English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this research, the application of the Physics-Informed Neural Network(PINN) model is explored to solve transport equation-based Partial DifferentialEquations (PDEs). The primary objective is to analyze the impact of differentactivation functions incorporated within the PINN model on its predictiveperformance, specifically assessing the Mean Squared Error (MSE) and MeanAbsolute Error (MAE). The dataset used in the study consists of a varied set ofinput parameters related to strut diameter, unit cell size, and thecorresponding yield stress values. Through this investigation the aim is tounderstand the effectiveness of the PINN model and the significance of choosingappropriate activation functions for solving complex PDEs in real-worldapplications. The outcomes suggest that the choice of activation function mayhave minimal influence on the model's predictive accuracy for this particularproblem. The PINN model showcases exceptional generalization capabilities,indicating its capacity to avoid overfitting with the provided dataset. Theresearch underscores the importance of striking a balance between performanceand computational efficiency while selecting an activation function forspecific real-world applications. These valuable findings contribute toadvancing the understanding and potential adoption of PINN as an effective toolfor solving challenging PDEs in diverse scientific and engineering domains.

Transport Equation based Physics Informed Neural Network to predict the Yield Strength of Architected Materials