Parametric system identification using neural networks

• A mathematical relationship, between ANN weights and ARMA parameters, is derived.
• Transfer functions are approximated from the ANN weights.
• An algorithm (NN2TF) that approximates transfer functions from ANN models is developed.
• Simulation runs for time and frequency responses are analyzed.
• Simulation runs are used to validate the algorithm’s results.

Neural networks are used in many applications such as image recognition, classification, control and system identification. However, the parameters of the identified system are embedded within the neural network architecture and are not identified explicitly. In this paper, a mathematical relationship between the network weights and the transfer function parameters is derived. Furthermore, an easy-to-follow algorithm that can estimate the transfer function models for multi-layer feedforward neural networks is proposed. These estimated models provide an insight into the system dynamics, where information such as time response, frequency response, and pole/zero locations can be calculated and analyzed. In order to validate the suitability and accuracy of the proposed algorithm, four different simulation examples are provided and analyzed for three-layer neural network models.

Figure optionsDownload as PowerPoint slide