Reliability Assessment Measures Research Articles

An alternative approach for estimating above ground biomass using Resourcesat-2 satellite data and artificial neural network in Bundelkhand region of India.

Determination of above ground biomass (AGB) of any forest is a longstanding scientific endeavor, which helps to estimate net primary productivity, carbon stock and other biophysical parameters of that forest. With advancement of geospatial technology in last few decades, AGB estimation now can be done using space-borne and airborne remotely sensed data. It is a well-established, time saving and cost effective technique with high precision and is frequently applied by the scientific community. It involves development of allometric equations based on correlations of ground-based forest biomass measurements with vegetation indices derived from remotely sensed data. However, selection of the best-fit and explanatory models of biomass estimation often becomes a difficult proposition with respect to the image data resolution (spatial and spectral) as well as the sensor platform position in space. Using Resourcesat-2 satellite data and Normalized Difference Vegetation Index (NDVI), this pilot scale study compared traditional linear and nonlinear models with an artificial intelligence-based non-parametric technique, i.e. artificial neural network (ANN) for formulation of the best-fit model to determine AGB of forest of the Bundelkhand region of India. The results confirmed the superiority of ANN over other models in terms of several statistical significance and reliability assessment measures. Accordingly, this study proposed the use of ANN instead of traditional models for determination of AGB and other bio-physical parameters of any dry deciduous forest of tropical sub-humid or semi-arid area. In addition, large numbers of sampling sites with different quadrant sizes for trees, shrubs, and herbs as well as application of LiDAR data as predictor variable were recommended for very high precision modelling in ANN for a large scale study.

An All-Stage Truncated Multiple Change Point Model for Software Reliability Assessment

We propose a software reliability growth modeling framework with multiple change point occurrence environment. Especially in our modeling framework, the probability distribution of the initial fault content follows a zero-truncated Poisson distribution. Therefore, our modeling approach in this paper can derive the proper mean time between software failures (MTBF), which is one of the important reliability assessment measures and is not able to derive in the usual nonhomogeneous Poisson process modeling, which is one of the well-known software reliability modeling approach. This paper also show numerical examples of application of our proposed multiple change point model to software reliability assessment by using actual fault counting data.

NONPARAMETRIC BOOTSTRAP INTERVAL ESTIMATION OF SOFTWARE RELIABILITY AND ITS APPLICATION TO AN OPTIMAL RELEASE PROBLEM BASED ON A DISCRETIZED MODEL

We discuss a simulation-based interval estimation method of software reliability and cost-optimal software release time based on a nonparametric bootstrap method via a discretized software reliability growth model. In general, it is very difficult to derive probability distributions of model parameters, software reliability assessment measures, and optimal software release time analytically even if we assume an asymptotic theory assuming a large number of samples. The bootstrap method overcomes the problem above by obtaining the probability distributions of the parameter based on the simulation-based approach. This paper includes numerical examples for confirming that our bootstrap approach yields simulation-based probability distributions of model parameters, software reliability assessment measures, and cost-optimal software release time from actual software fault-count data.

A Bootstrapping Approach for Software Reliability Measurement Based on a Discretized NHPP Model

Discrete software reliability measurement has a proper characteristic for describing a software reliability growth process which depends on a unit of the software fault-detection period, such as the number of test runs, the number of executed test cases. This paper discusses discrete software reliability measurement based on a discretized nonhomogeneous Poisson process (NHPP) model. Especially, we use a bootstrapping method in our discrete software reliability measurement for discussing the statistical inference on parameters and software reliability assessment measures of our model. Finally we show numerical examples of interval estimations based on our bootstrapping method for the several software reliability assessment measures by using actual data.

Lognormal Process Software Reliability Modeling with Testing-Effort

We propose a software reliability growth model with testing-effort based on a continuous-state space stochastic process, such as a lognormal process, and conduct its goodness-of-fit evaluation. We also discuss a parameter estimation method of our model. Then, we derive several software reliability assessment measures by the probability distribution of its solution process, and compare our model with existing continuous-state space software reliability growth models in terms of the mean square error and the Akaike’s information criterion by using actual fault count data.

Protection Dynamic Reliability Analysis System Based on 3RF Technique

Seeking a protection reliability system about basic data accumulation, reliability assessment, and improvement measures application has attracted attentions, but there are few discussions about its establishment. Based on characteristics of protection reliability, “3RF” technique-relay failure mode effect analysis (RFMEA), relay fault tree analysis (RFTA), relay failure reporting, analysis, and corrective active system (RFRACAS) is proposed, which could be used as a tool for protection reliability data collection, reliability modeling and quantitative analysis, as well as improvement measures formation. In RFMEA, protection failures are classified and an example of functional protection hardware RFMEA is given. In RFTA, a dynamic fault tree (DFT) model and its quantitative analysis based on sequential Monte Carlo (SMC) simulation is proposed to supply a basis for assessing protection reliability, searching weakness, and improving design and operation reliability of repairable redundant digital protection system. An application in a practical protective production is given to demonstrate the effectiveness of the proposed method. A closed-loop RFRACAS of protection system is illustrated. The combination of RFMEA, RFTA, and RFRACAS is analyzed at last.

Investigating the reliability and criticality of the maintenance characteristics of a diving support vessel

Maintenance tasks and their application in the shipping industry have evolved significantly in the recent years. Particularly in the offshore industry, safety onboard, environmental protection and intensive operational activities necessitate the minimization of down-time and the preservation of an excellent performance ratio. The first step of an innovative ship maintenance strategy, which is proposed by the authors and is based on criticality and reliability assessment, is presented herein using the FTA tool with time-dependant dynamic gates so as to represent in an accurate and comprehensive way the interrelation of the components of a system. The paper also presents a review of the maintenance standards and procedures, such as the ALARP concept, the Key Programme 3-Asset Integrity (KP3) initiative, the OREDA handbook as well as the RCM and RBI principles. As part of the reliability assessment, the Birnbaum and Criticality reliability importance measures are utilized to validate the results of the analysis. A case study of a diving support vessel (DSV) illustrates the application of this strategy. The main systems examined are: the vessel's power plant, propulsion, water system, lifting, hauling and anchoring, diving and finally the safety system. The reliability of the main systems and subsystems as well as of their critical components is identified and suggestions of how to improve the overall reliability of the various systems both at a component, system and managerial level are also proposed. Copyright © 2011 John Wiley & Sons, Ltd.

GENERALIZED MARKOVIAN SOFTWARE RELIABILITY MODELING AND ITS ALTERNATIVE CALCULATION

In this paper, we attempt generalization of the Markovian software reliability model (MSRM). Defining the stochastic process whose state space is the cumulative number of corrected faults, we show the theoretical framework of the MSRM by assuming that the time interval between software failures is distributed generally. We also consider the imperfect debugging environment where the debugging activities are uncertain. Several software reliability assessment measures are expressed with the distribution of the transition time between arbitrary two states. Furthermore, we propose the approximation method for practical computation of the quantitative measures. Finally, we investigate the validity of our proposed approximation method.

BOOTSTRAP CONFIDENCE INTERVALS OF SOFTWARE RELIABILITY MEASURES BASED ON A GAMMA FUNCTION MODEL

This paper focuses on the generalization of several software reliability models and the derivation of confidence intervals of reliability assessment measures. First we propose a gamma function model as a generalized model, and discuss how to obtain the confidence intervals from a data set by using a bootstrap scheme when the size of the data set is small. A two-parameter numerical differentiation method is applied to the data set to estimate the model parameters. We also show several numerical illustrations of software reliability assessment.

Discrete Program-Size Dependent Software Reliability Assessment: Modeling, Estimation, and Goodness-of-Fit Comparisons

In this paper we propose a discrete program-size dependent software reliability growth model flexibly describing the software failure-occurrence phenomenon based on a discrete Weibull distribution. We also conduct model comparisons of our discrete SRGM with existing discrete SRGMs by using actual data sets. The program size is one of the important metrics of software complexity. It is known that flexible discrete software reliability growth modeling is difficult due to the mathematical manipulation under a conventional modeling-framework in which the time-dependent behavior of the cumulative number of detected faults is formulated by a difference equation. Our discrete SRGM is developed under an existing unified modeling-framework based on the concept of general order-statistics, and can incorporate the effect of the program size into software reliability assessment. Further, we discuss the method of parameter estimation, and derive software reliability assessment measures of our discrete SRGM. Finally, we show numerical examples of discrete software reliability analysis based on our discrete SRGM by using actual data.

Generalized Discrete Software Reliability Modeling With Effect of Program Size

Generalized methods for software reliability growth modeling have been proposed so far. But, most of them are on continuous-time software reliability growth modeling. Many discrete software reliability growth models (SRGM) have been proposed to describe a software reliability growth process depending on discrete testing time such as the number of days (or weeks); the number of executed test cases. In this paper, we discuss generalized discrete software reliability growth modeling in which the software failure-occurrence times follow a discrete probability distribution. Our generalized discrete SRGMs enable us to assess software reliability in consideration of the effect of the program size, which is one of the influential factors related to the software reliability growth process. Specifically, we develop discrete SRGMs in which the software failure-occurrence times follow geometric and discrete Rayleigh distributions, respectively. Moreover, we derive software reliability assessment measures based on a unified framework for discrete software reliability growth modeling. Additionally, we also discuss optimal software release problems based on our generalized discrete software reliability growth modeling. Finally, we show numerical examples of software reliability assessment by using actual fault-counting data

Software reliability growth model with continuous error domain—application of a linear stochastic differential equation

AbstractThis paper considers the software error detection process in the testing phase, which is the final stage of the software development. The process is modeled by a stochastic process with a continuous changing variable. Employing a new mathematical technique based on the stochastic differential equation, a new software reliability growth model is constructed.First, the traditional basic differential equation, which describes the average behavior in time of the number of errors, is extended to the Itǒ‐type stochastic differential equation, and the probability distribution of the solution process is investigated. Then, using the derived distribution, several reliability assessment measures are derived.Finally, the unknown parameters of the model are estimated based on the actual test data, and the stochastic property of the temporal variation of the errors remaining in the software is examined numerically. Using MTBF (mean‐time between failure), which is the important reliability assessment measure, the problem to determine the release time of the software is discussed.

Software Reliability Growth Models with Testing-Effort

Many software reliability growth models have been proposed in the past decade. Those models tacitly assume that testing-effort expenditures are constant throughout software testing. This paper develops realistic software reliability growth models incorporating the effect of testing-effort. The software error detection phenomenon in software testing is modeled by a nonhomogeneous Poisson process. The software reliability assessment measures and the estimation methods of parameters are investigated. Testing-effort expenditures are described by exponential and Rayleigh curves. Least-squares estimators and maximum likelihood estimators are used for the reliability growth parameters. The software reliability data analyses use actual data. The software reliability growth models with testing-effort can consider the relationship between the software reliability growth and the effect of testing-effort. Thus, the proposed models will enable us to evaluate software reliability more realistically.