According to the company, its sensXPERT technology assesses machine, mold and material data in real time and uses machine learning software to analyze the material behavior.
The in-mold sensors can provide real-time insights and transparency to react to material deviations and eliminate scrap, increasing efficiency by up to 30%, Netzsch said.
When used in the manufacturing of automotive composite wheels and airplane wing components, there have reportedly been significant increases in overall equipment efficiency (OEE), including solid return of investment (ROI).
sensXPERT features an edge device which integrates hardware and software to make machine learning models that can capture small deviations of material and process parameters. Based on measuring data collected from in-mold sensors, smart machine learning algorithms are applied to simulate, predict and analyze material behavior on each individual machine. The learning models are trained with key parameters, including standard material and experimental data, such as glass transition temperature, pressure and required degree of curing, and are then continuously fine-tuned depending on the in-situ data measured over time.
According to Netzsch, the technology can work with any common thermoset, thermoplastic or elastomer processing techniques, including injection, compression and transfer molding, thermoforming, vacuum infusion and autoclave curing. It can connect with users’ existing manufacturing and control systems through standard industrial interfaces and is offered as a cloud-based equipment-as-a-service (EaaS) solution. An intuitive web app is also available for convenient on-site or remote user access.
“There is a growing need for digital technology solutions in the plastics processing industry to meet the challenges of tighter cost control, total quality assurance and enhanced sustainability,” said Dr Alexander Chaloupka, managing director & CTO. “By using the artificial intelligence of our machine learning software to evaluate critical material, machine and process data, we help our customers optimize their manufacturing efficiency in real time, eliminating the need for time and labor consuming retroactive adjustments.”
