Early fault detection for all injection molding machines
Reduction of machine downtimes
By detecting anomalies in injection molding machines at an early stage, condition monitoring can prevent both unwanted machine downtimes and unnecessary rejects.
In the plastics cluster project “ReGuMa – Reduction of planned and unplanned machine downtimes”, one or two defined error cases were analyzed at each company partner and the possibility of preventing unplanned downtimes was evaluated.
The aim was early fault detection for all types of injection molding machines using non-invasive sensors and intelligent evaluation of the sensor data.
Project partners: AISEMO GmbH, Aspöck Systems GmbH, Ing. Gerhard Fildan GesmbH, Ing. H. Gradwohl GmbH, MKW Kunststofftechnik GmbH, PTM Kunststofftechnologie GmbH.
Requirements
- Early detection of faults on injection molding machines
- Sensor data collection on various types of injection molding machines
- Evaluation of the sensor data
- Project management of the cluster coordination project
Solution
- Hardware
- Support with data analysis
- Coordination of cluster cooperation project
Success story “15% increased productivity through intelligent electronics development”
Erwin Schimbäck
Business Area Manager Sensors & Communication
Further projects
TechCalc
TechCalc automates often laborious recurring calculations for component and system design. Its easy expandability, flexible model switching and integrated visualization capability supports during the entire design process. Model connectivity, Python scripting and traceability make the development processes faster, more efficient and more reliable.
Digital Hydraulic Pressure Control Unit
The Digital Hydraulic Pressure Control Unit improves efficiency and reliability in production systems. With digital hydraulics, the pressure process can be controlled more precisely, more energy-efficiently and with a longer service life.
SMART FLANGE FOR SAW BLADE MONITORING
Smart flange for saw blade monitoring: Integrated sensor technology and edge functionalities enable real-time condition monitoring for predictive maintenance.
