Measurement and Control of Non-Linear Data Using ARMA Based Artificial Neural Network

Abstract

Abstract Non-linear processes like conical tank control system is complex because of its non-linear characteristics, long-term interval and time difference between the system input and output. In this context, neural network based controller works since it is able to control and train the non-linear data set of liquid level in order to optimize the network performance. Hence, this article proposes a neural network control using gradient descent with adaptive learning rate that improves the performance and minimizes the errors, by using moving average filter and Hanning window to enhance the non-linear data. The article mainly deals with an application involving ARMA and artificial neural-based network (ANN) to model a conical tank system. To remove the recurrent components and to predict the future values of the process, the present paper employs an Autoregressive Moving Average Model (ARMA) by identifying its time varying parameters and combining with artificial neural network. MATLAB R2016b was applied for the entire simulation and training of non-linear data set. The simulation results indicate a minimization in the difference between the net input to the output and target value with that of error. The results indicated that the simulation took only 13 s to train the entire network for 6,135 iterations with the ARMA based model.