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/

Zendy Plus

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

Zendy Tools

Zendy Open

We present a data-enabled physics-informed neural network (DEPINN) withcomprehensive numerical study for solving industrial scale neutron diffusioneigenvalue problems (NDEPs). In order to achieve an engineering acceptableaccuracy for complex engineering problems, a very small amount of prior datafrom physical experiments are suggested to be used, to improve the accuracy andefficiency of training. We design an adaptive optimization procedure with Adamand LBFGS to accelerate the convergence in the training stage. We discuss theeffect of different physical parameters, sampling techniques, loss functionallocation and the generalization performance of the proposed DEPINN model forsolving complex problem. The feasibility of proposed DEPINN model is tested onthree typical benchmark problems, from simple geometry to complex geometry, andfrom mono-energetic equation to two-group equations. Numerous numerical resultsshow that DEPINN can efficiently solve NDEPs with an appropriate optimizationprocedure. The proposed DEPINN can be generalized for other input parametersettings once its structure been trained. This work confirms the possibility ofDEPINN for practical engineering applications in nuclear reactor physics.

A data-enabled physics-informed neural network with comprehensive numerical study on solving neutron diffusion eigenvalue problems