Implementation of Artificial Neural Network on Temperature Control Process

Neural network controllers are network systems which have been inspired from biological neurons. Artificial neural networks (also known as ANN) work on the principle of learning where the networks learn based on the data provided to the network. The paper constitutes of implementation of ANN on temperature-controlled process like Single board heater system (also known as SBHS). Feedforward backpropagation algorithm has been used for system learning. ANN controller learning is done using Levenberg Margaret Algorithm which is the fastest algorithm for supervised learning[12]. ANN controller used has three layers namely input layer, hidden layer and output layer. The training data set which has been provided to the controller is the open loop response of the system. The responses performance plots, time series plot and regression plots for a variety of input data sets have been plotted.