Historically, some statistical methods have been studied for establishing when a process is in or out of control and what action have to be taken due to assignable causes. The control charts are one of the most common statistical tools used today. They are very useful and powerful tools for monitoring the quality of a process, allowing to observe all phases and variables that occur in the process. Much of the production processes are led by dynamic elements which allow autocorrelated observations and, with this, more costs and false alarms. To address this situation, some implementations of Artificial Neural Networks with X, EWMA and CUSUM control charts, are made for an AR(1) process. The results show that for small shifts, the EWMA chart outperform the X chart, while for large shifts the X chart performed better than the EWMA chart. In addition, the CUSUM chart performed well for all cases tested.