normal_switch_xts

Three-feature, three-state simulated process data under normal
 operating conditions as example data for different included functions.

datasets

Use multi-state splitting to apply Adaptive-Dynamic PCA (ADPCA) to
data generated from a continuous-time multivariate industrial or natural
process. Employ PCA-based dimension reduction to extract linear combinations
of relevant features, reducing computational burdens. For a description of
ADPCA, see <doi:10.1007/s00477-016-1246-2>, the 2016 paper from Kazor et al.
The multi-state application of ADPCA is from a manuscript under current
revision entitled "Multi-State Multivariate Statistical Process Control" by
Odom, Newhart, Cath, and Hering, and is expected to appear in Q1 of 2018.

Gabriel Odom

mvMonitoring

Multi-State Adaptive Dynamic Principal Component Analysis for
Multivariate Process Monitoring

Melissa Innerst

Ben Barnard

Karen Kazor

Amanda Hering

normal_switch_xts function

An xts data matrix with 10080 rows and four columns, corresponding to
 one week worth of data recorded at a 1-minute interval, and four columns as
 defined here:<ul>
<li>state -- the state indicator for the multivariate system, with three
 levels</li>
<li>x : x(t) = t + error</li>
<li>y : y(t) = t ^ 2 - 3t + error</li>
<li>z : z(t) = - t ^ 3 + 3t ^ 2 + error</li>
</ul>where t is a 10080-entry vector of autocorrelated and non-stationary hidden
process realizations. The states alternate each hour and are defined as
follows:<ul>
<li>State1 -- As presented</li>
<li>State2 -- Rotated by (yaw = 0, pitch = 90, roll = 30) and scaled by
 (1 * x, 0.5 * y , 2 * z).</li>
<li>State3 -- Rotated by (yaw = 90, pitch = 0, roll = -30) and scaled by
 (0.25 * x, 0.1 * y , 0.75 * z).</li>
</ul>See the vignette for more details.

Format

Process Data under Normal Conditions — normal_switch_xts

Process Data under Normal Conditions

normal_switch_xts: Process Data under Normal Conditions

Description

Usage

Arguments

Format