An explainable machine learning-based probabilistic framework for the design of scaffolds in bone tissue engineering.

Recently, 3D-printed biodegradable scaffolds have shown great potential for bone repair in critical-size fractures. The differentiation of the cells on a scaffold is impacted among other factors by the surface deformation of the scaffold due to mechanical loading and the wall shear stresses imposed by the interstitial fluid flow. These factors are in turn significantly affected by the material properties, the geometry of the scaffold, as well as the loading and flow conditions. In this work, a numerical framework is proposed to study the influence of these factors on the expected osteochondral cell differentiation. The considered scaffold is rectangular with a 0/90 lay-down pattern and a four-layered strut made of polylactic acid with a 5% steel particle content. The distribution of the different types of cells on the scaffold surface is estimated through a scalar stimulus, calculated by using a mechanobioregulatory model. To reduce the simulation time for the computation of the stimulus, a probabilistic machine learning (ML)-based reduced-order model (ROM) is proposed. Then, a sensitivity analysis is performed using the Shapley additive explanations to examine the contribution of the various parameters to the framework stimulus predictions. In a final step, a multiobjective optimization procedure is implemented using genetic algorithms and the ROM, aiming to identify the material parameters and loading conditions that maximize the percentage of surface area populated by bone cells while minimizing the area corresponding to the other types of cells and the resorption condition. The results of the performed analysis highlight the potential of using ROMs for the scaffold design, by dramatically reducing the simulation time while enabling the efficient implementation of sensitivity analysis and optimization procedures.

An Open-Source ABAQUS Plug-In for Delamination Analysis of 3D Printed Composites.

This article presents the development and implementation of the Delamination Plug-in, an open-source tool for modeling delamination tests in the ABAQUS software. Specifically designed for stochastic modeling of 3D printed composites, the plug-in combines the benefits of the graphical user interface (GUI) and the programming of commercial finite element (FE) software. The Delamination Plug-in offers an effortless alternative to the time-consuming analytical modeling and GUI work involved in delamination tests and includes algorithms for several tests, such as the double cantilever beam, end-loaded split, end-notched flexure, and modified end-loaded split tests, solved using the virtual crack closure technique and the cohesive zone method. It enables the user to develop simulations for both simple symmetric laminates and generally layered laminates with additional thermal stresses. The applicability of the tool is demonstrated through its use in two distinct delamination problems, one for conventional and one for 3D printed composite laminates, and its results are compared to analytical models and experimental data from the open literature. The results demonstrate that the Delamination Plug-in is efficient and applicable for such materials. This establishes the tool as an important means of automating delamination analysis and for the development and testing of 3D printed composites, making it a valuable tool for both researchers and industry professionals.

Measuring and Predicting the Effects of Residual Stresses from Full-Field Data in Laser-Directed Energy Deposition.

This article presents a novel approach for assessing the effects of residual stresses in laser-directed energy deposition (L-DED). The approach focuses on exploiting the potential of rapidly growing tools such as machine learning and polynomial chaos expansion for handling full-field data for measurements and predictions. In particular, the thermal expansion coefficient of thin-wall L-DED steel specimens is measured and then used to predict the displacement fields around the drilling hole in incremental hole-drilling tests. The incremental hole-drilling test is performed on cubic L-DED steel specimens and the displacement fields are visualized using a 3D micro-digital image correlation setup. A good agreement is achieved between predictions and experimental measurements.