Prof. Sheng-Tsaing Tseng (National Tsing-Hua University, Taiwan)
Title: Nano-Sols Shelf-Life Prediction via Accelerated Degradation Model
Abstract: In order to provide timely product’s lifetime information to the customers, conventionally, manufacturers usually use temperature (or voltage) as an accelerating variable for shortening life testing time. Based on well-known life-stress relationship (such as Arrhenius reaction or inverse power model), it allows us to extrapolate the lifetime of highly-reliable products at a normal used condition. In this talk, however, we will present a real case study that the shelf-life prediction of nano-sol products can be successfully obtained by adopting pH value as an accelerating variable. An accelerated profile-degradation model is proposed to describe the time-evolution of the particle size distributions under three different pH values. Then, we can analytically construct the confidence interval for the shelf-life of nano-sol products under its normal use condition.
Short Biography: Sheng-Tsaing Tseng is a Chair Professor in the Institute of Statistics at Tsing-Hua University, Taiwan. He is an elected member of ISI, a senior member of ASQ, and a member of the IEEE. He has received 2015 Merit MOST Research Fellow Award, Taiwan. Currently, he serves as an Associate Editor of Technometrics. Dr Tseng’s research interests include quality & productivity improvement, reliability lifetime analysis, and statistical decision methodology. His articles have appeared in major journals of Quality and Applied Statistics, such as Technometrics, Journal of Quality Technology, IIE Transactions, Naval Research Logistics, Statistica Sinica, IEEE Transactions on Reliability, IEEE Transactions on Semiconductor Manufacturing, International Journal of Production Research, European Journal of Operations research, Journal of Statistical Planning and Inference and others.
Prof. Ohi Fumio (Nagoya Institute of Technology, Japan)
Title: Recent Progress in Multi-state Reliability Theory
Abstract: The mathematical theory of multi-state systems started almost around 1978. Early study about the multi-state systems depends on the theory of binary state systems as taking over the formulae in the binary case. On the other hand, using the order theoretical concepts, we have tried to build a theoretical frame work of multi-state systems by natural extension of the concepts in the binary state systems theory. In this presentation, assuming the state spaces to be partially ordered sets, we first show that minimal and maximal state vectors uniquely determine the structure function of a multi-state system, where a state vector denotes a combination of states of the components. This assertion is the generalisation of that the minimal path and cut sets uniquely determine the structure function of the binary-state systems. Then, using this fact, we may have some stochastic bounds on the reliability of the systems. We also show stochastic bounds via a modular decomposition and some ageing properties of the multi-state systems as IFR, IFRA and NBU closure theorems. Finally we give some problems in the multi-state case to be solved in future.
Short Biography: Fumio Ohi received his Doctor of Engineering degree from Osaka University, Japan, in 1981. He joined Faculty of Engineering, Osaka University, as Research Assistant in 1978 and moved to Aichi Institute of Technology, Japan as Associate Professor in 1989. He has been working in Nagoya Institute of Technology (NIT), Japan, since 1995, and is currently Full Professor in the Department of Scientific and Engineering Simulation, Graduating School of Engineering, NIT. His research interests are fundamental theory of informatics including system reliability theory, classification problem of cellular automata, fractal analysis method of time series data, and multi-agent simulation of emergency evacuation flow of pedestrians.
Prof. Rui Kang (Beihang University, China)
Title: Measuring reliability under epistemic uncertainty: Status quo, existing problems and future directions
Abstract: In general, two types of uncertainty exist in reliability engineering, i.e., aleatory uncertainty, which refers to the inherent randomness in the physical world; and epistemic uncertainty, which results from our incomplete knowledge. Most of the existing researches in reliability are based on probability theory and only consider aleatory uncertainty. In this talk, we give a critical review of researches that consider epistemic uncertainty in reliability. Five frequently used non-probabilistic reliability metrics are systematically reviewed, i.e., evidence-theory-based reliability metrics, interval-analysis-based reliability metrics, fuzzy-interval-analysis-based reliability metrics, possibility-theory-based reliability metrics (posbist reliability) and uncertainty-theory-based reliability metrics (belief reliability). Problems of these existing metrics are discussed and it is pointed out that a qualified reliability metric to consider epistemic uncertainty needs to (1) compensate the conservatism in the estimations of the component-level reliability metrics caused by epistemic uncertainty; and (2) satisfy the duality axiom, otherwise it might lead to paradoxical and confusing results in engineering applications. Finally, we discuss some potential research directions in the areas of modeling epistemic uncertainty in reliability.
Short Biography: Rui Kang is a Distinguished Professor of School of Reliability and Systems Engineering, Beihang University, Beijing, China. He is a famous reliability expert for Chinese industry. He received his bachelor’s and master’s degree in electrical engineering in 1987 and 1990 from Beihang University. He has developed six courses and published eight books and more than 150 research papers. His main research interests include reliability and resilience for complex system and modeling epistemic uncertainty in reliability and maintainability. He is the Chief Editor of the Journal of Reliability Engineering, and the founder of China prognostics and health management society. He received several awards from the Chinese government for his outstanding scientific contributions, including Changjiang Chair Professor awarded by the Chinese Ministry of Education.
Prof. Joo Ho Choi (Korea Aerospace University, Korea)
Title: Bayesian Methods for Uncertainty Quantification in Reliability Engineering Problems
Abstract: In the recent years, Bayesian methods have attracted many researchers as a means to quantify uncertainties in various engineering fields. In the Bayesian approach, the probability itself is treated as random variables which represents our degree of belief. Based on such a framework, one can make inferences on the unknown quantities by means of posterior distribution which is characterized by combining the observations and the prior knowledge. As a result, it can treat aleatory (objective data) and epistemic (subjective knowledge) uncertainty in a unified framework. In this talk, Bayesian theory and some of its applications are outlined in the field of reliability engineering. It begins with the basic theory, philosophy, and a couple of mathematical examples that illustrates the concept. Modern simulation techniques are then explained to compute the posterior distribution based on the sampling algorithms, in which the two most popular methods, Markov Chain Monte Carlo and Particle Filtering methods, are addressed. Three application examples are presented to demonstrate the method in practice. First is the life prediction of turbine blades using field inspection data. Second is about teaching a verification, validation and uncertainty quantification course using paper helicopters. Third is the prognosis of crack growth in aircraft panel under variable amplitude loads.
Short Biography: Professor Joo-Ho Choi received Ph.D. degree of mechanical engineering from Korea Advanced Institute of Science and Technology (KAIST) in 1987. In 1988, he worked as a Postdoctoral Fellow at University of Iowa. During 1988-1996, he worked in the Samsung Corning as an engineer for TV glasses development and production. Since 1997, he joined the School of Aerospace and Mechanical Engineering at Korea Aerospace University and is now Professor. Over the last decade, his research has been focused on the reliability engineering, which includes the system reliability assessment, verification and validation (V&V) of the computer model, and the prognostics and health management (PHM) for optimum maintenance strategy. He has authored or coauthored over 90 journal articles. He has served as the vice-president of the Computational Structural Engineering Institute of Korea during 2008~2013, and the president in the reliability division of the Korean Society of Mechanical Engineers in 2014. He is now the president of Center for Reliability Engineering in Mechanical and Aerospace Industry in the Korea Aerospace University, and is a member of several professional organizations including COSEIK, KSME, KSPE, KSAS, ASME and AIAA.
Prof. N. Balakrishnan (McMaster University, Canada)
Title: Signatures, Joint Signatures and Associated Inference
Abstract: In this talk, after providing a brief introduction to the notion of signatures of coherent systems, I will describe the idea of joint signatures when two systems share some components, thus introducing dependence between their lifetimes in general. I will then use this idea of joint signatures to develop inference regard system lifetime and component lifetime characteristics of interest. I will present some examples to illustrate all the results discussed here.
Short Biography: Professor Balakrishnan has been actively involved in research work in diverse areas of Statistics, and has made significant contributions to many areas including Models and Analysis of Medical and Lifetime Data, Life-Testing and Reliability, Order Statistics, Robust Inference, Distribution Theory, Multivariate Distribution Theory, Characterization Theory, Inferential Methods, Industrial Statistics, Nonparametric Inference, Outliers, Multivariate Analysis, Bayesian and Empirical Bayesian Inference, Combinatorial Applications to Probability and Statistics, Record Values and Processes, Theory of Runs and Scans, Waiting Time Problems, Ranked Set Sampling, and Statistics in Finance. Among his publications are the following nine major papers:
- Ordering properties of order statistics from heterogeneous populations: A review with an emphasis on some recent developments (Co-authored with P. Zhao), Probability in the Engineering and Informational Sciences (2014), to appear (with discussions).
- Hybrid censoring: Models, inferential results and applications (Co-authored with D. Kundu), Computational Statistics & Data Analysis (2013), 57, 166-209 (with discussions).
- Nonparametric inference based on panel count data (Co-authored with X. Zhao and J. Sun), Test (2011), 20, 1-71 (with discussions).
- New multi-sample nonparametric tests for panel count data (Co-authored with X. Zhao), The Annals of Statistics (2009), 37, 1112-1149.
- A synthesis of exact inferential results for exponential step-stress models and associated optimal accelerated life-tests, Metrika (2009), 69, 351-396.
- Progressive censoring methodology: An appraisal, Test (2007), 16, 211-296 (with discussions).
- Permanents, order statistics, outliers, and robustness, Revista Matem´atica Complutense (2007), 20, 7-107.
- Analyzing unreplicated factorial experiments: A review with some new proposals (Co-authored with M. Hamada), Statistica Sinica (1998), 8, 1-41 (with discussions).
- Order statistics from non-identical exponential random variables and some applications, Computational Statistics & Data Analysis (1994), 18, 203-253 (with discussions).
In addition to writing numerous research papers in many journals, Professor Balakrishnan has also authored and edited several books and volumes. Over the years, these have received good reviews and several citations in the literature.