CS‐EWMA Chart for Monitoring Process Dispersion

Control charts are the most extensively used technique to detect the presence of special cause variations in processes. They can be classified into memory and memoryless control charts. Cumulative sum and exponentially weighted moving average control charts are memory‐type control charts as their control structures are developed in such a way that the past information is not ignored as it is done in the case of memoryless control charts, like the Shewhart‐type control charts. The present study is based on the proposal of a new memory‐type control chart for process dispersion. This chart is named as CS‐EWMA chart as its plotting statistic is based on a cumulative sum of the exponentially weighted moving averages. Comparisons with other memory charts used to monitor the process dispersion are done by means of the average run length. An illustration of the proposed technique is done by applying the CS‐EWMA chart on a simulated dataset. Copyright © 2012 John Wiley & Sons, Ltd.     

Spc of a near zero-defect process subject to random shocks

In this paper we study the problem of monitoring and control of a type of process in which long series with no non-conformities are observed together with occasional samples containing a large number of non-conformities. We call this a near zero-defect process subject to random shocks. Such processes occur often in practice, and a model is proposed for the identification of real non-random variations of process characteristics. Based on the statistical analysis carried out for this model, a procedure for decision-making in the control of this type of process is suggested, and analysis of some actual cases presented.     

Some Modifications of the Classical Pre‐control Technique

Pre‐control is a simple technique for the initial evaluations of the capability of a process. It can be seen as a tool to get the set‐up approval or fulfilment of the specifications of a production process. As the resultant information of pre‐control should be used to adjust the process, it can be understood as a form of feedback controller. It has sometimes been considered as an alternative to statistical control charts for monitoring processes, although these tools differ in a number of ways. In this work, we propose some new alternatives to the classical pre‐control, particularly in its initial phase that aim to qualify the process, that is, to certify that it is capable. We present a comparative analysis of the power of the different alternatives. Copyright © 2003 John Wiley & Sons, Ltd.     

Process monitoring with ICA‐based signal extraction technique and CART approach

In order to reduce the variation in a manufacturing process, traditional statistical process control (SPC) techniques are the most frequently used tools in monitoring engineering process control (EPC)‐controlled processes for detecting assignable cause process variation. Even though application of SPC with EPC can successfully detect time points when abnormalities occur during process, their combination can also cause an increased occurrence of false alarms when autocorrelation is present in the process. In this paper, we propose an independent component analysis‐based signal extraction technique with classification and regression tree approach to identify disturbance levels in the correlated process parameters. For comparison, traditional cumulative sum (CUSUM) chart was constructed to evaluate the identifying capability of the proposed approach. The experimental results show that the proposed method outperforms CUSUM control chart in most instances. Copyright © 2008 John Wiley & Sons, Ltd.     

The balance chart: A new SPC Concept

This paper outlines a new technique of statistical process control which goes a considerable way to resolving several existing problems. The technique described may be of particular value to automated control, small batch control and control of gauged processes. A new charting technique is described and compared with traditional control charts. The operation of the balance chart is outlined for attribute and variable processes and in precontrol mode. A graphical system for determining estimated Cp, Cpk and process mean values from limited process data is also included.     

New memory‐type dispersion control charts

The exponentially weighted moving average (EWMA) control chart is a memory‐type process monitoring tool that is frequently used to monitor small and moderate disturbances in the process mean and/or process dispersion. In this study, we propose 2 new memory‐type control charts for monitoring changes in the process dispersion, namely, the generally weighted moving average and the hybrid EWMA charts. We use Monte Carlo simulations to compute the run length profiles of the proposed control charts. The run length comparisons of the proposed and existing charts reveal that the generally weighted moving average and hybrid EWMA charts provide better protection than the existing EWMA chart when detecting small to moderate shifts in the process dispersion. An illustrative dataset is also used to show the superiority of the proposed charts over the existing chart.     

An alternative method to test for randomness of a process

The objective of this paper is to revisit an old technique for testing the randomness of a process. This method uses the mean square successive difference approach to estimate variance, compares this estimate with the usual variance estimate, and tests whether the two variance estimates are significantly different. If the test result is significant, it is concluded that the process is not random (i.e. not in control). The non-random results are addressed to accomplish quality improvement.     

Integrating artificial intelligence into on‐line statistical process control

Statistical process control (SPC) is one of the most effective tools of total quality management, the main function of which is to monitor and minimize process variations. Typically, SPC applications involve three major tasks in sequence: (1) monitoring the process, (2) diagnosing the deviated process and (3) taking corrective action. With the movement towards a computer integrated manufacturing environment, computer based applications need to be developed to implement the various SPC tasks automatically. However, the pertinent literature shows that nearly all the researches in this field have only focussed on the automation of monitoring the process. The remaining two tasks still need to be carried out by quality practitioners. This project aims to apply a hybrid artificial intelligence technique in building a real time SPC system, in which an artificial neural network based control chart monitoring sub‐system and an expert system based control chart alarm interpretation sub‐system are integrated for automatically implementing the SPC tasks comprehensively. This system was designed to provide the quality practitioner with three kinds of information related to the current status of the process: (1) status of the process (in‐control or out‐of‐control). If out‐of‐control, an alarm will be signaled, (2) plausible causes for the out‐of‐control situation and (3) effective actions against the out‐of‐control situation. An example is provided to demonstrate that hybrid intelligence can be usefully applied for solving the problems in a real time SPC system. Copyright © 2003 John Wiley & Sons, Ltd.     

Deep recurrent neural network‐based residual control chart for autocorrelated processes

With the growth of automation in process industries, there is correlation in the process variables. Deep learning has achieved many great successes in image and visual analysis. This paper concentrates on developing a deep recurrent neural network (RNN) model to characterize process variables at vary time lags, and then a residual chart is developed to detect mean shifts in autocorrelated processes. The experiment results indicate that the RNN‐based residual chart outperforms other typical methods (eg, autoregressive [AR]‐based control chart, back propagation network [BPN]‐based residual chart). This paper provides guideline for deep learning technique employed as an effective tool in autocorrelated process control.     

A modified CUSUM control chart for monitoring industrial processes

Control charts are the most popular tool of statistical process control for monitoring variety of processes. The detection ability of these control charts can be improved by introducing various transformations. In this study, we have enhanced the performance of CUSUM charts by introducing a link relative variable transformation technique. Link relative variable converts the original process variable in a form which is relative to its mean. So, the link relative represents the relative positioning of the observations. Average run length (ARL ) is used to compare our technique with the previous studies. The comparison shows the overall good detection performance of our scheme for a span of shifts in the mean. A real‐world example from the electrical engineering process is also included to demonstrate the application of proposed control chart.     

Mixed Exponentially Weighted Moving Average–Cumulative Sum Charts for Process Monitoring

The control chart is a very popular tool of statistical process control. It is used to determine the existence of special cause variation to remove it so that the process may be brought in statistical control. Shewhart‐type control charts are sensitive for large disturbances in the process, whereas cumulative sum (CUSUM)–type and exponentially weighted moving average (EWMA)–type control charts are intended to spot small and moderate disturbances. In this article, we proposed a mixed EWMA–CUSUM control chart for detecting a shift in the process mean and evaluated its average run lengths. Comparisons of the proposed control chart were made with some representative control charts including the classical CUSUM, classical EWMA, fast initial response CUSUM, fast initial response EWMA, adaptive CUSUM with EWMA‐based shift estimator, weighted CUSUM and runs rules–based CUSUM and EWMA. The comparisons revealed that mixing the two charts makes the proposed scheme even more sensitive to the small shifts in the process mean than the other schemes designed for detecting small shifts. Copyright © 2012 John Wiley & Sons, Ltd.     

Optimal process capability analysis for process design

Conventional process capability analysis is used to measure and control the quality level of a production process in real exercises for on-line quality management. There has been a deficiency in this type of management; namely, the defects which occur in the production process are only passively detected and modified afterwards. Additionally, conventional process capability expression has difficulty distinguishing between alternatives for process selection among possible candidates before process realisation. There is, therefore, considerable motivation for developing a process capability expression which can be used to evaluate alternatives at the beginning of the process design, i.e., off-line application. The conventional C_pm expression is built up by measuring mean deviation and process variances for on-line application. However, if C_pm is used for the process capability analysis for process design, an erroneous C_pm value is found and an inappropriate process design is ended. Thus, the proposed process capability expression revised from the conventional C_pm in consideration of the balance between tolerance cost and quality loss has been developed. This development is the main contribution of this research and, with this development, the appropriate mean and tolerance values can be determined simultaneously prior to the real production process so as to maximise the proposed process capability value. The production is then processed with the pre-determined mean and tolerance values in a real production process. The expectation after process realisation is that the produced responses will be the best of all the alternatives in terms of quality and cost, and that the process capability value obtained after the real production process will be close to the proposed process capability value maximised prior to the real production process.     

Estimating the change point of a normal process mean with a monotonic change

One of the essential steps for process improvement is to quickly recognize the starting time or the change point of a process disturbance. In this paper, we describe the behavior model of process mean and then obtain a maximum‐likelihood estimator (MLE) for the change point of the normal process mean without requiring the exact knowledge of the change type. Instead, we assume that the type of change present belongs to a family of monotonic changes. Finally, we study the performance of the proposed change‐point estimator relative to the MLEs for the process mean change point derived under a simple step change and linear trend change assumption. We do this for a number of monotonic change types following a signal from a Shewhart X̄ control chart. Copyright © 2008 John Wiley & Sons, Ltd.     

Monitoring the Weibull Shape Parameter by Control Charts for the Sample Range of Type II Censored Data

In this paper, we propose control charts to monitor the Weibull shape parameter β under type II (failure) censoring. This chart scheme is based on the sample ranges of smallest extreme value distributions derived from Weibull processes. We suggest one‐sided (high‐side or low‐side) and two‐sided charts, which are unbiased with respect to the average run length (ARL). The control limits for all types of charts depend on the sample size, the number of failures c under type II censoring, the desired stable‐process ARL, and the stable‐process value of β. This article also considers sample size requirements for phase I in retrospective charts. We investigate the effect of c on the out‐of‐control ARL. We discuss a simple approach to choosing c by cost minimization. The proposed schemes are then applied to data on the breaking strengths of carbon fibers. Copyright © 2011 John Wiley & Sons, Ltd.     

Robust design of a polysilicon deposition process using split-plot analysis

The technique used for the analysis of experimental data must be appropriate for the design and treatment structures of the experiment; failure to take this into account can produce misleading results. This paper illustrates how split-plot designs can be used for the analysis of robust design experiments. In particular, the polysilicon deposition process data presented by Phadke¹ is analysed, and comparisons are made between the split-plot analysis of the raw data and the analysis conducted using signal-to-noise ratios. In addition, we demonstrate how the split-plot analysis provides information about interactions between control and noise factors, and how interaction plots can be used to assess the performance of the control factors across the levels of the noise factors. This information is particularly important to select the settings of the control factors that minimize the variation in the response induced by the noise factors.     

A shewhart-like charting technique for high yield processes

A Shewhart-like charting technique is developed in this paper to overcome the difficulties the traditional control chart encounters in the control of processes with a very low fraction non-conforming. The technique uses the number of conforming items between two consecutive non-conforming ones to monitor the fraction non-conforming of a process, leading to a chart that is informative and easy to interpret. The approach discussed is especially suitable for real-time and automatic statistical quality control.     

How heterogeneity influences condition-based maintenance for gamma degradation process

In many applications, units from the same population exhibit heterogeneity that they degrade with different rates due to random factors. This article studies how this heterogeneity in degradation influences condition-based maintenance (CBM) policy. Many CBM polices are developed based on gamma process because it is popularly used to characterise monotone degradation processes. In this study, we also model the unit’s degradation by gamma process. To account for the heterogeneity among units’ degradation, we incorporate a random effect parameter in the gamma process. Then the optimal policy for CBM is obtained through Markov decision process. We show that when heterogeneity exists, the transition probability of degradation state depends on both unit’s age and observed degradation level. And consequently, the optimal maintenance policy is a monotone control limit policy. We conduct extensive numerical experiments to validate and demonstrate our findings in depth.     

Optimal control limits for CCC charts in the presence of inspection errors

The control chart based on cumulative count of conforming (CCC) items between the occurrence of two non‐conforming ones, or the CCC chart, has been shown to be very useful for monitoring high‐quality processes. However, as in the implementation of other Shewhart‐type control charts, it is usually assumed that the inspection is free of error. This assumption may not be valid and this may have a significant impact on the interpretation of the control chart and the setting of control limits. This paper first investigates the effect of inspection errors and discusses the setting of control limits in such cases. Even if inspection errors are considered, the average time to alarm increases in the beginning when the process deteriorates. Since this is undesirable, the control limits in the presence of inspection errors should be set so as to maximize the average run length when the process is at the normal level. A procedure is presented for solving this problem. Copyright © 2003 John Wiley & Sons, Ltd.     

Estimating the Change Point of the Process Fraction Non‐conforming with a Monotonic Change Disturbance in SPC

Knowing when a process has changed would simplify the search for and identification of the special cause. In this paper, we propose a maximum‐likelihood estimator for the change point of the process fraction non‐conforming without requiring knowledge of the exact change type a priori. Instead, we assume the type of change present belongs to a family of monotonic changes. We compare the proposed change‐point estimator to the maximum‐likelihood estimator for the process change point derived under a simple step change assumption. We do this for a number of monotonic change types and following a signal from a binomial cumulative sum (CUSUM) control chart. We conclude that it is better to use the proposed change point estimator when the type of change present is only known to be monotonic. The results show that the proposed estimator provides process engineers with an accurate and useful estimate of the time of the process change regardless of the type of monotonic change that may be present. Copyright © 2006 John Wiley & Sons, Ltd.     

A run-to-run control algorithm based on timely and delayed mixed-resolution information

In certain run-to-run (R2R) processes, timely accurate measurements are difficult to obtain due to slow laboratory measurement operations. Instead, only low-resolution categorical observations are observed online for important quality variables; continuous measurements for the same variables are provided after a specific amount of delay. Currently, most conventional R2R controllers cannot be applied if no continuous observations are available. It is therefore important to develop online algorithms for R2R process control based on mixed-resolution information that is partially timely and partially delayed. In this study, we take the lapping process in semiconductor manufacturing as an example and propose parameter estimation models with these mixed-resolution data for processes with the first-order autoregressive, AR(1), disturbance series. We also derive control strategies to generate recipes between production runs for better process control. The computational results of a performance evaluation show that the control performance of the proposed method is competitive compared to existing methods that are based on accurate measurements.