Resources on Neural Networks

Most control methods, other than PID, rely on a model of the controller. With Predictive and robust control methods the models are built into the control designs, with self-tuning control the models are estimated on-line from plant data. This sections deals with other model based control techniques, that do not fall into any other category.

  • NNSYSID and NNCTRL: Tools for System Identification and Control with Neural Networks, M.Norgaard, O.Ravn and N.K.Poulsen, IEE Computing & Control Journal, February 2001. Describes two toolboxes for use with Matlab that give neural network system identification and control design, including training algorithms, model validation and model structure selection. These toolboxes are freely downloadable at NNSYSID toolbox and NNCTRL toolkit.
Links to Other Resources