Abstract
Control charts are important tools for detecting the presence of special cause in the process and are widely used in manufacturing. It is known that neural network control charts can detect smaller shifts in the process mean better than statistical control charts. In this study, the average run length of various control charts are compared using gamma distribution generated data with various skewness to measure the robustness. From the results obtained, the neural network based control chart is found to be less robust compared to the statistical based control charts which includes Shewhart X¿ control chart, EWMA and CUSUM based control charts. Based on our results, we concluded that the EWMA control chart is the most robust.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
