Failure-averse Active Learning for Physics-constrained Systems

TL;DR

This paper introduces a failure-averse active learning method for physics-constrained systems that ensures safety by avoiding failures during the learning process, demonstrated on a composite fuselage assembly task.

Contribution

It develops a novel active learning approach that incorporates implicit physics constraints to prevent failures, with theoretical analysis and practical application.

Findings

Achieves zero-failure in the composite fuselage assembly process

Effectively explores safe regions to reduce model variance

Extends explorable regions using probabilistic constraint models

Abstract

Active learning is a subfield of machine learning that is devised for design and modeling of systems with highly expensive sampling costs. Industrial and engineering systems are generally subject to physics constraints that may induce fatal failures when they are violated, while such constraints are frequently underestimated in active learning. In this paper, we develop a novel active learning method that avoids failures considering implicit physics constraints that govern the system. The proposed approach is driven by two tasks: the safe variance reduction explores the safe region to reduce the variance of the target model, and the safe region expansion aims to extend the explorable region exploiting the probabilistic model of constraints. The global acquisition function is devised to judiciously optimize acquisition functions of two tasks, and its theoretical properties are provided. The proposed method is applied to the composite fuselage assembly process with consideration of material failure using the Tsai-wu criterion, and it is able to achieve zero-failure without the knowledge of explicit failure regions.