A Virtual Sensing Active Noise Control System Based on a Functional Link Neural Network for an Aircraft Seat Headrest

Abstract

Purpose The goal of this work is to propose a local Active Noise Control system for an aircraft seat’s headrest. This system should be able to extend the quiet zone beyond the physical microphones that can be placed behind the passenger’s head due to space constraints. Furthermore, the control algorithm should perform efficiently when non-linear phenomena exist during the sound propagation. Methods A functional link neural network and a computationally efficient Multiple Input Multiple Output approach are used for the system’s implementation. The quiet zone is extended by linearly estimating the acoustic pressure in front of the headrest surface. The main novelty of this paper is the combination of these methods in an attempt to improve acoustic pressure attenuation performance, while keeping computational complexity low. Results The proposed control algorithm has been evaluated through numerical simulations, including Finite Element Method and experimental tests at an aircraft cabin mock-up. The results show that for a real-world acoustic disturbance, a 10 dB reduction in sound pressure level was achieved 10 cm away from the headrest surface. In addition, the attenuation of some harmonics can reach 20 dB and in most cases is bigger than the linear FxLMS algorithm. Conclusions To summarize, it has been demonstrated that a multichannel functional link neural network using a simple virtual sensing technique can efficiently attenuate synthesized and real world acoustic disturbances captured in a tilt-rotor aircraft’s cabin. Finally, it can create an adequate quiet zone for gentle head movement while maintaining its stability.