Deep Transformer Networks for Time Series Classification: The NPP Safety Case

04/09/2021
by   Bing Zha, et al.
0

A challenging part of dynamic probabilistic risk assessment for nuclear power plants is the need for large amounts of temporal simulations given various initiating events and branching conditions from which representative feature extraction becomes complicated for subsequent applications. Artificial Intelligence techniques have been shown to be powerful tools in time-dependent sequential data processing to automatically extract and yield complex features from large data. An advanced temporal neural network referred to as the Transformer is used within a supervised learning fashion to model the time-dependent NPP simulation data and to infer whether a given sequence of events leads to core damage or not. The training and testing datasets for the Transformer are obtained by running 10,000 RELAP5-3D NPP blackout simulations with the list of variables obtained from the RAVEN software. Each simulation is classified as "OK" or "CORE DAMAGE" based on the consequence. The results show that the Transformer can learn the characteristics of the sequential data and yield promising performance with approximately 99 the testing dataset.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

07/18/2019

Post-Earthquake Assessment of Buildings Using Deep Learning

Classification of the extent of damage suffered by a building in a seism...
09/09/2019

Forecaster: A Graph Transformer for Forecasting Spatial and Time-Dependent Data

Spatial and time-dependent data is of interest in many applications. Thi...
05/13/2021

Paying Attention to Astronomical Transients: Photometric Classification with the Time-Series Transformer

Future surveys such as the Legacy Survey of Space and Time (LSST) of the...
04/30/2021

Is Core Damage Frequency an Informative Risk Metric?

Core Damage Frequency (CDF) is a risk metric often employed by nuclear r...
10/19/2018

Stochastic temporal data upscaling using the generalized k-nearest neighbor algorithm

Three methods of temporal data upscaling, which may collectively be call...
05/31/2019

Deterministic and stochastic damage detection via dynamic response analysis

The paper proposes a method of damage detection in elastic materials, wh...
05/02/2018

A Data-Driven Residential Transformer Overloading Risk Assessment Method

Residential transformer population is a critical type of asset that many...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.