Neural Network Based Intelligent Sootblowing System
Cost effective generation of electricity is vital to the economic growth and stability of this nation. To accomplish this goal a balanced portfolio of fuel sources must be maintained and established which not only addresses the cost of conversion of these energy sources to electricity, but also does so in an efficient and environmentally sound manner. Conversion of coal as an energy source to produce steam for a variety of systems has been a cornerstone of modern industry. However, the use of coal in combustion systems has traditionally produced unacceptable levels of gaseous and particulate emissions, albeit that recent combustion, removal and mitigation techniques have drastically reduced these levels. With the combustion of coal there is always the formation and deposition of ash and slag within the boilers. This adversely affects the rate at which heat is transferred to the working fluid, which in the case of electric generators is water/steam. The fouling of the boiler leads to poor efficiencies due to the fact that heat which could normally be transferred to the working fluid remains in the flue gas stream and exits to the environment without beneficial use. This loss in efficiency translates to higher consumption of fuel for equivalent levels of electric generation; hence more gaseous emissions are also produced. Another less obvious problem exists with fouling of various sections of the boiler creating intense peak temperatures within and around the combustion zone. Total nitrogen oxides (NOx) generation is primarily a function of both ''fuel'' and ''thermal'' NOx production. Fuel NOx which generally comprises 20%-40% of the total NOx generated is predominantly influenced by the levels of oxygen present, while thermal NOx which comprises the balance is a function of temperature. As the fouling of the boiler increases and the rate of heat transfer decreases, peak temperatures increase as does the thermal NOx production. Due to the composition of coal, particulate matter is also a by-product of coal combustion. Modern day utility boilers are usually fitted with electrostatic precipitators to aid in the collection of particulate matter. Although extremely efficient, these devices are sensitive to rapid changes in inlet mass concentration as well as total mass loading. Traditionally, utility boilers are equipped with devices known as sootblowers, which use, steam, water or air to dislodge and clean the surfaces within the boiler and are operated based upon established rule or operator's judgment. Poor sootblowing regimes can influence particulate mass loading to the electrostatic precipitators. The project applied a neural network intelligent sootblowing system in conjunction with state-of-the-art controls and instruments to optimize the operation of a utility boiler and systematically control boiler slagging/fouling. This optimization process targeted reduction of NOx of 30%, improved efficiency of 2% and a reduction in opacity of 5%. The neural network system proved to be a non-invasive system which can readily be adapted to virtually any utility boiler. Specific conclusions from this neural network application are listed below. These conclusions should be used in conjunction with the specific details provided in the technical discussions of this report to develop a thorough understanding of the process.
- Research Organization:
- Tampa Electric Company
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- FC26-02NT41425
- OSTI ID:
- 883335
- Country of Publication:
- United States
- Language:
- English
Similar Records
Tampa Electric Neural Network Sootblowing
Tampa Electric Neural Network Sootblowing