Abstract
The development of complex real-time platforms for the Internet of Things (IoT) opens up a promising future for the diagnosis and the optimization of machining processes. Many issues have still to be solved before IoT platforms can be profitable for small workshops with very flexible workloads and workflows. The main obstacles refer to sensor implementation, IoT architecture, and data processing, and analysis. In this research, the use of different machine-learning techniques is proposed, for the extraction of different information from an IoT platform connected to a machining center, working under real industrial conditions in a workshop. The aim is to evaluate which algorithmic technique might be the best to build accurate prediction models for one of the main demands of workshops: the optimization of machining processes. This evaluation, completed under real industrial conditions, includes very limited information on the machining workload of the machining center and unbalanced datasets. The strategy is validated for the classification of the state of a machining center, its working mode, and the prediction of the thermal evolution of the main machine-tool motors: the axis motors and the milling head motor. The results show the superiority of the ensembles for both classification problems under analysis and all four regression problems. In particular, Rotation Forest-based ensembles turned out to have the best performance in the experiments for all the metrics under study. The models are accurate enough to provide useful conclusions applicable to current industrial practice, such as improvements in machine programming to avoid cutting conditions that might greatly reduce tool lifetime and damage machine components.
Highlights
Over the past 10 years, different technologies have boosted data-acquisition, communications, and processing capabilities
The data volumes included in this work that were collected on the Fiware Internet of Things (FIoT) platform exceeded 1,500,000 datums grouped by category, over 3 months of machining center operations, the specific study described only analyzed a very limited part of this information
A real data-extraction architecture connected to an Internet of Things (IoT) platform for small workshops has been described
Summary
Over the past 10 years, different technologies have boosted data-acquisition, communications, and processing capabilities. The solution is based on the most suitable machine-learning algorithms for each of the proposed industrial tasks (identification of temperature patterns and machine working states) This suitability will be proven with a real and extensive dataset, where different machining processes are mixed with no clear identification: milling, drilling, etc. The existing bibliography, summarized, proposes solutions for certain industrial problems (e.g., tool breakage or wear monitoring in drilling, milling or turning, surface quality or dimensional accuracy prediction in machined workpieces, etc.) In this case, the solution is open to extract any useful information, merely by changing the inputs and outputs of the trained model and without any previous classification of the cutting process that took place. The most relevant results will be summarized in the conclusions (Section 6) and pointers will be given for future lines of research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
