Modeling and control of a pilot pH plant using genetic algorithm
Engineering Applications of Artificial Intelligence
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
IEEE Transactions on Neural Networks
Single layer neural networks for linear system identification using gradient descent technique
IEEE Transactions on Neural Networks
Hi-index | 0.01 |
The raw slurry preparing is a key process to guarantee product for alumina sintering production. To obtain the qualified raw slurry in the presence of uncertainty, a two-stage intelligent optimization system, which weakens uncertainty effects through optimization of raw material proportioning and re-mixing operation, is developed. At the first stage, an integrated model combining the first principle with neural networks is built to predict the raw slurry quality, and a multi-objective hierarchical expert reasoning strategy is proposed to determine an optimal set point of raw slurry proportioning. At the second stage, an optimal scheduling model with uncertainty is built to provide an optimal combination of selected tanks for the mixing of raw slurry in full-filled tanks. The practical running results show that the eligibility rate of raw slurry is effectively improved, and the raw slurry preparing process is successfully simplified and the energy consumption is also obviously reduced.