Due to the increase of the complexity of the products and the shorter time-to-market, it is also necessary to develop the required tooling to attend to the planned deadlines. This scenario requires advancing the state-of-the-art frontier to improve the tooling competitiveness and productivity.
To achieve such improvement and increase in competitiveness, it is necessary to insert the tooling chain in the context of Industry 4.0. Therefore, the focus could be on the use of digitization technologies for data gathering and analysis, seeking out continuous improvement in the process of development, production, and service provision of tools and devices. In the context of Industry 4.0, real-time condition monitoring and control of manufacturing processes can be achieved using IoT concepts, advanced sensors, Big Data, and machine learning algorithms.
These technologies enable smart monitoring of the manufacturing process, resulting in new tool adjustments and new process parameters in a semi-autonomous way, reducing human-machine interactions and more accurately attributing process improvement.
This paper aims to present the results of a pilot project to develop and validate a machining conditioning monitoring system combining measures conducted directly in the spindle unit and fixture devices. The system is based on different sensors and machine learning. The pilot project has been developed in an automotive company and partnership with two universities and targets the development of applications for a real operational environment.
This research project also aims to develop a system integrator algorithm for real-time data acquisition from the sensors, installed both on the spindle and at strategic points of the fixture devices, enabling the continuous operation monitoring of tools and deviations on the fixture devices, as well as the optimization of the application usage parameters.