Prediction of imminent failure using supervised learning in fiber bundle model

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.

arXiv comment13 pages, 12 figures

References in corpus (23)

• An index to quantify an individual's scientific research output
• Crackling Noise
• Machine Learning Predicts Laboratory Earthquakes
• Dynamics of a ferromagnetic domain wall: avalanches, depinning transition and the Barkhausen effect
• Failure Processes in Elastic Fiber Bundles
• First-Order Transition in the Breakdown of Disordered Media
• From damage percolation to crack nucleation through finite size criticality
• Crossover Behavior in Burst Avalanches of Fiber Bundles: Signature of Imminent Failure
• Inequality in Societies, Academic Institutions and Science Journals: Gini and k-indices
• Approach to failure in porous granular materials under compression
• Fracturing highly disordered materials
• Modes of failures in disordered solids
• Common dependence on stress for the statistics of granular avalanches and earthquakes
• Nucleation versus percolation: Scaling criterion for failure in disordered solids
• Near universal values of social inequality indices in self-organized critical models
• Failure processes of cemented granular materials
• Scaling forms for Relaxation Times of the Fiber Bundle model
• Avalanche precursors of failure in hierarchical fuse networks
• Breaking rate minimum predicts the collapse point of over-loaded materials
• Load Dependence of Power Outage Statistics
• Social Inequality Analysis of Fiber Bundle Model Statistics and Prediction of Materials Failure
• Size distribution of emitted energies in local load sharing fiber bundles
• Correlation between avalanches and emitted energies during fracture with variable stress release range

Cited by in corpus (2)

• Success of Social Inequality Measures in Predicting Critical or Failure Points in Some Models of Physical Systems
• Inequality of avalanche sizes in models of fracture