This WSQ course aims to provide a good understanding of the fundamentals of data analytics and data mining techniques for different manufacturing applications. Participants will learn techniques for advanced clustering methods for product quality management, correlation modelling, and data pattern methods for root cause analyses and neural networks for process performance prediction.

Learning Objectives:

Fundamentals of Data Mining

• Introduction to data mining concept and applications in manufacturing
• Process correlation modelling and data pattern analyses through statistical methods
• Advanced data clustering technologies for anomaly detection and classification
• Process performance prediction using artificial intelligence (neural networks, etc)

Case Studies by Grouping Projects Using Real Production Data

• Data preparation
  • Problem statement
  • Technical challenges
  • Project objectives
  • Data collection and pre-processing
• Data analysis
  • Major factor identification by correlation coefficient analysis
  • Correlation modeling by multiple regression method and root cause analysis
  • K-means clustering and pattern based regression modelling
  • Correlation modeling by fuzzy neural networks method for quality estimation
  • What-if predictive analysis for process improvement & DOE design
  • Project conclusion
• Improvement plan
  • Identifying yield improvement areas
  • Production/process improvement plan