File:MATLABCChart.png
| Uploaded by | DanielPenfield |
|---|---|
| Upload date | 2013-06-22T14:04:59Z |
| MIME type | image/png |
| Dimensions | 560 × 420 px |
| File size | 3.9 KB |
Summary
| Description | |
| Date | |
| Source | Own work |
| Author | DanielPenfield |
Licensing
DanielPenfield, the copyright holder of this work, hereby publishes it under the following license:
This file is licensed under the Creative Commons Attribution-Share Alike 3.0 Unported license.
Attribution:
- You are free:
- to share – to copy, distribute and transmit the work
- to remix – to adapt the work
- Under the following conditions:
- attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- share alike – If you remix, transform, or build upon the material, you must distribute your contributions under the same or compatible license as the original.
Source code
This media was created with Perl (interpreted programming language first released in 1987)
Here is a listing of the source used to create this file.
Here is a listing of the source used to create this file.
#!/usr/bin/perl -w
#
# randomly generate process observations that simulate a
# Poisson-distributed process in the state of statistical control
# (c_setup.csv) and simulate the same process experiencing a drift of
# magnitude $drift starting two hours into the $shift shift
# (c_monitoring.csv)
#
use strict;
use Math::Random;
my %shiftSchedule = (
"first" => { "start" => 6.00, "end" => 14.00 },
"second" => { "start" => 14.00, "end" => 22.00 },
"third" => { "start" => 22.00, "end" => 6.00 }
);
my $shift = "third"; # shift to monitor
my $inspectionRate = 1 / 2; # every 1/2 hour
my $drift = 1.5; # sigma drift to simulate
my $m = 25; # samples in control chart setup
my $target = 0.10; # fraction nonconforming target
my $c = $target;
my $n = 48; # observations per sample
my $hour;
my $i;
my $minute;
my @observations;
my $observation;
my $setupM = $m;
#
# simulate control chart setup
#
open(SETUPCSV, ">c_setup.csv") || die "! can't open \"c_setup.csv\" ($!)\n";
for ($i = 1; $i <= $m; $i++) {
@observations = Math::Random::random_poisson($n, $c);
$observation = 0;
map { $observation += $_ } @observations;
print SETUPCSV $observation . "\r\n";
}
close(SETUPCSV);
#
# simulate control chart monitoring
#
open(MONITORINGCSV, ">c_monitoring.csv") || die "! can't open \"c_monitoring.csv\" ($!)\n";
$m = $shiftSchedule{$shift}{"end"} - $shiftSchedule{$shift}{"start"};
if ($m < 0) {
$m += 24;
}
$m /= $inspectionRate;
for ($i = 1; $i <= $m; $i++) {
$hour = int($i * $inspectionRate + $shiftSchedule{$shift}{"start"});
if ($hour >= 24) {
$hour -= 24;
}
$minute = ($i & 0x1) ? (60 * $inspectionRate) : 0;
if ($i >= (0.25 * $m)) {
if ($i < (0.75 * $m)) {
$c = $target + ($drift * $target / (0.5 * $m)) * ($i - (0.25 * $m));
} else {
$c = $target + $drift * $target;
}
}
@observations = Math::Random::random_poisson($n, $c);
$observation = 0;
map { $observation += $_ } @observations;
printf MONITORINGCSV "'%d:%02d',%d\r\n", $hour, $minute, $observation;
}
close(MONITORINGCSV);
Source code
This media was created with MATLAB (numerical computing environment)
Here is a listing of the source used to create this file.
Here is a listing of the source used to create this file.
%
% display a c-chart control chart in MATLAB
%
clear
%
% rational subgroup size
%
n = 48
%
% Phase I
%
% compute the control chart center line and control limits based on a
% process that is simulated to be in a state of statistical control
%
setupobservations = csvread('c_setup.csv');
setupstats = controlchart(setupobservations, 'charttype', 'c', 'unit', n);
%
% Phase II
%
% read in the process observations representing the monitoring phase
%
observations = importdata('c_monitoring.csv');
%
% first column is the time of the observation (24 hour clock)
%
halfhourlylabel = observations.rowheaders;
%
% second column consists of the observations (counts of
% nonconformances per rational subgroup)
%
monitoringobservations = observations.data;
%
% just display labels on the "on the hour" ticks
%
emptylabel = cell(size(monitoringobservations,1) - size(halfhourlylabel,1), 1);
emptylabel(:) = {''};
hourlylabel = vertcat(halfhourlylabel(2:2:end), emptylabel);
%
% plot the control chart for the monitoring phase observations based
% on the "in control" estimates for the process mean
%
monitoringstats = controlchart(monitoringobservations, ...
'charttype', 'c', ...
'label', halfhourlylabel, ...
'unit', n, ...
'mean', setupstats.m, ...
'sigma', setupstats.m);
title('c chart for quality characteristic XXX')
xlabel('Sample')
ylabel('Number of nonconformances')
%
% the labels supplied to controlchart() only appear when the user
% selects a plotted point with her mouse--we have to explicitly
% set labels in the X axis if we want them
%
set(gca,'XTickLabel', hourlylabel)