Endi-QM | Energy efficiency through intelligent in-process quality monitoring

The project Endi-QM aims to significantly reduce the primary energy consumption in the hybrid injection moulding process. This goal should be achieved by analyzing data of the entire production cycle through the application of various data-driven and AI-supported methods and tools based on an IoT edge platform, on which the recorded data can be managed and processed in an orderly and secure manner.

Coordination: Arthur Stobert M.Sc. (ETA)

Duration: 01.05.2022 – 30.04.2025
Funded by: Federal Ministry of Economic Affairs and Climate Action

Motivation

The growing demands for energy efficiency and reducing of CO2 emissions in industrial production are currently big challenges for the whole industry. To achieve the goal of being climate-neutral by 2045, enshrined in the Climate Protection Act, manufacturing companies must take on more responsibility. Novel technologies in digitalization and Big Data provide great potential for companies to maximize the value of production information and simultaneously optimize the production process, making it possible to fine-tune management and resource optimization. Meanwhile, more resource- and energy-efficient production processes are realized.

The current development of IoT technology and computing power are empowering manufacturing companies to store and process production data in real-time via cloud or edge solutions. With the help of AI techniques, companies could gain the ability to monitor the state of production more accurately or make a better plan for the maintenance schedules. Therefore, the Endi-QM project strives for an intelligent, fully controllable, and energy-efficient hybrid injection moulding process.

Objectives & Approaches

The main objective of the Endi-QM project is to optimize the production process and reduce the primary energy consumption based on the collected data of the entire production process, from the receipt of raw materials to the quality control of the final products. To achieve this goal, the following objectives should be pursued, which require the control of the process and access to data of the entire production cycle:

  • An obvious waste of resources and energy is due to the rejection of produced parts since a scrap part wastes raw material, energy and time. Furthermore, the additional resources for the disposal of the scrap part should not be neglected. With the assistance of AI-supported methods, the process parameters will be self-adapted and continuously optimized so that the manufacturing quality can be constantly improved and energy consumption can be reduced at the same time.
  • Another valuable aspect of optimizing production is machine maintenance. The maintenance strategy greatly influences the reliability and productivity of a plant or process. In this project, condition-based maintenance is focused by means of the selected sensor technology on the machine. The goal is to increase productivity and reliability by avoiding unexpected downtimes. However, for some relevant machines or components, purely condition-based maintenance is insufficient. It is more helpful to quantify and estimate the RUL (Remaining Useful Life). The expected remaining service life of components and wear parts can be estimated using a predictive model from the machine's condition data.
Design of the IT-infrastructure for data acquisition, modeling and optimization
Design of the IT-infrastructure for data acquisition, modeling and optimization
Key innovation points in this project
Key innovation points in this project

Acknowledgement

This project is funded by the Federal Ministry of Economy and climate protection (BMWK). We are thankful for the opportunity to work on this project.

Funding source

Consortium partners