Failure Rate Function Research Articles

Interval estimation for inverse Gaussian distribution

AbstractIn this paper, we consider interval estimation for the inverse Gaussian (IG) distribution. Using generalized pivotal quantity method, we derive the generalized confidence intervals (GCIs) for the model parameters and some quantities such as the quantile, the reliability function of the lifetime, the failure rate function, and the mean residual lifetime. We verify that the GCI of the scale parameter is the same as its commonly used exact CI. We also obtain the generalized prediction intervals (GPIs) for future failure times based on the observed failure data set. In addition, we get the GCI for the reliability of the stress–strength model when the stress and strength variables follow the IG distributions with different parameters. We compare the proposed GCIs and GPIs with the Wald CIs and bootstrap‐ CIs by simulation. The simulation results show that the proposed GCIs and GPIs are superior to the Wald CIs and the bootstrap‐p CIs in terms of the coverage probability. Finally, two examples are used to illustrate the proposed procedures.

On some characterization results of -norm dynamic survival entropies

The information based on entropy of uncertainty associated with the residual life of a random variable is implemented in various fields, e.g., information theory, statistical physics, reliability theory, statistics, demography and economics, etc. In this paper, we propose two new -norm dynamic survival entropy (RNDSE) and -norm weighted dynamic survival entropy (RNWDSE) based on the survival function and some results on stochastic ordering are studied in detail. Further, we have investigated the bounds on RNDSE and RNWDSE in terms of failure rate function. In addition, some relationships between RNDSE, RNWDSE and failure function have also been well established. Finally, in order to illustrate the applications of RNDSE and RNWDSE, some useful distributions like exponential, Rayleigh, Weibull, Pareto, finite range distributions and one new distribution called T-exponential have been characterized.

A New Generalized Lomax Model: Statistical Properties And Applications

In this paper, a new version of the Poisson Lomax distributions is proposed and studied. The new density is expressed as a linear mixture of the Lomax densities. The failure rate function of the new model can be increasing-constant, increasing, U shape, decreasing and upside down-increasing. The statistical properties are derived and four applications are provided to illustrate the importance of the new density. The method of maximum likelihood is used to estimate the unknown parameters of the new density. Adequate fitting is provided by the new model.

Determination of failure rate function on the basis оf the markovian process

The life cycle of a construction (or its element) is considered as markovian process with discrete states and continuous time. Five operational states have been accepted, in which the construction may be. The corresponding system of differential equations is obtained for the case of a homogeneous markovian process with a constant conversion rate (Kolmogorov system). The method of uncertain coefficients is applied to solve the system of equations in analytical form. The obtained solutions make it possible to determine the probability of finding the construction in a particular state as well as the most likely transition time from one operational state to another. Security function defined as the probability of not finding the construction in its last (inoperable) state and the failure rate function. The graphs of the probability of finding a construction in each of the five states, reliability and failure rate functions are presented and investigated. The obtained analytical dependences make it possible to determine the longevity and residual life of the work both individual elements and structures as a whole and optimize scheduling for ongoing maintenance work, significantly improve the performance of the structure, reduce the cost of repair work and extend the life of the structure.

SOME INFERENCES ON OFFSET NORMAL DISTRIBUTION: PROPERTIES AND CHARACTERIZATIONS

The offset normal distribution, defined as the induced shape parameter of a Gaussian random configuration in the plane, is one of the most important probability distributions with tremendous applications both in pure and applied mathematics. In this paper some basic properties of the offset normal distribution are discussed. Based on the basic properties, several characterizations are presented by the left and right truncated moments. The first characterization result is based on a relation between left truncated moment and failure rate function. The second characterization result is based on a relation between right truncated moment and reversed failure rate function.

On the Burr XII-Power Cauchy distribution: Properties and applications

We propose a new four-parameter lifetime model with flexible hazard rate called the Burr XII Power Cauchy (BXII-PC) distribution. We derive the BXII-PC distribution via (ⅰ) the T-X family technique and (ⅱ) nexus between the exponential and gamma variables. The new proposed distribution is flexible as it has famous sub-models such as Burr XII-half Cauchy, Lomax-power Cauchy, Lomax-half Cauchy, Log-logistic-power Cauchy, log-logistic-half Cauchy. The failure rate function for the BXII-PC distribution is flexible as it can accommodate various shapes such as the modified bathtub, inverted bathtub, increasing, decreasing; increasing-decreasing and decreasing-increasing-decreasing. Its density function can take shapes such as exponential, J, reverse-J, left-skewed, right-skewed and symmetrical. To illustrate the importance of the BXII-PC distribution, we establish various mathematical properties such as random number generator, moments, inequality measures, reliability measures and characterization. Six estimation methods are used to estimate the unknown parameters of the proposed distribution. We perform a simulation study on the basis of the graphical results to demonstrate the performance of the maximum likelihood, maximum product spacings, least squares, weighted least squares, Cramer-von Mises and Anderson-Darling estimators of the parameters of the BXII-PC distribution. We consider an application to a real data set to prove empirically the potentiality of the proposed model.

Availability Optimization of Two-dimensional Warranty Products Under Imperfect Preventive Maintenance

For complex and durable products such as automobiles and construction machinery, the quality and reliability characteristics of these products become more and more complex. However, in many cases, the technical ability of users is not enough to perfect the daily maintenance of the product. Warranty policy plays an increasingly important role between manufacturers and users. Aiming at the problem that the availability of the two-dimensional (2D) warranty product is difficult to meet the actual needs of users during the warranty period, this paper makes use of the accelerated failure time (AFT) model to construct the failure rate function of the product based on imperfect preventive maintenance (PM), establishes the 2D warranty availability model and gives an effective solution. On this basis, this paper obtains the optimal PM interval with the numerical algorithm and particle swarm optimization (PSO) taking the maximal availability of the 2D warranty product as the optimization objective and compares the results and speed of the two algorithms. Finally, the validity and accuracy of the model are verified by a numerical example which provides a scientific basis for the manufacturer to formulate the 2D warranty strategy.

A Modification of the Quasi Lindley Distribution

In this paper, we introduce a modification of the Quasi Lindley distribution which has various advantageous properties for the lifetime data. Several fundamental structural properties of the distribution are explored. Its density function can be left-skewed, symmetrical, and right-skewed shapes with various rages of tail-weights and dispersions. The failure rate function of the new distribution has the flexibility to be increasing, decreasing, constant, and bathtub shapes. A simulation study is done to examine the performance of maximum likelihood and moment estimation methods in its unknown parameter estimations based on the asymptotic theory. The potentiality of the new distribution is illustrated by means of applications to the simulated and three real-world data sets.

Modelling the COVID-19 Mortality Rate with a New Versatile Modification of the Log-Logistic Distribution.

The goal of this paper is to develop an optimal statistical model to analyze COVID-19 data in order to model and analyze the COVID-19 mortality rates in Somalia. Combining the log-logistic distribution and the tangent function yields the flexible extension log-logistic tangent (LLT) distribution, a new two-parameter distribution. This new distribution has a number of excellent statistical and mathematical properties, including a simple failure rate function, reliability function, and cumulative distribution function. Maximum likelihood estimation (MLE) is used to estimate the unknown parameters of the proposed distribution. A numerical and visual result of the Monte Carlo simulation is obtained to evaluate the use of the MLE method. In addition, the LLT model is compared to the well-known two-parameter, three-parameter, and four-parameter competitors. Gompertz, log-logistic, kappa, exponentiated log-logistic, Marshall–Olkin log-logistic, Kumaraswamy log-logistic, and beta log-logistic are among the competing models. Different goodness-of-fit measures are used to determine whether the LLT distribution is more useful than the competing models in COVID-19 data of mortality rate analysis.

E‐Bayesian estimation of reliability characteristics of two‐parameter bathtub‐shaped lifetime distribution with application

AbstractThis article presents the expected Bayesian (E‐Bayesian) estimation of the scale parameter, reliability and failure rate functions of two‐parameter bathtub‐shaped lifetime distribution under type‐II censoring data with. Squared error loss function and gamma distribution as a conjugate prior distribution for the unknown parameter are used to obtain the E‐Bayesian estimators. Also, three different prior distributions for the hyperparameters for the E‐Bayesian estimators are considered. Some properties of the E‐Bayesian estimators are studied. Using minimum mean square error criteria, a simulation study is conducted to compare the performance of the E‐Bayesian estimators and the corresponding Bayes and maximum likelihood estimators. A real data set is analysed to show the applicability of the different proposed estimators. The numerical results show that the E‐Bayesian estimators perform better than the classical and Bayesian estimators.

The Marshall-Olkin Odd Burr III-G Family: Theory, Estimation, and Engineering Applications

We propose a new flexible class called the Marshall-Olkin odd Burr III family for generating continuous distributions and derive some of its statistical properties. We provide three special models which accommodate symmetrical, right-skewed and left-skewed shaped densities as well as bathtub, decreasing, increasing, reversed-J shaped and upside-down bathtub failure rate functions. The parameters are estimated by maximum likelihood, least squares and a percentile method. Some simulations investigate the accuracy of the three methods. We illustrate the utility of a special model through three applications to engineering field.

The Weibull log‐logistic mixture distributions: Model, theory and application to lifetime data

AbstractLifetime data collected from reliability tests are among data that often exhibit significant heterogeneity caused by variations in manufacturing, which makes standard lifetime models inadequate. Finite mixture models provide more flexibility for modeling such data. In this paper, the Weibull‐log‐logistic mixture distributions model is introduced as a new class of flexible models for heterogeneous lifetime data. Some statistical properties of the model are presented including the failure rate function, moments generating function, and characteristic function. The identifiability property of the class of all finite mixtures of Weibull‐log‐logistic distributions is proved. The maximum likelihood estimation (MLE) of model parameters under the Type I and Type II censoring schemes is derived. Some numerical illustrations are performed to study the behavior of the obtained estimators. The model is applied to the hard drive failure data made by the Backblaze data center, where it is found that the proposed model provides more flexibility than the univariate life distributions (Weibull, Exponential, logistic, log‐logistic, Frechet). The failure rate of hard disk drives (HDDs) is obtained based on MLE estimates. The analysis of the failure rate function on the basis of SMART attributes shows that the failure of HDDs can have different causes and mechanisms.

Some properties of the failure rate function for mixtures of Erlang distributions

We study some properties of the failure rate for a mixture of Erlang distributions. In particular, we discuss mixtures of Erlang distributions with the same scale parameter and we describe the behavior of the failure rate. Some remarks are also given for an infinite mixture of Erlangs, in particular with regard to stochastic order properties.

A generalization of the Inverse Weibull model: Properties and applications

A new flexible extension of the Inverse Weibull distribution is proposed and studied. The new density can be “right skewed”, “left skewed” and “unimodal” with various shapes, the new failure rate function can be a “decreasing” or “upside down” or “increasing” shaped. Some of its statistical properties are derived. The importance of the new distribution is shown via three applications to real data sets. The new distribution is better fit than many important competitive models based on three real data sets.

Optimal preventive maintenance level for a repairable product under warranty subject to multimode failure process

PurposeThe purpose of this paper is to develop a model that determines whether how much effort of preventive maintenance action is worthwhile for the consumer over the post-sale product life cycle of a repairable complex product where the product is under warranty and subject to stochastic multimode failure process, that is, damaging failure and light failure with different probabilities.Design/methodology/approachThe expected life cycle cost is designed for a warranted product from the consumer perspective. The product failure is quantified with failure rate function, which is the number of failures incurred over the product life cycle. The authors consider the failure rate function reduction method in their model where the scale parameter of a failure rate function is maximized by applying the optimal preventive maintenance level. The scale parameter of any failure distribution refers to the meantime to failure (MTTF). The first-order condition is applied with respect to the maintenance level in order to achieve the convexity of the nonlinear function of the expected life cycle cost function.FindingsThe authors have found analytically the close form of the preventive maintenance level, which can be used to find the optimal reduced form of the failure rate function of the product and the minimum product expected life cycle cost under the given condition of multimode stochastic failure process. The authors have suggested different maintenance policies to consumers in order to implement the proposed preventive maintenance model under different conditions. A numerical example further illustrated the analytical model by considering the Weibull distribution.Practical implicationsThe consumer may use this study in the accurate modeling of the life cycle cost of a product that is under warranty and fails with a multimode failure process. Also, the suggested preventive maintenance approach of this study helps the consumer in making appropriate maintenance decisions such as to minimize the expected life cycle cost of a product.Originality/valueThis study proposes an accurate estimation of a life cycle cost for a product that is under the support of warranty and fails with multimode. Furthermore, for such a kind of product, which is under warranty and fails with multimode, this study suggests a new preventive maintenance approach that assures the minimum expected life cycle cost.

A New Flexible Generalized Lindley Model: Properties, Estimation and Applications

A new method for generalizing the Lindley distribution, by increasing the number of mixed models is presented formally. This generalized model, which is called the generalized Lindley of integer order, encompasses the exponential and the usual Lindley distributions as special cases when the order of the model is fixed to be one and two, respectively. The moments, the variance, the moment generating function, and the failure rate function of the initiated model are extracted. Estimation of the underlying parameters by the moment and the maximum likelihood methods are acquired. The maximum likelihood estimation for the right censored data has also been discussed. In a simulation running for various orders and censoring rates, efficiency of the maximum likelihood estimator has been explored. The introduced model has ultimately been fitted to two real data sets to emphasize its application.

Comparison of estimators under different loss functions for two-parameter bathtub - shaped lifetime distribution

Chen is suggested a two-parameter distribution. This distribution can have increasing failure rate function or a bathtub-shaped that allows it to fit real lifetime data sets. The ML (Maximum Likelihood) and Bayes estimates of the parameters of Chen’s distribution are constituted in this paper. The approximate values of Bayesian estimates are obtained by using the Tierney-Kadane approach. Two-parameter bathtub-shaped distribution's estimations are derived using Jeffrey's extension prior under General entropy, Squared and Linex loss functions. Besides, performances of ML and Bayes estimates are compared concerning MSE's (Mean Square Error) by using Monte Carlo simulation. As a result, it has been seen that approximate Bayes estimates obtained under linex loss function are better than others. Moreover, real data analysis for his distribution is presented.

E- Bayesian Estimation of System Reliability (Series, Parallel) and Failure Rate Functions with Kumaraswamy Distribution based on Type II Censoring Data

In this paper, the failure rate function and the shape parameter for the kumaraswamy distribution and reliability function of a system with a number (m) of independent compounds associated with a system (serial, parallel) were estimated, by relying on observational data of the second type, knowing that the survival time of the compounds are independent. Based on the findings the graphical predictor of the failure rate and parameter - and the reliability function of the serial and parallel system is smaller than the Standard Bayesian estimator (MLE) in simulation and real data. Thus, a decreasing in AMPE with an increase in the sample size n and an increase in the size of the failure sample r as the physical prediction capabilities have a high efficiency. The using of the Bayesian prediction method to estimate the reliability of different production systems for other failure distributions such as the Burr family distributions and various other failure distributions. Based on the output he results are reasonably consistent with simulation and real data. The E-Bayesian method was used for estimating with three primary distribution functions for the above parameters and comparing them with the standard Bayesian method with a squared loss function and the maximum likelihood method where simulation experiments were employed to compare the estimation results and the results showed the advantage of the E-Bayesian method in estimating through comparison statistics (MAPE).

A New Modified Kies Family: Properties, Estimation Under Complete and Type-II Censored Samples, and Engineering Applications

In this paper, we introduce a new family of continuous distributions that is called the modified Kies family of distributions. The main mathematical properties of the new family are derived. A special case of the new family has been considered in more detail; namely, the two parameters modified Kies exponential distribution with bathtub shape, decreasing and increasing failure rate function. The importance of the new distribution comes from its ability in modeling positively and negatively skewed real data over some generalized distributions with more than two parameters. The shape behavior of the hazard rate and the mean residual life functions of the modified Kies exponential distribution are discussed. We use the method of maximum likelihood to estimate the distribution parameters based on complete and type-II censored samples. The approximate confidence intervals are also obtained under the two schemes. A simulation study is conducted and two real data sets from the engineering field are analyzed to show the flexibility of the new distribution in modeling real life data.

A Generalization of Binomial Exponential-2 Distribution: Copula, Properties and Applications

In this paper, we propose a new three-parameter lifetime distribution for modeling symmetric real-life data sets. A simple-type Copula-based construction is presented to derive many bivariate- and multivariate-type distributions. The failure rate function of the new model can be “monotonically asymmetric increasing”, “increasing-constant”, “monotonically asymmetric decreasing” and “upside-down-constant” shaped. We investigate some of mathematical symmetric/asymmetric properties such as the ordinary moments, moment generating function, conditional moment, residual life and reversed residual functions. Bonferroni and Lorenz curves and mean deviations are discussed. The maximum likelihood method is used to estimate the model parameters. Finally, we illustrate the importance of the new model by the study of real data applications to show the flexibility and potentiality of the new model. The kernel density estimation and box plots are used for exploring the symmetry of the used data.