Intelligent fault detection algorithm based on Hi/H∞ optimization and a cascaded neural networks

Abstract

Autonomous surface ships (ASSs) have attracted attention owing to their ability to perform various tasks in complex and challenging aquatic environments without relying on a crew. However, they require reliable sensors to ensure navigational safety. In this study, a robust and intelligent fault detection algorithm was designed for the integrated navigation system of an ASS. First, a residual observer-based fault detection algorithm using Hi/H∞ optimization is proposed to deal with process disturbances and measurement noise. Such noise can be modeled under the condition of a bounded l2-norm to account for the sensitivity and robustness of the residual observer against random noise with unknown properties. However, this fault detection algorithm is insensitive to soft faults, which manifest as noise characterized by a small amplitude and slow variation. Conventional strategies for evaluating the fault detection threshold rely on human experience, which is insufficiently sophisticated for fault detection. Therefore, a cascaded neural network is proposed for optimizing the fault detection algorithm when the amount of training data is limited. The cascaded neural network consists of a multi-feature time domain network, a frequency-domain fault detection network as well as a decision-level fusion network. The proposed algorithm was verified in simulations as well as on historical data collected from real ship sensors. The results demonstrated that the proposed algorithm offers intelligent fault detection, including soft faults, with a low false alarm rate for integrated navigation systems.