“…More specifically discussing the drilling process, in [11], [12] and [13], the authors present an approach that uses ANNs to predict the useful life of cutting tools. In [14], the use of ANNs and other machine learning methods have as its goal to predict the cutting force from semi-automatic Advanced Drilling Units (ADU). This is done by controlling the cutting parameters to keep the drilling process at an optimal level of quality assurance and optimal tool life exploitation.…”
This paper presents a case study carried out in an assembly cell where automated drilling of an aeronautical structure is performed. The study shows how techniques approached by the 4.0 industry have the potential to contribute to manufacturing, breaking the limits imposed by the previous state of the art systems. This paper proposes a method capable of calculating an indicator for the final quality of the drilled holes, by using a committee of neural networks, which analyses data obtained by monitoring the electric current consumed by the drilling system drive. The method has the potential to enhance the efficiency of the drilling process, avoiding measurement steps and physical inspections that increases the cell cycle time.The proposal contributes to the literature by presenting an unprecedented application and to the praxis by solving a relevant problem of the aerospace industry.
“…More specifically discussing the drilling process, in [11], [12] and [13], the authors present an approach that uses ANNs to predict the useful life of cutting tools. In [14], the use of ANNs and other machine learning methods have as its goal to predict the cutting force from semi-automatic Advanced Drilling Units (ADU). This is done by controlling the cutting parameters to keep the drilling process at an optimal level of quality assurance and optimal tool life exploitation.…”
This paper presents a case study carried out in an assembly cell where automated drilling of an aeronautical structure is performed. The study shows how techniques approached by the 4.0 industry have the potential to contribute to manufacturing, breaking the limits imposed by the previous state of the art systems. This paper proposes a method capable of calculating an indicator for the final quality of the drilled holes, by using a committee of neural networks, which analyses data obtained by monitoring the electric current consumed by the drilling system drive. The method has the potential to enhance the efficiency of the drilling process, avoiding measurement steps and physical inspections that increases the cell cycle time.The proposal contributes to the literature by presenting an unprecedented application and to the praxis by solving a relevant problem of the aerospace industry.
“…In extreme situations, the acquired machining data can be incorporated to the commercial software in to alarm or stop the tool rotation in extreme situations, as it is already the case of power [11].…”
Industry 4.0 is the need of the hour in current global market scenario and all the processes are moving toward automation and smart manufacturing. In machining, smart techniques implementation depends on developing a database for decision-making, which is the case for stack drilling in aerospace industry. In this application, choosing one optimal condition for several materials is a challenge due to their different machinability. Hence, material identification techniques are suitable approaches for adapting the cutting parameters in real time, which improves tool life, hole quality, and productivity. In that regard, the goal of the present paper is to create a specific force data map for axial drilling and circular milling processes based on its experimental force and power measurements. To do that, experiments were separately carried out on Titanium and Aluminum workpieces in a range of cutting speed and feed conditions. The results show that specific cutting and feed forces for each material can be identified on distinct regions of the map, without thresholds overlapping. Given that, these maps can be used as a signature to distinguish two metallic materials in real time machining. In this case, the specific data points at the interface layers may offer advantage to accurately identify tool position unlike monitoring gradient of feed forces while drilling stacked materials. Therefore, smart machining techniques seeking cutting parameters optimization can be implemented for a particular material.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.