Nuclear Power Plant Status Diagnostics Using an Artificial Neural Network

Bartlett, E.B.; Uhrig, R.E.

doi:10.13182/nt92-a34635

Cited by 157 publications

(40 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This continues for a predefined number of generations or until the problem is sufficiently optimized. GA has parallel search strategy and global optimization characteristics which helps the ANN to have a higher prediction accuracy and faster convergence compared to BP [24]. However the genetic operators like crossover and mutation are inherently complex and hence make the computational cost to increase exponentially [25].…”

Section: [3] [4] [5] [6] [7] [8]mentioning

confidence: 99%

Improving Fault Prediction using ANN-PSO in Object Oriented Systems

Kayarvizhy¹,

Kanmani²,

Uthariaraj³

2013

IJCA

View full text Add to dashboard Cite

Object oriented software metrics are computed and used in predicting software quality attributes of object oriented systems. Mapping software metrics to software quality attributes like fault prediction is a complex process and requires extensive computations. Many models have been proposed for fault prediction. Since accuracy is of prime importance in prediction models they are being constantly improved through various research studies. Artificial Neural network (ANN) has gained immense popularity due to its adaptability to the problem at hand by training with known data. Back propagation is a widely used ANN training technique. However the back propagation technique leads to slow convergence rate and an impending threat of getting caught in local minima. In this paper we explore the Particle Swarm Optimization (PSO) technique as an alternative to optimize the weights of ANN for fault prediction in object oriented systems. We evaluate the effect on prediction accuracy that PSO brings to ANN compared to other techniques like BP and Genetic Algorithm (GA). We also evaluate prediction accuracy improvements by optimizing the various parameters of PSO.

show abstract

Section: [3] [4] [5] [6] [7] [8]mentioning

confidence: 99%

Improving Fault Prediction using ANN-PSO in Object Oriented Systems

Kayarvizhy¹,

Kanmani²,

Uthariaraj³

2013

IJCA

View full text Add to dashboard Cite

show abstract

“…Recently, data processing algorithms based on artificial intelligence gained popularity in nuclear technology. In particular, ANNs found their application in a wide range of problems (Uhrig & Tsoukalas, 1999), such as diagnostics (Bartlett & Uhrig, 1992;Kim et al, 1992), signal validation (Fantoni & Mazzola, 1996a;1996b), anomalies detection (Ogha & Seki, 1991;Kozma & Nabeshima, 1995;Reifman, 1997) and core monitoring . ANNs allow modeling of complex systems without requiring an explicit knowledge or formulation of the relationship existing among the variables, and they can constitute a valuable alternative to structured models or empirical correlations (Thibault & Grandjean, 1991).…”

Section: Case Study For Nuclear Engineeringmentioning

confidence: 99%

Case Studies for Applications of Elman Recurrent Neural Networks

Übeylı¹,

Übeylı²

2008

Recurrent Neural Networks

View full text Add to dashboard Cite

“…The work of Bartlett and Uhrig 48 has been extended by Kim and Bartlett 50 to address the issue of accuracy of the previous fault diagnosis algorithms. A method presented in ref.…”

Section: Fault Detection and Identificationmentioning

confidence: 99%

Autonomous Control of Nuclear Power Plants

Basher¹

2003

View full text Add to dashboard Cite

Nuclear Power Plant Status Diagnostics Using an Artificial Neural Network

Cited by 157 publications

References 2 publications

Improving Fault Prediction using ANN-PSO in Object Oriented Systems

Improving Fault Prediction using ANN-PSO in Object Oriented Systems

Case Studies for Applications of Elman Recurrent Neural Networks

Autonomous Control of Nuclear Power Plants

Contact Info

Product

Resources

About