Statistical Process Control Techniques Research Articles

Improving the quality of Higher Education teaching through the exploitation of student evaluations and the use of control charts

Student evaluations of faculty members' teaching effectiveness are considered quite important in Higher Education (HE). In this paper, we elaborate on the framework of Nikolaidis and Dimitriadis, based mainly on Statistical Process Control techniques and tools, which enables a deeper analysis and broader exploitation of student evaluation data. More specifically, we thoroughly examine and evaluate through simulation, several popular types of control charts (CCs), identifying the most suitable among them, using as comparison criteria various statistical properties of CCs. The ultimate goal of our research is to provide decision makers in HE institutions with an easy-to-use reliable tool for not only monitoring the teaching process, but also identifying the effective and ineffective faculty members’ teaching performance to promote the quality of their Institution.

An Efficient Mixed-Memory-Type Control Chart for Normal and Non-Normal Processes

Statistical process control techniques are commonly used to monitor process performance. Control charting technique is the most sophisticated tool of SPC and is categorized as memory-less and memory-type control charts. Shewhart-type control charts have low efficiency in detecting the small changes in the process parameters and named as memory-less control charts, and memory-type control charts (for example cumulative sum (CUSUM) and exponentially weighted moving average (EWMA) charts) are very sensitive to small persistent shifts. In connection with enhancing the performance of CUSUM and EWMA charts, an efficient variant of memory-type charts for the location parameter is developed based on mixing the double exponentially weighted moving average (DEWMA) chart and CUSUM chart by performing exponential smoothing twice. Performance of the proposed efficient variant is compared with existing counterparts under normal and non-normal (heavy tails and skewed) environments. The study also provides an industrial application related to the monitoring of weights of quarters made by mint machine placed into service at U.S. Mint. From theoretical and numerical studies, it is revealed that proposed variant of memory-type charts outperforms the counterparts in detecting shifts of small and moderate magnitude.

A data-driven approach for Network Intrusion Detection and Monitoring based on Kernel Null Space

In this study, we propose a new approach to determine intrusions of network in real-time based on statistical process control technique and kernel null space method. The training samples in a class are mapped to a single point using the Kernel Null Foley-Sammon Transform. The Novelty Score are comp

Departmental action limits for TQA energy variations defined by means of statistical process control methods.

The purpose of this study is to define departmental action limits for energy percentage variation measured by means of step-wedge helical Tomotherapy quality assurance module. Individual charts using the Statistical Process Control techniques have been used to identify retrospectively out-of-control situations ascribable to documented actions performed on the Tomotherapy system. Using the in-control data of our analysis process capability indices (cp, cpk, cpm and cpmk) are calculated in order to document the real working condition of the Tomotherapy system. Our findings indicate use of an action limit of 1.0% for energy percentage variation difference between the measured and reference output is a good working condition of a Tomotherapy system. cp and cpk indices are suggested as good indices that correctly report the system capability. A method for calculating and reporting Tomotherapy action limits for the integrated self-checking TQA energy check was shown in this study. SPC technique has proven to be efficient in defining departmental action limits from retrospective data for TQA energy measurements, hence optimally enabling corrective improvements in the process of quality assurance.

Real-time quality monitoring and diagnosis for manufacturing process profiles based on deep belief networks

A large number of real-time quality data are collected through various sensors in the manufacturing process. However, most process data are high-dimension, nonlinear and high-correlated, so that it is difficult to model the process profiles, which restricts the application of conventional statistical process control technique. Motivated by the powerful ability of deep belief network (DBN) to extract the essential features of input data, this paper develops a real-time quality monitoring and diagnosis scheme for manufacturing process profiles based on DBN. The profiles collected from a manufacturing process are mapped into quality spectra. A novel DBN recognition model for quality spectra is established in the off-line learning phase, which can be applied to monitor and diagnose the process profiles in the on-line phase. The effectiveness of DBN recognition model for manufacturing process profiles is demonstrated by simulation experiment, and a real injection molding process example is applied to analyze the performance. The results show that the proposed DBN model outperforms alternative methods.

Improving Process Capability of Cutting and Drilling Processes of Elevator Assembly Parts

Statistical process control (SPC) technique has become more and more often used for manufacturing process improvement with understanding the process and detecting the process variation. This paper presents a study from a small enterprise classified as OEM supply elevator assembly parts. A process capability study is performed for cutting and drilling processes in order to verify the process capable of consistently meeting the required specification and delivering quality products since increasing a number of rework parts. Why-why analysis was used to identify the root cause and the principles of Poka Yoke and jig & fixture design were then applied by design a measure gauge for cutting and drilling processes. After improvement, the result shows that the Cpk of cutting process increase from 0.19 to 2.72 while Cpk of drilling process also increase from 0.36 to 4.50. Since the Cpk is greater than 1.3 this means that both two processes have a capable to produce the output meet specification.

Multivariate statistical control chart and process capability indices for simultaneous monitoring of project duration and cost

Statistical process control (SPC) techniques have been implemented in a few studies in order to determine action limits on the earned value management (EVM) indices to assist project managers in monitoring project performance. Nevertheless, these indices are correlated, reliance on univariate control charts when more than one variable are involved and they are correlated may lead to unsatisfactory results such as increasing the rate of false alarms. This study presented an approach to overcome this limitation by applying multivariate Hotelling's T2 control chart to take into account possible correlations between EVM indicators and describe the entire capability of the project performance more accurately. Furthermore, in order to quantify how well a project can meet its requirements, some practical multivariate process capability indices (PCIs) are introduced. This approach provides management with more reliable information about the deviations between planned and actual performance both in terms of time and cost simultaneously.

Profile Monitoring for Autocorrelated Reflow Processes with Small Samples

The methodology of profile monitoring combines both the model fitting and statistical process control (SPC) techniques. Over the past ten years, a variety of profile monitoring methods have been proposed and extensively investigated in terms of different process profiles. However, monitoring tasks still exhibit a primary problem in that the errors surrounding the functional relationship are frequently assumed to be independent within every single profile. However, the assumption of independence is an unrealistic assumption in many practical instances. In particular, within-profile autocorrelation often occurs in the profile data. To mitigate the within-profile autocorrelation, a monitoring method incorporating an autoregressive (AR)(1) model to cope with autocorrelation is proposed. In this paper, the reflow process with small samples in surface mount technology (SMT) is investigated. In Phase I, three different process models are compared in combination with the first-order autoregressive model, while an appropriate profile model is sought. The Hotelling T2 and exponentially weighted moving average (EWMA) control charts are used together to monitor the parameter estimates (i.e., profile shape) and residuals (i.e., profile variability), respectively.

Using Infant Mortality Data to Improve Maternal and Child Health Programs: An Application of Statistical Process Control Techniques for Rare Events.

Introduction The infant mortality rate (IMR) in the United States remains higher than most developed countries. To understand this public health issue and support state public health departments in displaying and analyzing data in ways that support learning, states participating in the Collaborative Improvement and Innovation Network to Reduce Infant Mortality (IM CoIIN) created statistical process control (SPC) charts for rare events. Methods State vital records data on live births and infant deaths was used to create U, T and G charts for Kansas and Alaska, two states participating in the IM CoIIN who sought methods to more effectively analyze IMR for subsets of their populations with infrequent number of deaths. The IMR and the number of days and number of births between infant deaths was charted for Kansas Non-Hispanic black population and six Alaska regions for the time periods 2013-2016 and 2011-2016, respectively. Established empirical patterns indicated points of special cause variation. Results The T and G charts for Kansas and G charts for Alaska depict points outside the upper control limit. These points indicate special cause variation and an increased number of days and/or births between deaths at these time periods. Discussion T and G charts offer value in examining rare events, and indicate special causes not detectable by U charts or other more traditional analytic methods. When small numbers make traditional analysis challenging, SPC has potential in the MCH field to better understand potential drivers of improvements in rare outcomes, inform decision making and take interventions to scale.

An effective combined multivariate control chart based on support vector data description

Conventional multivariate control charts usually focus on a specific process shifts range (small or large), and they cannot get the knowledge of manufacturing process through the learning of in-control data and be effective over the whole range of mean shifts, due to the characteristics of their own structures. In this paper, an effective combined multivariate control chart (named CDD chart, i.e., combined D-MCUSUM and D chart) with an adaptive control limit is proposed to improve the overall detection ability of monitoring techniques in multivariate statistical process control. Besides, this paper also provides a basic methodology for designing the adaptive control limit and recommended values of some key parameters (e.g. window size) for a better application. Based on these, a bivariate simulation experiment is conducted to evaluate the performance of the proposed control chart. Simulation results show that the CDD chart offers a better overall performance, compared with regular control charts (e.g. MCUSUM). In addition, a real industrial case also illustrates the effectiveness of the proposed control chart in applications.

SPC techniques using M/M/1 queueing model

In a manufacturing process, no two products can be exact, which might be due to many factors. These variations need to be monitored and controlled through the use of statistical process control (SPC). When they are small, and their effects are barely noticeable, we say the process is 'in control'. Otherwise, they lead the process to 'out of control'. Items enter the system and wait in a line for measurements; by following a queue discipline. Such a queue is then characterised according to service time, number of quality inspectors and waiting space. A good process control will also protect the product in the sense that the lots produced at permissible levels of quality will have a good chance to be in control. The objective of this paper is to introduce a control chart using M/M/1 queueing discipline to study and maintain a process control in a regular interval.

New Approach in Analyzing Risk Level of Flood in Tropical Region: A Case Study at Pahang River Basin, Malaysia

This study focuses on flood risk recognition factor that leads to major contribution of floods in Pahang River basin, identify the correlation between variables and determine factor that influence the flood risk pattern in Pahang. Four hydrological variables been applied. Chemometric technique of Principal Component Analysis (PCA) method and Statistical Process Control (SPC) method were being applied to identify the main contributor for flood, predicting hydrological modeling and risk of flood occurrence at Pahang river basin. Findings from Principal Component Analysis (PCA) confirmed that all selected variables were significant. The relationship between Suspended Solid and Stream Flow with Water Level were very high with correlation of coefficient value more than 0.7. SPC set up a new control limit for all variables. Data beyond the Upper Control Limit (UCL) value is considered as high risk for flood occurrence. Most of the trend pattern showed in year 2007 as high peak. Rapid development growth and anthropogenic activities caused the sediment of Suspended Solid triggered the Water Level and Stream Flow to arise than normal level. Thus, local authority should take earlier precaution for flood prevention and emergency responses plan at the study area for any development of land by takes obligatory action to the developers especially those development that arise along river channel.

A Fuzzy EWMA Attribute Control Chart to Monitor Process Mean

Conventional control charts are one of the most important techniques in statistical process control which are used to assess the performance of processes to see whether they are in- or out-of-control. As traditional control charts deal with crisp data, they are not suitable to study unclear, vague, and fuzzy data. In many real-world applications, however, the data to be used in a control charting method are not crisp since they are approximated due to environmental uncertainties and systematic ambiguities involved in the systems under investigation. In these situations, fuzzy numbers and linguistic variables are used to grab such uncertainties. That is why the use of a fuzzy control chart, in which fuzzy data are used, is justified. As an exponentially weighted moving average (EWMA) scheme is usually used to detect small shifts, in this paper a fuzzy EWMA (F-EWMA) control chart is proposed to detect small shifts in the process mean when fuzzy data are available. The application of the newly developed fuzzy control chart is illustrated using real-life data.

Applying Persuasive Design Techniques to Influence Data-Entry Behaviors in Primary Care: Repeated Measures Evaluation Using Statistical Process Control.

BackgroundPersuasive design is an approach that seeks to change the behaviors of users. In primary care, clinician behaviors and attitudes are important precursors to structured data entry, and there is an impact on overall data quality. We hypothesized that persuasive design changes data-entry behaviors in clinicians and thus improves data quality.ObjectiveThe objective of this study was to use persuasive design principles to change clinician data-entry behaviors in a primary care environment and to increase data quality of data held in a family health team’s reporting system.MethodsWe used the persuasive systems design framework to describe the persuasion context. Afterward, we designed and implemented new features into a summary screen that leveraged several persuasive design principles. We tested the influence of the new features by measuring its impact on 3 data quality measures (same-day entry, record completeness, and data validity). We also measured the impacts of the new features with a paired pre-post t test and generated XmR charts to contextualize the results. Survey responses were also collected from users.ResultsA total of 53 users used the updated system that incorporated the new features over the course of 8 weeks. Based on a pre-post analysis, the new summary screen successfully encouraged users to enter more of their data on the same day as their encounter. On average, the percentage of same-day entries rose by 10.3% for each user (P<.001). During the first month of the postimplementation period, users compensated by sacrificing aspects of data completeness before returning to normal in the second month. Improvements to record validity were marginal over the study period (P=.05). Statistical process control techniques allowed us to study the XmR charts to contextualize our results and understand trends throughout the study period.ConclusionsBy conducting a detailed systems analysis and introducing new persuasive design elements into a data-entry system, we demonstrated that it was possible to change data-entry behavior and influence data quality in a reporting system. The results show that using persuasive design concepts may be effective in influencing data-entry behaviors in clinicians. There may be opportunities to continue improving this approach, and further work is required to perfect and test additional designs. Persuasive design is a viable approach to encourage clinician user change and could support better data capture in the field of medical informatics.

New adaptive control charts for monitoring the multivariate coefficient of variation

Abstract An adaptive control chart is one of the most effective techniques in Statistical Process Control (SPC). The coefficient of variation (CV) is common in many real life applications, especially in manufacturing and materials engineering, finance, medical and biological sciences. This paper proposes three adaptive charts to monitor the multivariate coefficient of variation (MCV), in order to improve the sensitivity of the standard MCV chart, in detecting small and moderate MCV shifts. The proposed charts are designed using the Markov chain approach and they are compared with the existing standard MCV chart using the average time to signal (ATS), standard deviation of the time to signal (SDTS) and expected average time to signal (EATS) criteria. The performance comparison shows that the proposed adaptive MCV charts, particularly the variable sample size and sampling interval (VSSI) MCV chart, outperform the existing MCV charts, in terms of the ATS and EATS criteria. By allowing the sample size and sampling interval to be varied in the VSSI MCV chart, process engineers will have better control in process monitoring and at the same time are able to detect an out-of-control signal quicker. Illustrative examples are presented by considering the VSSI MCV chart to show the chart’s implementation.

Investigating the impact of hard total quality management practices on operational performance in manufacturing organizations

PurposeThe purpose of this paper is to investigate the impact of hard total quality management (TQM) practices on operational performance dimensions in manufacturing organizations.Design/methodology/approachThe study was designed in the Jordanian manufacturing sector. Organizations that are familiar with hard TQM practices specifically that had already implemented ISO 9001 certificate were randomly surveyed through structured questionnaire, yielded a sample of 40 responding organizations. Principal component factor analysis was used to analyze hard TQM practices implementation and organizations operational performance dimensions. As a result, specific hard TQM practices and operational performance dimensions were extracted. The hard TQM practices that significantly influence operational performance dimensions were tested using simple and multiple linear regression analysis.FindingsThe research findings showed that hard TQM practices in manufacturing sector include; continuous improvement, statistical process control (SPC), process management and quality tools and techniques. Meanwhile, operational performance dimensions include; quality and inventory management performance. Also, the findings showed that continuous improvement and SPC practices play a major role in obtaining the desired results of operational performance.Research limitations/implicationsThree limitations can be identified in this research, using subjective measures of TQM practices and operational performance, low response rate and using a sample of organizations from various industries. This paper can help Jordanian manufacturing organizations to foster proper practices and make the right decisions related to operational performance.Originality/valueThis study describes a reliable hard TQM model that can be used by manufacturing organizations to improve their operational performance. Also, the results of this study contribute to prior literature and recommend some best practices for manufacturing organizations.

Implementation of statistical process control in a bottling line in winnery industry

Introduction: The great demand of the markets has led to situations in which the production systems are characterized by the production of several batches but of small size. This new paradigm requires that adequate techniques be developed, both in terms of planning and in terms of Statistical Process Control (SPC), since there may be situations where it is not possible to collect enough data to properly estimate the parameters of the process (mean and variance). Objectives: Implementation of Statistical Process Control techniques in a wine industry in order to improve its final product. Methods: Whenever there is not enough data to properly estimate the parameters of the process, the suggested approach, is to adopt the developments proposed by Charles Quesenberry. In this case, the statistic of the sample at time i is transformed through the estimations of the process parameters using the information obtained (data) until the instant (i-1). The univariate study of process capability is performed through the capability indices QL and QU. Thus, in this paper, two situations of statistical control are addressed, one in which a univariate study is done, based on Q charts, and another in which the multivariate study is made, based on the MQ charts. Results: This study comprised the implementation of the SPC) of a wine brand that has low production volumes, in the process of bottling wine, which is considered a critical step since some care is needed, such as avoiding the occurrence of microbiological contaminations or oxidation of the wine. Conclusions: Whenever it is not possible to apply traditional control charts the use of the control Q charts (univariate analysis) and the control MQ charts (multivariate analysis) are the most appropriate choice not only for the control of one or more products but also for several sets of quality characteristics.

Dynamic Non-parametric Monitoring of Air-Pollution

Air pollution poses a major problem in modern cities, as it has a significant effect in poor quality of life of the general population. Many recent studies link excess levels of major air pollutants with health-related incidents, in particular respiratory-related diseases. This introduces the need for city pollution on-line monitoring to enable quick identification of deviations from “normal” pollution levels, and providing useful information to public authorities for public protection. This article considers dynamic monitoring of pollution data (output of multivariate processes) using Kalman filters and multivariate statistical process control techniques. A state space model is used to define the in-control process dynamics, involving trend and seasonality. Distribution-free monitoring of the residuals of that model is proposed, based on binomial-type and generalised binomial-type statistics as well as on rank statistics. We discuss the general problem of detecting a change in pollutant levels that affects either the entire city (globally) or specific sub-areas (locally). The proposed methodology is illustrated using data, consisting of ozone, nitrogen oxides and sulfur dioxide collected over the air-quality monitoring network of Athens.

Selection of quality-inspection procedures for short-run productions

Designing quality-inspection procedures may be difficult for short-run manufacturing processes, due to poor effectiveness of the classical statistical process control (SPC) techniques for these processes. This paper proposes a practical methodology to guide quality designers in selecting the more effective and economically convenient inspection procedures. First, the process of interest is decomposed into a number of steps, in which specific defects can occur. Next, several parameters related to inspection effectiveness and cost are combined into a probabilistic model. The more effective and economically convenient inspection procedures can finally be determined using two specific synthetic indicators. A case study concerning a short-run production of hardness testing machines is presented and discussed.

Time Control Chart for Two Inverted Models

Control charts are one of the powerful techniques of Statistical Process Control. Control charts are widely accepted and applied in industry which can be used to improve productivity, prevent defects and unnecessary process adjustment. Moreover, they also provide information in diagnosis and process capability. Life time data generally contain the failure times of sample products or inter failure times or number of failures experienced in a given time. The time to failure of a product is to be considered as a quality characteristic to assess the quality of the product. Control limits are evaluated for the time to failure. In this paper the time to failure of a product is considered to follow Inverse Rayleigh and Inverse Half Logistic distributions. Life time data are compared with the control limits to judge the quality performance of the product.