A cloud-based, knowledge-enriched framework for increasing machining efficiency based on machine tool monitoring

The ever-increasing complexity in manufacturing systems caused by the fluctuating customer demands has highly affected the contemporary shop-floors. The selection of the appropriate cutting parameters is becoming more and more challenging due to the increasing complexity of products. Until now, the knowledge of the machine operators concerning the modification of the machining parameters and the monitoring information is not sufficiently exploited by the optimization systems. Web and Cloud technologies together with wireless sensor networks are required to capture the shop-floor data and enable the ubiquitous access from multiple IT tools. For addressing these challenges, this research work proposes a Cloud-based, knowledge-enriched framework for machining efficiency based on machine tool monitoring. More precisely, it focuses on the optimization of the machining parameters and moves through an event-driven optimization algorithm, utilizing the existing machining knowledge captured by the monitoring system. Based on the features of a new part, a similarity mechanism retrieves the cutting parameters of successfully executed past parts that have been machined. Afterwards, the optimization module, using event-driven function blocks, adapts these parameters to efficiently optimize the moves and the cutting parameters. The monitoring system uses a wireless sensor network and a human operator input via mobile devices. A case study from the mould-making industry is used for validating the proposed framework.