ECCPM

“Manufacturing experts from the 1950s would easily recognize the pharmaceutical manufacturing processes of today. It is predicted that manufacturing will change in the next 25 years as current manufacturing practices are abandoned in favour of cleaner, flexible, more efficient continuous manufacturing.”

Dr. Janet Woodcock, AAPS Annual meeting, October 2011

The successful implementation of continuous pharmaceutical manufacturing systems requires a thorough understanding of the individual unit operations and of interconnected system behaviour. 

Suitable control concepts must be developed and implemented to ensure product quality and process stability. Process models and simulation tools are keys to a systematic, science-based control strategy development. 

This topic will be presented from the perspectives of a pharmaceutical company, a software solution provider and from the viewpoint of research.

ECCPM 2019

ECCPM General Information

The Challenges of Continuous Pharmaceutical Manufacturing

• Improve quality
• Improve process robustness
• Speed to market
• Platform development
• Flexible and efficient supply chains
• Make more complex products
• Personalise/precision medicine

The Drivers for Modernising Pharmaceutical Manufacturing

• Process and material understanding
• QA/QC strategy
• Real-time release testing
• Predictive modelling
• Regulatory alignment
• Economic alignment
• Human resource/expertise development

ABSTRACT

A Comparison of Machine Learning and Advanced Process Control tools for Pharmaceutical Process Development

Artificial Intelligence (AI) and Machine Learning (ML) have become ubiquitous terms in the past couple of years.  This presentation inspects and compares the current AI and ML approaches with alternative techniques that are already well established within the process industries, and now also in many of the innovative Pharmaceutical companies.

Advanced Process Control (APC) and Multi-Variate Analysis are data driven techniques to build models of the process that provide greater insight and understanding, then use those models to monitor for abnormal operational events and, more recently, directly adjust the process to achieve closed loop control of product CQAs. 

When we compare these “traditional” data-driven techniques with Machine Learning we see the same algorithms being applied and the common goal of improved decision making through data analysis, prediction and adjustment. There is a difference, however, and we’ll explore what it is within the talk.