individual
What campus are you from?
Daytona Beach
Authors' Class Standing
Westin Volpe, Junior
Lead Presenter's Name
Westin Volpe
Faculty Mentor Name
Sathya Gangadharan
Abstract
In military and commercial aircraft, vibrational frequencies generated by component wear, propeller wake, engine shake, and aircraft turbulence have substantial effects on pilots and crew. Sustained exposure to high and low vibrational frequencies leads to hypertension, vertigo, osteoarthritis, lumbago, and mental fatigue, which become detrimental to operator’s ability to perform effectively. The current solutions rely on two systems, passive energy-absorbing cushions and semi-active force cancellation devices, which are sometimes used concurrently. The passive systems integrate traditional foam with materials that dissipate vibrational frequencies, such as memory foam or gel pads, and generally perform effectively. However, these solutions exhibit reduced performance at low frequencies and tend to compress under sustained load. This compression diminishes their capacity to dampen vibrations, necessitates their regular replacement, and limits their ability to respond adaptively to varying loads. To mitigate these drawbacks, semi-active systems have been developed to dynamically adjust damping properties in response to varying loads, such as the active vibration attenuating seat suspension (AVASS). Despite their advantages, semi-active systems incur higher costs and complexity while demonstrating sensitivity to environmental instability and having control latency due to computational delay. To address these limitations, the proposed solution implements an intelligent control framework utilizing reinforcement learning to regulate magnetorheological (MR) dampers using integrated sensor data and biofeedback. The controller dynamically adjusts damping parameters in real time, improving vibration mitigation. This approach enhances robustness in the model and combats modeling uncertainty, control latency, environmental fluctuations, and load variations. This approach has the potential to be effective in fields that have sustained vibrational exposure, such as aircrafts, spacecrafts, and heavy machinery requiring adaptive vibration mitigation.
Did this research project receive funding support from the Office of Undergraduate Research.
No
Bio-Integrated Adaptive Seat System for Real-Time Vibration Mitigation in Aviation Utilizing Reinforcement Learning
In military and commercial aircraft, vibrational frequencies generated by component wear, propeller wake, engine shake, and aircraft turbulence have substantial effects on pilots and crew. Sustained exposure to high and low vibrational frequencies leads to hypertension, vertigo, osteoarthritis, lumbago, and mental fatigue, which become detrimental to operator’s ability to perform effectively. The current solutions rely on two systems, passive energy-absorbing cushions and semi-active force cancellation devices, which are sometimes used concurrently. The passive systems integrate traditional foam with materials that dissipate vibrational frequencies, such as memory foam or gel pads, and generally perform effectively. However, these solutions exhibit reduced performance at low frequencies and tend to compress under sustained load. This compression diminishes their capacity to dampen vibrations, necessitates their regular replacement, and limits their ability to respond adaptively to varying loads. To mitigate these drawbacks, semi-active systems have been developed to dynamically adjust damping properties in response to varying loads, such as the active vibration attenuating seat suspension (AVASS). Despite their advantages, semi-active systems incur higher costs and complexity while demonstrating sensitivity to environmental instability and having control latency due to computational delay. To address these limitations, the proposed solution implements an intelligent control framework utilizing reinforcement learning to regulate magnetorheological (MR) dampers using integrated sensor data and biofeedback. The controller dynamically adjusts damping parameters in real time, improving vibration mitigation. This approach enhances robustness in the model and combats modeling uncertainty, control latency, environmental fluctuations, and load variations. This approach has the potential to be effective in fields that have sustained vibrational exposure, such as aircrafts, spacecrafts, and heavy machinery requiring adaptive vibration mitigation.