Enhancing Functional Safety in Automotive AMS Circuits through Unsupervised Machine Learning

TL;DR

The paper tackles functional safety in automotive AMS circuits by proposing an unsupervised anomaly-detection framework that operates across multiple hardware-abstraction levels. It combines diverse anomaly injection, feature extraction, clustering with a novel centroid-selection algorithm, and a time-series analysis layer to enable early detection with reduced latency. Key contributions include a comprehensive anomaly-injection framework, a centroid-optimization method tailored to AMS data, and a time-series approach that accelerates detection, demonstrated on bandgap reference and operational amplifier circuits with up to 100% detection accuracy and up to a 5x latency reduction. The work provides evidence that such a framework can support proactive safety mechanisms in automotive SoCs, with implications for higher abstraction-level FuSa in future AMS designs.

Abstract

Given the widespread use of safety-critical applications in the automotive field, it is crucial to ensure the Functional Safety (FuSa) of circuits and components within automotive systems. The Analog and Mixed-Signal (AMS) circuits prevalent in these systems are more vulnerable to faults induced by parametric perturbations, noise, environmental stress, and other factors, in comparison to their digital counterparts. However, their continuous signal characteristics present an opportunity for early anomaly detection, enabling the implementation of safety mechanisms to prevent system failure. To address this need, we propose a novel framework based on unsupervised machine learning for early anomaly detection in AMS circuits. The proposed approach involves injecting anomalies at various circuit locations and individual components to create a diverse and comprehensive anomaly dataset, followed by the extraction of features from the observed circuit signals. Subsequently, we employ clustering algorithms to facilitate anomaly detection. Finally, we propose a time series framework to enhance and expedite anomaly detection performance. Our approach encompasses a systematic analysis of anomaly abstraction at multiple levels pertaining to the automotive domain, from hardware- to block-level, where anomalies are injected to create diverse fault scenarios. By monitoring the system behavior under these anomalous conditions, we capture the propagation of anomalies and their effects at different abstraction levels, thereby potentially paving the way for the implementation of reliable safety mechanisms to ensure the FuSa of automotive SoCs. Our experimental findings indicate that our approach achieves 100% anomaly detection accuracy and significantly optimizes the associated latency by 5X, underscoring the effectiveness of our devised solution.

Figures (12)

• Figure 1: Illustration of (a) point anomaly and (b) trend anomaly in a representative signal.
• Figure 2: Overview of the proposed anomaly detection framework for automotive AMS systems.
• Figure 3: Illustrative example circuit for anomaly model.
• Figure 4: Illustrative example of (a) non time series approach and (b) time series approach.
• Figure 5: Illustration of a Tri-stage amplifier, where k = 3.