Assignable Causes Research Articles

Joint optimisation of double warning T2-Hotelling chart and maintenance policy with multiple assignable causes

ABSTRACTStatistical process monitoring (SPM) and maintenance management as two key tools for process management can create profound economic benefits, particularly when they are coordinated. This paper demonstrates the value of integrating SPM and maintenance by presenting a multi-objective model consisting of both economic and statistical criteria. Furthermore, to more adapt to complex manufacturing systems, the proposed model consists of two features: (1) monitoring several correlated quality characteristics by designing a double warning lines ‘T2-Hotelling’ chart; and (2) considering the probability of occurrence for more than one assignable cause (AC). To show the effectiveness of the proposed integrated model, two comparative studies are conducted. The first one confirms that the integration of SPM and maintenance policy leads to more effective performance in both economic and statistical viewpoints. The latter results demonstrate that the proposed model outperforms the corresponding single objective models.

Capture and emission mechanisms of defect states at interface between nitride semiconductor and gate oxides in GaN-based metal-oxide-semiconductor power transistors

A physical insight into the capture and emission behavior of interface/oxide states in a GaN-based metal-oxide-semiconductor (MOS) structure is of great importance to understanding the threshold voltage (VTH) instability in GaN power transistors. A time-dependent VTH shift in Ni/Al2O3/AlGaN/GaN MOS-HFETs (heterojunction field-effect transistors) and a distribution of Al2O3/III-nitride interface states (Dit) were successfully characterized by constant-capacitance deep level transient spectroscopy. It is found that in situ remote plasma pretreatments in plasma-enhanced atomic-layer-deposition could suppress Dit (EC-ET > 0.4 eV) down to below 1.3 × 1012 cm−2 eV−1. Under high applied gate bias (e.g., VG > 8 V), tunnel filling of oxide states in the Al2O3 dielectric comes into play, contributing to remarkable VTH instability in the MOS-HFETs. The tunnel distance between the 2D Electron Gas (2DEG) channel and oxide states ET,ox in the Al2O3 dielectric decreases from 3.75 to 0.82 nm as VG increases from 2 to 8 V. A further increase of VG to 11 V makes the Fermi level approach ET,ox (EC − ET ∼ 1.62 eV), which may enable direct filling. High electric field induced tunnel filling of gate oxide states could be an assignable cause for VTH instability in normally-OFF III-nitride MOS-HFETs.

MULTIVARIATE CUSUM CONTROL CHART BASED ON THE RESIDUALS OF MULTIOUTPUT LEAST SQUARES SVR FOR MONITORING WATER QUALITY

Monitoring serially dependent processes using conventional control charts yields a high false alarm rate. Multioutput Least Squares Support Vector Regression (MLS-SVR) has the capability to encompass the cross-relatedness between output variables by learning multivariate output variables simultaneously. This research aims to develop a Multivariate Cumulative Sum (MCUSUM) control chart based on the residual obtained from the MLS-SVR model for monitoring autocorrelated data. The inputs of the MLS-SVR are selected using the significant lag of a partial autocorrelation function. The proposed control chart is applied to monitor water quality data and it can detect the assignable causes in those data caused by a broken pipeline.

Constrained optimal design of Control Chart for correlated data under Weibull Shock Model with multiple assignable causes

An appropriate technique for monitoring a stochastic system is to utilize the control charts. In statistical process, control a drift in characteristics of output may be due to one or several assignable causes. In the establishment of charts in statistical process control, an assumption is made that there is no correlation within the samples. However, in practice there are many cases where the correlation does exist within the samples. It would be more appropriate to assume that each sample is a realization of a multivariate normal random vector. Although some research works have been done on the economic design of control charts with single assignable cause with correlated data, the economic statistical design of control chart under Weibull shock model with multiple assignable causes and correlated samples have not been presented yet. Based on the optimization of the average cost per unit of time and taking into account the different combination values of Weibull distribution parameters, optimal design values of sample size, sampling interval, and control limit coefficient were derived and calculated. Then the cost models under non-uniform and uniform sampling scheme were compared. The results revealed that the model under multiple assignable causes with correlated samples with non-uniform sampling has a lower cost than that with uniform sampling.

Control charts for simultaneously monitoring of process mean and coefficient of variation with and without auxiliary information

AbstractA control chart is very useful to control assignable causes which detect the shifted process parameters (eg, mean and dispersion). Simultaneous monitoring of the process parameters is a well‐known approach utilized for the bilateral processes. In the current study, we proposed the blended control chart that monitors the process mean and process coefficient of variation simultaneously. Further, the sensitivity of control chart is enhanced by incorporating an auxiliary variable. We have utilized the concept of EWMA chart and also the log transformation to transform the distribution of sample coefficient of variation to the normal distribution for structuring a joint monitoring control chart. The performance comparison among proposed control charts is presented. On the basis of ARLs and SDRLs, several advantages of the proposed control charts are diagnosed. The empirical evidence is also provided to support proposed control chart with a real‐life dataset.

A regression spline control chart for monitoring characteristics exhibiting nonlinear profile over time

Purpose The purpose of this paper is to demonstrate the application of the control chart procedure to monitor the characteristics whose profile over time resembles a set of connected line segments. Design/methodology/approach Fit a regression spline model by taking the subgroup average of the characteristic as response variable and time as the explanatory variable. Then monitor the response variable using the regression spline control chart with the fitted model as center line and upper and lower control limits at three standard deviation units of the response variable above and below the center line. Findings The proposed chart is successfully deployed to monitor the daily response time profile of a client server of an application support process. The chart ensured the stability of the process as well as detected the assignable cause leading to the slowing down of the server performance. Practical implications The methodology can be used to monitor any characteristics whose performance profile over time resembles a set of connected line segments. Some of the examples are the consumption profile of utility providers like power distribution companies, usage profiles of telecom networks, loading profile of airline check-in process, e-commerce websites, etc. Originality/value To the best of the author’s knowledge, construction of control charts using regression spline is new. The usage of the control chart to monitor the performance characteristics which exhibits a nonlinear profile over time is also rare.

Modeling and Solving of Uncertain Process Abnormity Diagnosis Problem

There are many uncertain factors that contribute to process faults and this make it is hard to locate the assignable causes when a process fault occurs. The fuzzy relational equation (FRE) is effective to represent the uncertain relationship between the causes and effects, but the solving difficulties greatly limit its practical utilization. In this paper, the relation between the occurrence degree of abnormal patterns and assignable causes was modeled by FRE. Considering an objective function of least distance between the occurrence degree of abnormal patterns and its assignable cause’s contribution degree determined by FRE, the FRE solution can be obtained by solving an optimization problem with a genetic algorithm (GA). Taking the previous optimization solution as the initial solution of the following run, the GA was run repeatedly. As a result, an optimal interval FRE solution was achieved. Finally, the proposed approach was validated by an application case and some simulation cases. The results show that the model and its solving method are both feasible and effective.

Pain and depression are associated with both physical and mental fatigue independently of comorbidities and medications in primary Sjögren’s syndrome

ObjectivesTo report on fatigue in patients from the United Kingdom primary Sjögren’s syndrome (pSS) registry identifying factors associated with fatigue and robust to assignable causes such as comorbidities and medications...

Risk-adjusted Bernoulli chart in multi-stage healthcare processes based on state-space model with a latent risk variable and dynamic probability control limits

Healthcare-related processes are usually multistage in nature, and the output of each stage is the input of the subsequent stage. However, most existing monitoring schemes consider the individual stages of the healthcare process without considering both inter-stage and intra-stage links. The modeling of multistage healthcare processes based on the state-space model describes the cascade property of the risks and outcomes in subsequent stages. The present paper proposes a Bernoulli state-space model in which unmeasurable risks of processes are considered as a latent risk variable to give a realistic estimate of potential risks. In the proposed monitoring scheme for multistage medical processes, in addition to Parsonnet scores, the other categorical operational covariates are considered. Moreover, dynamic probability control limits are applied to remove the effect of patient risk distributions on in-control average run length performance. Simulation results reveal that the proposed risk-adjusted Bernoulli group exponentially weighted moving average chart for multistage healthcare processes performs satisfactorily under different shifts. Moreover, the proposed monitoring scheme helps to identify the out-of-control stage of the healthcare process to remove the corresponding assignable cause.

Statistically constrained economic design of control chart with Weibull in-control time for processes subject to multiple assignable causes

PurposeThe purpose of this paper is to develop an economic statistical design based on the concepts of adjusted average time to signal (AATS) and ANF for control chart under a Weibull shock model with multiple assignable causes.Design/methodology/approachThe design used in this study is based on a multiple assignable causes cost model. The new proposed cost model is compared with the same cost and time parameters and optimal design parameters under uniform and non-uniform sampling schemes.FindingsNumerical results indicate that the cost model with non-uniform sampling cost has a lower cost than that with uniform sampling. By using sensitivity analysis, the effect of changing fixed and variable parameters of time, cost and Weibull distribution parameters on the optimum values of design parameters and loss cost is examined and discussed.Practical implicationsThis research adds to the body of knowledge relating to the quality control of process monitoring systems. This paper may be of particular interest to practitioners of quality systems in factories where multiple assignable causes affect the production process.Originality/valueThe cost functions for uniform and non-uniform sampling schemes are presented based on multiple assignable causes with AATS and ANF concepts for the first time.

Monitoring Bernoulli processes considering measurement errors and learning effect

AbstractThis paper presents the effect of measurement errors and learning on monitoring processes with individual Bernoulli observations. A cumulative sum control chart is considered to evaluate the possible impacts of measurement errors and learning. We propose a time‐dependent learning effect model along with measurement errors and incorporate them into the Bernoulli CUSUM control chart statistic. The performance of the Bernoulli CUSUM control chart is then merely assessed by comparing the average number of observations to signal (ANOS) under two proposed conditions with the condition of no possible errors. Thus, the ANOS values are obtained under different proportions of non‐conforming items, once considering errors due to measurement by inspectors, and once considering both errors and learning effect together. The experimental results show that the efficiency of the control chart to detect assignable causes deteriorates in the presence of measurement errors and enhances when learning affects operators' performance. The proposed approach has a potential to be used in monitoring high‐quality Bernoulli processes as well as disease diagnosis, and other health care applications with Bernoulli observations.

A hybrid NSGA-II-DEA method for the economic-statistical design of the C-control charts with multiple assignable causes

In this paper, a multi-objective model for the economic-statistical design of the C-control charts is presented. The proposed model considers that multiple assignable causes can occur during the production process. Then, a hybrid meta-heuristic algorithm is developed to solve the model. The proposed algorithm consists of an improved version of the non-dominated sorting genetic algorithm II (NSGA-II) and the data envelopment analysis (DEA) which is called the IM-NSGA-II-DEA. For the proposed algorithm, new crossover and mutation operators based on the technique for order preference by similarity to ideal solution (TOPSIS) have been designed. After obtaining the non-dominated solutions, the DEA is employed to find the efficient ones. The performance of the IM-NSGA-II is evaluated in comparison with the classical NSGA-II and NRGA. The results of numerical experiments imply that the proposed method is superior to other algorithms in terms of objective function values and several multi-objective metrics.

Study on State Transition Tracking Method in Process Fraction Nonconforming

Abstract When a control chart signals that an assignable cause is present, process engineers are required to identify a time point of process changes and then search for the assignable cause of the process disturbance. In the statistical process control literature, there is a research area called change point detection. As one of change point detection problems, it has been considered how to identify the time of a step-change in the process fraction nonconforming using the maximum likelihood theory. However, the process fraction nonconforming may be changed multiple times until a chart signals. Such a multiple change-points model for the process fraction nonconforming has not been considered yet. In this study, we consider a multiple change-points model of the process fraction nonconforming under a p chart. Then, a method of tracking the transition of process fraction nonconforming is proposed using the maximum likelihood theory and information criterion.

A FRAMEWORK FOR ENHANCING THE RESPONSIVENESS TO DEFECTS VIA SPC AND WORKER EMPOWERMENT

The ultimate goal of the online quality control initiatives is to prevent the occurrence of defects or rather to detect the occurrence of defects as fast as possible in order to interfere with corrective actions. Generally, Statistical Process Control (SPC) tools such as control charts can be effectively applied to monitor the production processes and can be used as an indicator for the occurrence of assignable causes in the process which are mainly responsible for the occurrence of defects. Typically, the out of control signals resulted from control charts or other signs of developing defective items that are observed directly through visual inspection necessitate a rapid response from the shop floor operators. Meanwhile, the lack of worker empowerment and poor communication between shop floor workers and engineers as well as managers are mainly responsible for the late decisions and actions which lead to increased defect rates. This paper presents a framework that integrates SPC approaches with worker empowerment practices to enhance the responsiveness toward detected defects as well as preventing the occurrence of more ones. Besides, a case study concerned with the manufacturing of Unplasticized Polyvinyl Chloride (UPVC) pipes has been conducted to demonstrate the application of the proposed framework.

Multivariate Mixed EWMA-CUSUM Control Chart for Monitoring the Process Variance-Covariance Matrix

The dispersion control charts monitor the variability of a process that may increase or decrease. An increase in dispersion parameter implies deterioration in the process for an assignable cause, while a decrease in dispersion indicates an improvement in the process. Multivariate variability control charts are used to monitor the shifts in the process variance-covariance matrix. Although multivariate EWMA and CUSUM dispersion control charts are designed to detect the small amount of change in the covariance matrix but to gain more efficiency, we have developed a Mixed Multivariate EWMA-CUSUM (MMECD) chart. The proposed MMECD chart is compared with its existing counterparts by using some important performance run length-based properties such as ARL, SDRL, EQL, SEQL, and different quantile of run length distribution. A real application related to carbon fiber tubing process is presented for practical considerations.

An integrated model of statistical process control and maintenance planning for a two-stage dependent process under general deterioration

Consider a two-stage dependent process in which each stage has a unique quality characteristic. Based on a regression formula, the quality characteristic of the second stage is dependent on that of the first stage. There may be two assignable causes in the process. Each cause can lead to a change in the mean of the process. The process failure mechanism for each stage follows a general continuous distribution function, and two control charts are simultaneously used to monitor the process. Specifically, the first stage is monitored using a Shwehart control chart, and the second stage is monitored using a cause-selecting control chart. An integrated model is developed for maintenance planning (MP) and statistical process control (SPC). To analyse the performance of the integrated model, a stand-alone model for SPC is developed. A comparison of the two models, i.e., the integrated model and the stand-alone model, is conducted. Finally, using a fractional factorial design, a depth analysis is performed about the integrated model. [Received: 10 February 2018; Revised: 21 April 2018; Revised: 4 June 2018; Revised: 12 September 2018; Revised: 7 October 2018; Accepted: 9 October 2018]

A hybrid NSGA-II-DEA method for the economic-statistical design of the C-control charts with multiple assignable causes

A hybrid NSGA-II-DEA method for the economic-statistical design of the C-control charts with multiple assignable causes

A sequential monitoring Bayesian control scheme for attributes

ABSTRACTClassic approaches of Statistical Process Control (SPC) include the collection of samples from a production process and the computation of some output concerning a specific quality characteristic. This output, which is called chart statistic, is then compared against appropriately designed limits to decide whether an investigation for an assignable cause occurrence is needed. In recent years however, and especially in highly automated production processes, it is not unusual to have the ability of 100% inspection of the entire production. In such cases, the control procedure should be based on more appropriately designed SPC tools. This paper proposes a Bayesian model for production processes where all produced items are inspected. Each product may be conforming or nonconforming, and the output of the control procedure is the probability of out-of-control operation. This probability is compared against a critical probability to decide whether an intervention to the process is economically advisable. The case of inspection errors, namely, the case where a conforming item may be erroneously categorized as nonconforming and vice versa, is also investigated. Our numerical investigation reveals the economic superiority of the new scheme compared to simpler schemes that have been proposed over the years to tackle such problems.

Modified short-run statistical process control for test and measurement process

The key characteristics of test and measurement (T&M) manufacturing are short-run, multi-product families and testing at multi-stations. These characteristics render statistical process control (SPC) inefficacious because inherently meagre data do not warrant meaningful control limits. Measurement errors increase the risks of false acceptance and rejection, thereby leading to such consequences as unnecessary process adjustments and loss of confidence in SPC. This study presents a modified SPC model that incorporates measurement uncertainty from guard bands into the $$ \overline{\mathrm{Z}} $$ and W charts, thereby addressing the implications of short runs, multi-stations and measurement errors on SPC. The implementation of this model involves two phases. Phase I retrospective analysis computes the input parameters, such as the standard deviation of the measurement uncertainty, measurement target and estimate of the population standard deviation. Thereafter, five-band setting and sensitivity factor are proposed to estimate process standard deviation to maximise the opportunity to detect the assignable causes with low false-reject rate. Lastly, the $$ \overline{\mathrm{Z}} $$ and W charts are generated in Phase II using standardised observation technique that considers the measurement target and estimated process standard deviations. Run tests based on Nelson rules interpret the charts. Validation was performed in three case studies in an actual industry.

Constrained optimal design of X̅ control chart with multiple assignable causes under Burr XII failure mechanism

PurposeThe purpose of this paper is to develop a cost model by the variable sampling interval and optimization of the average cost per unit of time. The paper considers an economic–statistical design of the X̅ control charts under the Burr shock model and multiple assignable causes were considered and compared with three types of prior distribution for the mean shift parameter.Design/methodology/approachThe design of the modified X̅ chart is based on the two new concepts of adjusted average time to signal and average number of false alarms for X̅ control chart under Burr XII shock model with multiple assignable causes.FindingsThe cost model was examined through a numerical example, with the same cost and time parameters, so the optimal of design parameters were obtained under uniform and non-uniform sampling schemes. Furthermore, a sensitivity analysis was conducted in a way that the variability of loss cost and design parameters was evaluated supporting the changes of cost, time and Burr XII distribution parameters.Research limitations/implicationsThe economic–statistical model scheme of X̅ chart was developed for the Burr XII distributed with multiple assignable causes. The correlated data are among the assumptions to be examined. Moreover, the optimal schemes for the economic-statistic chart can be expanded for correlated observation and continuous process.Practical implicationsThe economic–statistical design of control charts depends on the process shock model distribution and due to difficulties from both theoretical and practical aspects; one of the proper alternatives may be the Burr XII distribution which is quite flexible. Yet, in Burr distribution context, only one assignable cause model was considered where more realistic approach may be to consider multiple assignable causes.Originality/valueThis study presents an advanced theoretical model for cost model that improved the shock model that presented in the literature. The study obviously indicates important evidence to justify the implementation of cost models in a real-life industry.