Physics-informed machine learning and its structural integrity applications: state of the art.

The development of machine learning (ML) provides a promising solution to guarantee the structural integrity of critical components during service period. However, considering the lack of respect for the underlying physical laws, the data hungry nature and poor extrapolation performance, the further application of pure data-driven methods in structural integrity is challenged. An emerging ML paradigm, physics-informed machine learning (PIML), attempts to overcome these limitations by embedding physical information into ML models. This paper discusses different ways of embedding physical information into ML and reviews the developments of PIML in structural integrity including failure mechanism modelling and prognostic and health management (PHM). The exploration of the application of PIML to structural integrity demonstrates the potential of PIML for improving consistency with prior knowledge, extrapolation performance, prediction accuracy, interpretability and computational efficiency and reducing dependence on training data. The analysis and findings of this work outline the limitations at this stage and provide some potential research direction of PIML to develop advanced PIML for ensuring structural integrity of engineering systems/facilities. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.

Defect driven physics-informed neural network framework for fatigue life prediction of additively manufactured materials.

Additive manufacturing (AM) has attracted many attentions because of its design freedom and rapid manufacturing; however, it is still limited in actual application due to the existing defects. In particular, various defect features have been proved to affect the fatigue performance of components and lead to fatigue scatter. In order to properly assess the influences of these defect features, a defect driven physics-informed neural network (PiNN) is developed. By embedding the critical defects information into loss functions, the defect driven PiNN is enhanced to capture physical information during training progress. The results of fatigue life prediction for different AM materials show that the proposed PiNN effectively improves the generalization ability under small samples condition. Compared with the fracture mechanics-based PiNN, the proposed PiNN provides physically consistent and higher accuracy without depending on the choice of fracture mechanics-based model. Moreover, this work provides a scalable framework being able to integrate more prior knowledge into the proposed PiNN. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.

Alkali/alkaline-earth metal-modified MnOx supported on three-dimensionally ordered macroporous-mesoporous TixSi1-xO2 catalysts: Preparation and catalytic performance for soot combustion.

The performance of catalysts used in after-treatment systems is the key factor for the removal of diesel soot, which is an important component of atmospheric fine particle emissions. Herein, three-dimensionally ordered macroporous-mesoporous TixSi1-xO2 (3DOM-m TixSi1-xO2) and its supported MnOx catalysts doped with different alkali/alkaline-earth metals (AMnOx/3DOM-m Ti0.7Si0.3O2 (A: Li, Na, K, Ru, Cs, Mg, Ca, Sr, Ba)) were prepared by mesoporous template (P123)-assisted colloidal crystal template (CCT) and incipient wetness impregnation methods, respectively. Physicochemical characterizations of the catalysts were performed using scanning electron microscopy, X-ray diffraction, N2 adsorption-desorption, H2 temperature-programmed reduction, O2 temperature-programmed desorption, NO temperature-programmed oxidation, and Raman spectroscopy techniques; then, we evaluated their catalytic performances for the removal of diesel soot particles. The results show that the 3DOM-m Ti0.7Si0.3O2 supports exhibited a well-defined 3DOM-m nanostructure, and AMnOx nanoparticles with 10-50 nm were evenly dispersed on the inner walls of the uniform macropores. In addition, the as-prepared catalysts exhibited good catalytic performance for soot combustion. Among the prepared catalysts, CsMnOx/3DOM-m Ti0.7Si0.3O2 had the highest catalytic activity for soot combustion, with T10, T50, and T90 (the temperatures corresponding to soot conversion rates of 10%, 50%, and 90%) values of 285, 355, and 393°C, respectively. The high catalytic activity of the CsMnOx/3DOM-m Ti0.7Si0.3O2 catalysts was attributed to their excellent low-temperature reducibility and homogeneous macroporous-mesoporous structure, as well as to the synergistic effects between Cs and Mn species and between CsMnOx and the Ti0.7Si0.3O2 support.