Self-supervised intermittent fault detection for analog circuits guided by prior knowledge

Abstract

Intermittent faults (IFs) are common in electronic systems, which are short-term, repeatable and cumulative. IF samples are difficult to collect, so detection is usually performed using one-class learning approaches, which require only fault-free samples to participate in the training. Teacher–student model typically uses the cognitive biases of teacher and student on fault signals to detect faults. Introducing prior knowledge of IFs in the teacher model may help to produce greater fault cognitive bias and thus improve detection. Inspired by this, this paper proposes a prior knowledge-guided teacher–student (PKGTS) model based on self-supervised learning. In analog circuits, IFs cause transient changes in the circuit signal in terms of amplitude, frequency, and waveform. Therefore, based on this prior knowledge, corresponding signal transformations are designed to simulate possible fault variations and introduce prior knowledge to the teacher through a pretext task. Finally, only the knowledge of the teacher’s fault-free state is imparted to the student. During the testing phase, IF detection is achieved through the cognitive biases of faults, as the student model does not have prior knowledge of faults. In two typical analog filtering circuit experiments, the effectiveness of the proposed method under different noise levels and fault intensities is verified.