A benchmark software for MSPC

Version (9.79 MB) by GIEM
GUI tutorial for understanding the PCA-based Multivatiate Statistical Process Control (MSPC) strategy
Updated 8 Sep 2018

View License

A Graphical User Interface (GUI) is developed in MATLAB as a tutorial for understanding the PCA-based MSPC strategy. It uses a nonlinear model of a binary distillation column implemented in Simulink. The nonlinear model has four manipulated variables, four controlled variables and three input measured disturbances, plus 41 molar fractions corresponding to every column stage. The methodology for PCA-based MSPC is implemented in two phases. During Phase I, the user can simulate the distillation column under normal operating conditions at three different operating points. When the simulation is finished, the GUI obtains the corresponding PCA model automatically. In Phase II, the user can simulate several scenarios with different combinations of disturbances and failures and monitorize them through Squared Prediction Error (SPE) and T2 control charts. Contribution plots are used in conjunction with these control charts to check the original variables responsible of such abnormal situations.
The application allows starting a new benchmark from scratch or opening a previously saved one. User can save its progress at any time as well as export simulation results to an Excel file. Each sheet in this Excel file corresponds to a test in the benchmark. If Excel is not present, the software will attempt to write file in CSV format.
This work is part of a Master Thesis available at http://mseg.webs.upv.es/App%20Data/VillalbaT.pdf. It includes a tutorial for this software.
To start the GUI run "MSPC_main.m".
Note that, the first time the software is run, the simulation may take some time to run.

Cite As

GIEM (2024). A benchmark software for MSPC (https://www.mathworks.com/matlabcentral/fileexchange/47169-a-benchmark-software-for-mspc), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2015b
Compatible with R2009b and later releases
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes

description updated

some improvements in contribution plots

description updated

Results can be also exported to mat-file as cell arrays

Improvements in the error management routine
Automodel selection: error fixed for short simulation times (around 100 min or less) when getting observations to compute the initial PCA model
This version allows multiple instances of figures

Initially developed with R2009b. This version includes compatibility with R2014b and later

Common dialogs are used to open/save files
Standard menu and toolbar added to figures
Combos added to the score plot to change PCs
Possibility to change the number of PCs manually
Variable descriptions added to Excel file

Description updated

Example updated