Neural Network Modeling and Control of Stoker-Fired Boiler Plant

Abstract

The work described in this paper aims to address the development of a Neural Network Based Controller (NNBC) to control chain grate stoker fired boilers. Artificial Neural Networks (ANNs) were used to estimate future emissions from and control the combustion process. The resultant ANNs were able to characterise the dynamics of the process and delivered rational multi-step-ahead predictions wth test data collected at an industrial chain grate stoker at HM Prison Garth, Lancashire. This technique was built into a carefully designed control strategy, to control the industrial stoker. Test results showed that the developed NNBC was able to optimise the industrial stoker boiler plant whilst delivering the load demand required and in so doing, the NNBC also managed to maintain low pollutant emissions.

Simulation and Research of Boiler Combustion Process Based On the Improved RBF Neural Network

“…,in order to avoid particles into local minimum, and to accelerate the convergence speed of particle swarm optimization, we can constantly change approach 1 c , 2 c .For different objectives, . Equation (2-1) is the first iteration of the particle velocity, that it has a memory capacity of the middle term is "cognitive" section, indicating its own learning, and the final one to "society" section, on behalf of the sharing of information between the particles and mutual cooperation.…”

“…Neural networks are frequently used in modeling, which can help people to build up the actual work structure of relationships between various factors, such as mutual influence [2]. It with many other people in the relevant fields of the lessons learned, methods, algorithms, used in combination with studies on combustion, changing look of the boiler to the boiler working environment in a good combustion state parameters of the corresponding the ratio of these data records found, timely adjustment according to working conditions, a trend of future development.…”