Identification of Nonlinear Systems From the Knowledge Around Different Operating Conditions: A Feed-Forward Multi-Layer ANN Based Approach

TL;DR

This paper presents a neural network-based method for identifying nonlinear systems across different operating conditions, tested on nuclear reactor and servo control systems, with analysis of various ANN configurations.

Contribution

It introduces a multi-layer ANN approach for nonlinear system identification at multiple operating points, evaluating different network configurations for optimal performance.

Findings

Optimal ANN configurations vary with system and data.

The approach achieves consistent identification accuracy.

Root mean square errors are minimized with specific network setups.

Abstract

The paper investigates nonlinear system identification using system output data at various linearized operating points. A feed-forward multi-layer Artificial Neural Network (ANN) based approach is used for this purpose and tested for two target applications i.e. nuclear reactor power level monitoring and an AC servo position control system. Various configurations of ANN using different activation functions, number of hidden layers and neurons in each layer are trained and tested to find out the best configuration. The training is carried out multiple times to check for consistency and the mean and standard deviation of the root mean square errors (RMSE) are reported for each configuration.