Minimizing the cost of integrated systems approach to process control and maintenance model by EWMA control chart using genetic algorithm

This paper studies integrated systems approach to Statistical Process Control (SPC) and Maintenance Management (MM). Previously, only four policies which are in control alert signal, out of control alert signal, in control no signal, and out of control no signal, were used in the consideration (Zhou & Zhu, 2008). The objectives of this research are to develop an integrated model between Statistical Process Control and Planned Maintenance of the EWMA control chart. To do this, warning limit is considered to increase the policy from four to six such as warning limit alert signal and warning limit no signal. A mathematical model is given to analyze the cost of the integrated model before the genetic algorithm approach is used to find the optimal values of six variables (n, h, w, k, η, r) that minimize the hourly cost. A comparison between four-policy and six-policy models shows that the six policy model contains the hourly cost higher than that of the four policy model, it is because the addition of the warning limit in the model leads into increased ability of defective product detection. This consequently results to the increase of repairing and maintenance of machines; therefore the hourly cost is higher. Finally, multiple regressions are employed to demonstrate the effect of cost parameters.