Research Article  Open Access
Tingting Shan, Liusan Wu, Xuelong Hu, "A Combined UpperSided Synthetic S^{2} Chart for Monitoring the Process Variance", Mathematical Problems in Engineering, vol. 2020, Article ID 9102059, 6 pages, 2020. https://doi.org/10.1155/2020/9102059
A Combined UpperSided Synthetic S^{2} Chart for Monitoring the Process Variance
Abstract
In order to monitor the process variance, this paper proposes a combined uppersided synthetic S^{2} chart for monitoring the process standard deviation of a normally distributed process. This combined uppersided synthetic S^{2} chart comprises a synthetic chart and an uppersided S^{2} chart. The design and performance of the proposed chart are presented, and the steadystate average run length comparisons show that the combined uppersided synthetic S^{2} chart outperforms the standard synthetic S^{2} chart as well as several run rules S^{2} charts, especially for larger shifts in the process variance.
1. Introduction
A product that meets the customer’s expectations is generally preferred, which means that this product should be produced by a stable process. However, variation is unavoidable in the output of every process. Variation can be attributed to the usual causes of variation and unusual causes of variation. A process working under only usual causes of variation is called statistical incontrol (IC) and the output of the process is usually assumed to follow a distribution with nominal mean and variance. A process working under both types of variations is declared outofcontrol (OOC) and the assumed distribution of the output of the process deviates from the nominal values (see Montgomery [1]). Statistical process control (SPC) is a powerful collection of tools in achieving process stability through the reduction of variability. Among which, control charts have been shown to be the most effective ones to detect the unusual causes of variation.
Much research has been done on monitoring shifts in the process mean. Among them, the Shewharttype charts are the most widely used in practice. Collani and Sheil [2] pointed out that some manufacturing circumstances, such as faulty raw material, unskilled operators, and loosening of machine settings, may cause an increase in the process variance without influencing the level of the process mean. Consequently, it is also important to monitor the process variance in practice. The Shewhart S^{2} chart is often used for its advantage in detecting larger shifts in the process variance, but becomes less effective in detecting small or moderate shifts.
In order to improve the performance of the classical Shewharttype charts, many alternative approaches have been proposed, such as the exponentially weighted moving average and cumulative sum control charts. Recently, Wu and Spedding [3] proposed a synthetic chart which comprises an and a CRL (conforming run length) chart. This control chart is known to outperform the classical Shewharttype charts over the entire range of shifts. Since then, much research has been done on the synthetic type charts. Among them, Davis and Woodall [4] investigated the zerostate and steadystate performances of the synthetic chart using a Markov chain method. Costa and Rahim [5] applied the synthetic chart methodology along with a noncentral chisquare statistic for monitoring the process mean and variance and proved that this approach is more effective and simple than the classical joint and R chart. Costa et al. [6] also proposed a synthetic control chart based on the noncentral chisquare statistic with a twostage testing, which outperforms the joint and S charts as well as several CUSUM schemes and has a similar performance with the joint and S charts with double sampling (DS). In recent years, Wu et al. [7] proposed a combined synthetic chart for monitoring the process mean. It is shown that the combined synthetic chart always outperforms the individual and the synthetic chart under different conditions. Zhang et al. [8] investigated the effect of process parameter estimation on the performance of the synthetic chart and pointed out that the run length performance of the synthetic chart is quite different in the known and in the estimated parameter cases. Hu et al. [9] investigated the overall performance of the synthetic chart with measurement errors. The above research studies were mainly focused on the univariate synthetic control charts, while for multivariate charts, Pramod and Vikas [10] investigated the effect of some new sampling strategies on the performance of the synthetic T^{2} chart. Felipe et al. [11] proposed a synthetic type chart for bivariate autocorrelated processes. The chart was shown to perform better than other competing charts. In order to monitor the multivariate coefficient of variation, Quoc et al. [12] investigated the properties of the onesided synthetic control charts. For an overview of the synthetic type charts, readers may refer to Athanasios et al. [13].
Unlike the synthetic charts for the process mean or the mean vector, not much research has been done on the synthetic charts for the process variance. Chen and Huang [14] and Huang and Chen [15] developed a synthetic R and S chart for monitoring the process variance, respectively. Being motivated by the above work, we propose a combined uppersided synthetic S^{2} chart for monitoring the process variance and we show that it outperforms the standard uppersided synthetic S^{2} chart and several run rules S^{2} charts.
The organization of this paper is as follows. Section 2 discusses the combined uppersided synthetic S^{2} chart in detail. The optimal design of the proposed synthetic chart using the Markov chain method is presented in Section 3. The comparisons between different control schemes are given in Section 4. Finally, conclusions are drawn in Section 5.
2. The Combined UpperSided Synthetic S^{2} Chart
Assume that at time , the quality characteristic of consecutive items is equal to . We assume that the ’s are independent normal random variables, where and are the nominal mean and standard deviation, respectively, both assumed known, while and are the standardized mean and standard deviation shifts, respectively. The sample variance for the sample is given bywhere is the mean of the subgroup. Since we are only interested in monitoring the process variance, we will assume that only the variance is likely to change (i.e., ). As it is important to find assignable causes that deteriorate the process, in this paper, we will only focus on the increasing variance case (i.e., ). The combined synthetic uppersided S^{2} chart consists of a synthetic subchart and an uppersided S^{2} subchart. The control flow of the combined uppersided synthetic S^{2} chart is outlined as follows:(i)Step 1: determine the sample size , the lower control limit of the synthetic subchart and, the upper warning limit and control limit of the uppersided S^{2} subchart, where are the control and warning limit coefficients, respectively.(ii)Step 2: at each sample point , take a sample of () items of the quality characteristic and compute the sample variance as in equation (1).(iii)Step 3: if , the process is declared as outofcontrol and the control flow goes to step 6.(iv)Step 4: if , the sample is a conforming one and the control flow goes back to step 2.(v)Step 5: if , the sample is considered as nonconforming, and determine the CRL (conforming run length), i.e., the number of conforming samples between two consecutive nonconforming samples plus one. If , the process is deemed to be incontrol and the control flow goes back to step 2. Otherwise, the process is declared as outofcontrol and the control flow goes to step 6.(vi)Step 6: signal an outofcontrol status to indicate an increase in the variance of the process. Find and remove potential assignable causes. Then move back to step 2.
Compared with the standard synthetic S^{2} chart, a control limit is added to the combined uppersided synthetic S^{2} chart. The basic motivation for this operation is due to the usage of the magnitude of the latest sample and the distance between the two consecutive nonconforming samples.
3. Design of the Combined UpperSided Synthetic S^{2} Chart
The average run length () is the expected number of consecutive samples taken until the chart gives an outofcontrol signal. In this paper, we compute the steadystate of the combined uppersided synthetic S^{2} chart using the Markov chain method. Other researchers who have considered the steadystate of the synthetic type charts are Wu et al. [7], Khoo et al. [16], Machado and Costa [17], and Khoo et al. [18]. The run length properties of the combined uppersided synthetic S^{2} chart can be determined using a procedure similar to that in Davis and Woodall [4]. To obtain the steadystate ARL of the combined synthetic S^{2} chart, we use the Markov chain method, where the transition probability matrix is equal towhere is a row vector, is a transition probability matrix for the transient states, the column vector satisfies with , and the probabilities of a sample in the safe and warning regions on the uppersided S^{2} subchart are and , respectively. If the variability in the quality characteristic shifts from to , the probabilities of a sample in the safe and warning regions are as follows:where is the cumulative distribution function (c.d.f.) of the chisquare distribution with degrees of freedom.
Since the number of steps until the process reaches the absorbing state is known to be a discrete phasetype random variable of parameters (see Neuts [19] and Latouche and Ramaswami [20]), we can easily obtain the probability mass function (p.m.f.) and the c.d.f. of the run length distribution of the combined uppersided synthetic S^{2} chart:
The steadystate ARL is given bywhere is the vector with the stationary probabilities of being in each nonabsorbing state and is an identity matrix, and is the transition probability matrix for the transient states in . As suggested by Crosier [21] and Khoo et al. [16], we will use the cyclical steadystate probability column vector that can be obtained using the simplified procedure proposed by Champ [22]:(i)Solve for subject to (ii)Compute , where is a vector of length obtained from by deleting the entry corresponding to the absorbing state
Champ [17] showed that vector can directly be obtained usingwhere is a matrix and is a column vector of length .
The outofcontrol ARL () should be small to detect the assignable causes quickly while, at the same time, the incontrol ARL () should be large to keep a smaller false alarm rate. In this case, the design of the combined synthetic S^{2} chart is based on minimizing the for a desired shift with the constraint , while is the smallest allowable incontrol ARL, i.e.,subject to
4. Numerical Results
In this section, we present the performance of the combined uppersided synthetic S^{2} chart, the standard uppersided synthetic S^{2} chart as well as several run rules S^{2} chart. The desired is set to be 370.4 and 500.
4.1. Comparison with the Standard Synthetic S^{2} Chart
For different combinations of and , Tables 1 and 2 present the optimal parameters and (denoted as ) of the combined uppersided synthetic S^{2} chart (recorded in columns 3 to 6), as well as the optimal parameters and (denoted as ) of the standard uppersided synthetic S^{2} chart (recorded in columns 7 to 9). As it can be seen from Tables 1 and 2, the optimal parameters of the proposed chart decrease as the shift size increases. For example, when n = 5 and increases from 1.2 up to 2, decreases from 16 down to 3 and decreases from 5.5 down to 4.5. When the sample size n increases, the of the proposed chart decreases, which means the chart’s performance is getting better than before. For example, in Table 1, when , the decreases from 28.88 down to 15.50 when n increases from 5 up to 10. Moreover, we can see that the combined uppersided synthetic S^{2} chart always performs better than the standard uppersided synthetic S^{2} chart. For instance, if and , for the combined uppersided synthetic S^{2} chart, we have when and when , respectively, while for the same cases of the standard uppersided synthetic S^{2} chart, we have when and when , respectively. Denote the absolute and relative advantages of the combined uppersided synthetic S^{2} chart over the standard uppersided synthetic S^{2} chart as and , respectively. For the two cases presented above, we have and when , as well as and when . It appears that, with the increase of the shift size , the absolute advantage is always smaller than 1, while increasing the shift size will cause a significant increase in the relative advantage .


4.2. Comparisons with Different Run Rules S^{2} Charts
From the work in Section 4.1, it can be seen that the combined synthetic S^{2} chart performs better than the standard synthetic S^{2} chart for different shift size . However, it is known that adopting different run rules schemes to the Shewharttype charts can improve the chart’s performance (see Castagliola et al. [23], Amdouni et al. [24], Tran [25], Shongwe [26], and so on). Motivated by this fact, the uppersided run rules S^{2} charts with different schemes are presented in this section as a comparison to the proposed chart.
Run rules charts have been studied by many researchers. Among them, Castagliola et al. [23] studied properties of the Shewhart CV (coefficient of variation) charts with 2of3, 3of4, and 4of5 run rules. Tran [25] studied the properties of the 2of3, 3of4, and 4of5 run rules t charts. These works focused on the twosided Shewhart charts with run rules, while Amdouni et al. [24] investigated the CV chart by means of onesided 2of3 and 3of4 Shewhart charts. Since we only focus our attention on the uppersided chart, the properties of the 2of3, 3of4, and 4of5 run rules uppersided S^{2} charts are investigated and are compared with the proposed scheme. As an example, the transition probability matrix Q of the 2of3 run rules uppersided S^{2} chart is given as follows:
The probabilities in equation (11) are equal to , , and , where is the control limit of the run rules charts. Then using equation (5), we can obtain the ARL of the uppersided 2of3 run rules S^{2} chart. Similar method can also be used to obtain the ARL of the uppersided 3of4 and 4of5 run rules S^{2} charts. Due to the large size of Q, the transition probability matrix of the 3of4 and 4of5 run rules is not presented here.
For different combinations of and , Tables 3 and 4 present the values of the combined uppersided synthetic S^{2} chart (recorded in column 3), as well as the values of the run rules S^{2} charts (recorded in columns 4 to 6). The optimal parameters of different run rules S^{2} charts are obtained with the constraint on the desired and the values are computed for different shift size . From Tables 3 and 4, it can be noted that the combined uppersided synthetic S^{2} chart performs uniformly better than the run rules S^{2} charts, especially for small shifts. For example, when n = 5 and , the is much smaller than the of the 2of3 run rules S^{2} chart. Moreover, we can note that the 2of3 run rules S^{2} chart is generally preferred to the 3of4 or 4of5 run rules S^{2} charts, especially for large shifts. This may be due to the fact that 3of4 or 4of5 run rules need to accumulate more samples to make a decision of the process status than the 2of3 run rules.


5. Conclusions
In this paper, we proposed the combined uppersided synthetic S^{2} chart for monitoring the process variance. A Markov chain method is used to obtain the run length distribution of the combined uppersided synthetic S^{2} chart. Through the comparisons of two control charts, we can note that the combined uppersided synthetic S^{2} chart performs better than the standard uppersided synthetic S^{2} chart, especially with the shift size increasing. In addition, it is also shown that the proposed chart performs better than several run rules S^{2} charts. The combined uppersided synthetic S^{2} chart can be a good alternative in practice for the detection of the process variance. Finally, it could be interesting to further our research on the design of combined synthetic S^{2} chart with estimated process variance.
Data Availability
The data used to support the findings of this study are available from the corresponding author upon request.
Conflicts of Interest
The authors declare that they have no conflicts of interest.
Acknowledgments
This work was partially supported by the National Natural Science Foundation of China (no. 71802110), China Postdoctoral Science Foundation (no. 2017M611785), Natural Science Foundation of Jiangsu Province (no. BK20170894), Social Science Fund Project of Jiangsu Province (no. 17GLC001), Humanity and Social Science Youth Foundation of Ministry of Education of China (no. 19YJC630025), Philosophy and Social Sciences in Jiangsu Province (no. TJS216050), and Key Research Base of Philosophy and Social Sciences in JiangsuInformation Industry Integration Innovation and Emergency Management Research Center.
References
 C. Douglas, Montgomery. Introduction to Statistical Quality Control, Wiley, Hoboken, NJ, USA, 7th edition, 2007.
 E. V. Collani and J. Sheil, “An approach to controlling process variability,” Journal of Quality Technology, vol. 21, pp. 87–96, 1989. View at: Google Scholar
 Z. Wu and T. A. Spedding, “A synthetic control chart for detecting small shifts in the process mean,” Journal of Quality Technology, vol. 32, no. 1, pp. 32–38, 2000. View at: Publisher Site  Google Scholar
 R. B. Davis and W. H. Woodall, “Evaluating and improving the synthetic control chart,” Journal of Quality Technology, vol. 34, no. 2, pp. 200–208, 2002. View at: Publisher Site  Google Scholar
 A. F. B. Costa and M. A. Rahim, “A synthetic control chart for monitoring the process mean and variance,” Journal of Quality in Maintenance Engineering, vol. 12, no. 1, pp. 81–88, 2016. View at: Google Scholar
 A. F. B. Costa, M. S. de Magalhães, and E. K. Epprecht, “Monitoring the process mean and variance using a synthetic control chart with twostage testing,” International Journal of Production Research, vol. 47, no. 18, pp. 5067–5086, 2009. View at: Publisher Site  Google Scholar
 Z. Wu, Y. Ou, P. Castagliola, and M. B. C. Khoo, “A combined synthetic & X chart for monitoring the process mean,” International Journal of Production Research, vol. 48, no. 24, pp. 7423–7436, 2016. View at: Google Scholar
 Y. Zhang, P. Castagliola, and M. B. C. Khoo, “The synthetic chart with estimated parameters,” IIE Transactions, vol. 43, no. 9, pp. 676–687, 2017. View at: Google Scholar
 X. Hu, P. Castagliola, J. Sun, and M. B. C. Khoo, “The effect of measurement errors on the synthetic x̄ chart,” Quality and Reliability Engineering International, vol. 31, no. 8, pp. 1769–1778, 2014. View at: Publisher Site  Google Scholar
 D. Pramod and G. Vikas, “New sampling strategies to reduce the effect of autocorrelation on the synthetic T^{2} chart to monitor bivariate process,” Quality and Reliability Engineering International, vol. 35, no. 1, pp. 30–46, 2019. View at: Google Scholar
 D. S. Felipe, C. L. Roberto, A. G. M. Marcela, and F. B. C. Antonio, “Synthetic charts to control bivariate processes with autocorrelated data,” Computers and Industrial Engineering, vol. 97, pp. 15–25, 2016. View at: Google Scholar
 T. N. Quoc, P. T. Kim, C. Philippe, C. Giovanni, and L. Salim, “Onesided synthetic control charts for monitoring the multivariate coefficient of variation,” Journal of Statistical Computation and Simulation, vol. 89, no. 10, pp. 1841–1862, 2019. View at: Google Scholar
 C. R. Athanasios, C. Subhabrata, C. S. Sandile, A. G. Marien, and B. C. K. Michael, “An overview of synthetictype control charts: techniques and Methodology,” Quality and Reliability Engineering International, vol. 35, no. 7, pp. 2081–2096, 2019. View at: Google Scholar
 F.L. Chen and H.J. Huang, “A synthetic control chart for monitoring process dispersion with sample range,” The International Journal of Advanced Manufacturing Technology, vol. 26, no. 78, pp. 842–851, 2005. View at: Publisher Site  Google Scholar
 H. J. Huang and F. L. Chen, “A synthetic control chart for monitoring process dispersion with sample standard deviation,” Computers & Industrial Engineering, vol. 49, no. 2, pp. 221–240, 2005. View at: Publisher Site  Google Scholar
 M. B. C. Khoo, V. H. Wong, Z. Wu, and P. Castagliola, “Optimal design of the synthetic chart for the process mean based on median run length,” IIE Transactions, vol. 44, no. 9, pp. 765–779, 2012. View at: Publisher Site  Google Scholar
 M. A. G. Machado and A. F. B. Costa, “Some comments regarding the synthetic chart,” Communications in StatisticsTheory and Methods, vol. 43, no. 14, pp. 2897–2906, 2014. View at: Publisher Site  Google Scholar
 M. B. C. Khoo, Z. L. Chong, and P. Castagliola, “Synthetic double sampling np control chart for attributes,” Computers & Industrial Engineering, vol. 75, pp. 157–169, 2014. View at: Google Scholar
 M. Neuts, MatrixGeometric Solutions in Stochastic Models: An Algorithmic Approach, Dover Publications Inc, New York, NY, USA, 1981.
 G. Latouche and V. Ramaswami, Introduction to Matrix Analytic Methods in Stochastic Modelling, ASASIAM, Alexandria, VA, USA, 1999.
 R. B. Crosier, “A new twosided cumulative sum quality control scheme,” Technometrics, vol. 28, no. 3, pp. 187–194, 1986. View at: Publisher Site  Google Scholar
 C. W. Champ, “Steadystate run length analysis of a shewhart quality control chart with supplementary runs rules,” Communications in StatisticsTheory and Methods, vol. 21, no. 3, pp. 765–777, 1992. View at: Publisher Site  Google Scholar
 P. Castagliola, A. Ali, H. Taleb, G. Celano, and P. Stelios, “Monitoring the coefficient of variation using control charts with run rules,” Quality Technology & Quantitative Management, vol. 10, no. 1, pp. 75–94, 2013. View at: Google Scholar
 A. Amdouni, P. Castagliola, H. Taleb, and G. Celano, “Onesided run rules control charts for monitoring the coefficient of variation in short production runs,” European Journal of Industrial Engineering, vol. 10, no. 5, pp. 639–662, 2016. View at: Google Scholar
 K. P. Tran, “Designing of run rules t control charts for monitoring changes in the process mean,” Chemometrics and Intelligent Laboratory Systems, vol. 174, pp. 85–93, 2018. View at: Google Scholar
 S. C. Shongwe, J.C. MalelaMajika, and E. M. Rapoo, “Onesided and twosided wofw runsrules schemes: an overall performance perspective and the unified runlength derivations,” Journal of Probability and Statistics, vol. 2019, Article ID 6187060, 20 pages, 2019. View at: Publisher Site  Google Scholar
Copyright
Copyright © 2020 Tingting Shan et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.