An Intelligent Emissions Controller for Fuel Lean Gas Reburn in Coal-Fired Power Plants

ABSTRACT

The application of artificial intelligence techniques for performance optimization of the fuel lean gas reburn (FLGR) system is investigated. A multilayer, feedforward artificial neural network is applied to model static nonlinear relationships between the distribution of injected natural gas into the upper region of the furnace of a coal-fired boiler and the corresponding oxides of nitrogen (NO_x) emissions exiting the furnace. Based on this model, optimal distributions of injected gas are determined such that the largest NO_x reduction is achieved for each value of total injected gas. This optimization is accomplished through the development of a new optimization method based on neural networks. This new optimal control algorithm, which can be used as an alternative generic tool for solving multidimensional nonlinear constrained optimization problems, is described and its results are successfully validated against an off-the-shelf tool for solving mathematical programming problems. Encouraging results obtained using plant data from one of Commonwealth Edison's coal-fired electric power plants demonstrate the feasibility of the overall approach.

Preliminary results show that the use of this intelligent controller will also enable the determination of the most cost-effective operating conditions of the FLGR system by considering, along with the optimal distribution of the injected gas, the cost differential between natural gas and coal and the open-market price of NO_x emission credits. Further study, however, is necessary, including the construction of a more comprehensive database, needed to develop high-fidelity process models and to add carbon monoxide (CO) emissions to the model of the gas reburn system.     

An intelligent emissions controller for fuel lean gas reburn in coal-fired power plants

The application of artificial intelligence techniques for performance optimization of the fuel lean gas reburn (FLGR) system is investigated. A multilayer, feedforward artificial neural network is applied to model static nonlinear relationships between the distribution of injected natural gas into the upper region of the furnace of a coal-fired boiler and the corresponding oxides of nitrogen (NOx) emissions exiting the furnace. Based on this model, optimal distributions of injected gas are determined such that the largest NOx reduction is achieved for each value of total injected gas. This optimization is accomplished through the development of a new optimization method based on neural networks. This new optimal control algorithm, which can be used as an alternative generic tool for solving multidimensional nonlinear constrained optimization problems, is described and its results are successfully validated against an off-the-shelf tool for solving mathematical programming problems. Encouraging results obtained using plant data from one of Commonwealth Edison's coal-fired electric power plants demonstrate the feasibility of the overall approach. Preliminary results show that the use of this intelligent controller will also enable the determination of the most cost-effective operating conditions of the FLGR system by considering, along with the optimal distribution of the injected gas, the cost differential between natural gas and coal and the open-market price of NOx emission credits. Further study, however, is necessary, including the construction of a more comprehensive database, needed to develop high-fidelity process models and to add carbon monoxide (CO) emissions to the model of the gas reburn system.     

Factor analysis of submicron particle size distributions near a major United States-Canada trade bridge

A factor analytic model has been applied to resolve and apportion particles based on submicron particle size distributions downwind of a United States-Canada bridge in Buffalo, NY. The sites chosen for this study were located at gradually increasing distances downwind of the bridge complex. Seven independent factors were resolved, including four factors that were common to all of the five sites considered. The common factors were generally characterized by the existence of two or more number and surface area modes. The seven factors resolved were identified as follows: fresh tail-pipe diesel exhaust, local/street diesel traffic, aged/evolved diesel particles, spark-ignition gasoline emissions, background urban emissions, heavy-duty diesel agglomerates, and secondary/transported material. Submicron (<0.5 microm) and ultrafine (<0.1 microm) particle emissions downwind of the bridge were dominated by commercial diesel truck emissions. Thus, this study obtained size distinction between fresh versus aged vehicle exhaust and spark-ignition versus diesel emissions based on the measured high time-resolution particle number concentrations. Because this study mainly used particles <300 nm in diameter, some sources that would usually exhibit number modes >100 nm were not resolved. Also, the resolved profiles suggested that the major number mode for fresh tailpipe diesel exhaust might exist below the detection limit of the spectrometer used. The average particle number contributions from the resolved factors were highest closest to the bridge.     

The potential of pathogens for pest control

A large number of viruses, bacteria, fungi and protozoa can kill or incapacitate insects. Some of these have the potential for a significant role in the management and regulation of pest species of insects, either as naturally occurring entomopathogens or as applied or introduced insecticidal agents. The usefulness of entomopathogens, especially the feasibility of development as microbial insecticides, is examined by consideration of their effectiveness, safety and specificity, production and propagation, and marketability and profitability. Effectiveness, a major consideration in assessing potential, is influenced by several factors including efficacy, dissemination, persistence, compatibility with other regulatory agents, and establishment in the host population, and by factors such as humidity, temperature, chemicals, and formulation, that directly influence the activity of the pathogen.     

Identification and Control of NOx Emissions Using Neural Networks

ABSTRACT

We investigate the application of two classes of artificial neural networks for the identification and control of discrete-time nonlinear dynamical systems. A fully connected recurrent network is used for process identification, and a multilayer feedforward network is used for process control. The two neural networks are arranged in series for closed-loop control of oxides of nitrogen (NO_x) emissions of a simplified representation of a dynamical system. Plant data from one of Commonwealth Edison's coal-fired power plants are used for testing the approach, with initial results indicating that the method is feasible. However, further work is required to determine whether the method remains feasible as the number of state variables and control variables are increased.