Process tracking and monitoring based on discrete jumping model

摘要

The jumping model has been used as an effective tool in tracking and detecting changes for continuous statistics in various applications. In this article, we extend the current jumping model from the continuous case to the discrete case to track and monitor the changes in attribute data. In this method, the jumping model-based posterior distribution of the process mean is constructed with attribute data and prior knowledge of the process. The posterior distribution consists of several components that account for theweights of the process to be “in-control”or “out-of-control.”Using the component representing the in-control weight as the monitoring index, a jumping model-based control chart is developed to monitor the attribute data process. The proposed chart is further extended to cover different out-of-control modes. The performance of the jumping model-based chart is investigated and compared to conventional control charts through numerical studies and a real-world data set. The results demonstrate the effectiveness of the proposed chart.