scholarly journals The Performance of Robust Multivariate Ewma Control Charts

2018 ◽  
pp. 52-58
Keyword(s):  
Control Chart ◽  
Control Charts ◽  
Moving Average ◽  
Statistical Tool ◽  
M Estimator ◽  
One Step ◽  
Exponential Weighted Moving Average ◽  
Mewma Control Chart ◽  
Mean Vector ◽  
Weighted Moving Average

Multivariate Exponential Weighted Moving Average (MEWMA) control chart is a popular statistical tool for monitoring multivariate process over time. However, this chart is sensitive to the presence of outliers arising from the use of classical mean vector and covariance matrix in estimating the MEWMA statistic. These classical estimators are known to be sensitive to the outliers. To address this problem, robust MEWMA control charts based on modified one-step M-estimator (MOM) and Winsorized modified one-step M-estimator (WM) are proposed. Their performance is then compared with the standard MEWMA control chart in various situations. The findings revealed that the proposed robust MEWMA control charts are more effective in controlling false alarm rates especially for large sample sizes and high percentage of outliers.

scholarly journals Novel Condition Monitoring Method for Wind Turbines Based on the Adaptive Multivariate Control Charts and SCADA Data

2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
Qinkai Han ◽  
Zhentang Wang ◽  
Tao Hu
Keyword(s):  
Control Chart ◽  
Condition Monitoring ◽  
Control Charts ◽  
Moving Average ◽  
Monitoring Method ◽  
Abnormal State ◽  
Exponential Weighted Moving Average ◽  
Multivariate Control ◽  
Mewma Control Chart ◽  
Weighted Moving Average

A novel condition monitoring method based on the adaptive multivariate control charts and the supervisory control and data acquisition (SCADA) system is developed. Two types of control charts are adopted: one is the adaptive exponential weighted moving average (AEWMA) control chart for abnormal state detection, and the other is the multivariate exponential weighted moving average (MEWMA) control chart for anomaly location determination. Optimization procedures for these control charts are implemented to achieve minimum out-of-control average running length. Multivariate regression analysis is utilized to obtain the normal condition prediction model of wind turbine with fault-free SCADA data. After comparing the regression accuracy of several popular algorithms in the MRA, the random forest is adopted for feature selection and regression prediction. Various tests on the wind turbine with normal and abnormal states are conducted. The performance and robustness of various control charts are compared comprehensively. Compared with conventional control charts, the AEWMA control chart is more sensitive to the abnormal state and thus has a more effective anomaly identification ability and better robustness. It is shown that the MEWMA control chart combined with the out-of-limit number index can effectively locate and identify the abnormal component.

scholarly journals KOMPUTASI METODE MULTIVARIATE EXPONENTIALLY WEIGHTED MOVING AVERAGE (MEWMA) UNTUK PENGENDALIAN KUALITAS PROSES PRODUKSI MENGGUNAKAN GUI MATLAB (STUDI KASUS: PT. Pismatex Textile Industry Pekalongan)

2020 ◽  
Vol 9 (3) ◽  
pp. 283-291
Author(s):  
Riza Fahlevi ◽  
Hasbi Yasin ◽  
Dwi Ispriyanti
Keyword(s):  
Control Chart ◽  
Textile Industry ◽  
Control Charts ◽  
Moving Average ◽  
Exponentially Weighted Moving Average ◽  
Quality Control Tool ◽  
Weight Value ◽  
Mewma Control Chart ◽  
Weighted Moving Average ◽  
Exponentially Weighted

Control chart is one of the effective statistical tools to overcome the problem of process quality in a production. Multivariate Exponentially Weighted Moving Average (MEWMA) control chart is an effective quality control tool in processes with more than one variable and correlated (multivariate). The MEWMA control chart has a weight value (λ) which makes this chart more sensitive in detecting small shifts process mean. The weight (λ) has values ranging from 0 to 1 ( ), where this weight will be given to each data. The MEWMA control chart in this study was used to form a control chart by the product defects percentage of grade B and grade B at PT. Pismatex Textile Industry Pekalongan. In this study, GUI Matlab was formed to assist the computational process in forming MEWMA control charts to control the quality of production at  PT. Pismatex Textile Industry Pekalongan. Based on the result, the optimal weight is obtained at the weight value λ = 0.9. Keywords: Multivariate Exponentially Weighted Moving Average (MEWMA), Weight (λ), GUI Matlab, Percentage of product defects.

scholarly journals PENERAPAN PENGENDALIAN KUALITAS DENGAN MEWMA DAN FUNGSI DENSITAS KERNEL MULTIVARIAT (Studi Kasus: PT Sukorejo Indah Textile Kab. Batang)

2019 ◽  
Vol 8 (1) ◽  
pp. 46-57
Author(s):  
Mifta Fara Sany ◽  
Rukun Santoso ◽  
Arief Rachman Hakim
Keyword(s):  
Quality Control ◽  
Product Quality ◽  
Control Chart ◽  
Control Charts ◽  
Average Length ◽  
Moving Average ◽  
Control Limit ◽  
Trial And Error ◽  
Mewma Control Chart ◽  
Weighted Moving Average

In an era of industrial revolution 4.0, technology is increasingly sophisticated, requiring companies to be more creative. Product quality control is an effort to minimize the defective products produced by the company. The production of weaving sarongs at PT SUKORINTEX pays attention to the accuracy of the length and width of the sarong to conform to the standards set by the company. To find out the quality of woven sarong products at PT SUKORINTEX, analysis was performed using Multivariate Exponentially Weighted Moving Average (MEWMA) control charts and multivariate kernel control charts. The research variable was the characteristics of the X sarongs which is reflected in 2 variates, namely the average length and average width. Based on the results and discussion that has been done, the MEWMA control chart used a weighting λ which is determined using trial and error. MEWMA control charts can be said to be stable and controlled by λ = 0.1, Upper Control Limit (UCL) of 14.62943, and Lower Control Limit (LCL) of 0. Multivariate kernel control chart were declared uncontrolled with α = 0.1 and level = 0.06130611 because there were data that was outside the contour. Chart improvement was done by trial and error and obtained a controlled chart results at α = 0.01 and a level value of 0.03125701. Based on this case study, the quality control of the average length and width of WADIMOR woven sarong types 30 STR with MEWMA is better than the multivariate kernel density, because MEWMA is controlled and stable in controlling product quality. The results of the MEWMA control chart show a capable process because more than 1 process capability index value is obtained. Keywords: Multivariate Exponentially Weighted Moving Average (MEWMA) control chart, multivariate kernel control chart, process capability.

scholarly journals Monitoring of mechanical sugarcane harvesting through control charts

2015 ◽  
Vol 35 (6) ◽  
pp. 1079-1092 ◽  
Author(s):  
Murilo A. Voltarelli ◽  
Rouverson P. da Silva ◽  
Cristiano Zerbato ◽  
Carla S. S. Paixão ◽  
Tiago de O. Tavares
Keyword(s):  
Process Control ◽  
Statistical Process Control ◽  
Control Chart ◽  
Control Charts ◽  
Moving Average ◽  
Grinding Wheel ◽  
Individual Values ◽  
Statistical Process ◽  
Minas Gerais State ◽  
Weighted Moving Average

ABSTRACT Statistical process control in mechanized farming is a new way to assess operation quality. In this sense, we aimed to compare three statistical process control tools applied to losses in sugarcane mechanical harvesting to determine the best control chart template for this quality indicator. Losses were daily monitored in farms located within Triângulo Mineiro region, in Minas Gerais state, Brazil. They were carried over a period of 70 days in the 2014 harvest. At the end of the evaluation period, 194 samples were collected in total for each type of loss. The control charts used were individual values chart, moving average and exponentially weighted moving average. The quality indicators assessed during sugarcane harvest were the following loss types: full grinding wheel, stumps, fixed piece, whole cane, chips, loose piece and total losses. The control chart of individual values is the best option for monitoring losses in sugarcane mechanical harvesting, as it is of easier result interpretation, in comparison to the others.

DEWMA Control Chart for the Coefficient of Variation

2011 ◽  
Vol 201-203 ◽  
pp. 1682-1688 ◽  
Author(s):  
Eui Pyo Hong ◽  
Hae Woon Kang ◽  
Chang Wook Kang
Keyword(s):  
Control Chart ◽  
Coefficient Of Variation ◽  
Control Charts ◽  
Moving Average ◽  
Exponentially Weighted Moving Average ◽  
Average Technique ◽  
Small Shift ◽  
Production Run ◽  
Weighted Moving Average ◽  
Exponentially Weighted

When the production run is short and process parameters change frequently, it is difficult to monitor the process using traditional control charts. In such a case, the coefficient of variation (CV) is very useful for monitoring the process variability. The CV control chart, however, is not sensitive at small shift in the magnitude of CV. The CV-EWMA (exponentially weighted moving average) control chart which was developed recently is effective in detecting a small shifts of CV. In this paper, we propose the CV-DEWMA control chart, combining the DEWMA (double exponentially weighted moving average) technique. We show that CV-DEWMA control chart perform better than CV-EWMA control chart in detecting small shifts when sample size n is larger than 5.

On the effect of measurement errors in simultaneous monitoring of mean vector and covariance matrix of multivariate processes

2016 ◽  
Vol 40 (1) ◽  
pp. 318-330 ◽  
Author(s):  
Amirhossein Amiri ◽  
Reza Ghashghaei ◽  
Mohammad Reza Maleki
Keyword(s):  
Measurement Errors ◽  
Control Charts ◽  
Moving Average ◽  
Real Data ◽  
Simulation Studies ◽  
Process Mean ◽  
Extensive Simulation ◽  
Monitoring Procedure ◽  
Mean Vector ◽  
Weighted Moving Average

In this paper, we investigate the misleading effect of measurement errors on simultaneous monitoring of the multivariate process mean and variability. For this purpose, we incorporate the measurement errors into a hybrid method based on the generalized likelihood ratio (GLR) and exponentially weighted moving average (EWMA) control charts. After that, we propose four remedial methods to decrease the effects of measurement errors on the performance of the monitoring procedure. The performance of the monitoring procedure as well as the proposed remedial methods is investigated through extensive simulation studies and a real data example.

Design of a Variable Sampling Interval EWMA Median Control Chart

2019 ◽  
Vol 26 (05) ◽  
pp. 1950021 ◽  
Author(s):  
Kim Phuc Tran ◽  
Philippe Castagliola ◽  
Thi Hien Nguyen ◽  
Anne Cuzol
Keyword(s):  
Control Chart ◽  
Control Charts ◽  
Food Production ◽  
Average Run Length ◽  
Moving Average ◽  
Sampling Interval ◽  
Performance Comparison ◽  
Variable Sampling Interval ◽  
Variable Sampling ◽  
Weighted Moving Average

In the literature, median type control charts have been widely investigated as easy and efficient means to monitor the process mean when observations are from a normal distribution. In this work, a Variable Sampling Interval (VSI) Exponentially Weighted Moving Average (EWMA) median control chart is proposed and studied. The Markov chains are used to calculate the average run length to signal (ARL). A performance comparison with the original EWMA median control chart is made. The numerical results show that the proposed chart is considerably more effective as it is faster in detecting process shifts. Finally, the implementation of the proposed chart is illustrated with an example in food production process.

Monitoring the Coating Thickness of Pharmaceutical Tablets with MaxGWMA Control Chart

2013 ◽  
Vol 372 ◽  
pp. 325-330
Author(s):  
Thanh Lam Nguyen ◽  
Ming Hung Shu ◽  
Bi Min Hsu
Keyword(s):  
Control Chart ◽  
Coating Thickness ◽  
Control Charts ◽  
Moving Average ◽  
Coating Process ◽  
Small Shift ◽  
Pharmaceutical Tablets ◽  
Pharmaceutical Ingredients ◽  
The Status ◽  
Weighted Moving Average

So as to monitor and detect small shifts in the mean and variability of a manufacturing process, exponentially weighted moving average (EWMA) control charts are widely employed. Some of its extensions have been proposed to improve its performance. Among them, the Maximum generally weighted moving average (MaxGWMA) control chart is found as the superior. In the industry of coating pharmaceutical tablets, controlling the thickness of the coating layer containing active pharmaceutical ingredients is of great importance and in order to keep track on the coating quality, various methods using modern technologies have been proposed. However, decision support systems on the status of the coating process are not fully developed. Hence, in this study, MaxGWMA control chart was proposed to monitor the coating thickness of the tablets so that any small shift in the coating process can be quickly detected and further corrective actions can be implemented to make the process in control.

Detecting leaks through AMR data analysis

2015 ◽  
Vol 15 (6) ◽  
pp. 1368-1372
Author(s):  
K. Claudio ◽  
V. Couallier ◽  
C. Leclerc ◽  
Y. Le Gat ◽  
X. Litrico ◽  
...  
Keyword(s):  
Moving Average ◽  
Huge Amount ◽  
Water Losses ◽  
Statistical Tool ◽  
Time Consumption ◽  
Multiple Components ◽  
Consumption Data ◽  
User Friendly ◽  
Exponential Weighted Moving Average ◽  
Weighted Moving Average

Automatic meter reading (AMR) provides real-time consumption data, enabling to collect a huge amount of information about daily, even hourly, consumptions. It is then easy to assess lost volumes on the network, using supplied volumes information. However, because of the multiple components of water losses, the metering and calculation inaccuracies, the occurrence of new (detectable) leaks is hard to detect. Therefore this paper aims at proposing a user-friendly statistical tool that helps to quickly and reliably detect new leakage occurrence. The use of process control chart (like exponential weighted moving average) enables us to detect changes in the water loss time series, in particular, a new leak occurrence.

Sign in / Sign up

Export Citation Format

Share Document