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

During applying data-oriented diagnosis systems to distinguishing the type ofand evaluating the severity of nuclear power plant initial events, it is ofvital importance to decide which parameters to be used as the system input.However, although several diagnosis systems have already achieved acceptableperformance in diagnosis precision and speed, hardly have the researchersdiscussed the method of monitoring point choosing and its layout. For thisreason, redundant measuring data are used to train the diagnostic model,leading to high uncertainty of the classification, extra training timeconsumption, and higher probability of overfitting while training. In thisstudy, a method of choosing thermal hydraulics parameters of a nuclear powerplant is proposed, using the theory of post-hoc interpretability theory in deeplearning. At the start, a novel Time-sequential Residual Convolutional NeuralNetwork (TRES-CNN) diagnosis model is introduced to identify the position andhydrodynamic diameter of breaks in LOCA, using 38 parameters manually chosen onHPR1000 empirically. Afterwards, post-hoc interpretability methods are appliedto evaluate the attributions of diagnosis model's outputs, deciding which 15parameters to be more decisive in diagnosing LOCA details. The results showthat the TRES-CNN based diagnostic model successfully predicts the position andsize of breaks in LOCA via selected 15 parameters of HPR1000, with 25% of timeconsumption while training the model compared the process using total 38parameters. In addition, the relative diagnostic accuracy error is within 1.5percent compared with the model using parameters chosen empirically, which canbe regarded as the same amount of diagnostic reliability.

Post-hoc Interpretability based Parameter Selection for Data Oriented Nuclear Reactor Accident Diagnosis System