Niels Vandervoort from J&J Innovative Medicine and Nicolas Catrysse from Siemens

Digital Process Twin cuts J&J production time & costs

When you’re in the pharmaceutical industry, a short time to market can save lives. That’s why J&J Innovative Medicine uses the Digital Process Twin from Siemens to make production more efficient.

J&J's Digital Twin: Accelerating Innovation

Getting new products onto the market as fast as possible — at J&J Innovative Medicine in Belgium — that’s not merely a question of economics; it’s often a matter of life and death. To optimize its production processes, the company set up a pilot project using a Digital Process Twin from Siemens. “The results were impressive,” says Niels Vandervoort, Senior Manager Pilot Plant Data & Systems at J&J Innovative Medicine. “The pilot project helped us make big cuts in processing times, chemical product consumption and costs.”

Scientist in lab coat examining test tube in laboratory setting

Cooking with pharmaceutical ingredients

How does a medication come into being at J&J Innovative Medicine? The lab develops a stepwise chemical plan (a process) to prepare a new active ingredient. Once the lab phase is done, fabrication is ramped up in several phases, from one liter to tens of thousands of liters in the case of commercial production. Development takes place at two Belgian facilities, the Chemical Development Mini Plant (the CDMP, in Beerse) and the Chemical Development Pilot Plant (CDPP, in Geel).

“Making chemical products is a little like cooking,” Niels explains. “You mix ingredients in a reaction vessel, and out comes something new. In the ‘cooking’ process, you have to concentrate a lot on important parameters like temperature, pressure and mixing speed to make sure you always get the right products safely and with reliable quality. We watch those parameters constantly.”

At J&J, we try to minimize the environmental impact of our production processes. That’s why we set up a pilot project with the Digital Process Twin from Siemens.

Niels Vandervoort, Senior Manager Pilot Plant Data & Systems, J&J Innovative Medicine

From dissolution to crystallization

“The reactor vessel contains a solvent in which chemical products are dissolved under the right conditions to react together in the best way. Then you have to get the newly formed chemical products out of the vessel to make the final medication,” Niels says. “To do that, it’s important to keep the new chemical products from dissolving and to make them resolidify or crystallize instead. To achieve this, the dissolving solvent is replaced by a crystallizing solvent: the solvent switch. The switch is often done by distillation or boiling. For a thousand-liter tank, that can eat up a lot of time. For instance, if a synthesis takes 80 hours in all, the solvent switch alone can use up 20 of those hours.”

“If we optimize the solvent switch, we save a lot of time and increase efficiency across the board. Any business wants to produce as efficiently as it can, but things get even more urgent where human lives are involved. An optimized switch also helps us use less chemical products. Which is important because at J&J, we try to minimize the environmental impact of our production processes. That’s why we set up a pilot project with the Digital Process Twin from Siemens – optimizing one solvent switch at first, with the ultimate goal of optimizing all switches.”

The model constantly makes predictions, which it then compares with the actual data. That lets us constantly improve the process.

Nicolas Catrysse, BD Digitalization Solutions, Siemens

A virtual solvent switch

“First we created a process model in gPROMS FormulatedProducts, an advanced process modeling platform. It’s a revolutionary software that lets us gather mechanical knowledge — how you should expect a reaction like this to proceed on a (bio)scientific basis. So the process model is actually a virtual replica of the production process, and it’s one of the basic components of a Digital Twin. Which means that at this level, our approach differs from a more data-focused model. That gives us a lot of advantages — it lets us carry out larger-scale optimizations, we need massively less data (by a factor of five), and not only can we put the changes into operation faster, but they’ll be easier to maintain,” explains Nicolas Catrysse, Business Development Digitalization Solutions at Siemens.

“After we built the model, we calibrated it with data derived from the process, meaning from real life. With that data, we built a digital application with the gPROMS Digital Applications Platform, or gDAP. That procedure takes place in an open loop. Then we looked at how the model responded to the input from the process control system, and we wound up with a closed loop. The gDAP constantly makes predictions along the way, which it then compares with the actual data. That lets us constantly improve the process.”

“I often compare it with a GPS,” Niels adds. “We’re traveling from a certain composition of solvents — location A, to another composition — location B. The model will guide us from A to B in real time by the shortest route, or the fastest one or the most ecological one. It outputs the ideal route and keeps optimizing it as a function of actual conditions — is there a detour or an accident?”

Total costs down 35%

The pilot project’s results were impressive. The Digital Process Twin made it possible to cut solvent consumption by 30%. Switch time was cut by 35% and so was total cost. “The results outdid our expectations,” Niels explains.

“The efficiency is not just economically worthwhile but also more robust. Today we’ve expanded the pilot project to four more solvent switches, where we hope to get similar results because these economies aren’t just limited to this specific use case.”

“On top of that, there are also substantial advantages when you’re setting up new processes. Just optimizing existing solvent switches is very profitable all by itself. And if we can apply the model before we expand production — meaning in the lab — we save even more time and resources. After all, experimenting in the laboratory is much less expensive than experimenting on an industrial scale. So now we’re looking at how we can use lab data to make models that we can apply later for larger-scale production.”

Running a test virtually saved us a lot of time and resources.

Niels Vandervoort, Senior Manager Pilot Plant Data & Systems, Johnson & Johnson Innovative Medicine

Apply models in a GMP environment

Using these models in a Good Manufacturing Practice (GMP) environment presents considerable challenges. Everything has to meet the GMP standards set by the U.S. Food and Drug Administration (FDA) and Europe’s European Medicines Agency (EMA). That means dealing with audit trails, versioning, data integrity, security and so much more. Nicolas: “When we apply models at a commercial production scale, we cover all the additional requirements by way of our SIPAT software platform. We can do that thanks to our knowledge of process analytical technology (PAT). SIPAT additionally has the ability to act as a central PAT quality data management system, both in the lab, at a pilot plant and on a commercial scale. That system makes these models practical, efficient and fast, with stunning results.”

Broad availability of models

“Just recently we also used the Digital Process Twin for a new process development involving freeze-drying. This was a reaction that caused the temperature inside the reaction vessel to rise, yet the temperature also had to be kept below a certain value or the reaction would fail. The process worked in the lab, but expanding to industrial scale makes the parameters change. In that case, normally we would set up a test configuration and experiment until we get the right parameters. But this time we could run the configuration virtually and the model showed that the process just wouldn’t work at all at that scale. So that saved us a lot of time and resources.”

Virtual all the way from lab to pharmacy

Digital Process Twins are very promising for the pharmaceutical sector, Niels concludes. “This is just the beginning. There are clearly a lot of ways to produce much more efficiently and with less impact on the environment. With this technology we’ll also be able to develop new processes much faster in the future, and with Siemens, we have an ideal partner to do that — thanks to their combination of software knowledge, their knowledge of our field and their experience with processes in pharmaceuticals and other sectors.

Eventually we’ll be able to use virtual models all the way from the development stage to commercial production. The time that saves us will also save a lot of lives.”

Two smiling technicians in a modern industrial facility