A learning algorithm for continually running fully recurrent neural networks
Neural Computation
| Hi-index | 0.00 |
Refrigeration systems are characterized by the fact that they posses a large number of state variables that are coupled non-linearly with each other. Hence, the use of neural networks for modeling such processes is more appealing than employing traditional modeling approaches. This paper presents the results of the experiments conducted on a medium-sized laboratory setup of a refrigeration system. Using data collected from the setup, recurrent multilayer perceptron networks are trained to mimic the behavior of the system. The networks are validated not only with test data collected under similar external conditions but also with those that are gathered when the measurements of the external temperature are beyond the range inspected during the collection of the training data. Despite a significant change in external conditions, the validation results showed a fairly good performance in a multi-step prediction of the temperature and relative humidity inside the refrigerator.