A Denoising Based Autoassociative Model for Robust Sensor Monitoring in Nuclear Power Plants
Open Access
- 22 March 2016
- journal article
- research article
- Published by Wiley in Science and Technology of Nuclear Installations
- Vol. 2016, 1-17
Abstract
Sensors health monitoring is essentially important for reliable functioning of safety-critical chemical and nuclear power plants. Autoassociative neural network (AANN) based empirical sensor models have widely been reported for sensor calibration monitoring. However, such ill-posed data driven models may result in poor generalization and robustness. To address above-mentioned issues, several regularization heuristics such as training with jitter, weight decay, and cross-validation are suggested in literature. Apart from these regularization heuristics, traditional error gradient based supervised learning algorithms for multilayered AANN models are highly susceptible of being trapped in local optimum. In order to address poor regularization and robust learning issues, here, we propose a denoised autoassociative sensor model (DAASM) based on deep learning framework. Proposed DAASM model comprises multiple hidden layers which are pretrained greedily in an unsupervised fashion under denoising autoencoder architecture. In order to improve robustness, dropout heuristic and domain specific data corruption processes are exercised during unsupervised pretraining phase. The proposed sensor model is trained and tested on sensor data from a PWR type nuclear power plant. Accuracy, autosensitivity, spillover, and sequential probability ratio test (SPRT) based fault detectability metrics are used for performance assessment and comparison with extensively reported five-layer AANN model by Kramer.Keywords
This publication has 22 references indexed in Scilit:
- Using cross-validation for model parameter selection of sequential probability ratio testExpert Systems with Applications, 2012
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- The AutoAssociative Neural Network in signal analysis: II. Application to on-line monitoring of a simulated BWR componentAnnals of Nuclear Energy, 2005
- Probabilistic model for sensor fault detection and identificationAIChE Journal, 2003
- On-line monitoring of instrument channel performance in nuclear power plant using PEANOProgress in Nuclear Energy, 2003
- Heuristic, systematic, and informational regularization for process monitoringInternational Journal of Intelligent Systems, 2002
- Detection, identification, and reconstruction of faulty sensors with maximized sensitivityAIChE Journal, 1999
- Reducing data dimensionality through optimizing neural network inputsAIChE Journal, 1995
- Autoassociative neural networksComputers & Chemical Engineering, 1992
- Sequential Tests of Statistical HypothesesThe Annals of Mathematical Statistics, 1945