Rewiring the manufacturing process through Industry 4.0 technology
Embedding new age technologies, Fourth Industrial Revolution (Industry 4.0/ 4IR) technology helps in effectively optimising the manufacturing process. This requires strengthening of an organisation’s Operating Technology (OT) and Information Technology (IT) layers. Connecting these capabilities to manufacturing will help businesses collect real time data through the implementation of Industrial Internet of Things (IIoT). Developing such Advance Analytics (AA) models can help ingest data, provide insights, and enable the organisers to make decisions in real-time. Therefore, through inputting algorithms into AA models is one of the fundamental benefits of leveraging Industry 4.0 technology such as IIoT. To understand this better, we must look at how the process works.
Demonstrating improvement in business output
Machine setting is a crucial factor in the course of drug production. It is historically judgment-driven, based on the experience of the operator. Factories with a classical machine setting come with instructions but the turn-around time of setting up the cycle time of the machine for different formulations gets impacted by the skillset of the operator. In fact, setting up the cycle time can take anywhere between 15 mins-2 hours, depending on the operator’s experience. This setup needs to change for every new formulation. However, when you can derive insights from the data you have amassed, setting parameters for determining the accurate machine settings (such as the material properties to be inserted based on the product, size of the tablet, etc.) gets optimised. Conventionally, this data has been available to pharma companies, however, it doesn’t get used effectively owing to the absence of such AA models. Through the deliberate shift towards data-backed prescribed parameters, AA models are enabling analytics to drive business value; be it cost production, or improved people and equipment productivity.
The same application can be done for enhancing quality and yield – By looking at the analytical and qualitative performance of every product in real time it is possible to predict from the parameters of the ‘golden batch’ (the ideal batch that is perfect from all processing parameters and has given the highest quality product), the progress of the upcoming batches. This can enable pharma companies to tweak the process in real time and ensure they have the output and most robust or repeatable product. This has the potential to achieve a 2–3 year improvement in process capability.
In essence, deploying such AA models across the spectrum of a business can enhance their productivity, costs, quality, delivery, and environmental sustainability.
Transitioning toward a future-ready workforce
As a sector, while we have historically generated a lot of data, we have never had the wherewithal to produce insights from them. Hiring the right talent and vetting their capabilities becomes one enabler in the journey of evolving the business’ workforce. Conventionally, the pharma sector has been used to recruiting employees from a very different talent pool; limited to manufacturing operators, mechanical/ electronic engineers or pharmacy/ life science students. The industry is now beginning to invest in data scientists and data engineers, given the need for different skillsets to handle and analyse big data.
These two distinct functions will play a pivotal role in building factories of the future. Data engineers will integrate and manage the complex pipeline of the OT and IT layers. Once all the data is uploaded onto the cloud, then comes the function of the data scientist who will perform advanced statistical analysis on the data that comes in and compute the same to derive insights. These insights will aid in modifying algorithms and building AA models that will be able to predict how a product will behave and from there, prescribe the process that would need to run within required parameters. The process of going from data collection to analytics to predictions and now prescriptions is a big transition the pharma industry is making in terms of optimising operational and workforce efficiency.
The second enabler is upskilling the current workforce. In touchless factories, it will be important for the existing workforce to be able to learn how to consume data. Investing in their upskilling will qualify them to work closely with the data engineers and scientists to provide inputs which in the grand scheme of things will significantly improve operational time.
Delivering on the promise of sustainability
Sustainability is no longer a ‘trend talk’ when it is inherently ingrained into the business. Industry 4.0 is directly related to social sustainability performance and therefore, its incorporation into manufacturing will warrant sustainable output. Digital analytics, automation and digitisation are key advancements that will help support progress across the 3 scopes of sustainability. Its important to clearly carve out the deliverables for each of these technologies within each scope. Optimising energy consumption through digital tools can result in up to 25-30% savings on energy consumption. Pharma companies are also looking at circularity from the components we use. For example, water is going to be the most constrained resource of the future. To mitigate this, the industry has been able to progress with the use of improved processes through digital automation to recycle up to 80% of water and reuse them in the production process, apart from also creating recharging/harvesting watersheds.
It is my belief that the advancement of the industry through touchless factories will begin with the early adoption of Industry 4.0 to achieve early success. The continuity of these successes will encourage industry peers to also upgrade, which will accelerate the growth of touchless manufacturing ecosystems in the country, putting us at a globally competitive advantage.
The writer is Global Chief Technology Officer, Cipla
