Introduction to the theory of neural computation
Introduction to the theory of neural computation
Neural networks: algorithms, applications, and programming techniques
Neural networks: algorithms, applications, and programming techniques
Introduction to artificial neural systems
Introduction to artificial neural systems
Practical neural network recipes in C++
Practical neural network recipes in C++
Fundamentals of Artificial Neural Networks
Fundamentals of Artificial Neural Networks
Advanced Methods in Neural Computing
Advanced Methods in Neural Computing
Backpropagation Networks for Grapheme-Phoneme Conversion: a Non-Technical Introduction
Artificial Neural Networks: An Introduction to ANN Theory and Practice
| Hi-index | 0.00 |
Primary aluminium is produced using a highly dynamic and unstable technique known as the Hall-Heroult process. An important consideration for aluminium smelting is minimisation of process variation, which is monitored by measuring particular parameters of the Hall-Heroult process and administering corrective action as appropriate to return or maintain the process within a predetermined control range. A critical parameter to be controlled is electrolyte temperature. Due to the high temperature and corrosive environment associated with the Hall-Heroult process it is beneficial to have some alternative methodology of electrolyte temperature measurement than the existing thermocouple technique. In this paper it is shown that a neural network is applied to predict electrolyte temperature in the Hall-Heroult cell, yielding significant productivity improvements. In particular, the backpropagation, BP, neural network is used to develop an appropriate process model. Moreover, it is shown that careful consideration given to the training data used to develop the neural network model has given an accurate electrolyte temperature prediction methodology.