Automated fault tree learning from continuous-valued sensor data: a case study on domestic heaters

TL;DR

This paper introduces an automated method for learning fault trees from continuous sensor data, demonstrated on a large dataset of domestic heaters, combining decision-tree discretization with Boolean fault tree learning for failure analysis.

Contribution

It presents the first fully automated approach to derive explainable fault trees from raw continuous data, scaling effectively to large real-world datasets.

Findings

Fault trees achieved high significance scores above 0.95.

Method successfully models meaningful failure relationships.

Approach is validated on five-year, real-world sensor data.

Abstract

Many industrial sectors have been collecting big sensor data. With recent technologies for processing big data, companies can exploit this for automatic failure detection and prevention. We propose the first completely automated method for failure analysis, machine-learning fault trees from raw observational data with continuous variables. Our method scales well and is tested on a real-world, five-year dataset of domestic heater operations in The Netherlands, with 31 million unique heater-day readings, each containing 27 sensor and 11 failure variables. Our method builds on two previous procedures: the C4.5 decision-tree learning algorithm, and the LIFT fault tree learning algorithm from Boolean data. C4.5 pre-processes each continuous variable: it learns an optimal numerical threshold which distinguishes between faulty and normal operation of the top-level system. These thresholds discretise the variables, thus allowing LIFT to learn fault trees which model the root failure mechanisms of the system and are explainable. We obtain fault trees for the 11 failure variables, and evaluate them in two ways: quantitatively, with a significance score, and qualitatively, with domain specialists. Some of the fault trees learnt have almost maximum significance (above 0.95), while others have medium-to-low significance (around 0.30), reflecting the difficulty of learning from big, noisy, real-world sensor data. The domain specialists confirm that the fault trees model meaningful relationships among the variables.