Search

A bi-objective flexible cell scheduling problem (CSP) under time-of-use (TOU) electricity tariffs in both deterministic and fuzzy environments are developed with the following objectives: (1) total cost of production system and (2) total delivery tardiness of jobs. To create a form of green and energy-conscious strategy, cost of produced emission and consumed power and some limitations on entire energy consumption, total manufactured emission, setup time, part defect (pert) percentage, system productivity, total number of tool slots, operations, and automated guided vehicles (AGVs) are respected. Besides, a self-adaptive two-phase subpopulation genetic algorithm (SATPSPGA) is taken to find a near-optimum solution of suggested bi-objective fuzzy mixed integer linear programming (FMILP) model. In view of the fact that no benchmark is existing in the literature, a self-adaptive non-dominated ranked genetic algorithm (SANRGA) and a non-dominated sorting genetic algorithm (NSGA-II) were employed to solve the model. To validate the result, a GAMS model of problem is utilized and compared with algorithm outcomes as well. Lastly, several numerical examples are offered to show the utility of the proposed methodology. [ABSTRACT FROM AUTHOR]

The cases where a functional relationship between a response variable and one or more explanatory variables is used to monitor the quality of a product or process appear to be common in practice. This relationship usually is referred to as profile with parameters that are rarely known and have to be estimated prior to starting online monitoring. Phase II initiates after a statistically in-control condition is established, and parameters of the underlying distribution are estimated. It is obvious that phase II analysis of control charting is affected by errors in the estimated parameters. In this paper, the effect of estimation error on phase II analysis of simple linear profiles is studied. The in-control and out-of-control performance of the exponentially weighted moving average (EWMA)-3 method are evaluated using average run length (ARL) criterion. Overall, the in-control ARL in average decreases about 96.7 % when we have m = 100 samples in phase I to estimate the parameters. This value reduces to 2.4 % for m = 900 for a fixed sample size of n = 4. The behavior of the EWMA-3 chart in the out-of-control situation totally depends on the direction of the occurring shifts and whether the ill-estimated parameter is overestimated or underestimated. [ABSTRACT FROM AUTHOR]

The traditional control charts are developed based on the assumption that the successive observations are independent and identically distributed. In some processes, the independence assumption is violated when there is autocorrelation between observations. To solve this problem, two methods, classified as model-based and model-free, could be applied. When a control chart alarms an assignable cause, it is essential to detect the process change point in order to remove the root cause. In the presence of autocorrelated data, different methods for change-point identification have been applied only for model-based methods. Hence, this is considered as the research gap and an attempt is made to fill this gap by applying maximum likelihood function in unweighted batch mean control chart, one of the most applied model-free methods. In this article, an estimator is presented to determine the change point for the first-order autoregressive process, AR(1). When a real change occurs, the performance of proposed estimator is evaluated through simulation. [ABSTRACT FROM AUTHOR]

When an out-of-control condition is detected by a control chart, a search begins to identify and eliminate the source(s) of the signal. Identification of the time when a process first changed is an important step in root cause analysis which helps a process engineer to eliminate the source(s) of assignable cause effectively. The time when a change takes place in the process is referred to as the change point. In multivariate environment, since there is more than one variable involved, then root cause analysis is relatively harder compared to the case of univariate because it is not clear exactly which variable has contributed to the out-of-control condition and in what direction its mean has shifted. Hence, a procedure that identifies the change point, performs diagnostic analysis, and specifies the direction of the shift in the mean of the contributing variable(s) all simultaneously could help to conduct root cause analysis effectively. Although different multivariate methods exist in the literature that allow to either estimate change point in the process mean vector or identify the contributing variables leading to the out-of-control condition, but in this research, an integrated supervised learning solution is proposed, which helps to (1) detect of an out-of-control condition, (2) identify the change point leading to shift in the mean vector, (3) specify the variable(s) contributing to the out-of-condition, and (4) identify the direction of the shift in the mean of each contributing variable simultaneously. A real case study is used to evaluate and compare the performance of the proposed integrated approach to existing methods in the literature. [ABSTRACT FROM AUTHOR]

In most statistical process control applications, the quality of a process or product is characterized by univariate or multivariate quality characteristics and monitored by the corresponding univariate and multivariate control charts, respectively. However, sometimes, the quality of a process or a product is better characterized by a relationship between a response variable and one or more explanatory variables. This relationship, which can be linear, nonlinear, or even a complicated model, is referred to as a profile. So far, several methods have been proposed for monitoring simple linear profiles. In this paper, a new method based on cumulative sum statistics is proposed to enhance monitoring of linear profiles in phase II. The performance of the proposed method is evaluated by average run length criterion. A comprehensive comparison is also conducted between the performance of the proposed method and the existing methods for monitoring simple linear profiles. The results show that the proposed method performs satisfactorily. In addition, the effects of reference value, sample size, and corrected sum of squares of explanatory variables on the performance of the proposed method are investigated. [ABSTRACT FROM AUTHOR]