MACHINE LEARNING-BASED ANALYSIS ENGINE TO IDENTIFY CRITICAL VARIABLES IN MULTI-STAGE PROCESSES: APPLICATION TO THE INSTALLATION OF BLIND FASTENERS

Abstract

Quality control in manufacturing is a recurrent topic as the ultimate goals are to produce high quality products with less cost. Mostly, the problems related to manufacturing processes are addressed focusing on the process itself putting aside other operations that belong to the part’s history. This research work presents a Machine Learning-based analysis engine for non-expert users which identifies relationships among variables throughout the manufacturing line. The developed tool was used to analyze the installation of blind fasteners in aeronautical structures, with the aim of identifying critical variables for the quality of the installed fastener, throughout the fastening and drilling stages. The results provide evidence that drilling stage affects to the fastening, especially to the formed head’s diameter. Also, the most critical phase in fastening, which is when the plastic deformation occurs, was identified. The results also revealed that the chosen process parameters, thickness of the plate and the faster type influence on the quality of the installed fastener. Keywords: Analysis Engine, Multi-Stage Processes, Critical Variables, Machine Learning, Blind Fasteners.