Manufacturing

Predict Process Conditions with Digital Twin in Manufacturing

By Holger Amort, MSAT Data Analyst, TQS Integration, A Cognizant Company

For a life sciences manufacturer seeking to predict process conditions, digital twin might just be the answer they’re looking for.

Digital twin is a term with several different definitions and it is often used interchangeably with terms such as Industry 4.0 or the Industrial Internet of Things (IIOT). Fundamentally though, digital twins are digital representations of a physical asset, process or product that behave similarly to the object they represent. It’s a concept that has been around for a long time. 

Earlier models were based on engineering principles and approximations, but they required very deep domain expertise, were time consuming and limited to a few use cases. Today, digital twins are virtual models that are built entirely by using massive historical datasets and machine learning (ML) to extract the underlying dynamics. 

Building a digital twin requires:

  1. A large historical data set or data historian
  2. High data quality and sufficient data granularity
  3. Very fast data access
  4. A large GPU for the model development and real time predictions
  5. A supporting data structure to manage the development, deployment, and maintenance of ML models


This data driven approach makes digital twins accessible for a wide range of applications. Therefore, the potential for digital twins is enormous in areas like process enhancements and optimization, equipment life cycle management, energy reductions, and safety improvements. Other digital twin benefits to a life sciences manufacturer include:

  • Replicate and track manufacturing processes to more efficiently monitor attributes for FDA regulations
  • Improve data Integrity through access to secured and audited data 
  • Move to PAT continuous manufacturing from batch manufacturing 
  • Enhance productivity and reduce downtime
  • Secured data transfer between CMOs and tier 1 manufacturers
  • Reduce in infrastructure costs by moving data to the cloud


The following shows how a digital twin could be applied to a batch process. The model is built with 30 second interpolated data using a window of past data to predict future (5 min) data points:

Cognizant

Digital twin may deserve the hype that currently surrounds it. They do more than predict process conditions, by also providing explanatory power on what drives the process -- the underlying dynamics. This dashboard shows a replay of this analysis including the estimate of the model weights.

The availability of enterprise level data historians and deep learning libraries allow digital twins to be implemented on the equipment and process level throughout manufacturing. The technology offers insights into process dynamics that were not previously available, improving data integrity and data access while achieving trust and data transparency with your partners. This helps to digitalize data management and processes to lower risk and improve efficient data sharing with partners.

Please contact us for more information or visit us here to learn more about Cognizant’s Manufacturing Solutions.

The editorial staff had no role in this post's creation.