The processing of post-consumer recycled materials, PCR, remains one of the key technical challenges for the plastics industry. As the recycled content in a product increases, variability in material properties also rises, which in practice translates into lower stability of the injection molding process and higher scrap rates. In the Rezi-AI research project, the SKZ plastics center and AI specialist plus10 are developing a data-driven solution intended to automatically stabilize such process fluctuations. The aim of the project is to use process engineering tools to bring the stability of PCR material processing to a level comparable to that of virgin material processing. To achieve this, predictive AI models are used to calculate the probability of scrap in real time based on process and material data. On this basis, dynamic recommendations for adjusting process parameters are generated. The solution is intended to stabilize part quality, optimize cycle times and reduce energy consumption. According to the project assumptions, it is also meant to strengthen the economic viability of the industrial use of recyclates and contribute to reducing the carbon footprint in plastics processing.
A networked injection molding cell as a data source
For the purposes of the project, SKZ built a fully networked injection molding cell in which all process-relevant data is recorded and consolidated with cycle-by-cycle precision. This includes both machine data and information from the hot runner system, mold and temperature control systems, as well as quality parameters such as demolding temperature and part weight.
In addition, energy consumption by individual major consumers is recorded to enable a comprehensive data-driven evaluation of the entire process. Data communication is based on full integration of the OPC UA and MQTT standards, which enables direct feedback between process parameters and part quality.
Mold technology and cavity-level control
In cooperation with mold maker GHD Präzisionsformenbau, a special 2-cavity block mold was developed, designed specifically for investigating material variability. An integrated flow indicator enables differentiated analysis of material behavior during filling.
The Ewikon hot runner system used was equipped with a servo-electric needle valve controlled by the motion Control system. As part of the project, this valve was additionally opened for external software-based control.
This makes it possible to compensate for material fluctuations and differences in filling not only through conventional machine parameters, but also individually for each cavity through the needle stroke of the hot runner system.
Clamp modules with flow indicators for developing AI-based control systems when using post-consumer recycled materials in the Rezi-KI project (Photo: Jakob Schüder, SKZ)
Integration of material data and digital infrastructures
Another area of the project is the integration of material data. Since recyclate batches are naturally subject to greater fluctuations, batch-specific measurement values are incorporated directly into the AI models. In the future, this data is planned to be made available directly by material suppliers via API-based interfaces.
This approach is intended to be supported by emerging industrial data spaces developed, among others, within Manufacturing-X and initiatives such as MaterialDigital.
First demonstration during the SKZ Technology Day
Project manager Jakob Schüder emphasizes the significance of the initiative: "Rezi-AI demonstrates how artificial intelligence can play a key role in sustainable plastics processing. Our goal is to make the processing of post-consumer recyclates just as stable and efficient as virgin material processing, despite sometimes significant material fluctuations. We would like to extend special thanks to our project partner plus10, whose expertise in AI and software significantly supports this innovative approach."
The ongoing test series are currently being used to validate the developed AI models.
The first results of AI-supported process control are to be demonstrated using the block mold during the SKZ Technology Day, which will take place on June 25, 2026 in Würzburg.
