Economic models and process quality control

Quality is an important business strategy in the economic and technological environment of today. To achieve high product quality, it is important to take explicit account of the cost of quality, and to use this cost as another management control. A new direction for achieving a cost-effective quality management system is to design statistical process controls so as to directly incorporate quality costs. This paper discusses the major approaches to the economic design of statistical process controls, and compares several different model formulations. The practical implication of these techniques is stressed. In particular, two economic models of the chart are presented: a full economic model requiring a user-specified process and nine cost parameters, and a semi-economic model using five user-specified parameters. Both of these could serve as approaches to reducing the total cost of process control. Because of its simplicity in application the semi-economic model should gain greater acceptance by practitioners for the design of process control techniques.     

简化的测量过程统计控制方法

休哈特控制图平均值控制界限的设置对于计量标准或测量设备来说有很大的局限性,根据计量标准或测量设备的特点,提出简化的测量过程统计控制方法,该方法省去了标准偏差或极差控制图。根据标准偏差试验结果的大小,提出了子组最少测量次数的确定方法,平均值控制界限以各组平均值算得的标准偏差来设置,平均值控制图异常的判断准则简化为3种判据,进而大大减少了实施统计控制的工作量,便于推广应用。     

Integrating statistical process monitoring with feedforward control

Feedforward control is a particular form of engineering process control. If a known input variable z_t can be measured and appropriate relationships built between the input variable, a compensatory variable x_t, and the desired output y_t, then a feedforward control system can be developed. Using feedforward control, we show under both sudden jump shifts and trends in the mean of the input and compensatory variables that the use of statistical process monitoring tools, such as the exponentially‐weighted moving average and the cumulative sum (CUSUM), significantly reduces variability in both the output variable and the controller relative to the use of feedforward control alone. Copyright © 2000 John Wiley & Sons, Ltd.     

Application of X̄ control chart with modified limits in process control

The conventional Shewhart X̄ chart is developed based on the assumption that the within‐sample variation is due to the inherent process variation, and any significant variation between samples is attributed to the existence of assignable causes. In the manufacturing industry there are processes where there is variation between samples due to the inherent process variation. A straightforward application of the conventional Shewhart X̄ chart would thus result in more frequent false alarms. The problems associated with various Shewhart X̄ charts in monitoring such a process are discussed using a real data set from an integrated circuit (IC) assembly process. A Shewhart X̄ chart with modified limits is adapted for such a process. In addition to the usual ability to signal for assignable causes, the X̄ chart with modified limits is also developed as a tool to signal the need for adjustment of controllable process variables for improving the process capability. Practical application of this chart in monitoring an IC assembly process is discussed. Copyright © 1999 John Wiley & Sons, Ltd.