The time is now for predictive maintenance

May 18, 2022
Zach Gilula, Pharma Machine Health Lead at Augury, discusses how machine health data enables people to do their jobs more efficiently

Zach Gilula, Pharma Machine Health Lead, Augury

A good digital strategy must start with machines. By integrating predictive maintenance into wider digital maintenance ecosystems, pharma companies can capture enormous value. Ultimately, this helps unlock the capacity necessary to get the highest quality products to patients who need them. But how does this work in practice?

Pharma Manufacturing recently spoke with Zach Gilula, Pharma Machine Health Lead at Augury, about the numerous benefits of predictive maintenance for the industry.

Q: When we talk about maintenance and reliability strategies in manufacturing, what exactly does that entail?

A: Generally speaking, we’re talking about the systems, processes and people that bring potentially lifesaving products to market. Supply chains in pharma are constantly stressed by machine failures, downtime, inefficient use of resources, and quality control. In heavily regulated industries, risk aversion often limits the ability to innovate.

Whether you’re Big Pharma or a CDMO, or you manufacture vaccines or oral solid doses, there needs to be a focus on investment to maintain and optimize equipment. Utilizing data and standards across plants ultimately lowers operational risk, increases capacity, and prioritizes both employees and patients.

Q: How would you characterize the typical maintenance strategy in today’s pharma plants?

A: It isn’t very different than what you would have seen in plants decades ago. People still get calls on Saturday nights to go back to the plant to get a machine running. There are some predictive maintenance tools (ultrasound, IR, vibration, etc.) but collecting that data and contextualizing it still limits what we can do with it. Generally, the pharma industry spends untold resources on maintaining equipment through redundancies and a heavy preventative maintenance schedule. Third-party facilities management companies love this industry because pharma pays them to take on the burden, but they face the exact same problems. What’s missed in all of this is the rich data available at the machine layer. We’re finally starting to see companies recognize it’s time for a change.

Q: Do you think pharma is lagging behind other industries when it comes to maintenance strategies?

A: Pharma is unique because it is a heavily regulated industry. Companies have to be compliant up and down the processes. Ultimately our products are going to patients who could be facing life-threatening illnesses and there’s no room for error. The industry as a whole is extremely risk averse. You’re not going to see pharma rush to adopt brand new technologies, but when the technology and value is proven, the adoption will come fast. We’re at that point with predictive maintenance and AI. The innovators are using this use-case to prove that digital transformation is happening.

Q: When it comes to pharma’s shift towards predictive maintenance 4.0, what role does data and technology play?

A: At a biomanufacturing conference in San Francisco last week, supply chain leaders described what they’ve experienced over the last couple years with COVID. Supply chains and people were stressed. One of the life jackets these leaders used to navigate a global pandemic was data. Data today should act as an driver for achieving goals, becoming more agile, and delighting customers.

The most innovative manufacturers are using data and AI to predict when a failure is going to occur, plan for resource needs (spare parts, labor), make the repair, confirm the right repair was done, and document all of this in a standardized way across their entire manufacturing portfolio. Once you reach an appropriate level of machine health you can mobilize mechanical data with operational, process and quality data. There’s pressure to create more capacity, hire more people, produce more products, etc. One of the easiest ways to do this is by unlocking your machine health data and enabling your people to do their jobs more efficiently than ever before.

Q: As pharma’s maintenance ecosystems become more reliant on smart systems and automation, are people still important?

A: If you don’t prioritize and enable your people, the best technology in the world will still fail. There has been a labor issue in manufacturing for decades and it hasn’t gotten any better with a global pandemic. Continuous improvement has led to massive achievements in automation, systems and processes. Those improvements have yielded faster drug development, higher quality products, and faster time to market. If we eliminate more non-value add activities and more risk, we will continue to see innovation accelerate. Everyone will benefit.

Maintenance and reliability professionals are spending a lot of time in react mode. Where are the failures happening? Why are they happening? How do I increase wrench-time? Do we have the parts we need? There is a hunger to know and a hunger for data.

There are workforce impacts, too. We’re at a point where the technology and ecosystems exist to help enable and upskill the next generation. Hiring is utterly competitive and with all innovation you need to consider training, upskilling and change management. You cannot separate your digital strategy from your people strategy.

Q: As companies look to manufacturing operations to achieve these efficiency goals, how are they benchmarking manufacturing performance?

A: While pharma is unique in some ways, there are generally more similarities to other manufacturing industries than differences. You need to have the data to be able to compare moving forward.

A very straightforward way to do this is utilizing a standard predictive maintenance AI tool to understand what a healthy machine looks like. You can compare the performance of your pumps in China versus your pumps in Texas. Why does one fail more often? Are our standard operating procedures the same? Different operators? Do we have different bearing suppliers? Did a specific batch have different characteristics that impacted performance? This is what the top manufacturers are asking and learning today. If you don’t have contextualized data, it becomes very difficult to benchmark.

Q: Looking ahead, what are some of the potential positive, long-term benefits of predictive maintenance for the pharma industry?

A: There are many. Our supply chains need to be more resilient because there isn’t another option. Populations are growing older, people expect transparency from the companies that manufacture drugs, and ESG will continue to dictate how we do what we do. The demand for the products we produce is expanding and we need to predictably rely on the machines that help create them. The benefits are numerous.

More reliability means more capacity. We will be able to avoid having to build new plants to reduce our carbon footprint by simply making the existing plants more efficient.

Can we extend the life cycle of this asset by slowing down the RPMs while maintaining positive outcomes? Can we reduce redundancy and CAPEX because we operate so efficiently? Does quality increase when machine health increases? The answer is yes.

When we unlock predictive maintenance data, we enable a massive opportunity for people with non-technical backgrounds to join the workforce while also evolving technical professionals to be far more strategic.

Most importantly, patients win. The patients are our family and friends, the patients are our pets! The patient is you. We all deserve the best from our industry and it starts with machine health. 

Latest from Industry Perspectives