Abstract:

In order to invigorate research and to encourage readers to contribute to new areas of importance in performability engineering, this journal has been bringing out special issues or special sections of an issue on some topics of current interest or importance. This first issue of the seventh year of the IJPE existence, we present to our readers, the upcoming and potential area of Data Mining and its possible applications to Reliability and Risk. With this objective in view, we invited Professor Claudio Rocco of Venezuela who is a member of IJPE Editorial Board and has extensively worked in this area to bring out a special section on data mining. He was kind enough to accept this responsibility and was able to select four papers which were reviewed and revised for this section which is presented here. Data mining is an important area and has developed its own methodologies. It is hoped that this section will be able to generate interest in our readership in this important area.

The first paper of the special section by Utkin and Coolen describes an approach of obtaining reliability growth models through the framework of predictive learning using Kolomogorov-Smirnov confidence limits and nonparametric inferences. The largest and smallest risk measures are determined as a function of the regression parameters through a minimizing process and finally the pessimistic and optimistic reliability growth models. In the second paper by Zhang and Ramirez-Marquez, an evolutionary algorithm based on a data mining technique is used to determine an approximation to minimal cut sets of a flow network by defining an optimization problem and using an evolutionary algorithm to solve it. Generally, for complex and large networks, obtaining an exact value of reliability may become prohibitive and an approximation to the true reliability may suffice. Similarly, in the third paper by Fuqing, Kumar and Misra, it is again approximate system reliability is obtaining from incomplete data set using Support Vector Machine and Monte Carlo simulation. In the fourth paper by Baraldi, Compare, Zio, De Nigris and Rizzi of special section on Data Mining, a technique based on the Adaboost algorithm, which has been effectively used for addressing classification problems, is proposed for identifying contradictory PD patterns within an a priori analysis aimed at improving the diagnostic performance.

I would like to thank Professor Rocco for the effort put in bringing out this special section and thank all the authors who contributed to this section.

The next four papers of the present issue are the papers contributed to the journal through usual channel and represent variety of interesting and important topics. For example the fifth paper of this issue by Kosmowski of Poland considers human factors during design of safety related functions for a complex and hazardous installation and its protection. The next paper by S?derholm, and Karim of LTU, and Candell of Saab Aerotech, of Sweden present a methodology and support tool box for design of experiment and simulation for identification of significant e-maintenance services. The seventh paper of this issue by Abrahamsen and Aven of Norway presents an interesting application of bubble diagram for projects risk management. This paper aims to provide a rational framework for managing risks. The last paper of this issue is by Guo with Guo and Thiart of South Africa and they present a scheme for parameter estimation and simulation scheme, which the authors claim to be a foundational work for Poisson random fuzzy reliability and risk analysis. It is hoped that the readers of IJPE will find papers presented here interesting and stimulating which is the objective of this journal.