Hotelling's Control Chart Research Articles

T² Hotelling Control Chart with Bootstrap Method for Paper Production Quality Control

T² Hotelling Control Chart with Bootstrap Method for Paper Production Quality Control

A control chart for monitoring image processes based on convolutional neural networks

In this paper, the problem of monitoring image processes with spatially correlated pixels over time is considered. An exponentially weighted moving average (EWMA) control chart for monitoring such processes based on a convolutional neural network (CNN) is proposed. A comparison of its performance with a Hotelling's control chart and with a control chart based on generalized likelihood ratio (GLR) approach is conducted through a simulation study. The new method outperforms other methods in most of the cases considered in the simulation study. A technique for mean intensity shift localization based on CNNs is proposed and evaluated.

Study of a proportional spool valve noise by means of Functional Data Analysis: Cavitation and intensity detection

Cavitation inside hydraulic components is a well-known issue, that arises under specific operating conditions. When this phenomenon occurs in valves, it leads to several issues, such as materials damage, performance reduction, and noise. The latter of them is becoming increasingly important in the transport sector, which is moving towards new technologies (i.e., electrification) that are notoriously quiet. Therefore, cavitation detection is becoming a matter of interest for several applications. The purpose of the work presented is to develop a diagnostic technique to detect the onset of cavitation in proportional valves. A 2-way 2-position proportional spool valve has been placed inside an acoustic enclosure; noise signals have been recorded by means of a high frequency microphone, for different flow rates and valve openings. Sound pressure levels have been analysed by means of statistical techniques; a Functional Data Analysis (FDA) has been performed in the open-source R environment, in which the experimental data, collected under different non-cavitation conditions, have been firstly used to perform a Functional Principal Component Analysis (FPCA) and then to define a threshold. Then, a further experimental dataset has been evaluated through a Hotelling control chart, from which it is possible to distinguish cavitating conditions as they fall outside the limits.

Application of the T2 Hotelling Multivariate Control Chart for Online Learning Evaluation of Compulsory Statistics Courses in the Mathematics Undergraduate Study Program at Andalas University

The world of education is one aspect of life that has been affected by Covid-19, so on March 17, 2020 the Ministry of Education and Culture issued a Circular regarding online learning. Andalas University Mathematics Undergraduate Study Program is one of the study programs at Andalas University that also implements an online learning process. In this study, an online learning evaluation will be carried out based on the Mathematics Statistics I and Mathematics Statistics II courses in the Andalas University Mathematics Undergraduate Program in the odd semester 2019/2020 and the even semester 2019/2020. The analysis used to measure the success of online learning is the analysis of quality control using the T2 Hotelling control chart. In addition, an analysis of the process ability of the two courses will also be carried out. The results obtained by using the T2 Hotelling control chart are that the online learning process in the two courses is under control, while by analyzing the process ability it can be said that the online learning process in the two courses is still not working well, which means it is not fully within the limits. specifications that have been determined in the academic regulations of Andalas University.

Comparison of short runs control chart and T2 Hotelling control chart for monitoring sunergy glass production process

In recent years, the manufacturing industry has tended to reduce mass production and produce in small quantities, which is called “Short Run Production”. In such a situation, the course of the production process is short, usually, the number of productions is less than 50. Therefore, a control chart for the short run production process is required. This paper discusses the comparison between multivariate control chart for short run production (V control chart) and T2 Hotelling control chart applied to sunergy glass data. Furthermore, a simulation of Average Run Length (ARL) was carried out to determine the performance of the two control charts. The results obtained are that the production process has not been statistically controlled using either the V control chart or the T2 Hotelling control chart. The number of out-of-control on the control chart V using the the EWMA test is more than the T2 Hotelling control chart. Based on the ARL value, it shows that the V control chart is more sensitive than the T2 Hotelling control chart.

Deviance residual‐based control charts for monitoring the beta‐distributed processes

AbstractBeta‐distributed process outputs are common in manufacturing industry because they range from 0 to 1 based on inputs like yield. Under the normality assumption, Shewarts control charts and Hotelling's control charts based on the deviance residual have been applied to monitor the process mean of the beta‐distributed process outputs. The normality assumption can be violated according to the shape of the beta distribution. Therefore, without the normality assumption, we propose antirank control charts, exponentially weighted moving average (EWMA) control charts and cumulative sum (CUSUM) control charts. The proposed control charts outperform the existing control charts in the experimental results. The previous research has been focused on monitoring the process mean only. For the first time, in order to monitor the process variance of the beta‐distributed process outputs, we propose the multivariate exponentially weighted mean squared deviation (MEWMS) chart, the first norm distance of the MEWMS deviation from its expected value (MEWMSL1) chart, the chart based on MEWMS deviation with the approximated distribution of trace (MEWMSAT), the multivariate trace sum squared deviation (MTSSD) chart and the multivariate matrix sum squared deviation (MMSSD) chart based on the deviance residual. The proposed control charts are compared and recommended in terms of the experimental results. This research can be a guideline for practitioners who monitor the deviance residual.

The Integrated Statistical Control Method of Technical Condition of Radio-Electronic Equipment for Prototyping of Robotic Systems

In the article, the approach of integrated statistical control and diagnostics of the radio-electronic equipment, which is based on the analysis, integration of the measuring information arriving from the thermal imager, magnetic field sensors, tension and humidity of air and also statistical control of equipment parameters, is presented. The solution of a control and diagnostics problem is based on monitoring of changes in the average level of a multi-parameter process. Here, Hotelling control charts, integration and processing of the measured information are used to provide the analysis and decision-making on the influence of the operator. The algorithm implements a technique of integrated statistical control of the technical condition of the radio-electronic equipment and is capable to determine the level of its precritical condition. The proposed technique increases the reliability of the identification of technical conditions of radio-electronic equipment and expands the scope of technical means of control and diagnostics.

Quality Control of HDPE Bottles Production Processes based on Multivariate Attribute Data using T2 Hotelling Control Chart as A Responds of Environment and Sustainability Issues

This research was conducted to determine the current process capability in producing the M500 bottle, where the process capability index can be calculated from the results of a control chart whose data is considered to be statistically controlled. Multivariate control charts can be used in controlling the quality of the process at CV X because the quality characteristics of the products are more than one, and the controls must be carried out together. Correlated variables used in making multivariate control charts are different thicknesses, leaks, and dents. The results of the hotelling’s T2 control chart show that the process has not been controlled because four observations are out of control. MYT decomposition results show that variables that cause observations to become uncontrolled are different thicknesses and dents. After revising the control chart, it is known that the current multivariate process capability index is 0.79, which means the process is said to be incapable and needs to be improved. The suggested improvement given to overcome the problem of different thicknesses is to position the die right in the middle so that the thickness on all sides is the same and for dented conditions can be reduced by adjusting the blowing temperature and pressure according to the standard.

Analysis of the Stability of the Chemical Composition of Wastewater in the Production of Printed Circuit Boards

A method for analyzing the stability of the chemical composition of wastewater in the manufacture of printed circuit boards using statistical methods of process control is proposed. The correlation and normal distribution of the monitored indicators is evaluated. Types of control charts are selected that provide control of both the average level of the process and its dispersion. To control the stability of independent indicators, Shewhart charts are used. Monitoring of correlated indicators is carried out using the Hotelling control chart. If it is necessary to control the multidimensional dispersion of the process, generalized variance charts can be used. The proposed approach ensures the detection of process violations before the monitored indicators are out of tolerance.

Using Multivariate Control Chart to Maintain the Quality of Drinking Water in Accordance with Standard

ABSTRACT This research aims to find the multivariate control chart which is suitable for production process, determine the current capability process, and also find the dominant variable which is correspondent to the improvement of drinking water quality. This research use a secondary data collected from January 2016 until February 2017. There were four group of variable used in this research. The first group was consist of color, turbidity, maximum containing level of copper and manganese. The second group consist of level of total dissolved solid, hardness, calcium and magnesium. The third level was consist of ph. value and alkaline; and fourth group consist of nitrate and nitrite. The result of data processing showed us that Multivariate Exponentially Weighted Moving Average or MEWMA control chart can detect the out of control data in the each group of variable faster than T2 Hotelling control chart. Then, the capability process index for the first group of variable is 2.238, the capability process index for second group of variable is 4.208, the capability process index for third group of variable is 1.438, and capability process index for fourth group of variable is 1.346. All group of variable have capability process index more than 1. This condition indicated that process goes well in all group of variable although there were some data is out of control in each group variable.

Fault Analysis Of Process System Using Multi Block Principal Component Analysis

This research looks into the issues of the quality improvement based on process control instead of product control using multivariate statistical process contro. A deterministic model of a proton exchange membrane fuel cell (PEM-FC) power plant was used as a case study to represent a multi variable or mukti equipment system. A three-step approach is proposed which can be classified into fault detection, fault isolation, and faulr diagnosis. The fault detection and the isolation utilize the multivariate analysis and yhe contro chart method , which uses the series multi-block principal component analysis of extended of PCA method. The series block principal component abalysis is solved using the non linear iteration partial least squares (NIPALS) algorithm. The SB-PCA can advangeouly incorporate the control chart, namely, T2 Hotelling control chart. In the fault diagnosis chart, the normalized variable method was successfully applied in this study with promising results. As a conclution, the result of this study demonstrated the potentials of multivariate statistical process control in solving fault detection and diagnosis problem for multi variable and multi equipment system.Keywords : statistical process control, principal component, fault analysis

Optimization methodology of alternating current P-GMAW process by voltage-current signal analysis

For maintenance and quality assurance during the execution of manufacturing processes, it is necessary to use careful experimental procedures to ensure customer satisfaction and high competitive standards in the market. This paper, which focuses on the class of non-destructive testing, proposes an optimization methodology for the alternating current pulsed gas metal arc welding (P-GMAW) process. The methodology is based on the numerical characterization of electrical signals of current and voltage by processing the obtained digital signals. The numerical characterization is performed by calculating the area under the curve of the electrical signals, which were then used to estimate the indicator difference relative percentage (DRP) of the signs of the experimental design for an experiment taken as a reference. Among the results, the study finds that the proposed method shows better results for signs composed of all its original wave frequencies at the expense of analysis performed on signals reconstructed from its three largest original wave frequencies. The results of the optimizations also showed more variability among themselves. In addition to the optimization analysis, the efficacy was evaluated in a T2 Hotelling control chart as a tool for control. Additionally, due to its application in multivariate processes, this study also analyzes the DRPs of electrical signals using statistical process monitoring.

Fuzzy T2 Hotelling (T_f^2 ) Control Chart

Statistical Process Control (SPC) is a method used to monitor a process for identifying special causes of variation and necessary to improve the process. One technique commonly used in the SPC is to determine whether the process is stable or not, both the mean and variability. Multivariate control charts are used if necessary to control together two or more related quality characteristics. Sometimes in a process production there is a lack of precision in the calculation, especially if the data used in the form of either data or qualitative attributes. Fuzzy set theory, specifically discusses the development of concepts and techniques related to the sources of uncertainty or imprecision in nature. Control charts are constructed by transforming crisp numbers into fuzzy numbers can be an alternative to obtain representative results of several variables in which there are several quality characteristics. Transformation of some functions, which are used in this study is Fuzzy Median Transformation (FMT). The advantages of FMT is that it can be used for the data in the form of asymmetry. This paper will discuss about the algorithm for Fuzzy T2 Hotelling control chart and its application to the production data of PT. IGLAS (Persero). From the results of the application of Fuzzy T2 Hotelling control chart got that out of the 5 variables that were analyzed, the dominant variables that lead to out of control is variable bottle molding process

Random projections and Hotelling’s T2 statistics for change detection in high-dimensional data streams

The method of change (or anomaly) detection in high-dimensional discrete-time processes using a multivariate Hotelling chart is presented. We use normal random projections as a method of dimensionality reduction. We indicate diagnostic properties of the Hotelling control chart applied to data projected onto a random subspace of Rn. We examine the random projection method using artificial noisy image sequences as examples.

ANALISIS KUALITAS PELAYANAN DAN PENGENDALIAN KUALITAS JASA BERDASARKAN PERSEPSI PENGUNJUNG

One of the factors which determine customer safisfaction is costumer perceive about service quality that focus to five service quality dimension that are tangible, reliability, responsiveness, assurance, and empathy. This research study service serve quality at UPT Perpustakaan Universitas Diponegoro Semarang with object to know customer perceive with respect to some variables in service quality dimension and satisfaction level. Importance-Performance Analysis used to map relation between importance with performance of respective variables to be and see gap between performance with importance of them variables. Customer Satisfaction Index (CSI) used to analyze all satisfaction respondent level. The T 2 Hotelling control chart to know servicing process stability with respect to costumer perceive. Research result shows that the gap is all negative value. It means library performance that represented by 21 variables include 5 service quality dimension still under expected costumer. The value CSI is 62,903% that meaning at enough satisfaction criterion. There are five points at above upper control limit in the T 2 Hotelling control chart. Therefore it can be said that process haven’t been controlled by statistical. Keywords: Service Quality, Importance-Performance Analysis , Customer Satisfaction Index, Hotelling T 2 Control Chart.

A Nonrigorous Approach Of Incorporating Sensitizing Rules Into Multivariate Control Charts

Multivariate control charts are becoming more important in the monitoring of processes in manufacturing industries because the quality of a process is usually determined by several correlated variables (quality characteristics). The most popular multivariate process control procedure is based on the Hotelling control chart. It is used to monitor the mean vector of a process. A nonrigorous approach of using four sensitizing rules is introduced to improve the performance of a conventional Hotelling chart. The use of these rules on a conventional Hotelling chart do not require a transformation of the T2 statistics into normal random variables. Thus, the T2 statistics incorporating these rules can be plotted on the same scale as they are plotted on a Hotelling chart. Numerous SAS and Mathematica programs are given to aid quality control practitioners in implementing these rules in real life problems. The aim of this article is to make the implementation of sensitizing rules appealing and user friendly to practitioners.

A Performance Analysis of Hotelling's χ2 Control Chart with Supplementary Runs Rules

Hotelling's 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.

Computing the Percentage Points of the Run-Length Distributions of Multivariate CUSUM Control Charts

Multivariate CUSUM control charts are often used instead of the standard Hotelling's control charts in many practical problems when detection of small shifts in the process mean is important. However, design of multivariate CUSUM control charts are usually based on the average run length (ARL). In this work, we will compute the percentage points of the run-length distributions of two multivariate CUSUM control charts. It will be shown that interpretations based on ARL can be misleading since the in-control run-length distribution of a multivariate CUSUM is highly skewed. On the other hand, the percentage points of the run-length distribution provide additional information such as the median run length, early false out-of-control signals, and the skewness of the run-length distribution for a particular scheme. These extra information might provide quality control engineers further knowledge of a particular multivariate CUSUM control chart scheme.