Artificial Intelligence (AI) in Manufacturing

Many see artificial intelligence (AI) in manufacturing as a major part of what is being termed a “new industrial revolution.” This next stage of industrialization is being driven by robotics, digitalization, and AI.

Combined, they make it possible to automate a great many time-consuming manual tasks, integrate information technology (IT) and operational technology (OT) systems, raise efficiency markedly, improve product quality, heighten supply chain visibility, and optimize inventory management. 

AI in Manufacturing Today

Manufacturers are leveraging AI to improve day-to-day operations, launch new products, customize designs, and plan their future financials. An MIT survey revealed that about 60% of manufacturers are already using AI. 

But AI usage is happening more in some parts of the world than others, with the U.S. lagging behind. Capgemini studies show Europe to be in the lead. 51% of European manufacturers are implementing AI, compared with Japan at 30%, and the U.S. at 28%. The two most common use cases for AI in manufacturing, according to Capgemini, are maintenance and quality control.

Another study highlights how manufacturers now regard AI. EY interviewed more than 500 CEOs from leading manufacturing firms across the world. 86% of CEOs acknowledged that AI was crucial to success. But only 30 of them have been able to scale AI and other emerging technologies to drive business value.

“Manufacturing data is a good fit for AI/machine learning,” said Cem Dilmegani, the founder of AI Multiple, an AI analyst firm. “Manufacturing is full of analytical data which is easier for machines to analyze.”

5 Examples of AI in Manufacturing

1. Improving manufacturing processes

AI is being used inside many manufacturing operations to streamline processes and improve productivity. For example, textile company Lindström worked with QPR to harmonize and enhance business processes and a process management model to ensure future competitiveness and success. 

“We choose QPR to help execute our vision of having the fastest and most reliable processes in the industry,” said Harri Puputti, senior vice president of corporate quality at Lindström Group. 

2. Plant productivity 

A digitalization platform from Mitsubishi Power known as Tomoni encompasses controls, instrumentation, data analytics, AI, and more. It is aimed at making plants smarter. The average power plant, for example, has nearly 10,000 sensors that can generate over a million points of data every minute. Tomoni takes this confusion of data and puts it into a usable form. 

Tomoni is a suite of digital and AI solutions that can help create an increasingly smart facility that will become capable of various levels of autonomous operation. Increased digitization of interconnected devices and systems assists control systems to do more and interface more effectively with advanced analytics. 

3. Preventive maintenance

Compressor manufacturer and oil and gas solutions provider Baker Hughes is harnessing AI to identify maintenance issues. The company partnered with Microsoft Azure and an AI company called C3.ai to create an AI-based application that allows operators to view real-time production data, better project future production, and optimize operations for improved production rates. 

The application continuously uses machine-learning (ML) algorithms to quickly aggregate historical and real-time data across production operations and creates a virtual representation of production across the value chain. It also detects anomalies, forecasts production, and prescribes actions to improve production performance. Engineers can use it to pinpoint which injection wells to tune for higher production output.

Shell, for example, is using the C3.ai platform on Microsoft Azure to accelerate digital transformation across its business, improve efficiencies, increase safety, and reduce environmental impact, according to Jay Crotts, CIO of Shell Group. The company is also using AI to implement predictive maintenance and the monitoring of half a million valves.

4. Product design

Original equipment manufacturer, Sentry Equipment, evolved its SentryGuard sampling machine to provide guidance to operators using the Aveva System Platform to slash development time. It provides the ability to analyze sample data, provide alerts, and guide operators to resolution.

“Data collection was not as easy as we thought. AVEVA System Platform simplified that complexity, allowing us to focus on the value-add of our SmartAlarm application rather than figuring out how to collect data and present it,” said Richard Alves, development engineer at Sentry Equipment. “It saved us as much as 80% in engineering time.”

5. Zero touch and zero defects 

The more people working on an assembly line, the more opportunities there are for errors to creep in. Therefore, automation and robotics are being introduced by many manufacturers to eliminate errors. But that takes AI to ensure that even the slightest deviation from standard practices and workflows is detected at once.

“When combined with other digital technologies and standard ways of working, AI will drive and enable zero-touch operations and zero defects,” said Sachin Lulla, global digital strategy and transformation leader at EY.