Manufacturing

IBM joins GMIS Mission to change the future of manufacturing

Share this post:

We are delighted to announce that IBM has joined the Global Manufacturing and Industrialisation Summit (GMIS) as a founding partner. The news first broke at Think 2018 – IBM’s landmark conference, and a unique opportunity for IBMers, partners and clients to innovate together. Given our focus on the power of collaboration, it was an apt occasion for the announcement, as the GMIS is the world’s first cross-industry forum. Together, we will transform the future of manufacturing and build stronger societies, communities and businesses through innovation.

Maximizing the potential of Artificial Intelligence

We are particularly excited about this partnership, as it gives us an exceptional opportunity to maximize our leadership in AI technologies. As part of our work with the GMIS, we’ll be continuing to develop new technology applications that will underpin the manufacturing sector and drive Industry 4.0. We are already bringing Artificial Intelligence and machine learning together with our industry expertise, to help manufacturers accelerate their Industry 4.0 journeys. This means that creating a set of purpose-built offerings that support AI-powered manufacturing and enhance asset optimisation. Below, we explore some of these tools and capabilities.

AI-powered data analysis

Data is a crucial tool in helping manufacturers understand how their assets and operations are performing. The challenge is that there is a lot of it, and it comes from many and various sources across the shop floor, such as real-time data from equipment instrumented with connected sensors, digitized manuals, and databases of historical data. Because the data is so disparately generated, getting a clear picture becomes difficult, and can prevent operators from spotting patterns. Here, AI-powered and machine learning solutions come into play, by integrating data from multiple sources to establish a true and complete picture.

Perhaps the simplest example of the potential of AI within manufacturing is around equipment trouble-shooting and repair optimization. When a complex asset in a production environment fails to function as it should, it can be difficult and time-consuming to discover why. Technicians can read the instruction manual to determine how the asset ought to function or they can try reviewing past maintenance logs to understand if the problem is recurring. They can listen out for unusual noises, watch for obvious visual indicators, and, in a pinch, take the asset apart. But these methods are often slow, require tribal knowledge, and, in the case of disassembling an asset, costly. With artificial intelligence, we can speed up the process.

AI-powered diagnostics

AI-powered solutions, such as IBM Acoustic Insights, are able to interpret audio cues to determine the location and nature of a fault. These solutions are quick to train, and manufacturers are already gathering audio data from their machines, equipment and products to advanced data models. As more data is collected, the accuracy and speed of the diagnosis improves.

When you combine this data with information from an operations manual, it becomes easier to identify problems. Not only can AI-powered solutions like these identify problems faster, they can accurately determine the right fix by using machine learning to analyze unstructured data associated with repairs, maintenance, procedures and techniques. The result is enhanced insights and the ability to recommend optimum repair methods and procedures.

The IBM IoT Equipment Advisor is just such a tool. It combines machine learning techniques with Watson’s cognitive methodologies to provide insights for diagnosis and repair. By consuming varied sources of data, can spot faults and recommend appropriate fixes, thereby improving equipment availability and performance.

Watson the problem-solver: a use case from the US Army

In the video below, we hear how Watson was able help the US Army maintain its Stryker fleet. By integrating data from maintenance manuals, previous work orders and on-board sensor data, Watson could pinpoint maintenance problems, predict vehicle breakdown and recommend remedial action. All through the power of AI.

Purpose-built offerings for Industry 4.0

At IBM we are focusing on helping firms optimize both assets and operations, to eliminate unplanned downtime and improve factory key performance indicators. To support this aim, we are building a set of purpose-built applications, bringing our AI together with industry experience, to address challenges related to Industry 4.0. You can learn more about these solutions on our website. To learn more about our partnership with GMIS, take a look at our press release.

Portfolio Marketing Lead, IoT for Manufacturing

Jen Clark

Jen is an author at the Watson IoT blog.

More stories
By Brian Massey on November 19, 2018

Smart, connected fabric: how AI, IoT and Mitsufuji create safer working environments

How can you keep your company relevant and vital in today’s connected world? Can you leverage technology and analytics to advance overall safety for employees? When do you use IoT technology to gain insights into employee’s activities in near real time? How do you provide notifications and preventative measures for their safety? These are questions […]

Continue reading

By Lauren Longhi on November 9, 2018

The top 5 takeaways from the Industrial IoT World conference

From October 29-30, companies from across industries gathered in Atlanta, GA for the Industrial IoT World conference to accelerate their projects “from inspiration to implementation.” As a leader in the IIoT space, IBM was invited to share its expertise. I joined IBM five months ago, and was excited to see our capabilities in person. Here […]

Continue reading

By Binny Samuel on October 22, 2018

Why data science experimentation drags out production optimization programs

Production optimization programs aim to increase production throughput and eliminate waste by leveraging data insights. But what happens when data identification – and creating analytical models relevant to use cases – becomes a job in its own right? Can out-of-the-box templates both support production optimization and reduce the need for data science experimentation? This blog explores […]

Continue reading