Analysis and Application of Selected Control Charts Suitable for Smart Manufacturing Processes

Smajdorová, Tereza; Noskievičová, Darja

doi:10.3390/app12115410

Cited by 5 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such cases of highly skewed data distribution, nonparametric or robust methods are necessary to estimate the control limits. The non-parametric control charts offer options to industrial practitioners; however, they are hard to implement in reallife practice due to a lack of knowledge and support in terms of computational tools [6].…”

Section: Introductionmentioning

confidence: 99%

Robust Control Chart Application in Semiconductor Manufacturing Process

Sufinah Dahari,

Muzalwana Abdul Talib,

Adilah Abdul Ghapor

2024

ARASET

View full text Add to dashboard Cite

Statistical Process Control (SPC) charts are frequently used in the semiconductor manufacturing environment to monitor process quality and detect special-cause variations, hence, to take corrective actions when necessary. The important aspects of control charts to consider on production floors are identifying the primary objective of implementing control charts, the type of data to monitor and the most appropriate control limits to establish. When the quality data is a type of attribute data like the proportion of defectives from a production lot, a p-chart approach is most suitable. In p-chart applications, although the assumption of normally distributed process data is not mandatory, the widespread practice is to assume the normal distribution of process data when establishing the control limits. Yet again, the reality of industrial settings is that process data are most likely influenced by outliers, resulting in highly skewed distributions. This paper addresses these issues by proposing robust SPC charting techniques to detect special-cause variations in the semiconductor manufacturing processes. Here, we present a case study of a semiconductor company in Malaysia, Dominant Opto Technologies Sdn. Bhd. to propose three robust statistical approaches for monitoring the proportion of defectives in production lots. We apply M-estimates, median, and interquartile range to calculate the upper control limits (UCL) and found that robust estimators are more effective in detecting early process deterioration and capturing the out-of-control (OOC) conditions better than traditional control charts. By proposing robust methods, this study enlightens the practical aspects of process quality improvement for real-life manufacturing setups. Because a high OOC rate may impact manufacturing productivity, we recommend the decision-makers choose the types of control charts based on the implications of each robust approach toward quality and productivity. The significance of this study includes providing insights into setting up the appropriate attribute control charts for detecting defective proportions for professionals and SPC researchers working in these areas.

show abstract

Section: Introductionmentioning

confidence: 99%

Robust Control Chart Application in Semiconductor Manufacturing Process

Sufinah Dahari,

Muzalwana Abdul Talib,

Adilah Abdul Ghapor

2024

ARASET

View full text Add to dashboard Cite

show abstract

“…The research examined these control charts' efficacy in automated, technologically sophisticated settings. This study assessed charts for smart manufacturing continuous monitoring and quality control [8]. Shewhart time-between-events control charts are compared and analyzed in a renewal process to measure their effectiveness.…”

Section: Introductionmentioning

confidence: 99%

Shift Detection Comparison For Sized Biased And Area Biased Exponential Distributions Based Control Charts

Anjum,

Iqbal,

Kashif

et al. 2024

Migrat. Lett.

View full text Add to dashboard Cite

Probability distribution models are very helpful to solving many real-life problems. The development of new or extensions to an existing model is a very attractive area of research. Among many types of probability distribution models, weighted distributions are becoming more important for modeling data. Weighted distributions can help discover defects in manufacturing and outliers by weighting significant observations. Control charts are the most important tools to monitor process efficiency. In recent decades, researchers have focused on weighted distributions, especially those with size and area biased exponential distribution. This research introduces a novel control chart for a characteristic following a size-biased and area-biased exponential distribution to emphasize the relevance of weighted distributions. Charts are effectively determines size-biased and area-biased exponential distribution control chart limits also Monte Carlo simulations are used to assess different Average Run Length (ARL) values.

show abstract

“…ARL is defined as the average number of samples to be plotted on the control chart before the out-of-control signal is observed. However, many researchers criticized the sole dependence of the ARL as the performance measure of control charts, for example, see Teoh et al [23], Khoo et al [24], Lee and Khoo [25], Smajdorová and Noskievičová [26]. In addition, as pointed out by Graham et al [27], the ARL as a performance measure has many drawbacks.…”

Section: Introductionmentioning

confidence: 99%

Optimal statistical design of the double sampling np chart based on expected median run length

Tuh

Kon

Chua

et al. 2022

Front. Appl. Math. Stat.

View full text Add to dashboard Cite

Double sampling (DS) control charts are widely regarded as an effective process monitoring tool owing to their remarkable properties, such as the ability to detect small and moderate process shifts efficiently with the reduced sample size. Since the shape of the run length distribution is highly right-skewed for the process small shift size and becomes almost symmetric when the process shift size is large, the use of median run length (MRL) as a performance measure is therefore more representative. Existing works on the DS np chart construction were performed by taking an approach that the shift size of the process fraction nonconforming is assumed to be known. However, the shift size of the fraction nonconforming is usually unknown by the quality practitioners in practice. Herein, to address this issue, the expected median run length (EMRL) has been suggested as a performance measure for the unknown shift size. This paper suggests an optimal design procedure for the DS np chart based on the EMRL criterion. An example is provided to illustrate the construction of the EMRL-based DS np chart. The DS np chart is compared with a competing chart based on the EMRL criterion. Findings obtained reveal that when the shift size is unknown, the EMRL is an alternative performance measure for the DS np chart, with greater sensitivity observed for the DS np chart in contrast to the standard np chart for detecting a wide range of shifts.

show abstract

Analysis and Application of Selected Control Charts Suitable for Smart Manufacturing Processes

Cited by 5 publications

References 47 publications

Robust Control Chart Application in Semiconductor Manufacturing Process

Robust Control Chart Application in Semiconductor Manufacturing Process

Shift Detection Comparison For Sized Biased And Area Biased Exponential Distributions Based Control Charts

Optimal statistical design of the double sampling np chart based on expected median run length

Contact Info

Product

Resources

About