Artificial Neural Network for non-Linear Dynamic Process of a Cyclone Scrubber

1276 Words3 Pages

INTRODUCTION
The development of a low cost process for removal of acid gases and solid particles in flue gases from incinerators is desirable. A cyclone scrubber is one of the processes, which can absorb the gases, separate particles, and decrease the gas temperature simultaneously. For understanding the phenomena of gas absorption and particle separation simultaneously in a cyclone scrubber, it is very important to understand the gas absorption and the particle separation exclusively. This paper studied the absorption phenomena of gas-liquid in a cyclone scrubber. Despite the relatively simple design and the broad use of these types of scrubbers, the processes taking place with the simultaneous absorption and separation, their interactions, and fluid dynamics are quite complex and give rise to rather complicated problems in design and optimization. Consequently, its modeling is a complex task since a system of nonlinear differential equations must be solved and many transport and chemical parameters ought to be evaluated. Hence, the development of more simple and reliable models comprises the subject of numerous researches.
A process model is a functional relationship among variables that explains the cause and effect relationships between inputs and outputs. Models can be developed from fundamental principles, such as the laws of conservation of mass, energy, and momentum, and other chemical engineering principles. Such models are capable of explaining the underlying physics of the system and are called phenomenological models. However, due to the complexity of the process in the cyclone scrubber system, it is very difficult to obtain accurate phenomenological models. Even if an accurate phenome- nological model is obtained, ...

... middle of paper ...

...e proposed model more confidence.

Table 3 Mean absolute relative errors between experimental and calculated values

Gas-liquid system
Mean absolute relative error, %
CO2-Ca(OH)2-H2O:
L/G = 0.16
L/G = 0.1
L/G = 0.07
CO2-NaOH-H2O:
L/G = 0.16
0.385
0.540
0.366

0.725

CONCLUSION
This paper investigates modeling strategy by artificial neural networks for the non-linear dynamic processes of a cyclone scrubber. The three layer feed-forward neural network (3-FFNN) has been chosen for neural network modeling.
The comparison between the simulation results of the neural network and experimental data has been discussed to show the validity of the proposed model. The comparison illustrates that the accuracy of 3-FFNN is satisfactory with experimental. In conclusion, the highly non-linear behavior of cyclone scrubber can be modeled successfully by utilizing the 3-FFNN.

More about Artificial Neural Network for non-Linear Dynamic Process of a Cyclone Scrubber

Open Document