Skip to main content
Cover Image

Best Practices in Data Collection for Successful Manufacturing Intelligence

Robust Manufacturing Intelligence (MI) capabilities are fundamental to successful manufacturing enterprise management. And robust MI capabilities start with sound data collection practices. The analytics feeding management dashboards will work with any properly formed data that can be drawn from manufacturing databases. However, if that data is compromised, the decisions made by management based on the compromised data may be faulty and put the organization at risk.

The key to world-class, sound decision making is a solid data collection foundation. This webinar examines data collection best practices:

  • The requirements standards such as ISA 95, FDA Q10, and ISO 9001 and good manufacturing practices place upon the data collection process.
  • The business implications of poor data collection.
  • What data collection best practices should be implemented:
    • Operator workflow support
    • SOP enforcement
    • Input error reduction
    • Data integrity
  • How data collection integrates with manufacturing management systems

The end result is compliant process and testing data collection that dependably provides high-quality data to feed the analytics that informs MI. Data collection with integrity is a core requirement to make MI work while keeping auditors and customers satisfied.

 

About the Presenter:

Jeffery Cawley is VP of Industry Leadership at Northwest Analytics where among other roles, he investigates how process based analytics solve the problems imposed by modern manufacturing and testing activities, and how to employ process management methods to meet regulatory and commercial standards and good practices. In addition to his work at Northwest Analytics he has served two terms on the AOAC Statistics Committee and twelve years on the executive board of the Institute of Food Technologists Quality Assurance Division. He is a frequent speaker and writer on applying process analytics and management methods to testing and manufacturing.