A Distributed Error and Anomaly Communication Architecture for Analog and Mixed-Signal Systems

With the increasing use of autonomous and mission critical systems, in field concurrent testing (i.e. testing while device is in operation) is becoming progressively more important. However, concurrent testing of analog and mixed-signal systems often needs to rely on anomaly indicators, because of the absence of clear 1/0 error conditions in analog circuits. In this paper we show how simultaneous monitoring of different but related anomalies across a mixed-signal system can lead to improved diagnosis of error conditions and rules out false errors. However, to achieve such kind of federated learning between different modules across the system, we need an architecture through which all modules within the system can communicate their anomaly information with minimum overhead. To that end, first, we develop a data structure (Weighted Alarm Collector - WAC) to efficiently encapsulate all the anomaly information in a system. Second, we show how WACs can be merged through hierarchies in a scalable manner. Based on this, we also develop an architecture to facilitate learning across different modules across hierarchies. The main benefits of this architecture are that a) it enables distributed error learning within a system and b) the architecture is scalable and can be built bottom up, which is compatible with current IP based modular design methodology. Finally we show some applications of this architecture on some common industry use-cases.