit to effectively deal with all of the above problems. SPC/PI+ includes the Cumulative Sum (CUSUM) and Exponentially Weighted Moving Average (EWMA) charts, as effective
alternatives to the Shewhart chart to reduce false alarms and improve chart sensitivity. The problem of autocorrelation is identified with the CORRELOGRAM and the EWMA Predict chart is used to iteratively select the best weighting
factor and model the process. The difference between the EWMA model and the actual data is then charted on a Shewhart chart for Individuals. This chart of residuals then becomes a true Special cause chart while the process mean
(common cause) is displayed as an EWMA chart. The problem of Non-normal data is identified with normal probability plots and statistical tests, and automatically compensated for with power transformations. In
addition, SPC/PI+ is packed with features such as Real Time data collection through the serial port, add data directly to charts, point & click scroll, magnify, data ID, data exclude, auto analyze, the ability to label every
data point with a comment, ability to exclude data, calculate limits over partial ranges, set target values as chart centers, Gage R & R and more, all with the convenience of a point & click Windows environment.
SPC/PI+ - POINT & CLICK SIMPLICITY! To Order Call 1-800-461-9902 in North America or e mail: info@qualitran.com |
