Optimising control of coal flotation by neuro-immune algorithm
MetadataShow full item record
Coal flotation is widely used to separate commercially valuable coal from the fine ore slurry, and is an industrial process with nonlinear, multivariable, time-varying and long time-delay characteristics. The online detection of ash content of products as the operation performance evaluation in the flotation system is extraordinarily difficult because of the low solid content and numerous micro-bubbles in the slurry. Moreover, it is time-consuming by manual analysis. Consequently, the optimal separation is not usually maintained. A novel technique, called the neuro-immune algorithm (NIA) inspired by the biological nervous and immune systems, is presented in this paper for predicting the ash content of clean coal and performing the optimizing control to the coal flotation system. The proposed algorithm integrates the deeply-studied artificial neural network (ANN) and the developing artificial immune system (AIS).A two-layer back-propagation network was constructed offline based on the historical process data under the best system situation, using five parameters: the flow and the density of raw slurry, the input flows of water, the kerosene and the GF oil, as the inputs and the ash content of clean coal as the output. The immune cell of AIS is made up of six parameters above as the antigen. The cytokine based clone selection algorithm is used to produce the relative antibody. The detailed computation procedures about the hybrid neuro-immune algorithm are minutely discussed. The ash content of clean coal was predicted by NIA using the practical process data s: (308.6 174.7 146.1 43.6 4.0 9.4), and the absolute difference between the actual and computed ash content values was 0.0967%. The optimizing control on NIA was simulated considering two different situations where the ash content of clean coal was controlled downward from 10.00% or upward from 9.20% predicted by ANN to the target value 9.50%. The results indicate that the target ash content and the value of controlling parameters are obtained after several control cycles.
Showing items related by title, author, creator and subject.
Han, O.; Kim, M.; Kim, B.; Subasinghe, Nimal; Park, Chul hyun (2014)The amenability of beneficiating a fine hard coal from Hwa-Sun coal mine using column flotation has been studied using a CoalPro flotation column developed by Canadian Process Technologies (CPT). After initial testwork ...
Santoso, Binarko (1994)The Early Permian coal samples for the study were obtained from the Vasse Shelf, southern Perth Basin, located approximately 200 km south- west of Perth. The selected coal samples for the study were also obtained from the ...
Neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learningConradie, A.; Aldrich, Chris (2010)The time cost of first-principles dynamic modelling and the complexity of nonlinear control strategies may limit successful implementation of advanced process control. The maximum return on fixed capital within the ...