IStatistical quality control techniques are useful in monitoring the process behaviour. Attribute tontrol charts are widely psed in process control. The selection of sample size, sampling interval and control ~idth of the control qhart is import~t in minimising the quality costs'. Control chart parameters, Ilike 30" cpntrollilnits and fixed fraction sampling at conveniently selected sampling intervals result in deplomble cost penaltie4 in quality' control. The best selection of tl¥:se pammeters OOpends on seveml pi"OCess pnrnmclers,! like frequency of occupancy of a shift in tOO process, cost of swnpling, c~t of investigation for tiOOfng assignable cause, probability of false alarms, penalty cost of OOfecti ves and pro~ss correction costs. ' \ I A general model has been developed to determine the'total quality cost as a function of these 1 parameters. Probability of not identifying a process shift (J3-risk) and probflbility of wrongly concludinlg thai the process got shifted (a-risk) are considered in OOveloping 100 model. This cost equation is op~mised to determine optimum values cl control chart parameters. Fibonacci sea~h is I used to quicken 100 analytical method for detennining optimum sampling size and control wid~ The li'roposals made by Duncan, Montgomery , Gibra and Chiu for determining the optimum control chart parameters are critically examined and compared widt 100 present model. Case studies were conducted in two foun~s.Optimum control chart parameters in casting of cylinOOr liners and cast plates are determined. It has been found dtat quaqty costs are considerably reduced by using optimally designed con~1 chart parafeters with'proposed method.