An adaptive process control system was installed in Cortez Gold Mines Mill #2 Grinding Plant in Nevada. The installation, commissioning, and testing of the system took approximately 80 manweeks, but final test results show that the system paid for itself through increased throughput within two weeks of commissioning. Both crisp and fuzzy rules are used in the expert rule base which is also integrated with continually adapting neural network models. The expert rules and models are used by predictors, and optimizers to allow the control system to provide optimum process performance under continually varying feed conditions. The selection, installation, rule and predictor configuration, and statistically verifiable testing of the control system in the Cortez Gold Mines Mill #2 Grinding Plant is described in the paper.
展开▼
