J. Carlos García-Díaz

Optimization of univariate and multivariate exponentially weighted moving-average control charts using genetic algorithms

Exponentially weighted moving-average (EWMA) and multivariate EWMA (MEWMA) process control charts can be applied to detect small changes in statistical process control efficiently. This paper presents a software program developed in Windows environment for the optimal design of the EWMA and MEWMA chart parameters, to protect the process in the case of shifts of given size. Optimization has been done using genetic algorithms.

Design and optimization of EWMA control charts for in-control, indifference, and out-of-control regions

The design of quality control charts is normally carried out considering a process shift size that is considered important to be detected. The EWMA control chart is one of the best available options to use when good performance is needed to detect small process shifts. This paper presents a method for design of EWMA charts for control processes, in which the detection of small shifts is not necessary, and at the same time is effective in detecting important shifts. In such cases the EWMA control chart can also be designed successfully to deal with these requirements. A Markov chain approach is also applied to determine the ARL of the modified EWMA control chart. The implementation and interpretations are provided and numerical examples are used to illustrate the application procedure. We also investigate some basic properties of the proposed scheme. Genetic algorithms have been used to carry out this design.

A Performance Analysis of Hotelling’s T2 Chi Square Control Chart with Supplementary Runs Rules

Abstract Hotellings control chart is widely employed to control several related characteristics of a process because of its simplicity. However, it has little power when detecting small or moderate process shifts. The use of supplementary runs rules is described in this article showing the average run length improvements achieved and the runs rules appearance frequency.

Uncertainty and sensitive analysis of environmental model for risk assessments: An industrial case study

The objectives of this paper are the application of uncertainty and sensitivity analysis methods in atmospheric dispersion modeling to study the prediction of the dispersion of pollutants in the atmosphere. The Gaussian Plume Model is used to study the impact of meteorology on the dispersion of the emissions from an industrial source complex. The determination of ground-level concentration and maximum ground-level concentration is useful for the prediction of violations of air quality regulations. The Industrial Source Complex Short-Term (ISCST-3) air pollution model was adopted to predict the ground-level concentration of sulfur dioxide (SO2) emitted by a power plant located in an industrial region site in Spain. Quantitative uncertainty analysis has become a common component of risk assessments. Uncertainties were defined a priori for each of the following variables: wind speed, wind direction, and pollutant emission rate. In order to obtain information about the uncertainty of computer code results, a number of code runs was performed using the nonparametric tolerance limits method. The Monte Carlo method was used to propagate uncertainty across codes. The Spearman rank correlation coefficient was used as a sensitivity measure.

Economic design of EWMA control charts using regions of maximum and minimum ARL

Nowadays, it is common to find industries that utilize processes that either have a value of the process capability index C pk larger than two or are very difficult to adjust. In these cases, the detection of very small shifts may not be of interest due to the possible extra variability introduced into the process by the detection process. It would be more interesting in these situations to decide what shift size is important for detection, and to design a chart capable of quickly detecting this shift whilst having a low probability of false alarms for the shifts that we do not wish to detect. The Exponentially Weighted Moving Average (EWMA) control chart, although originally developed to successfully detect small shifts, can be designed to cope with these requirements. This paper presents a method for the economic-statistical design of EWMA charts for control processes, in which the detection of small shifts is not necessary, and which is, at the same time, effective in detecting important shifts. A genetic algorithm is used to optimize the design. A sensitivity analysis of the optimal solution is performed to determine the influence of certain factors on the economic model.

Fault diagnosis and comparing risk for the steel coil manufacturing process using statistical models for binary data

Abstract Advanced statistical models can help industry to design more economical and rational investment plans. Fault detection and diagnosis is an important problem in continuous hot dip galvanizing. Increasingly stringent quality requirements in the automotive industry also require ongoing efforts in process control to make processes more robust. Robust methods for estimating the quality of galvanized steel coils are an important tool for the comprehensive monitoring of the performance of the manufacturing process. This study applies different statistical regression models: generalized linear models, generalized additive models and classification trees to estimate the quality of galvanized steel coils on the basis of short time histories. The data, consisting of 48 galvanized steel coils, was divided into sets of conforming and nonconforming coils. Five variables were selected for monitoring the process: steel strip velocity and four bath temperatures. The present paper reports a comparative evaluation of statistical models for binary data using Receiver Operating Characteristic (ROC) curves. A ROC curve is a graph or a technique for visualizing, organizing and selecting classifiers based on their performance. The purpose of this paper is to examine their use in research to obtain the best model to predict defective steel coil probability. In relation to the work of other authors who only propose goodness of fit statistics, we should highlight one distinctive feature of the methodology presented here, which is the possibility of comparing the different models with ROC graphs which are based on model classification performance. Finally, the results are validated by bootstrap procedures.

A multiobjective approach for optimization of the multihead weighing process

Packaging technology can be of strategic importance to a company, as it can be a key to competitive advantage in the modern food industry. A multihead weighing process is a packaging process based on the sum of weights from several individual hoppers. The final quality of the packaged product in a modern automated food packing system should fulfill mo objectives -the quality of the packaging process itself and the sensory quality of the packaged food. The first one is often related to the proximity of the total weight to a nominal value of sale and to the variability of the packaging process, and the second one can be achieved by minimizing the total residence time of the food in the packing system. In this paper, we jointly address both objectives through multi objective programming. More precisely, a biobjective algorithm is developed, in which a subset of hoppers is selected from the set of available ones at each packing operation, in such a way that the relative importance of both aforementioned objectives is dynamically managed and adjusted. We conduct numerical experiments to examine the quality of the solutions being produced.

Bi-objective optimisation of a multihead weighing process

A multihead weighing process is a packaging technology that can be of strategic importance to a company, as it can be a key to competitive advantage in the modern food industry. The improvement in the process quality and sensory quality of food packaged in a multihead weighing process investigated in this paper is relevant to industrial engineering. A bi-objective ad hoc algorithm based on explicit enumeration for the packaging processes in multihead weighers with an unequal supply of the product to the weighing hoppers is developed. The algorithm uses an a priori strategy to generate Pareto-optimal solutions and select a subset of hoppers from the set of available ones in each packing operation. The relative importance of both aforementioned objectives is dynamically managed and adjusted. The numerical experiments are provided to illustrate the performance of the proposed algorithm and find the optimum operational conditions for the process. [Received 19 March 2016; Revised 8 November 2016; Revised 18 January 2017; Accepted 6 March 2017]

Competitive Models for the Spanish Short-Term Electricity Demand Forecasting

The control and scheduling of the demand for electricity using time series forecasting is a powerful methodology used in power distribution systems worldwide. Red Electrica de Espana, S.A. (REE) is the operator of the Spanish electricity system. Its mission is to ensure the continuity and security of the electricity supply. The goal of this paper is to improve the forecasting of very short-term electricity demand using multiple seasonal Holt–Winters models without exogenous variables, such as temperature, calendar effects or day type, for the Spanish national electricity market. We implemented 30 different models and evaluated them using software developed in MATLAB. The performance of the methodology is validated via out-of-sample comparisons using real data from the operator of the Spanish electricity system. A comparison study between the REE models and the multiple seasonal Holt–Winters models is conducted. The method provides forecast accuracy comparable to the best methods in the competitions.