José M. Aragón

NEURAL NETWORK MODEL FOR FLUIDISED BED DRYERS

The application of an artificial neural network (ANN) to model a continuous fluidised bed dryer is explored. The ANN predicts the moisture and temperature of the output solid. A three-layer network with sigmoid transfer function is used. The ANN learning is made by using a set of data that were obtained by simulating the operation by a classical model of dryer. The number of hidden nodes, learning coefficient, size of learning data set and number of iterations in the learning of the ANN were optimised. The optimal ANN has five input nodes and six hidden nodes. It is able to predict, with an error less than 10%, the moisture and temperature of the output dried solid in a small pilot plant that can treat up to 5 kg/h of wet alpeorujo. This is a wet solid waste that is generated in the two-phase decanters used to obtain olive oil.

Fluidized Bed Drying of 2-Phase Olive Oil Mill By-Products

This study is focused on the fluidized bed drying of solid olive oil mill by-products (SOB) resulting from the 2-phase oil extraction method. The most usual method used in SOB drying is the rotary dryer, which revealed some problems and disadvantages that can be easily solved with the development of new drying techniques based on exhaustive studies of the solid and a better comprehension of the drying process. Two-phase SOB drying in a fluidized bed proved to be a suitable alternative that provides high-efficiency drying at relatively low air temperatures (T < 150°C). Drying kinetics modeling was developed based on well-known empirical models such as Henderson & Pabiss model and Pages model. An n-order potential model is presented, showing a good accuracy for the description of the experimental drying curves of 2-phase SOB and it was possible to correlate satisfactorily its fitting parameters with the process variables.

Experimental Fluid Dynamics Study in a Fluidized Bed by Deterministic Chaos Analysis

Differential pressure fluctuations in gas-solid fluidized beds were analyzed by chaos analysis (construction of attractors, correlation dimension, Kolmogorov entropy) and mutual information. Experimental fluidization tests of three different particles were conducted. Two of them are from Geldart group B and one from Geldart group D. The fluidization experiments were performed in a cylindrical bed with 0.07 m i.d. and 1.0 m high. Pressure fluctuations were measured by three pressure transducers, and their signal time series were analyzed in the time domain (mean and standard deviation) and in the frequency domain (power spectra) for comparison and complementation of chaos analysis. Analyses in the time domain allowed a good estimation for determining whether or not the system is fluidized. The Fourier spectra provided more detailed information that could identify other phenomena such as the presence of bubbles. The chaos tools produced sensitive results, offering a qualitative and quantitative analysis for identification of the phenomena that occur in fluidization. Three different fluidization regimes could be indentified: multiple bubble bed, slugging bed, and exploding bubble bed.

Applications of Neural Networks to pH Control

The neutralization of an acidic waste water was controlled by two NNs. One predicts future pH values, the other manipulates an alkaline current.