Search

Modern combustion engines require an efficient cycle-by-cycle fuel injection control scheme to optimise the single combustion events during transient operation. The online optimisation of the respective control inputs typically needs accurate while sufficiently simple models of the combustion quantities. Based on a recently presented cycle-by-cycle optimisation scheme with a hybrid model, this paper focuses on two aspects to enhance the accuracy as well as computational efficiency for an online computation. Firstly, the proper calibration of Gaussian processes nested in a combined physics-/data-based model structure is addressed. Respective test bench measurements and a tailored two-step training procedure are presented. Secondly, the computational efficiency of the online cycle-by-cycle optimisation is increased by mapping computationally intensive calculations into the data-based models through offline preprocessing. In addition, a data-driven approximation of the complete optimisation scheme is proposed to further minimise the computational demand. Simulation studies are used to evaluate the performance of these approaches.

Modern combustion engines require an efficient cycle-by-cycle fuel injection control scheme to optimise the single combustion events during transient operation. The online optimisation of the respective control inputs typically needs accurate while sufficiently simple models of the combustion quantities. Based on a recently presented cycle-by-cycle optimisation scheme with a hybrid model, this paper focuses on two aspects to enhance the accuracy as well as computational efficiency for an online computation. Firstly, the proper calibration of Gaussian processes nested in a combined physics-/data-based model structure is addressed. Respective test bench measurements and a tailored two-step training procedure are presented. Secondly, the computational efficiency of the online cycle-by-cycle optimisation is increased by mapping computationally intensive calculations into the data-based models through offline preprocessing. In addition, a data-driven approximation of the complete optimisation scheme is proposed to further minimise the computational demand. Simulation studies are used to evaluate the performance of these approaches. [ABSTRACT FROM AUTHOR]

Co‐firing coal and biomass has been applied in existing coal‐fired power stations recently. Online blend‐type identification was investigated by support vector machine (SVM) using flame emission spectrum for combustion optimisation. A spectrometer was used to capture the flame emission spectrum during co‐combustion in a 0.3 MW furnace. A total of 22 flame features were defined and extracted from the flame emission spectrum for blend‐type identification. ReliefF was applied to calculate the important weights of the extracted fame features. Alkali metals atomic excitation spectral intensities and the means of spectral signals show obviously higher important weights than the other flame features. Ultraviolet signal is more important than visible and infrared signals for blend‐type identification. SVM was adopted to identify the blend types. The method of 'ReliefF + SVM' was proposed to obtain the optimum feature vector. The number of optimum features can be reduced from 22 to 17 if only the prediction accuracy is considered. The optimum sampling number is 12. At the optimum feature vector (17 features) and the optimum sampling number (12), the average prediction accuracy of the five fuels is 99.67%. The results demonstrate that combining SVM and flame emission spectrum is suitable for online blend‐type identification during co‐combustion. [ABSTRACT FROM AUTHOR]

This paper is concerned with the development of a neural network based controller (NNBC) for chain grate stoker fired boilers. The objective of the controller was to increase combustion efficiency and maintain pollutant emissions below future medium term legislation. Artificial neural networks (ANNs) were used to estimate future emissions from and control the combustion process. Initial tests at Casella CRE Ltd demonstrated the ability of ANNs to characterise the complex functional relationships which subsisted in the data set, and utilised previously gained knowledge to deliver multistep ahead predictions. This technique was built into a carefully designed control strategy, which fundamentally mimicked the actions of an expert boiler operator, to control an industrial chain grate stoker at HM Prison Garth, Lancashire. Test results demonstrated that the developed novel NNBC was able to optimise the industrial stoker boiler plant whilst keeping the excess air level to a minimum. In addition, the ANN also managed to maintain the pollutant emissions within possible future limits for boilers in the size range of 1 to 50 MW. This prototype controller would thus offer the industrial coal user a means to improve the combustion efficiency on chain grate stokers as well as meeting probable medium term legislation limits on pollutant emissions. [ABSTRACT FROM AUTHOR]

Presents an abstract of the article "Evaluating the Strain and Fuel Concentration of Counterflow Diffusion Flames by Selected Species," by Heidi Bohm and Francois Lacas, which appeared in the 2005 issue of "Progress in Computational Fluid Dynamics, An International Journal." Response of methane-nitrogen/air and methane/air counterflow diffusion flames to the strain rate and to the initial fuel concentration; Limit at which the pollutions of polyaromatic hydrocarbons can be minimized.