This is the first issue of the year 2014 and the International Journal of Performability Engineering (IJPE) enters the 10^th year of its publication. We are sometimes receiving queries from students, teachers and researchers expecting promotions, and also from some librarians, particularly from India about the impact factor of IJPE. Let us not forget that IJPE is a highly specialized technical journal. In this issue, for the benefit of our readers, we have explained on page 94 of this issue what does impact factor with its limitations and applicability signify. We also bring to our readers a note, on pages 119-120, on the visibility factor of IJPE in the scientific world which would inform our readers how IJPE has fared since its inception.in 2005. I must say here that we are not in competition with any other journal but we will continue to provide the best of literature to the profession we are engaged in and I leave it to our readers to judge after reading these two notes to assess the value and usefulness of contributions that this journal has made to the scientific world over years.

As usual, we present to our readers a section on the Accelerated Life Testing, in this issue. We all know that the greatest contribution of reliability engineering is not only to be able to quantify and design reliability in products but also to demonstrate it through tests. The objective of reliability testing is to ferret out potential problems with the design as early as possible and provide confidence that the system meets its reliability requirements.

Accelerated life testing of a product is often resorted to by subjecting the product to stresses in excess of its normal conditions of use in order to uncover faults and potential modes of failure in a short amount of time in the laboratory. The stresses can be any of the environmental stresses of use such as temperature, vibration, voltage, pressure, humidity, cycling rate etc. This kind of testing is particularly necessitated in case of high reliability products since it may take a very long time before a failure is encountered in normal environmental conditions of use. The main objective of an accelerated test is either of the following:

(i) To discover failure modes

(ii) To predict the normal field life from the high stress laboratory life

By analyzing the product's response to such high stress level tests in the laboratory, one can make prediction about the service life and maintenance intervals of a product.

The following steps are usually followed while conducting accelerated life tests:

• Objective and scope of the test is defined
• Stresses to be considered are identified and their levels are determined
• The accelerated test is conducted and collected data is analyzed.

Three types of Accelerated life tests (ALT) are often used in practice, viz., constant-stress ALT, progressive-stress ALT and step-stress ALT. In constant-stress ALT, the stress is kept at a constant level throughout the test whereas in progressive-stress ALT, the stress is continuously increased over time. However, in Step-stress ALT, starting with some level of stress, the stress is increased in steps in such a way that it will change at specified times. If the product does not fail at the specified time, stress level is raised and held over a fixed time. This procedure is repeatedly until the product fails or the censoring time is reached. Usually, to determine a life-stress relationship, the models that are generally used are: Arrhenius Model, Eyring Model, Inverse Power Law Model Temperature-Humidity Model and Temperature Non-thermal Model.

Once an accelerated life experiment has been modelled, testing the fit of the proposed model can be done. I am happy to note that all relevant aspects related to accelerated life testing have been presented in this special section.

I am grateful to Dr. Jean-Fran?ois Dupuy of France, who very kindly accepted our invitation to bring out this special section on accelerated life testing and to make this issue possible. My sincere thanks are also due to all those authors, who have contributed to this issue. We will continue to present various aspects of performability engineering and new research to our readers through this journal in the years to come.

Traditional lifetime data analysis involves analysing time-to-failure data obtained under normal operating conditions (or stresses) in order to evaluate the reliability characteristics of a set of items (system, component, or product). Obtaining such data may however require an unreasonable amount of time. This is the case, for example, for highly-reliable units such as those encountered in the nuclear, aeronautic or electronic fields since these units are designed to operate without failing during years or decades. One way to obtain the desired reliability information is thus to test the units at higher-than-usual levels of stresses and to infer, or extrapolate, the reliability characteristics of the units at use conditions. Obviously, this extrapolation is only possible if appropriate models relating the failure times of the units and the accelerating factors (stresses) are available. A huge amount of literature has been devoted so far to the design, modelling, and analysis of experiments using higher-than-usual levels of stresses to accelerate the collection of failure time data. The phrase "accelerated life testing" has been adopted to describe such methods.

In particular, numerous contributions have been made to the development of statistical methods for planning accelerated life testing experiments. This is the topic of the paper by N. Chandra et al. who propose an optimal experiment plan for a 3-steps step-stress accelerated life testing when the units lifetime belong to the Lomax family of distributions. This is also the topic of the paper by F. Haghighi who constructs a step-stress experiment in a competing risk setting (that is, several independent causes of failure act simultaneously on the units). The construction of this plan uses the additional information provided by some available degradation data.

The analysis of accelerated failure time data requires a careful modeling of the relation between the accelerating variables and the reliability characteristics of the units under study (such models are called accelerated life or accelerated failure time models). J.-F. Dupuy provides a review of the most widely used accelerated life models and a description of the associated statistical inference. D.I. De Souza et al. propose to use the Maxwell distribution law to extrapolate the information resulting from an accelerated life test experiment to normal or design operating conditions. G. Babykina and V. Couallier propose a new reliability model for analysing recurrent failure time data, which takes account of aging, previous failures and covariates. This model is applied to repeated pipe failures in water distribution systems.

Once an accelerated life experiment has been modeled, the investigator usually faces the issue of testing the fit of the proposed model. This step allows to validate the conclusions and extrapolations obtained from the model. M.S. Nikulin and Q.X. Tran propose a chi-squared statistic for testing the appropriateness of parametric accelerated failure time models with possibly time-varying covariates. The proposed methodology is applied to two accelerated failure tests conducted on insulating structures and electric insulating fluids.

All the aspects of accelerated life testing (planning of experiments, modeling and model validation) are therefore present in this special issue.

JEAN-FRAN?OIS DUPUY

IRMAR/INSA of Rennes, F-35708 Rennes, France

Email : jean-francois.dupuy@insa-rennes.fr

In this paper we obtain the optimum time for changing the stress level in 3-step, step stress accelerated life testing under the cumulative exposure model. The lifetimes of test units are assumed to follow a two-parameter Lomax distribution. The scale parameter of the Lomax failure time distribution at constant stress level is assumed to be a log-linear function of the stress level. We also assume that there may exist a quadratic relationship between the log mean failure time and stress. As an extension of the results for the linear model, the optimum plan for a quadratic model is also proposed. We derive the optimum test plans by minimizing the asymptotic variance of the maximum likelihood estimator of the mean life at a design (use) stress.

A step-stress test in the presence of competing risks and using degradation measurements is considered. It is assumed that underlying degradation path follows a concave degradation model and the intensity functions corresponding to competing risks depend only on the level of degradation. In this work, information from step-stress test at high level of stress is extrapolated, through a tempered failure rate model, to obtain the estimates of intensity functions at normal use conditions. No assumptions are made about failure times distribution. Finally, the results are used to estimate reliability function.

In classical life data analysis, one typically collects failure-time data by operating a set of units under usual (or design) stress conditions. But in reliability engineering, due to a variety of reasons such as cost and time constraints, one often wishes to collect the data more quickly than is allowed under the normal operating conditions. This can be achieved by applying higher-than-usual levels of stresses to the units, resulting in accelerated life testing data. In this paper, we provide a short review of the methods and models used to analyze such data. We concentrate on accelerated failure time models and on the related statistical inference. We describe some open questions and future research directions.

The International of Journal of Performability Engineering is a refereed interdisciplinary journal which presents all engineering aspects of performance of products, systems or services. This journal was started in July 2005, and this year is in the tenth year of its publication. We like to present here how this journal has been progressing since its inception in 2005. Undoubtedly, we have come a long way and will continue making special efforts to ensure that we have participation and representation of all major countries of the world and the journal has a wide coverage of the topics within the planned scope of this journal. It is a matter of great satisfaction that the journal, in general, has been appreciated and has been received very well by the scientific community of the world. This is reflected through the demand /orders received for the copies of the papers published in this journal. We will of course continue to keep the standard of this journal very high and strive to provide high quality papers to our readers following a rigorous refereeing process involving competent reviewers so that the published papers are brief, precise and are of high standard.

We have been bringing out special issues in the important and new emerging areas of research and invite acclaimed researchers and practitioners to serve as Guest Editors in order to provide their interaction with researchers and professionals in the area.

IJPE also provides a unique facility to authors/researchers to present their new ideas before the scientific community through the medium of Short Communications/Short Papers, which otherwise might take quite some time to develop the idea into a full-fledged research paper.

Book reviews of latest books are often published in the journal to apprise our readership of new arrivals in the literature to keep them up-to-date in their respective area.

The details of IJPE issues published, during the period July 2005-Nov. 2013, are as follows:

List of 47 Countries which have contributed papers to IJPE: The following countries (in alphabetic order) contributed papers to the IJPE during this period:

Abu Dhabi, Algeria, Australia, Brazil, Canada, China, Czech Republic, Denmark, Egypt, Finland, France, Germany, Greece, Holland, Hong Kong, Hungary, India, Iran, Israel, Italy, Japan, Jordan, Korea (South), Kuwait, Latvia, Malaysia, Morocco, New Zealand, Norway, Oman, Pakistan, Poland, Portugal, Romania, Russia, Singapore, Slovenia, South Africa, Spain, Sweden, Switzerland, Taiwan, Turkey, Ukraine, United Kingdom, United States of America, Venezuela.

Major contributing countries happen to be (in alphabetic order): Australia, Canada, China, France, Germany, India, Israel, Italy, Japan, Norway, Sweden, South Korea, Taiwan, U.K., U.S.A. (The highest number of papers published have been from U.S.A.).

The journal is being abstracted by several scientific data bases, which include Elsevier’s SCOPUS, EI Village, Compendium, Google Scholar, ProQuest, INSPEC(UK), NSD (Norway), SCIMAGO etc. The number of citations from July 2005 to November 2012 for 305 papers published during the period has been 821.

We like to thank a large number of anonymous reviewers of papers, who over this period have given us their precious time and advice to keep the standard of this journal very high. We like to thank them here collectively and would like to record our gratitude to them.

In many situations where the amount of time available for testing is considerably less than the expected lifetime of the component, we often use accelerated life-testing. To translate test results obtained under accelerated conditions to normal using conditions, the “Maxwell Distribution Law “can be used. In this paper, a combined approach of a sequential life testing and an accelerated life testing is applied to a low alloy high-strength steel component. The underlying sampling distributions are assumed to be three-parameter Weibull and Inverse Weibull models and a linear acceleration is employed. To estimate the three parameters of both models, we use a maximum likelihood approach for censored failure data and apply truncation mechanisms developed by De Souza [1] for both models. An example illustrates the application of this procedure.

The paper deals with statistical analysis of repeated pipe failures in Water Distribution Systems, affected by a time-dependent factor. Several systems observed over a given time period are considered. A particular parametric model, formulated in the counting process framework, is employed. This model accounts for system aging, harmful repairs and covariates. Practical issues in maximum likelihood parameter estimations in the presence of a calendar time-dependent covariate are discussed. The proposed methodology is applied to a real dataset. The results clearly show an improvement of estimates quality when a calendar time-dependent covariate is integrated to the model.

The theory of the Chi-squared tests has been developed very actively till now, especially in accelerated trials. We discuss here some applications of this theory in the analysis of parametric accelerated life models (ALM) with time depending covariates when data are right censored.

This paper proposes a competing risks model for the reliability analysis of units subject both to degradation phenomena and catastrophic failures. The paper is mainly addressed to the analysis of real data presented in Huang and Askin (2003) which refer to some electronic devices subject to two independent failure modes. The first mode is the light intensity degradation, which is treated as a degradation phenomenon since the light intensity is observed and measured at given inspection times. The other failure mode is the solder/Cu pad interface fracture, which is classified as a catastrophic failure. The main reliability characteristics, such as the probability density functions and the cumulative distribution functions of each failure mode in the presence of both modes, are estimated. Likewise, the estimate of the hazard function, of the unit reliability under the competing risks model, and of the proportion of failures caused by each failure mode are derived.

This article presents probabilistic models addressing the problem of assessing the survivability and life expectancy of items subjected to repetitive multi phases usage cycles. This life profile characterizes the operational pattern of many daily used technologies, such as air and ground vehicles, home and services appliances, medical instruments, industrial machineries, etc. The topic was first studied by us in Filis et al. [3], where simple approximated solutions were given for the Weibull life distribution. Here we show that the model can be generalized to any family of life distributions having zero location parameter, and scale parameter varies with alternating working and environmental conditions.

An exception is the exponential distribution for which we show that exact calculations can be performed with low computational effort.

Preventive maintenance intervals for a product or system are generally specified by the manufacturer without consideration of the usage environment or usage frequency. This means that the intervals may not be optimal for each product or system instance if degradation and/or failure depend not only on time but also certain other factors. For example, some products tend to fail if the temperature is lower than a certain value. Product lifetime is usually in terms of calendar time or usage time. Online monitoring system enables us to identify such features. We investigated the failures of a product for which lifetime is in terms of usage time. A set of real was analyzed using a logistic regression model on the usage time scale with seasonal effects. On the basis of our results, we propose an optimal maintenance policy with lower expected costs than the existing one.

The Impact factor is a copyrighted term introduced by Dr. Eugene Garfield Founder and Chairman Emeritus, of the Institute of Scientific Information (ISI) or Thomson Reuters and is exclusively employed for the journals covered by Thomson Reuters using the number of citations available in Thomson Reuters’ Web of Science Data Base. Since Web of Science is a subscription based data base maintained by Thomson Reuters and cannot be accessed free by general scientific community, its data regarding number of citations is not openly available for comparison. It is basically the average frequency with which the papers of a journal have been cited in a particular year or period. The annual impact factor is a ratio of citations and the number of papers published in a year. In general, the impact factor of a journal is calculated by dividing the number of current year citations to the source items published in that journal during the previous two years. Thus the procedure of abstracting and retrieving citations bears heavily on efficiency and the validity of information thus collected. Thomson Reuters also maintain another database called as Web of Knowledge. There have been several criticisms on the use of Impact factor and its effectiveness in ranking a journal and a reader can find host of other factors attempting to define factors to rank a journal. For example, one of the drawbacks of Impact factor is that review articles generally are cited more frequently than typical research articles. Highly specialized journal in new areas will obviously have low citation rate. Older journals will have more citations than newer ones since such journals have a larger citable body of literature than smaller or younger journals. All things being equal, the larger the number of previously published articles, the more often a journal will be cited. A five-year impact factor may be more useful in some cases and is be calculated by combining the statistical data available from consecutive five years period.

Moreover, small publishers or users or librarians usually cannot afford to have access to subscription based databases. But in addition to the databases maintained by Thomson Reuters, there are several other databases whose task is to abstract the papers published in the scientific and technical and maintain a record of citations used in the papers. Many of them are open and free for access to scientific community.

Among such database are Google Scholar, and SCIMAGO etc. that are freely available on web. The SCImago Journal and Country Rank is a portal that includes the journals and country scientific indicators developed from the information contained in the worldwide database SCOPUS ? (of Elsevier B.V.). This platform takes its name from the SCImago Journal Rank (SJR) indicator, developed by SCImago from the widely known algorithm Google PageRank?. This indicator shows the visibility of the journals contained in the Scopus? database from 1996 onwards and SJR can be accessed by anyone free on the web. In fact, in our opinion, such information should be open and stand for verification and scrutiny, anytime and anywhere for the sake of good and affordable science or research.

This paper develops a new degradation model of the PV module performance based on two degradation processes. The first is the initial photon degradation related to physical process in the solar cell itself, where the function of the performance loss caused by this mechanism is exponentially distributed. The second is the continuous degradation process; it is related to the long term weathering and to the degradation of the module package resulting in a degradation of the module performance. In this case, the function of the performance loss caused by this mechanism follows the Weibull distribution. The obtained results by simulation are discussed and corroborated by mathematical analysis of a simpler equivalent model. The analysis covers lifetime energy loss, Cumulative loss of energy (kWh, %), annual cost of energy loss, and the total cost of energy loss. Finally, the objective reached is the reliability evaluation of the PV module.

Condition monitoring vibration data is widely used to assess the health condition of the gearbox. The objective of this paper is to develop a scheme for early fault detection of a gearbox under varying load condition by considering multi-sensor vibration data. Time synchronous averaging (TSA) method is used to reduce the noise and then remove the periodic signals from the data. Several vector auto-regressive (VAR) models are fitted to the historical data obtained in healthy gearbox condition considering different load levels. After testing the independence and multivariate normality of residual data, a multivariate Hotelling’s T-squared control chart is applied to detect the early fault occurrence of a gearbox.

Distributed control systems in power plants are the latest trends to optimize and control performance. Reliability prediction of input-output components of distributed control systems have a key role to play in the power plant scenario. Triple modular redundancy is a means of increasing reliability of systems. Triple modular redundancy of three modules each containing m cards is studied in this paper. Also, in this paper the reliability of analog input card, digital output card and analog output card are predicted with triple modular redundancy and 128 cards/dpu and standby redundancy (1 out of 2). The results of triple modular redundancy as against standby redundancy are compared for different mission times.

The International Journal of Performability Engineerng (IJPE) is a peer-reviewed journal and was started in July 2005 as a quarterly international journal. Since 2010, IJPE has become a bimonthly journal. The statistics of number of citations based on the citations record available from freely available databases such as Google Scholar etc. for the papers published from 2005 up to 2012 is as given below in the Table 1. The numbers of citations, in this Table have been prepared based on the following sources of information:

1. Google Scholar (http://scholar.google.co.in/)
2. The SCImago Journal and Country Ranking
3. SCOPUS (http://www.scopus.com/
4. Microsoft Academic Research (http://academic.research.microsoft.com/)

Since the Impact Factor is a copyrighted term of Thomson Reuters, we cannot use this term to show how IJPE has made impact in the scientific world, we have used a term which we will call as Journal Visibility Factor (JVF), retaining a similar definition as that of the impact factor, which is defined as the number citations divided by the number of papers published during a given period of time.

Table 1: Number of Year-wise Citations of IJPE Papers and IJPE’s JVF

Legend for various columns shown in the Table 1 is as follows:

Column 1 (C1) – Year of publication,

Column 2 (C2) -Number of Issues published in that year

Column 3 (C3) -Number of papers published in that year,

Column 4 (C4) –Number of Citations During that year,

Column 5 (C5)– Journal Visibility Factor (JVF) for that year,

Column 6 (C6) - Cumulative Number of papers published from 2005 till that year, Column 7 (C7) - Cumulative Number of Citations from 2005 till that year,

Column 8 (C8) - Cumulative Journal Visibility Factor (CJVF) from 2005 till that year,

Also, C5*= C4/C3, and C8*-C7/C6, both being JVF.

As we can see from the foregoing Table that Journal Visibility Factor improves with the passage of time as the papers published in any journal become more and more visible to the scientific world and more citations get added to the papers published in the journal.

In addition to above databases, the NSD - a scientific data base of Norway (http://dbh.nsd.uib.no) which covers very many technical journals, places IJPE at higher acceptance level in comparison to many other journals in the area the IJPE deals with.

Even if we consider only citations in the past two years based on the above data sources for the assessment in 2012, the picture of IJPE citations emerges as follows:

But according to Thomson Reuters’ analysis, we received the following reply from them:

"… …Using this citation count as a numerator, and the total number of articles published by the journal in 2010 and 2011 as a denominator, we got the journal's 2012 Impact Factor, 0.0xx."

When contacted for this wide discrepancy, Thomson Reuters stated that they use Web of Science (WoS) for counting the number of citations.

To know the position of International Journal of Performability Engineering in respect to Thomson Reuters’ number of citations, we conducted a sample search for the IJPE for the period July 2005 to Dec. 2012 so that we can compare those results with results of Table 1. According to WoS the total number of cited papers of IJPE papers since July 2005 until Dec.2012 is only 14 with number of citations as 28, whereas according to Web of Knowledge (WoK), which is also a Thomson Reuter’s product, the number of cited papers of IJPE is 42 with total number of citations as 130 for the same period. This is incomprehensive. Also there are found to be incomplete listing of information about papers published in IJPE. It is not known how WoS or WoK collect and retrieve the information from a journal. When dealing with ranking of journals based on certain criteria, it is absolutely necessary to have utmost clarity and care in the procedure followed for collecting and retrieving data from the journal and should be openly available to all.

The very fact that authors from 47 countries have so far contributed their valuable contributions to the IJPE in such a short span of its existence and that we have been regularly receiving requests for the purchase of reprints of the papers published in IJPE, speaks volume of its visibility. IJPE has maintained the highest academic integrity and standards. Each paper is reviewed very carefully by competent referees and revised before a paper is published in the journal. IJPE has the most knowledgeable and well-known experts on its Editorial Board to advise and support its activities. If some organization does not take note of all this, we are not unduly bothered about it. As said before, we will continue to serve our readers to the best of our competence and provide the best of literature through IJPE.