Determination of Optimal Design Parameters of Moving Average Control Charts

The economic design of a control chart can reduce the cost of process control and promote the competitiveness of an enterprise. This type of design has been studied for over four decades since Duncan’s pioneering work in 1956. Few studies, however, have focused attention on the economic design of a moving average (MA) control chart. Montgomery pointed out that an MA control chart is more effective than a Shewhart control chart for detecting small process shifts and is considered by some to be simpler to implement than the CUSUM. This study proposes an economic model of an MA control chart with multiple assignable causes. This economic model is then applied to a realistic case from the chemical industry, and sensitivity analysis shows that the magnitude of shift, rate of occurrence of assignable causes and penalty cost, when the process is out of control, should be more carefully estimated when conducting an economic analysis.. ID="A1"Correspondance and offprint requests to: Yun-Shiow Chen, Department of Industrial Engineering and Management, Yuan-Ze University, 135 Yuan-Tung Road, Nei-Li 32026, Taoyuan Shian, Taiwan. E-mail:ieyschen@saturn.yzu.edu.tw     

Generally weighted moving average control chart for monitoring process variability

Most applications of the EWMA control chart for monitoring processes depend on detecting shifts in the process mean. The problem of detecting an increase in process variability, which can also strongly affect the quality of products, is perhaps more important. When a process moves from the pilot phase to the production phase, the mean may not shift but the variation will probably increase because new sources of variation are introduced, including new people and materials. A simulation is performed to evaluate the ARL to false alarm and to monitor the change in the process variability of the EWMA control chart and the GWMA control chart. An extensive comparison reveals that the GWMA control chart is more sensitive than the EWMA control chart in monitoring the variance of a process. The results of this study can be applied to monitor the process variability in automated industries.     

Detection of the eroding surface in the EDM process based on the current signal in the gap

To achieve high removal rate and low electrode wear in sinking electrical discharge machining process (EDM), rough machining parameters have to be selected according to the size of the eroding surface. In general, the size of the eroding surface varies according to the depth of the machining. Thus, it has to be determined on-line. This paper shows that the electric current signal in the gap depends on the size of the eroding surface. The significance of the process attributes of the electric current signal is established by inductive machine learning and the general decision rules are derived. The size of the eroding surface can be detected on-line by monitoring and evaluating the electric current signal in the gap.     

关于精确平均点度随机网络仿真模型的研究

为提高仿真模型的可信度,提出了一种随机网络生成算法。研究内容包括：随机节点的区域性分布,中心节点、OVERLAY功能节点的选择,实验推演新的概率连通公式,增加点度分类约束策略及随机网络快速连通策略等。在算法基础上建立了具有精确平均点度的随机网络仿真模型。对该随机网络仿真模型的性能做了一定的阐述、模拟和分析,表明该模型是通用性的、可定制的。与现有算法相比,该算法收敛性好,并能线性逼近所模拟的实际网络。     

药芯焊带轧制力学解析及实验对比

针对药芯焊带轧制实际 ,本文在合理假设的基础上 ,利用工程法推导出药芯焊带轧制的平均单位压力、包带轧后厚度、前滑值等轧制参数的计算数学模型 ,借助计算机对该数学模型求数值解 ,并用实验进行验证 ,数值解与实验值具有吻合较好     

点声源声场两种声强计算方法误差分析

分别推导出了点声源声场基于算术平均声压的声强计算误差公式和基于几何平均声压的声强计算误差公式 ,并进行了计算机仿真 ,且对这两种误差进行了对比分析 ,在高频区由几何平均声压而得到的计算声强的误差小于由算术平均而得到的计算声强的误差 ,几何平均声强具有比算术平均声强可测范围宽的特性。当声波是空间位置和时间的周期函数时 ,平面波误差项永远是一负偏差项。近场误差项不影响曲线形状 ,只是使曲线进行上下平行移动 ,随着 Δr/ r的增大 ,曲线向上移动 ,曲线和横轴的交点 (误差为零的点 )向右移动。     

探讨出租车计程MPE-4%~+1%及C值极平差影响

①C值k值统计。②C极平差等等因素对Δ计程的影响。③MU评定。④Uk=2≮0.3MPE半区间。⑤分析MPE。⑥公路法MPE±2%。⑦滚筒法MPE±3%。     

证明人口系统稳定性与妇女临界生育率的一种新方法

在时间年龄座标平面中,人口系统中同龄人群的生命历程可用一个与两座标轴正向成45°夹角的定向矢量函数表示。在此基础上,定义了死亡率、女性比例函数、生育模态归一函数,即可简捷得出妇女临界生育率。最后,以1978年度的妇女临界生育率为基准,分析了近年来我国人口数量的变化趋向。     

Packet Reservation Window Multiple Access for Microcellular Voice/Data Transmission

We propose a new packet reservation multiple access (PRMA) scheme for the joint transmission of voice and data traffics in a microcellular medium. The collision resolution protocol within the system is based on a modification of the window random access algorithm, which has superior properties compared to the conventional slotted Aloha. The proposed algorithm, which we call packet reservation window multiple access (PRWMA), works in distinct modes for voice and data without prioritization, and the user performs slightly different operations depending on the information type. Simulation results show that PRWMA outperforms PRMA by a significant margin in terms of voice user capacity.