Root cause analysis using artificial intelligence

Abstract

A complex hardware system experiences several different types of failure modes when deployed in its field of use. Although each failure mode merits its very own root cause analysis, experience has shown us that a majority of root cause analyses require us to answer a very similar set of questions. These recurring questions often use very similar type of field data to be answered. For example, usage parameters such as hours of operation, total power cycles, vibration fatigue, etc. are used almost always while trying to figure out the failure mechanism. By taking advantage of this, we can automate the process of finding the most likely failure mechanism for a given failure mode. In the current work, we start by computing what we believe are parameters that are most relevant across all different types of failure modes. Once these parameters are computed, we will build a Bayesian Network to model the cause-effect relationship between the degradation parameters (cause) and failure modes(effect) that occur on the field. Bayesian Network is a probabilistic graphical model which concisely describes the relationship between many random variables and their conditional independence via an acyclic directed graph. Once the topology of the Bayesian network is laid out by a domain expert, the conditional probabilities can be learnt from existing data, thereby completely describing the system using the notion of joint probabilities. Two real life field issues are used as examples to demonstrate the accuracy of the network once it is modelled and built. This paper demonstrates that accurately modelling the hardware system as a Bayesian Network substantially accelerates the process of root cause analysis.