Joint Sensor and Actuator Fault Diagnosis for Autonomous Ships

Abstract

Listen

Translate article

In this paper, we introduce an innovative approach for joint diagnosis of sensor and actuator faults in autonomous ships, leveraging an adaptive extended Kalman filter enriched with a forgetting factor. The fundamental concept involves filtering and augmenting measurements from the sensor systems into the ships’ state space model. This method is designed to enhance the accuracy of the diagnostic process by dynamically adapting to changes in the sensor's behavior over time. To validate the efficacy of our proposed method, we conduct numerical simulations. Through these simulations, we aim to demonstrate the practical applicability and reliability of our approach in real-world scenarios, emphasizing its potential for enhancing the fault diagnosis capabilities of autonomous ships.