Model Predictive Control Based on Improved DBD Algorithm and Application of Electrode Control in EAF

In order to achieve electrode lifting control precisely, applied predicting model to the identification and control electrode up-down control system in EAF, shorting the time of adjustment greatly. With this model, system can predict the state of EAF for the next time. The output of system is optimized compensated by special predicting program which contains improved DBD algorithm based on BP algorithm. The operating result of system shows that adaptive control of EAF based on ANN is a feasible way of electrode control. In arc ignition process, it has apparent effect and improves the stability of arc, so that power factor is advanced and current drain is reduced.