Fault Detection and Tolerant Control for Aero2 2D0F Two-rotor Helicopter
원문 초록
Stability and satisfactory performance are critical control requirements for Unmanned Aerial Vehicle (UAV) applications. While conventional control systems for UAVs aim to ensure flight stability and safe operation while accomplishing tasks, UAVs may experience various flight faults that can degrade performance or, in severe cases, lead to instability. Unsatisfactory performance or instability of a UAV poses risks to lives, properties, and the flying environment. Therefore, it's essential to design a system capable of detecting faults, pinpointing their location, assessing their severity, and using this information to mitigate them, enabling the vehicle to continue operating satisfactorily. Despite the importance of analysing fault performance to select optimal fault detection and tolerance strategies, limited research has been conducted, especially with real systems. This study examines the performance of a 2-degree-of-freedom (2DOF) bi-rotor helicopter's control system in the presence of various actuator faults. Results from different fault conditions demonstrate that faults degrade the performance of conventional control systems on UAVs and introduce vibrations into the system, particularly when faults cause asymmetry or imbalance. However, additional experiments reveal that effective fault diagnosis and accommodation methods can help maintain satisfactory system performance despite the presence of faults.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Data-Driven Sensor Fault Diagnosis with Proven Guarantees using Incrementally Stable Recurrent Neural Networks
Explainable fault and severity classification for rolling element bearings using Kolmogorov-Arnold networks
DKDL-Net: A Lightweight Bearing Fault Detection Model via Decoupled Knowledge Distillation and Low-Rank Adaptation Fine-tuning
Multi-scale Quaternion CNN and BiGRU with Cross Self-attention Feature Fusion for Fault Diagnosis of Bearing
Fault Identification Enhancement with Reinforcement Learning (FIERL)
Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process
토론
이 논문과 연결된 포럼 글이 아직 없습니다.