Using neural networks in reliability prediction (original) (raw)

Neural-network-based reliability analysis: a comparative study

Computer Methods in Applied Mechanics and Engineering, 2001

A study on the applicability of dierent kinds of neural networks for the probabilistic analysis of structures, when the sources of randomness can be modeled as random variables, is summarized. The networks are employed as numerical devices for substituting the ®nite element code needed by Monte Carlo simulation. The comparison comprehends two network types (multi-layer perceptrons and radial basis functions classi®ers), cost functions (sum of square errors and cross-entropy), optimization algorithms (back-propagation, Gauss±Newton, Newton±Raphson), sampling methods for generating the training population (using uniform and actual distributions of the variables) and purposes of neural network use (as functional approximators and data classi®ers). The comparative study is performed over four examples, corresponding to dierent types of the limit state function and structural behaviors. The analysis indicates some recommended ways of employing neural networks in this ®eld. Ó

2.1.2 Predicting the Reliability of a Complex System Using an Artificial Neural Network

INCOSE International Symposium, 2004

The capability to predict the reliability of complex systems that must be deployed without overly prolonged or expensive testing is of increasing importance to the military test and evaluation community. The presentation of subsystem reliability data to an artificial neural network is a critical factor in the capability of such networks to produce accurate system predictions. By producing a matrix of values corresponding to subsystem reliabilities, using a zero (0) for a nonexistent parallel resource and a one (1) for a nonexistent series subsystem, it was possible to train an artificial neural network to accurately predict the overall system reliability.

Prediction of software reliability using neural networks

Proceedings. 1991 International Symposium on Software Reliability Engineering, 1991

Software reliability growth models have achieved considerable importance in estimating reliability of software products. This paper explores the use of feed-forward neural networks as a model for software reliability growth prediction. To empirically evaluate the predictive capability of this new approach data sets from di erent software projects are used. The neural networks approach exhibits a consistent behavior in prediction and the predictive performance is comparable to that of parametric models.

IEEE_Paper_2006_Reliability_ANN_New.pdf

This paper presents a new methodology for reliability evaluation of composite generation and transmission systems, based on non-sequential Monte-Carlo simulation and artificial neural network concepts. Artificial neural network (ANN) techniques are used to classify the operating states during the Monte Carlo sampling. A polynomial network, named Group Method Data Handling (GMDH), is used and the states analyzed during the beginning of the simulation process are adequately selected as input data for training and test sets. Based on this procedure, a great number of success states are classified by a simple polynomial function, given by the ANN model, providing significant reductions in the computational cost. Moreover, all types of composite reliability indices (i.e.

An Artificial Neural-Network-Based Approach to Software Reliability Assessment

TENCON 2005 - 2005 IEEE Region 10 Conference, 2005

In this paper, we propose an artificial neuralnetwork-based approach for software reliability estimation and modeling. We first explain the network networks from the mathematical viewpoints of software reliability modeling. That is, we will show how to apply neural network to predict software reliability by designing different elements of neural networks. Furthermore, we will use the neural network approach to build a dynamic weighted combinational model. The applicability of proposed model is demonstrated through four real software failure data sets. From experimental results, we can see that the proposed model significantly outperforms the traditional software reliability models.

Software Reliability Prediction using Neural Network with Encoded Input

A neural network based software reliability model to predict the cumulative number of failures based on Feed Forward architecture is proposed in this paper. Depending upon the available software failure count data, the execution time is encoded using Exponential and Logarithmic function in order to provide the encoded value as the input to the neural network. The effect of encoding and the effect of different encoding parameter on prediction accuracy have been studied. The effect of architecture of the neural network in terms of hidden nodes has also been studied. The performance of the proposed approach has been tested using eighteen software failure data sets. Numerical results show that the proposed approach is giving acceptable results across different software projects. The performance of the approach has been compared with some statistical models and statistical models with change point considering three datasets. The comparison results show that the proposed model has a good prediction capability.

Conceptual Software Reliability Model using Neural Network

International Journal of Computer Applications, 2015

Reliability is the one of the most important attribute of the software for customer satisfaction. It is big challenge for the software development organizations to achieve the reliability of the software. Since research on software reliability is being carried out for last three decades and various software reliability models have been developed. These models calculate the reliability of the software and help to take decision to deploy the software or continue the testing process to meet the reliability objective. The models used so far, worked on the basis of some conventions which must be made before the beginning of the project like software development environment, the nature of software failures, the probability of individual failures. Recent research in the field of the Neural Network can also be applied to calculate the software reliability. The best thing to use Neural Network is to calculate the reliability without making any basic assumptions. In this paper, a conceptual model is proposed to develop the software reliability model using the approach of Neural Network.

Reliability Estimation and Optimization: A Neuro Fuzzy Based Approach

IJCSIS, 2018

Abstract — Software reliability, generally utilized on the present day, is the development of software utilizing a few current software parts. In this paper, we have proposed a model which makes the use of three parameters: Complexity, Changeability and Portability. The software reliability computing using Neural Network, Fuzzy-Logic as well as Neuro-Fuzzy. The considered model shows that Neuro-Fuzzy strategy is prepared well and predicts attractive outcomes thorough Mean Absolute Relative Error and another is Mean Relative Error whereas distinguished along new computing methods. Keywords- component; Software Reliability, Complexity, Changeability, Portability, Neural Networks, ANFIS, Fuzzy Logic

A General Neural Network Model for Estimating Telecommunications Network Reliability

IEEE Transactions on Reliability, 2009

This paper puts forth a new encoding method for using neural network models to estimate the reliability of telecommunications networks with identical link reliabilities. Neural estimation is computationally speedy, and can be used during network design optimization by an iterative algorithm such as tabu search, or simulated annealing. Two significant drawbacks of previous approaches to using neural networks to model system reliability are the long vector length of the inputs required to represent the network link architecture, and the specificity of the neural network model to a certain system size. Our encoding method overcomes both of these drawbacks with a compact, general set of inputs that adequately describe the likely network reliability. We computationally demonstrate both the precision of the neural network estimate of reliability, and the ability of the neural network model to generalize to a variety of network sizes, including application to three actual large scale communications networks.