Why we are writing on this topic:
Artificial intelligence will be present in all aspects of our lives. Let’s try to understand how it works, what it does and what we can expect. Also, in manufacturing.
For centuries factory workers have relied on their experience, intuition and certain paper manuals to make the necessary adjustments. It was the usual way of doing things for a long time, but human actions can be subject to error, with consequences. Dependence on experience makes employee departure a business risk. Using AI, manufacturers can address labor shortages while improving factory productivity. Without losing the benefits of human input.
Two companies with a long history of this AI-based approach show that the “connected worker” is indeed capable of much more than its less connected predecessor.
To TwentyNext, it’s all about data, says Martijn van Grieken, director of data science. “Anyone with data can recognize patterns and help companies streamline their business processes. This certainly applies to the manufacturing industry.
Recognizing patterns is one thing, but at least as necessary is the next step, says Van Grieken. “If you deploy this knowledge intelligently, you can ultimately change people’s behavior so a business can perform better. Of course, you have to do this in a transparent and positive way, otherwise it will backfire. Do it in a way that helps individual employees. This can be done, for example, by automating repetitive work. This is an improvement for everyone: the employee gets rid of tedious work, fewer errors are made and the company can increase production qualitatively and quantitatively.
Use case 1: From quality control to new behavior
For a large manufacturer, TwentyNext has implemented a quality control system. Martijn van Grieken: “Cameras and sensors constantly monitor the production process. The characteristics of the production environment – think temperature and humidity – but also the steps of the manufacturing process itself are linked to the requirements of the final product. If anything changes in these conditions, it is directly related to the quality of the final product, thanks to the data collected. You can intervene where necessary, so that’s already great. But the structural gain is deeper: you can start automating repetitive (smart) work so detected errors don’t happen again. Ultimately, this leads to a change in behavior in the factory and results in a more (cost-)efficient production process. »
“How can you increase your results by working smarter instead of working harder?” The answer to this question ultimately helps you address labor shortages, use energy more sustainably, and offset rising prices. »
Use case 2: Custom design and infinite scaling
CAD/CAM (Computer Aided Design and Computer Aided Manufacturing) design is usually time-consuming work for highly skilled workers. But it is also a task that determines the progress of the work on the floor. As many manufacturers work with more and more variables, the task becomes more and more complex. Martijn van Grieken: “Here, too, it is often repetitive (smart) work, which TwentyNext can capture very well in algorithms, mathematical formulas. So, it turns out that an algorithm can design much better than the engineer because it is able to examine thousands of checks and variants every second. This leads to designs that are cheaper, lighter, stronger and less damaging to the environment. These designs can also be made quickly and customized. You can compare our algorithm to a virtual CAD/CAM engineer creating a custom design in 30 seconds, while a live engineer would take at least 2 hours. And you can deploy as many algorithms as you want. We are very proud of this because it means that a major business bottleneck disappears and can be turned into infinite scaling.
For the next steps in manufacturing, according to Van Grieken, the same basic question applies every time: “How can you increase results by working smarter instead of harder?” By answering this question, you can ultimately solve labor shortages, use energy more sustainably, and offset rising prices. In this way, AI in manufacturing has everything to do with solving our grand societal challenges. »
This is also the mission of Laurens de Koning, vice-president of sales at 4Industry. Right from the start of the company, now four years ago, he has focused on the digitization of operational processes in the manufacturing industry. “All of these companies are working on ‘continuous improvement’, but most of the time it’s still a paper-based process. If you can digitize this, many benefits immediately arise. More importantly, you get a real solution faster, which is also easier to share with all stakeholders. »
In Industry 4.0, artificial intelligence is essential. “But the human factor remains paramount,” says De Koning. “Only with ‘connected workers’ will you get real results. The worker on the ground must be connected to the data collected by the sensors of the plant. After all, this person must convert the data into action.
Use case 3: 140 plants, 140 different processes
4Industry works for a global player in the food industry, with 140 production plants around the world. Laurens de Koning: “They do exactly the same thing in all these 140 factories, with four identical ingredients. Yet all of these factories had their own processes, so there was not much to learn from each other; through standardization, there would be benefits to be gained. We were able to change that by digitizing all knowledge, to begin with. Then the processes could be compared and, if possible, adapted to each other. This requires a change of employees, but the result is that solutions to recurring problems can be offered much earlier and are therefore resolved much faster. If, for example, the factory in Zimbabwe is down, machine learning allows us to look globally at factories that have already suffered from this problem, and the local manager can use this experience elsewhere. Always from a human point of view, but with machine learning and digital workflow that enable it. »
Labor market pressure
This is exactly where 4Industry comes in. “Our platform ensures that AI-derived actions are fetched and executed,” he says. To achieve this, De Koning and his colleagues are ensuring that all communications previously shared on paper are now digital and collected on one platform. “We digitize paper, share knowledge and improve processes.” This not only helps your own company to become more efficient, but also, for example, sister companies elsewhere in the world. For large manufacturing industry, this is an advantage that cannot be underestimated. “An error or improvement identified in one factory can easily be shared with another.”
“AI in manufacturing has everything to do with solving our key societal challenges.”
Digitalization is particularly important due to the pressure on the labor market and the high average age of workers in the manufacturing sector. “This jeopardizes the sustainability of companies. If you are not digitizing, how do you share knowledge? Older employees are retiring, but their successors are not used to a paper reality. The new generation is accustomed to the life of the application. They order their food, drinks or a friend directly from the couch. And then they walk into the factory and have to work with paper? There is a good chance that such a person will leave after a few months, with a double loss for the company: a talent is lost, and the investment in this person has been for naught.
Digitization cannot wait, which obviously requires a change of culture among people who were not used to it. “Using our platform is simple in itself. It is simply software built on one of the best Low Code enterprise platforms. In addition, you can explain the advantages very well. But you shouldn’t underestimate what such a change triggers in people. They must therefore be involved from the start.
This article is part of the AI Innovation Series, organized by the AI Innovation Center. The series focuses on the application of AI in the manufacturing industry. Learn more here.