Automated Manufacturing Technologies with Machine-Learning and Artificial Intelligence for Smart Sustainment
Abstract
Increasing pressure and growing complexities of designs drive aerospace and defense industry to accelerate innovation, while reducing cost and managing complexities. Manufacturers are researching on innovative technologies to increase the production rates, while creating a datadriven factory of the future for managing flexible rates. Automated fiber placement (AFP) technologies considerably increase the production rates and reduce the part count with advanced joining technologies. Aircraft manufacturers are considering in-situ consolidation of thermoplastic material systems coupled with AFP to eliminate time-0consuming and costly autoclave processes. However, the quality assurance and certification of advanced AFP conceptswith such materials have not matured to implement them in primary/secondary aircraft structures. Primary goal of the proposed research is to develop a framework for material qualification and structural certification of AFP structures built around digital-twin concept aided by in-process guidance systems and machine-learning algorithms. AFP technology fits well into the concept referred to as digital thread, which is a communication framework that connects design and manufacturing elements in order to effectively integrate all aspects of manufacturing process. This requires convergence of various fields, traditionally functioning in their own silos, from concept to end of service life through model-based design/simulations and inspections. AFP in-process inspection systems will provide build feedback for data verification of digital twin in order tomaintain continuity of the digital thread throughout the parts life. Digital twin can be used for repair design and global-local analyses during sustainment accounting the allowable defects present during manufacturing of the part. In addition, the digital twin defect information can be used for repairing structures using the same automated fiber placement system without interrupting the manufacturing process. Upon calibration of the system using machine-learning algorithm,probability of detection and analysis validation exercises will be carried out to compare the fidelity of automated inspection data compared to traditional post-manufacturing inspection methods used by part manufacturers. Validation exercise will then be expanded from panel-levels to large components manufactured using AFP technologies with advanced materials. This will lay the foundation for developing a certification framework for AFP structures in order to accelerate the process for introducing novel materials and advanced AFP technologies required to reduce certification time by ensuring material performance meet program goals.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- May 05, 2021
- Source ID
- N000142112506
Entities
People
- Waruna Seneviratne
Organizations
- Office of Naval Research
- United States Navy
- Wichita State University