Future Engineering Journal


This study involved the application of artificial neural network (ANN) as a new approach for thermoacoustic refrigerators to predict the temperature difference across the stack under some operating conditions. One ANN model for a standing wave thermoacoustic refrigerator, had been developed based on the experimental data from other literature. Temperature difference across the stack was chosen as a response to the input parameters, mean pressure and frequency in the proposed ANN model. A multi-layer feed-forward neural network with a back propagation algorithm had been proposed for predicting the temperature difference across the stack of the thermoacoustic refrigerator. This proposed ANN model has three layers with configuration 2-12-1, namely, input layer with two neurons representing the two operating parameters, one hidden layer with an optimal 12 hidden neurons, and output layer with one neuron representing the temperature difference across the stack, as response. The high ability of ANN for data prediction was proven in this study through achieving an average prediction error of 0.2% and a regression coefficient (R) of 0.99979 during testing phase. This research work provides a new approach based on ANN technique to solve complex thermoacoustic problems with linear or nonlinear nature through either modeling, optimization or system identification.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.