The identification and control for chain boiler combustion system based on neural networks

It is difficult to have good performance for chain boiler combustion control system due to large delay time, varying coal's quality and steam load. A neural network identification method for nonlinear system's delay time is discussed. Using the abrupt mutation resulted from the training error sum square of the real output and the expected output of the network, this method changes the input sample period of the neural network so that it can discriminate the delay time of the nonlinear model. Combining the discrimination of neural network system with long time delay and the control method based on model prediction, it can be applied to control the nonlinear long delay time system with variable parameters or unknown delay time. Simulating with a 10t/h chain boiler model, the results show it has much better advantage of celerity and robustness.