How tech giants are putting machine learning to the test to improve the manufacturing process
Major companies are investing in machine learning-powered approaches to improve all aspects of manufacturing. Firms are using this technology to bring down labour costs, reduce product defects, shorten unplanned downtimes, improve transition times, and increase production speed.
Artificial intelligence will help drive the fourth industrial revolution – Industry 4.0 – with machine learning and deep learning rapidly becoming mainstream technologies. Recent developments and partnerships have shown how IBM, Microsoft and SAP, among others, are exploring the future of manufacturing.
The mission of the Europe-based Korea Institute of Science and Technology (KIST) is contributing towards globalisation of Korean research and innovation by building an open platform where notable South Korean and European institutions and industrial partners can collaborate. Manufacturing is a key contributor for both Korean and European economies and Industry 4.0 is one of the main focus areas.
IBM and KIST Europe are partners in SmartFactory-KL, which is a manufacturing facility built with modular components which can be reconfigured for different manufacturing tasks. The components in the facility are equipped with sensors and connected through the Internet of Things (IoT) to a “digital twin,” a complete digital replica of the factory’s physical assets, processes and systems, running in the IBM Cloud.
KIST Europe and IBM’s data scientists used IBM Watson Studio to design, train, test and use a machine learning model that can predict whether a given measurement is reliable.
Quartic.ai, meanwhile, has established an Industrial AI and IoT solution that enables industries to turn their assets into smart, Industry 4.0 equivalents. Quartic.ai can help manufacturers to release the stranded intelligence in their plants and enable their subject matter experts and engineers to turn their experience and knowledge into AI applications without extensive data science experience.
Rajiv Anand, CEO and co-founder of Quartic.ai, gives an example of how AI has impacted the business of their customers. He said that increasing equipment reliability is often seen from the perspective of increasing uptime. However, in the case of one large chemical processing customer, repeated failure of a shaft seal on an agitator had led to safety issues due to the leak of dangerous materials from a sealed, high pressure vessel. This is where AI came into play. Anand said that the problem could not have been solved without using machine learning models. Using historical data from past seal failures, they were able to develop machine learning models that start alerting operations staff when a seal leak is developing and is likely to occur.
SAP is specifically targeting manufacturers with a new set of products aimed at helping them manage and monitor their systems. The new offerings, part of SAP’s Digital Manufacturing Cloud, include the SAP Digital Manufacturing Cloud Solution For Execution, which integrates with existing manufacturing systems on the shop floor in order to provide visibility into operations at the component and material level.
The SAP Digital Manufacturing Cloud For Insights provides data-driven performance management capabilities. The company also announced a new ‘predictive quality’ offering, which allows predictive algorithms to be applied so manufacturers can reduce the number of defects in their products.
According to TrendForce, smart manufacturing is projected to grow substantially in the coming five years. It has estimated the global smart manufacturing market will grow at a projected compound annual growth rate of 12.5% to be well over $200 billion in 2018 and will increase to more than $320 billion by 2020.