Defect prevention is particularly critical in operations such as aircraft assembly or service. Failure Modes and Effects Analysis (FMEA) procedures have been deployed manually for many years. However, the manual procedures fail to utilize capability to build intelligence into inspection processes that can facilitate elimination of human error. In this work, we introduce an artificial intelligence (AI)-based concept that can iteratively learn to assure zero defects from a given inspection process. This work introduces a schema that can serve as a knowledge management framework in a relational database for instantiation with inspection process information and data from a detection system. A companion algorithm is presented for the case of a wiring harness bracket installation in a fuselage. The schema and algorithm analyze and assess potential defects posed by Foreign Object Debris (FOD)in parallel to the assembly inspection. A closed loop of logic was introduced to enable anomaly detection by this algorithm to assure zero defects.


A Defect Prevention Concept Using Artificial Intelligence

Division / Sponsors: 
Design Engineering Division and Computers & Information In Engineering Division


Paper Proceedings: https://asmedigitalcollection.asme.org/IDETC-CIE/IDETC-CIE2020/volume/83907

IDETC2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.