Life sciences may be the ideal industry for the implementation of AI technologies. After all, bringing a treatment all the way through the drug development process is an extremely complicated undertaking, with tremendous amounts of data and a wide array of ever-changing variables to manage. Moreover, every step must be made with an eye on validation, ensuring products align with Good Manufacturing Practice standards.
For decades, the manufacturing execution system (MES) and distributed control system (DCS) have been central to accomplishing these goals in traditional life sciences manufacturing, and they aren’t going away any time soon. However, an MES and DCS are designed and operated very differently.
“Unlike in a DCS, where a PID loop is often designed in a predetermined way, very similar to others, many elements of an MES are tailored to the unique ways individual organizations run their businesses, so the workflows and rules incorporated within workflow elements vary from one organization to another.”
As Emerson’s Kristel Biehler explores in her most recent article in Control Engineering magazine, though the systems are different, teams must have easy ways to navigate those differences to efficiently, safely, and effectively bring new treatments to market. There’s a catch, though. Today, companies have far less access to expert personnel to manage and maintain the MES and DCS, so one of the key competencies of managing those systems to drive faster release and increased operational excellence is finding ways to streamline recipe creation.
AI to the rescue
Enter AI. With its ability to rapidly sift through, sort, and comprehend data, AI software can support personnel as they develop recipes and shepherd them all the way through to commercial manufacturing. But there’s a catch:
“While there are AI-based recipe creation tools available today, most of these are designed specifically for simple MES solutions, and not for easy integration with the rest of the value chain. This means that many AI technologies are not able to handle the most complicated treatment development processes. They are often much better suited to small scale research and development where fewer requirements need to be embedded within workflow objects, but struggle when a company is ready to move to large scale manufacturing subject to full Good Manufacturing Practices, which includes implementation of risk mitigation strategies, often built into a traditional MES solution.”
Kristel shares that teams looking for new AI software to bolt onto their automation architecture are looking at life sciences technologies from the wrong angle. While some bolt-on solutions can be effective, the most powerful and interoperable tools are those already being built into modern automation software. In short, the most effective, comprehensive solutions are not bolt-on but rather built-in. Modernization is the key.
A seamless ecosystem for AI
At the heart of that modernization is an automation infrastructure built around an enterprise operations platform (EOP). Emerson’s automation solutions for life sciences, including DeltaV™ MES, DeltaV DCS, DeltaV Process Knowledge Management (PKM), and more have AI solutions built in. That, Kristel explains, provides significant value for manufacturers.
“Iterative design helps ensure new AI technology does not require countless hours of new training but instead operates seamlessly as an intuitive part of the workflow and systems that users already know. More importantly, those same AI tools will be built on decades of institutional knowledge, providing more reliable answers, and supplying guardrails based on the principles that help life sciences organizations protect their business interests and the investments they have already made in their automation infrastructure. In instances where the MES is already designed to integrate seamlessly with other critical systems—DCS, PKM, ERP, etc.—the AI technologies will interact seamlessly with those systems as well, making it possible to scale more efficiently and effectively.”
The seamless data fabric provided in the EOP and driven by Emerson’s Boundless Automationsm vision and Inmation™ data fabric help drive contextualized data across all the applications necessary at every stage of the treatment development lifecycle. This data superhighway easily, intuitively, and securely moves critical, contextualized data where it needs to be, eliminating the data silos that can be created by external systems and AI software.
AI is opening new vistas of opportunity for life sciences manufacturing, but only if it is applied thoughtfully and effectively. Like any software, AI tools have the potential to create silos of data that lead to reduced visibility and manufacturing roadblocks. Forward-thinking organizations are pursuing AI strategies built around embedded industrial AI to help ensure effective implementation, faster ROI, and increased operational excellence across their enterprises.
