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

Introduction There is a need to develop a low cost method for removing acid gases and solid particles from flue gases from incinerators. Cyclone scrubbers are a process of absorbing gases, separating particles and lowering the gas temperature. To understand both gas absorption and particle separation in cyclone scrubbers it is important to understand gas absorption and particle separation. In this paper we studied the absorption of gas and liquid in cyclone scrubbers.

An artificial neural network is a simulated mathematical model inspired by a biological neural network. An artificial neural network can simulate and process a nonlinear relationship between input and output. The adaptive weight between artificial neurons is adjusted by a learning algorithm that reads observational data with the purpose of increasing the output. Artificial neural networks are very powerful. However, even though some neuron mathematics is simple, the whole network becomes complicated. Because this ANN is considered a "black box" algorithm. Care must be taken when selecting ANN as a tool for problem solving. It is impossible to cancel the decision making process of the system in the future.

The artificial neural network continues to deal not only with the behavior of these investors but also on past performance and volatility of stocks and indices. This level of data mining and processing will enable predictive analysis to reveal nonlinear patterns. This can only be achieved by the computational power of AI. Until recently, the power of machine learning was applied to financial markets, only by people who were as secret as pockets and algorithms. Several companies have established their own native artificial intelligence system and any company can sign a license agreement that allows them to distribute information from a proprietary AI framework. For investors, this means that there are more choices than before.

Dynamic environments such as financial markets are very difficult to model with neural networks. Both methods continue to train neural networks over a period of time, or use dynamic neural networks. As time goes on, dynamic neural networks "track" changes in the environment and adjust architecture and weight accordingly. As time goes on, they adapt to dynamic problems and you can track local optimal values ​​over time using metaheuristic optimization algorithms of multiple solutions. One such algorithm is a multi-group optimization algorithm, a derivative of particle group optimization. In addition, genetic algorithms with enhanced diversity or memory have also been shown to be robust in dynamic environments.