International Journal of Industrial Engineering & Production Research

---

  Although control charts are very common to monitoring process changes, they usually do not indicate the real time of the changes. Identifying the real time of the process changes is known as change-point estimation problem. There are a number of change point models in the literature however most of the existing approaches are dedicated to normal processes. In this paper we propose a novel approach based on clustering techniques to estimate Shewhart control chart change-point when a sustained shift is occurrs in the process mean. For this purpose we devise a new clustering mechanism, a new similarity measure and a new objective function. The proposed approach is not only capable of detecting process change-points, but also automatically estimates the true values of the out-of-control parameters of the process. We also compare the performance of the proposed approach with existing methods.

---

  In an increasing number of practical situations, the quality of a process or product can be effectively characterized and summarized by a profile. A profile is usually a functional relationship between a response variable and one or more explanatory variables which can be modeled frequently using linear or nonlinear regression models. In this paper, we study the effect of non-normality on profile monitoring in Phase II when within or between autocorrelation is present. Different levels of autocorrelation and skewed and heavy-tailed symmetric non-normal distributions are used in our study to evaluate the performance of three existing monitoring schemes numerically. Simulation results indicate that the non-normality and autocorrelation can have a significant effect on the in-control performances of the considered schemes. Results also indicate that the out-of-control performances of the schemes are not very sensitive to low and moderate levels of autocorrelation in moderate and large shifts .

---

In this research, an iterative approach is employed to recognize and classify control chart patterns. To do this, by taking new observations on the quality characteristic under consideration, the Maximum Likelihood Estimator of pattern parameters is first obtained and then the probability of each pattern is determined. Then using Bayes’ rule, probabilities are updated recursively. Finally, when one of the updated derived statistics falls outside the calculated control interval a pattern recognition signal is issued. The advantage of this approach comparing with other existing CCP recognition methods is that it has no need for training. Simulation results show the effectiveness and accuracy of the new method to detect the abnormal patterns as well as satisfactory results in the estimation of pattern parameters.

---

Identification of a real time of a change in a process, when an out-of-control signal is present is significant. This may reduce costs of defective products as well as the time of exploring and fixing the cause of defects. Another popular topic in the Statistical Process Control (SPC) is profile monitoring, where knowing the distribution of one or more quality characteristics may not be appropriate for discussing the quality of processes or products. One, rather, uses a relationship between a response variable and one or more explanatory variable for this purpose. In this paper, the concept of Maximum Likelihood Estimator (MLE) applied to estimate of the change point in binary profiles, when the type of change is drift. Simulation studies are provided to evaluate the effectiveness of the change point estimator.

---

Monitoring the reliability of products in both the manufacturing and service processes is of main concern in today’s competitive market. To this end, statistical process control has been widely used to control the reliability-related quality variables. The so-far surveillance schemes have addressed processes with independent quality characteristics. In multistage processes, however, the cascade property must be effectively justified which entails establishing the relationship among quality variables with the purpose of optimal process monitoring. In some cases, measuring the values corresponding to specific covariates is not possible without great financial costs. Subsequently, the unmeasured covariates impose unobserved heterogeneity which decreases the detection power of a control scheme. The complicated picture arises when the presence of a censoring mechanism leads to inaccurate recording of the process response values. Hence, frailty and Cox proportional hazards models are employed and two regression-adjusted monitoring procedures are constructed to effectively account for both the observed and unobserved influential covariates in line with a censoring issue. The simulation-based study reveals that the proposed scheme based on the cumulative sum control chart outperforms its competing procedure with smaller out-of-control average run length values.

---

CCC-r control chart is a monitoring technique for high yield processes. It is based on the analysis of the number of inspected items until observing a specific number of defective items.  One of the assumptions in implementing CCC-r chart that has a significant effect on the design of the control chart is that the inspection is perfect. However, in reality, due to the multiple reasons, the inspection is exposed to errors. In this paper, we study the economic-statistical design of CCC-r charts when the inspection is imperfect. Minimization of the average cost per produced item is considered as the objective function. The economic objective function, modified consumer risk, and modified producer risk are simultaneously considered, and then the optimal value of r parameter is selected.

---

This work used two methods for Monitoring and control of autocorrelated processes based on time series modeling. The first method was the simultaneous monitoring of common and assignable causes. This method included applying five steps of data gathering, normality test, autocorrelation test, model selection and control chart selection on all non-stationary process observations. The second method was a novel one for the separate monitoring and control of common and assignable causes. In this method, the process was divided into the parts with and without assignable causes.
The first method was greatly non-stationary due to not separating common and assignable causes. This method also implied that the common causes were hidden in the process. The novel method for the separate monitoring of common and assignable causes could turn the process into a stationary one, leading to identifying, monitoring, and controlling common causes without any interference from the assignable causes. The results showed that, unlike the first method, the second method could be very sensitive to the common causes; it could, therefore, suitably monitor, identify and control both assignable and common causes.
The current work was aimed to use control charts to monitor and control the bootomhole pressure during the drilling operation.
 

---

The article highlights the development of a Non-Gaussian Process Monitoring Strategy for a Steel Billet Manufacturing Unit (SBMU). The non-Gaussian monitoring strategy being proposed is based on Modified Independent Component Analysis (ICA) which is a variant of the widely employed conventional ICA. The Independent Components(IC) being extracted by modified ICA technique are ordered as per the variance explained akin to that of Principle Component Analysis (PCA). Whereas in conventional ICA the variance explained by the ICs are not known and thereby causes hindrance in the selection of influential ICs for eventual building of the nominal model for the ensuing monitoring strategy. Hotelling T² control chart based on modified ICA scores was used for detection of fault(s) whose control limit was estimated via Bootstrap procedure owing to the non-Gaussian distribution of the underlying data. The Diagnosis of the Detected Fault(s) was carried out by employment of Fault Diagnostic Statistic. The Diagnosis of the Fault(s) involved determination of the contribution of the responsible Process and Feedstock characteristics. The non-Gaussian strategy thus devised was able to correctly detect and satisfactory diagnose the detected fault(s)

---

This paper aims to introduce a joint optimization approach for maintenance, quality, and buffer stock policies in single machine production systems based on a P control chart. The main idea is to find the optimal values of the preventive maintenance period, the buffer stock size, the sample size, the sampling interval, and the control limits simultaneously, such that the expected total cost per time unit is minimized. In the considered system, we have a fixed rate of production and stochastic machine breakdowns which directly affect the quality of the product. Periodic preventive maintenance (PM) is performed to reduce out-of-control states. In addition, corrective maintenance is required after finding each out-of-control state. A buffer is used to reduce production disturbances caused by machine stops. To ensure that demand is met during a preventive and corrective maintenance operation. All features of three sub-optimization problems including maintenance, quality control, and buffer stock policies are formulated and the proposed integrated approach is defined and modeled mathematically. In addition, an iterative numerical optimization procedure is developed to provide the optimal values for the decision variables. The proposed procedure provides the optimal values of the preventive maintenance period, the buffer stock size, the sample size, the sampling interval, and the control chart limits simultaneously, in a way that the total cost per time unit is minimized. Moreover, some sensitivity analyses are carried out to identify the key effective parameters.