Transforming India’s manufacturing sector with AI

Manufacturers are racing to embrace digital technologies like artificial intelligence (AI) to bring factories into the future. These technologies are critical enablers of Industry 4.0 and will empower the manufacturing market to continue to be the backbone of the global economy.

Industry-wide, manufacturers face various challenges that make it difficult to speed production while still providing high-value and high-quality products to their customers. Companies need to implement a digital infrastructure that positions them to fully embrace the skills and knowledge of their best assets—people.

Today’s manufacturing industry relies on a combination of skilled employees and automation. But the factory of the future, which is a marriage of physical and digital capabilities, requires more real-time data, connectivity, and AI technology at the forefront.

Transforming the manufacturing sector in India

The manufacturing sector in India is expected to become an essential driver of the country’s economic growth due to the strength of strategic industries, including automotive, engineering, chemicals, pharmaceuticals, and consumer durables. Approximately 16% of India’s gross domestic product (GDP) was derived from the manufacturing industry pre-pandemic, and manufacturing is forecast to be among the fastest-growing sectors in the years ahead. India is also on route to becoming a key global manufacturing hub, with a goods export capacity worth US$1 trillion by 2030.

According to PwC’s “’Towards a Smarter Tomorrow: Impact of AI in the Post-COVID Era” report, India’s manufacturing sector has seen a 20% increase in AI and machine learning (ML) adoption over the past two years, with 54% of Indian manufacturing companies using AI and analytics. AI and ML implementations in the 12 to 18-month period following the pandemic have shown that the manufacturing segment has reaped maximum benefits from AI in three business functions: manufacturing and operations, supply chain and logistics, and IT and cybersecurity.

At a time when Indian enterprises have begun to adopt advanced analytics and data-driven decision-making and started upskilling the nation’s workforce to capitalise on next-generation AI innovations, here’s how AI can help India’s manufacturing sector move up the value chain:

Refine product inspection and quality control.

A typical manufacturing environment includes automated optical inspection (AOI) machines to identify which products meet standards and which are defective, but these machines have an accuracy rate of about 60–70%. In a school setting, this may be a passable grade, but it is not stellar. High quality is one of the predominant goals in the manufacturing sector.

Processes like AOIs can be significantly optimised when they are augmented by AI taught to recognise patterns.

High-resolution cameras with AI-based recognition software can perform quality checks at any point of the production process and accurately identify points where a product becomes defective. Is it because the machine is not functioning well? Or is it some other factor affecting the product’s quality? When we can answer these questions, the manufacturing processes become faster and more effective and produce higher-quality products. This can be especially beneficial to highly regulated industries like automotive and aerospace, which must meet stringent quality standards set by regulatory agencies.

Augment human capabilities

The ultimate goal of AI is to make processes more effective—not by replacing people but by filling in the gaps in people’s skills. By working side-by-side, the collaboration between people and industrial robots can result in higher-quality products, reduce human errors, and allow people to focus on higher-value and more strategic work processes.

Enable preventative maintenance.

Predictive maintenance analyses the historical performance data of machines to forecast when one is likely to fail, limit the time it is out of service, and identify the root cause of the problem. Yield-energy-throughput (YET) analytics can ensure that those individual machines are as efficient as possible when operating, helping increase their yields and throughput and reduce the energy they consume.

AI’s ability to process massive amounts of data, including audio and video, enables it to identify anomalies to prevent breakdowns quickly, whether it’s an odd sound in an aircraft engine or a malfunction on an assembly line detected by a sensor.

With a machine failure, production stops. Meanwhile, the use of predictive maintenance can reduce machine downtime by 30–50% and increase machine life by 20–40%. With manufacturing’s increasing reliance on machinery and the need to boost uptime and productivity, companies require much more than good luck and happy thoughts to keep production humming.

How to implement AI in manufacturing successfully

The big challenge with AI implementation, which exists beyond manufacturing, is data management. Organisations either do not have enough data or they have so much that it becomes overwhelming and not actionable. In many manufacturing environments, most can still not extract specific data from machinery. Therefore, the AI is unable to highlight patterns and outliers.

The governing principle in driving Industry 4.0 or smart factory initiatives is, “If we can digitalize it, then we can visualise it.” After we can visualise it, we can optimise it.

There is abundant data generated in the manufacturing process, and we must aggregate, prioritise, catalogue, and use the data to solve business problems. The definition of data and how we govern data are absolutely important. Data must be consistent, reusable, transparent, trustworthy, and secure. We must also have a strategy for storing and using data from both physical and logical perspectives.

Data scientists are key to successfully incorporating AI into any manufacturing operation. They are needed to help companies process and organise big data, turn it into actionable insights, and write the AI algorithm to perform the necessary tasks.

But the data scientists themselves cannot do all the work. Involvement from business owners who understand the processes involved in manufacturing and production is also crucial, as they are familiar with how each parameter and factor will influence the outcome of the AI algorithm.

Rolling out successful AI projects takes time. Think about AI as a brain; you need to train it. You probably need to have a process for the machine learning algorithm. We need the process owner and management to know this takes time. Immediate effects are not likely; it is a process.

Still, imagination is never-ending, and AI capabilities will be too. Think about our brains; they contain unlimited power.

The AI evolution will give manufacturing organisations that same power. Productivity and efficiency will be rocketed to new heights, processes will be smoother, and the possibilities will be endless.