ENBIS: European Network for Business and Industrial Statistics

My abstracts

The following abstracts have been accepted for this event:

• Uncertainty Calculations in a System Reliabilty Tool
  
  Authors: Jan-Willem Bikker (CQM BV)
  Primary area of focus / application: Reliability
  Keywords: Reliability, Monte Carlo, Uncertainty modelling, Bayesian, Design of Experiments
  

  Submitted at 4-Apr-2018 08:45 by Jan-Willem Bikker
  Accepted
  

  4-Sep-2018 12:00 Uncertainty Calculations in a System Reliabilty Tool
  The Dutch consultancy firm CQM (Consultants in Quantitative Methods, ~35 consultants) supports many customer’s projects in R&D (biostatistics, marketing, product development, reliability). One customer is a large electronics manufacturer with whom we co-developed a software tool for reliability prediction of their product portfolio. The tool is widely used within the organisation, with an eye towards warranty and services. The systems are composed of various sorts and types of components from a predefined library. Lifetime of and degradation in the light-source are described using typical survival models with temperature and current as typical regressors. The output consists of various graphs and tables describing survival rates over time according to several criteria and failure mechanisms, as well as breakdown of failure over the criteria or over subcomponents.
  
  The system’s build-up is much more complex than just serial or parallel, and uses Monte Carlo simulation for the calculations. For instance, a system is considered still functional if only a few light-sources are down. A novel feature translates the uncertainty of each subcomponent’s reliability to the output on system level, which helps in the interpretation. The knowledge of a subcomponent’s failure may come from stress tests, leading to a covariance matrix of the model parameters’ estimates, or sometimes from practical educated guesses, in which case the uncertainty takes on the character of a Bayesian prior. As system could have several dozens of different subcomponents, there is a computational challenge to deliver fast system-level uncertainty intervals for the various failure curves. The talk explains how DoE schemes with up to hundreds of factors are used, and highlights some of the development aspects where computer science, mathematics, and statistics meet.
• Using Split-Plot Diagnostics to Reveal Hidden Information
  
  Authors: Pat Whitcomb (Stat-Ease, Inc.)
  Primary area of focus / application: Other: Software
  Secondary area of focus / application: Design and analysis of experiments
  Keywords: Design of Experiments, Split-plot RSM design, Random effects, Fixed effects
  

  Submitted at 4-Apr-2018 16:02 by Pat Whitcomb
  Accepted (view paper)
  

  3-Sep-2018 11:30 Using Split-Plot Diagnostics to Reveal Hidden Information
  The aim of this talk is to motivate DOE practitioners to use RSM split-plot designs while properly accounting for fixed effects for the model coefficients and random effects for the variance components.
  
  By way of a case study, this talk features innovative diagnostics for split-plot designs that reveal outliers and other abnormalities. These diagnostics are derived from restricted maximum likelihood (REML) tools that estimate fixed factor effects and random variance components. The presentation begins by laying out the benefits of split-plot designs versus traditional response surface method (RSM). It then demonstrates how diagnostic plots tailored for split-plot designs can reveal surprising wrinkles in experimental data.
• Modelling and Inference of Partially Observed Competing and Propagating Flaw Indications
  
  Authors: Emmanuel Remy (EDF R&D), Sophie Mercier (University of Pau), Laurent Bordes (University of Pau), Emilie Dautreme (EDF R&D)
  Primary area of focus / application: Other: Statistical Methods for Degradation Data
  Keywords: Degradation process, Residual lifetime, Censored data, Log-composite-likelihood function
  

  Submitted at 5-Apr-2018 20:31 by Emmanuel REMY
  Accepted
  

  5-Sep-2018 11:10 Modelling and Inference of Partially Observed Competing and Propagating Flaw Indications
  Passive components within EDF (Électricité de France - Electricity of France) electric power plants are periodically controlled in order to ensure that their degradation is lower than a critical level and to guarantee the safety and the availability of the installations. The physical deterioration of these systems consists in flaw indications, which first initiate one by one and then independently propagate over time. The inspections are carried out at discrete times and the non-destructive testing process allows to measure the size of the largest flaw indication, together with the total number of existing indications on each component. Although detected, too small indications cannot be measured, leading to censored observations.
  
  Taking into account this partial information coming from the field, a specific stochastic model is developed. We consider that the flaw indications initiate according to a Poisson process and next propagate according to competing independent gamma processes. A parametric estimation procedure is proposed and applied to the real dataset. The fitted model is then used to assess useful indicators for reliability and maintenance engineers, such as the distribution of the residual operating time of the component until its degradation reaches the specified degradation threshold.
• The Steady-State Behavior of Multivariate Exponentially Weighted Moving Average Control Charts
  
  Authors: Sven Knoth (Helmut Schmidt University, University of the Federal Armed Forces Hamburg)
  Primary area of focus / application: Process
  Secondary area of focus / application: Quality
  Keywords: Multivariate Statistical Process Control, Fredholm integral equation of the second kind, Nyström method, Markov Chain approximation, Non-central Chisquare distribution, Spherical distribution
  

  Submitted at 8-Apr-2018 18:29 by Sven Knoth
  Accepted
  

  4-Sep-2018 12:00 The Steady-State Behavior of Multivariate Exponentially Weighted Moving Average Control Charts
  Multivariate Exponentially Weighted Moving Average (MEWMA) charts are popular, handy and effective procedures to detect distributional changes in a stream of multivariate data. For doing appropriate performance analysis, dealing with the steady-state behavior of the MEWMA statistic is essential. Going beyond early papers like Prabu and Runger (1997), we derive quite accurate approximations of the respective steady-state densities of the MEWMA statistic. It turns out that these densities could be rewritten as the product of two functions depending on one argument only, which allows feasible calculation. Using the new methods it was found that for large dimensions, the steady-state behavior becomes different to what one might expect from the univariate monitoring field. Based on the integral equation driven methods, steady-state and worst-case average run lengths are calculated with higher accuracy than before.
• An Analysis for Industry 4.0: Change Point Detection of the Effects of Industrial Revolutions on Performance Indicators
  
  Authors: Ozgun Sarikulak (ASELSAN A.Ş.), Murat Caner Testik (Hacettepe University)
  Primary area of focus / application: Process
  Secondary area of focus / application: Modelling
  Keywords: Industrial revolution, Industry 4.0, CUSUM, Change point estimator, Missing point imputation, Control charts
  

  Submitted at 10-Apr-2018 15:54 by Ozgun Sarikulak
  Accepted
  

  4-Sep-2018 11:40 An Analysis for Industry 4.0: Change Point Detection of the Effects of Industrial Revolutions on Performance Indicators
  Industrial revolutions have huge impacts on human history when those revolutions compare with other historic moments. Alterations of energy regime, improvements of production processes and changes in the ways of communication and transportation affect the social and economic life.
  
  In this study, performance indicators of England, France, Netherlands, Germany and USA are studied retrospectively by using cumulative sum (CUSUM) control charts to estimate the change points. Hence, reflections of industrial revolutions on the performance indicators are evaluated. The data used in the analysis include income per capita and energy consumption per capita from the 18th to 21st century. Autoregressive Integrated Moving Average models are used to represent autocorrelation structures of the time series of indicators. CUSUM control charts are implemented for the residuals of the models, where non-normal residuals are transformed to normal distribution. The last reset time corresponding to a CUSUM signal is taken as the estimate of a change in the performance indicator and this is analyzed for the effects of a war or an economic crisis besides an industrial revolution. If an effect of war or a crisis is found, corresponding out-of-control observations are omitted from the dataset and missing point imputation is performed.
  
  According to the study results, reflections of the industrial revolutions’ effects can be observed from performance indicators. This study is also consistent with the years that are accepted in the literature for industrial revolutions. In addition, this study shows that the era of industrial revolutions also altered the patterns of income per capita and energy consumption per capita.
• EMUE: Towards a Comprehensive Set of Examples of Measurement Uncertainty Evaluation to Support Guides and Standards
  
  Authors: Maurice Cox (NPL)
  Primary area of focus / application: Metrology & measurement systems analysis
  Secondary area of focus / application: Modelling
  Keywords: EMPIR project EMUE, Measurement uncertainty, Joint Committee for Guides in Metrology (JCGM), Guide to the expression of uncertainty in measurement (GUM), Learn by example, Adaptable examples
  

  Submitted at 10-Apr-2018 16:50 by Maurice Cox
  Accepted (view paper)
  

  4-Sep-2018 10:30 EMUE: Towards a Comprehensive Set of Examples of Measurement Uncertainty Evaluation to Support Guides and Standards
  EMPIR project EMUE, Examples of Measurement Uncertainty Evaluation, which started in July 2018, will promote the harmonized evaluation of measurement uncertainty according to internationally recognized standards and guides across broad disciplines of measurement. This initiative will be accomplished by providing new or improved examples that will be widely disseminated and so improve the use of accepted uncertainty principles. Many examples will be in a form that can readily be adapted to other areas.
  
  Reliable statements of uncertainty are needed in diverse areas of measurement such as environment, energy and quality of life. These areas would benefit from carefully elaborated examples that are practical and specific to these domains and as far as possible are in a form that can be adapted to end-users’ data and knowledge. ISO/IEC 17025, General requirements for the competence of testing and calibration laboratories, states that it should be ensured “that the form of reporting of the result does not give a wrong impression of the uncertainty”, with the implication that practitioners should pay an appropriate level of attention to evaluating and reporting uncertainty. Since many end-users “learn by example”, a diverse set of practical examples, ranging in complexity from the simple to the sophisticated, would be highly beneficial and is being provided by EMUE.
  
  Industrial need includes uncertainty evaluation problems that cannot directly be tackled by applying existing guidance given in the Guide to the expression of uncertainty in measurement (GUM), but require to be supported by methods of numerical simulation. Societal need includes ways in which uncertainty statements are made concerning cancer therapy and doping control, for instance. EMUE is addressing such needs.
  
  Some examples being provided by EMUE will concern the traditional metrology areas of calibration, testing, comparison and conformance assessment. Selected examples will relate to the thematic areas of environment, energy, quality of life, and industry and society. The examples will be offered to the Joint Committee for Guides in Metrology (JCGM) and its member organizations (BIPM, IEC, IFCC, ILAC, ISO, IUPAC, IUPAP and OIML) for use in a developing document illustrating the application of the GUM suite of documents, and so support the agreed GUM New Perspective. They will also be provided to standards committees and other bodies and end-users that have expressed a need for them.
  
  The talk will describe some of the planned content of the set of examples and outline the guiding principles by which they are being developed.