Plastic crack-tip fields under thermoplastic loads

Ebrahimi, Saman; Rabczuk, Timon; Anitescu, Cosmin

doi:10.1016/j.euromechsol.2022.104805

Cited by 3 publications

(1 citation statement)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, Cosmin Anitescu et al ingeniously connected fundamental boundary value problems (BVPs) to the loss function, utilizing deep neural networks (DNNs) as function approximators to address approximate PDEs. Their methodology leveraged mechanical system energy as the foundation for constructing the loss function, ultimately validating its efficacy across multiple engineering scenarios. − The approach of relating the underlying BVP to the loss function is impressive, but for additive compounding experiments, general empirical formulas do not usually exist, which means it is difficult to express the problem in terms of a partial differential equation (PDE). The traditional method of lubricant design involves designing formulation parameters empirically, determining tribological properties through friction and wear experiments after preparation, and repeating the process until optimal ratios are found .…”

Section: Introductionmentioning

confidence: 99%

GNBoost-Based Ensemble Machine Learning for Predicting Tribological Properties of Liquid-Crystal Lubricants

Shi,

Li,

Guo

et al. 2024

Langmuir

View full text Add to dashboard Cite

The intricate development of liquid-crystal lubricants necessitates the timely and accurate prediction of their tribological performance in different environments and an assessment of the importance of relevant parameters. In this study, a classification model using Gaussian noise extreme gradient boosting (GNBoost) to predict tribological performance is proposed. Three additives, polysorbate-85, polysorbate-80, and graphene oxide, were selected to fabricate liquid-crystal lubricants. The coefficients of friction of these lubricants were tested in the rotational mode using a universal mechanical tester. A model was designed to predict the coefficient of friction through data augmentation of the initial data. The model parameters were optimized using particle swarm optimization techniques. This study provides an effective example for lubricant performance evaluation and formulation optimization.

show abstract