Process Optimization in Injection Molding Using AI to Reduce Scrap

From Dipl.-Ing. Annedore Bose-Munde 3 min Reading Time

Related Vendor

Artificial intelligence is transforming plastics processing: It contributes significantly to process optimization. At the VDI PIAE (Plastics in Automotive Engineering) Congress, a demonstration will show how this works in injection molding

Through a comparison process, the actual data is compared in real time with the ideal digital parameters during production. This means that deviations become immediately apparent. The AI essentially acts as a “virtual machine setter.”(Bild:  plus10 GmbH)
Through a comparison process, the actual data is compared in real time with the ideal digital parameters during production. This means that deviations become immediately apparent. The AI essentially acts as a “virtual machine setter.”
(Bild: plus10 GmbH)

Digitalization and the use of artificial intelligence (AI) are not merely trends, but essential factors in process optimization in plastics processing. At the VDI PIAE (Plastics in Automotive Engineering) Congress, it will be impressively demonstrated how AI contributes to increased efficiency in injection molding.

On March 18 and 19, the PIAE Congress will open its doors at the Kongresshaus Baden-Baden to once again highlight the importance of plastics in automotive engineering. This year, for the first time, the event will feature in-depth “Spotlight” sessions on current topics.

In total, visitors can expect 50 expert presentations from OEMs and suppliers, covering topics ranging from recyclable materials and lightweight construction to AI-supported processes and new manufacturing concepts. A key focus will be the effective use of AI in the injection molding of technically complex parts.

KI-Tolo as a Virtual “Machine Setter”

“Learning a complex process model solely from the approximately 700 live data points of an injection molding process—that is, without manual modeling—offers many opportunities for real-time process optimization,” says Felix Georg Müller, CEO and co-founder of Plus10 GmbH.(Bild:  plus10 GmbH)
“Learning a complex process model solely from the approximately 700 live data points of an injection molding process—that is, without manual modeling—offers many opportunities for real-time process optimization,” says Felix Georg Müller, CEO and co-founder of Plus10 GmbH.
(Bild: plus10 GmbH)

Felix Georg Müller, CEO and co-founder of Plus10 GmbH, a spin-off of the Fraunhofer Institute for Manufacturing Engineering and Automation IPA, explains the benefits of intelligent optimization tools. “The tool suggests situational adjustments to machine settings. These are based on high-frequency process data combined with contextual data on raw materials and environmental conditions. The goal is to prevent scrap,” explains Müller. The live-learning optimization tool Hopper is an example of how AI can function as a “virtual machine setter” by analyzing data in real time and making predictions before errors occur.

AI processes data and optimizes parameters in real time during the process

Müller emphasizes: “Learning a complex process model based solely on the approximately 700 live data points from an injection molding process and the associated peripheral equipment—that is, without manual modeling—is very exciting and offers many opportunities for real-time process optimization.” He will demonstrate two practical examples at PIAE: a two-component injection molding machine for PC-TPE parts and another example involving COC injection molding with an insert. “In both examples, I’ll show how the Hopper optimization tool learns a process model and optimizes it ‘on the fly,’” Müller explains.

AI tool with versatile applications

The Hopper AI tool is already being used in the injection molding of both thermoplastic and elastomer components. Müller explains: “In general, injection molders can use the Hopper AI tool to manufacture sophisticated materials—some of which are difficult to process—where even the slightest fluctuations in raw material quality can lead to scrap during continuous operation.”

Freudenberg, for example, uses it to manufacture radial shaft seals. Other applications include typical engineering plastics such as PA, PBT, PEEK, PC, POM, TPE, and COC/COP.

The use of AI reduces scrap by 6 to 18 percent

Müller highlights the economic benefits: “Feedback on real-world injection molding applications using the Hopper shows a reduction in scrap ranging from 6 to 18 percent. Specifically, this means that the yield rate increases, since both scrap and cycle time can be actively optimized.”

The continuous optimization cycle of the Hopper AI tool.(Bild:  plus10 GmbH)
The continuous optimization cycle of the Hopper AI tool.
(Bild: plus10 GmbH)

In addition, tool changeover time can be reduced by about 30 minutes, as the machine is immediately configured with a parameter set tailored to the current material batch. This minimizes the need for manual fine-tuning. “This eliminates the need for time-consuming manual fine-tuning, which is particularly difficult for less experienced staff,” said Müller.

Addressing the Skilled Labor Shortage with AI

AI tools like Hopper are not only crucial for efficiency and product quality, but also help address the shortage of skilled workers in the industry. They offer versatile applications and significant cost-saving potential, as the PIAE Congress will impressively demonstrate.

Subscribe to the newsletter now

Don't Miss out on Our Best Content

By clicking on „Subscribe to Newsletter“ I agree to the processing and use of my data according to the consent form (please expand for details) and accept the Terms of Use. For more information, please see our Privacy Policy. The consent declaration relates, among other things, to the sending of editorial newsletters by email and to data matching for marketing purposes with selected advertising partners (e.g., LinkedIn, Google, Meta).

Unfold for details of your consent