By the end of 1997, totally ten 300 MW grade W-flame double arch boilers, firing anthracite or meager coal, were operating in China. These W-flame boilers were designed and supplied separately by four different manufa...By the end of 1997, totally ten 300 MW grade W-flame double arch boilers, firing anthracite or meager coal, were operating in China. These W-flame boilers were designed and supplied separately by four different manufacturers in the world, using either their own technology or foreign patent. It is shown by a recent survey that all these boilers are having a normal operation. However, there is still some room to be improved, such as boiler furnace configuration. Also, for raising the burnout rate and avoiding local slagging, furnace volume and burner layout need to be deliberated. And the tineness of pulverized coal and the air / coal ratio need to be improved. Some suggestions are made in this paper for optimizing the boiler design, Test data for the minimum stable combustion load and NOx emission are given too.展开更多
A Bayesian-Gaussian Neural Network (BGNN) is put forward in this paper to predict the static and transient performance of Circulating Fluidized Bed (CFB) boilers. The advantages of this network over Back-Propagation N...A Bayesian-Gaussian Neural Network (BGNN) is put forward in this paper to predict the static and transient performance of Circulating Fluidized Bed (CFB) boilers. The advantages of this network over Back-Propagation Neural Networks (BPNNs), easier determination of topology, simpler and time saving in training process as well as selforganizing ability, make this network more practical in on-line performance prediction for complicated processes. Simulation shows that this network is comparable to the BPNNs in predicting the performance of CFB boilers. Good and practical on-line performance predictions are essential for operation guide and model predictive control of CFB boiIers, which are under research by the authors.展开更多
文摘By the end of 1997, totally ten 300 MW grade W-flame double arch boilers, firing anthracite or meager coal, were operating in China. These W-flame boilers were designed and supplied separately by four different manufacturers in the world, using either their own technology or foreign patent. It is shown by a recent survey that all these boilers are having a normal operation. However, there is still some room to be improved, such as boiler furnace configuration. Also, for raising the burnout rate and avoiding local slagging, furnace volume and burner layout need to be deliberated. And the tineness of pulverized coal and the air / coal ratio need to be improved. Some suggestions are made in this paper for optimizing the boiler design, Test data for the minimum stable combustion load and NOx emission are given too.
文摘A Bayesian-Gaussian Neural Network (BGNN) is put forward in this paper to predict the static and transient performance of Circulating Fluidized Bed (CFB) boilers. The advantages of this network over Back-Propagation Neural Networks (BPNNs), easier determination of topology, simpler and time saving in training process as well as selforganizing ability, make this network more practical in on-line performance prediction for complicated processes. Simulation shows that this network is comparable to the BPNNs in predicting the performance of CFB boilers. Good and practical on-line performance predictions are essential for operation guide and model predictive control of CFB boiIers, which are under research by the authors.
