The global pandemic has persuaded a number of manufacturers to pursue an AI-driven transformation of their operations, according to studies by Cap Gemini and the Boston Consulting Group. What has been noticed is the way in which they are combining human experience and insight with AI tools to find ways to differentiate themselves from their competitors, as well as drive down costs and protect their profit margin. So, what are the most popular ways of using AI in manufacturing industries?

AI and real-time monitoring

The ability of AI to monitor operations in real time offers a number of benefits, including “troubleshooting production bottlenecks, tracking scrap rates, meeting customer delivery dates, and more,” as Louis Columbus writes in Forbes. Use of AI in this scenario also assists with gathering data that can then be used to develop other machine learning models that may be supervised, or unsupervised, in their use.

AI adoption trends

The recent Cap Gemini report Scaling AI in Manufacturing Operations: A Practitioners Perspective analyses the primary ways in which manufacturers have adopted AI over the last few months – so let’s take a look at a few of them.

Some 29% of manufacturers are using AI for machinery maintenance and production, and this has proved to be the most popular use. Why? Because AI tools can alert management about when machinery is about to fail in some way. For example, General Motors analyzes images from cameras mounted on assembly robots, to spot signs and indications of failing robotic components with the help of its supplier.

Phone manufacturer Nokia has introduced a video app that uses machine learning to alert an assembly operator if there are inconsistencies in the production process. Furthermore, the issues are spotted in real time.

AI-based image recognition software and technologies are being used for real-time in-line inspection. This has been adopted by Audi, which installed an image recognition system based on deep learning at its Ingolstadt press shop.

AI is also being used by the French Danone Group to deliver accurate forecasts of demand for its products. They’re using machine learning to improve planning coordination across marketing, sales, account management, supply chain, and finance, and this has led to a 30% reduction in lost sales and a 50% reduction in demand planners’ workload.

Machine learning tools are also being deployed in the maintenance of high-speed rail lines across Europe. Thales SA has developed an AI algorithm to predict potential problems and identify when specific parts need to be replaced, which has proved to be successful as the rail industry has achieved zero unplanned shutdowns.

There are many more examples, and Columbus’ article has a number of excellent references you may wish to read if you are interested in how AI and machine learning is going to improve manufacturing industries now and in the future.

This article is republished from hackernoon.com