Improving the quality assessment of drilled holes in aircraft structures

This paper presents a case study conducted in an assembly cell specifically designed for the automated drilling of an aeronautical structure. 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 that utilizes a committee of neural networks to calculate an indicator for the final quality of drilled holes. The method analyzes data obtained by monitoring the electric current consumed by the drilling system drive. Considering the tests carried out on a real product, the method presents an accuracy of 95% and has the potential to increase the efficiency of the drilling process, reducing the cycle time by up to 25%, since it can avoid measurement steps and physical inspections which increase the cycle time of the drilling process. The proposal contributes to the literature by presenting an unprecedented application and to the praxis by solving a relevant problem of the aerospace industry.

Automated summary

This paper presents a case study of an assembly cell designed for automated drilling of an aeronautical structure, demonstrating the potential of Industry 4.0 techniques to overcome limitations of previous systems. The proposed method utilizes a neural network committee to calculate a quality indicator for drilled holes based on monitoring the drilling system's electric current consumption. Test results show 95% accuracy and the potential to reduce drilling cycle time by 25%, avoiding measurement and physical inspections. This innovative application contributes to literature and solves a significant problem in the aerospace industry.