Real Time Statistical Process Control for Autocorrelated Serial Data: A Simulation Approach

Abstract

Computer measurement systems play an important role on process automation and Industry 4.0 implementation strategies. They can be easily integrated on modern production systems, enabling real time test and control of multiple product and process characteristics that need to be monitored. If for one side the big data provided by these systems is an important asset for production analytics and optimization, on the other hand, the high frequency data sampling, commonly used in these systems, can lead to autocorrelated data violating, this way, statistical independence requirements for statistical process control implementation. In this paper we present a simulation model, using digital recursive filters, to properly handle and deal with these issues. The model demonstrates how to eliminate the autocorrelation from data time series, creating and ensuring the conditions for statistical process control application through the application of real time control charts. A performance comparison between Shewhart of Residuals and Exponentially Weighted Moving Average (EWMA) of Individual Observations control charts is made for autocorrelated data time series with the presence of different mean shift amplitude perturbations.