Key points are not available for this paper at this time.
The increasing concern about the depletion of the energy repositories places the energy efficiency issues in high priority. In the manufacturing sector, the improvement of energy efficiency is a challenging task due to the complexity of manufacturing systems and the requirements for flexible operation targeting highly customised products. Towards this end, the estimation of the energy consumption of a machining task, and therefore the machining cost, is necessary. This paper presents a machine tool monitoring methodology that integrates sensory systems, a scheduling module, and human operators to perform real-time monitoring on the shop-floor. A monitoring system is designed to capture real-time measurements from sensors attached on machine tools and perform the necessary pre-processing to transmit these measurements to a Cloud server via wireless sensor networks. Furthermore, the input from human operators is utilized to collect the machining parameters. The collected information is fused through an information fusion mechanism to extract meaningful results. The results are stored in a database for the reuse in future tasks by estimating the energy consumption of new cases, through a case-based reasoning approach, prior the job dispatching. Therefore, the machining parameters of the new case can be modified targeting energy consumption reduction. The proposed system is delivered as a Cloud software-as-a-service to realise the philosophy of Cloud manufacturing.
Mourtzis et al. (Fri,) studied this question.