AlQadi Hadeel, Abdelfattah Walid, Abbas Tahir, Ahmadini Abdullah Ali H, Sayed Amani Idris Ahmed, Ahmad Bakhtiyar
Department of Mathematics, College of Science, Jazan University, P.O. Box. 114, 45142, Jazan, Kingdom of Saudi Arabia.
Department of Mathematics, College of Science, Northern Border University, Arar, Saudi Arabia.
Sci Rep. 2025 Jul 9;15(1):24730. doi: 10.1038/s41598-025-09735-z.
This study introduces a novel Adaptive EWMA (AEWMA) control chart designed to monitor the mean of a normally distributed process with enhanced responsiveness. The proposed methodology dynamically adjusts the smoothing constant based on a proposed continuous function of the estimated mean shift derived from the EWMA statistic. The Monte Carlo simulations are conducted to assess the performance of the AEWMA chart across various magnitudes of process mean shifts, using run-length profiles as the primary evaluation metric. The results indicate that the AEWMA chart outperforms traditional methods in terms of detection efficiency. To demonstrate its practical applicability, the AEWMA chart is applied to a real-world manufacturing dataset, specifically analyzing the flow width resistance of substrates. The findings highlight the efficiency of the proposed chart, making it a valuable tool for improving process monitoring and quality control in industrial environments.
本研究介绍了一种新型自适应指数加权移动平均（AEWMA）控制图，旨在监测正态分布过程的均值，并提高其响应能力。所提出的方法基于从EWMA统计量得出的估计均值偏移的连续函数，动态调整平滑常数。进行了蒙特卡罗模拟，以运行长度分布作为主要评估指标，评估AEWMA控制图在各种过程均值偏移幅度下的性能。结果表明，AEWMA控制图在检测效率方面优于传统方法。为证明其实际适用性，将AEWMA控制图应用于一个实际制造数据集，具体分析基板的流宽阻力。研究结果突出了所提出控制图的效率，使其成为工业环境中改进过程监测和质量控制的宝贵工具。
