#2 Machine tool spindle predictive behaviour
The testbed is aimed at creating multiple target-oriented digital twins of machine tools for the production
of automotive components. It will deploy simulation and machine learning models of machine tools,
drives, and spindles for detecting their condition and behavior to predict manufacturing-relevant and
quality-influencing parameters (load, forces, vibrations etc.) for reducing unexpected rejects, breakdowns
and downtime, by optimizing load and performance indexes.
Main foreseen activities for this testbed are:
1. design and installation of redundant IoT modules able to log data at high sample rates, and also to
log and process in real time a set of data (stream processing) for creating embedded digital twin
models of machine tools;
2. creation or forecasting of data coming from individual subsystems in a machine tool by using
simulation models of physical behavior;
3. training of machine learning models on the cloud for their subsequent utilization on edge device
Nerve by TTT (smartification of systems);
4. creation of data driven performance models for machine tools;
5. early detection of failures for monitored subsystems;
6. automated preparation of predictive maintenance plans;
7. optimization of machine tool spindle control systems.
Objectives
Smartifying the machine tools (in particular drives and spindles) by integrating embedded IoT twins for smart sensing, edge computers with real time data processing, and IoTwins components at both edge and cloud
Providing intelligent data transmission solutions that limit the volume of exchanged data without losing value for the training process
Optimizing the machine tool control system;
Developing a cloud-based digital twin to simulate the best performance of the machine tool either to optimize energy efficiency, cycle time, tool costs, quality or maintenance and spare part costs
Extending residual useful life of critical components in the machine tool
Producing failure models for each machine tool and for the whole shop floor
Developing predictive maintenance algorithms for each component of the machine tool and for the whole shop floor, based on the information gathered and elaborated and the scenarios simulated with distributed digital twins
Involved Partners
