Prediction of imminent failure using supervised learning in fiber bundle model

TL;DR

This study demonstrates that supervised machine learning applied to avalanche time series from fiber bundle models can predict imminent failure in disordered solids, with effectiveness varying across different failure modes and system parameters.

Contribution

The paper introduces a novel approach using supervised learning on avalanche data to predict failure in fiber bundle models, highlighting the importance of inequality measures and feature importance shifts.

Findings

Supervised learning can predict failure time with high accuracy.

Inequality measures are crucial for predictions, especially with imperfect training data.

Predictability varies with system parameters and failure modes.

Abstract

Prediction of breakdown in disordered solids under external loading in a question of paramount importance. Here we use a fiber bundle model for disordered solids and record the time series of the avalanche sizes and energy bursts. The time series contains statistical regularities that not only signify universality in the critical behavior of the process of fracture, but also reflect signals of proximity to a catastrophic failure. A systematic analysis of these series using supervised machine learning can predict the time to failure. Different features of the time series become important in different variants of training samples. We explain the reasons for such switch over of importance among different features. We show that inequality measures for avalanche time series play a crucial role in imminent failure predictions, especially for imperfect training sets i.e., when simulation parameters of training samples differ considerably from those of the testing samples. We also show the variation of predictability of the system as the interaction range and strengths of disorders are varied in the samples, varying the failure mode from brittle to quasi-brittle (with interaction range) and from nucleation to percolation (with disorder strength). The effectiveness of the supervised learning is best when the samples just enter the quasi-brittle mode of failure showing scale-free avalanche size distributions.