A Self-Building and Cluster-Based Cognitive Fault Diagnosis System for Sensor Networks

Cognitive fault diagnosis systems differentiate from more traditional solutions by providing online strategies to create and update the fault-free and the faulty classes directly from incoming data. This aspect is of paramount relevance within the big data framework, since measurements are there immediately processed to detect and identify the upsurge of potential faults. This paper introduces a novel cognitive fault diagnosis framework for processes described by nonlinear dynamic systems that inspects changes in the existing relationships among sensors. The proposed framework is based on an evolving clustering algorithm that operates in the parameter space of time invariant linear models approximating such relationships. During the operational life, parameter vectors associated with models thought not to belong to the nominal state are either labeled as outlier or fault. New classes of faults, here considered to propagate to the model parameters according to an abrupt profile, are created online as they appear. At the same time, existing classes can merge, depending on the information content carried by incoming data.

I. Introduction

Fault diagnosis systems (FDSs) are tools designed to detect, isolate, identify, and, possibly, mitigate the occurrence of faults affecting complex systems. FDSs have been subject of extensive research for their relevance in real-world applications, see [1]–[4] for a comprehensive review. In their traditional framework, it is required the availability of the fault-free nominal state and a fault dictionary, containing the fault signatures. Both requests constitute a strong demand, hard to be met in most of real-world applications.