Optimize Plant Performance using multivariate data analysis

Course Id:  PMV101   |   Duration:  2.00 day(s)   |   CEUs Awarded:  1.4   |   Level:  Introductory


Course Objective

Manufacturers are collecting more data than ever but face the challenge of deriving useful information from these large data sets. Part of the challenge is understanding the relationships amongst all the available variables (raw materials, process conditions etc.) and how these relationships impact process performance (yield, final quality etc.). Aspen ProMV finds the independent driving forces affecting process performance and effectively extracts actionable insights from available historical data. Learn how to use this desktop software on your historical process data to improve understanding of key process relationships.

Benefits

  • Gain the practical skills and knowledge to use multi-block modelling to model your process.
  • Improve understanding of key process relationships
  • Identify key contributors to poor process performance
  • Troubleshoot and correct recurring process problems
  • Optimize process performance

Audience

Engineers / scientists / statisticians responsible for process troubleshooting, control and optimization

Approach

  • Clear guidance on fundamental topics
  • Multivariate analysis workflows
  • Hands-on software labs
  • Experienced instructor-guided demonstration

Prerequisites

Some familiarity with the Empirical Modeling is helpful but not essential.

Class Schedule

Class Agenda

PMV101: Optimize Plant Performance using multivariate data analysis

Latent Variables: Motivation & Concepts

  • Nature of historical data
  • Why latent variable models?
PCA: Principle Component Analysis
  • Geometric and algebraic interpretations
  • Goodness of fit & goodness of prediction
  • PCA tools: score & loading plots, analysis of residuals
  • Model interrogation: contribution plots
  • Calculating the principal components
PLS: Projection to Latent Structures / Partial Least Squares
  • MLR->Principal Component Regression->PLS
  • PLS: Geometric & algebraic interpretations
  • PLS tools: score & loading plots, analysis of residuals
  • Model interrogation: contribution plots
  • Calculating the principal components
Multivariate SPC
  • A multivariate approach to process monitoring (MSPC)
  • Detecting & diagnosing abnormal operation
  • Interpreting and Optimizing processes using Empirical Models Correlation vs. causation
  • Soft sensors and inferentials
  • Model Explorer - visual exploration of the models
  • Model Optimizer – optimizing processes based on models from historical data
All the sections have workshops using Industrial process data

Aspen Technology, Inc. awards Continuing Education Units (CEUs) for training classes conducted by our organization. One CEU is granted for every 10 hours of class participation.