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

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