Homogeneously weighted moving average control chart with an application in substrate manufacturing process

Cumulative sum and exponentially weighted moving average are also named as memory-type statistical process control charts for they are good at quickly detecting the presence of small disturbances. This research study proposes a new memory-type control chart. The aim of the study was to propose such a control charting statistic that give a specific weight to the current sample and the remaining weight is equally distributed among the previous samples. The performance of the proposed chart is measured in terms of average run length. The evaluated performance is compared with some existing memory-type control charts and the superiority of the proposed chart is established over its competitors. The effect of non-normality on the performance of proposed chart is assessed using Gamma, Student's t and Logistic distributions. The study found that design parameters of the proposed chart can be adjusted to make it more robust to non-normality. Finally, the application of the proposed chart is demonstrated using a real dataset from substrates manufacturing process where flow width of the resist is the quality characteristic to be monitored.