作者: R.L. Broderick
DOI: 10.1109/DASC.2004.1390736
关键词:
摘要: This work presents a combined statistical and adaptive approach for the verification of an adaptive, online learning, sigma-pi neural network that is used aircraft damage flight control. Adaptive control systems must have ability to sense its environment, process dynamics, execute actions. project was completed class in complex at Nova Southeastern University. Verification neural-based system currently urgent significant research engineering topic since these are being looked upon as new survivability, both commercial military applications. The most shortcoming prior current approaches verifying networks application linear non-linear problem. Advances computational power techniques estimating aerodynamic stability derivatives provide opportunity real-time New needed substantially increases confidence use life, safety, mission critical systems.