A dynamic modular neural network (DMNN) for NOx emission prediction in MSWI process is provided. First, the input variables are smoothed and normalized. Then, a feature extraction method based on principal component analysis (PCA) was designed to realize the dynamic division of complex conditions, and the prediction task to be processed was decomposed into sub-tasks under different conditions. In addition, aiming each sub-tasks, a long short-term memory (LSTM)-based sub-network is constructed to achieve accurate prediction of NOx emissions under various working conditions. Finally, a cooperative strategy is used to integrate the output of the sub-networks, further improving the accuracy of prediction model. Finally, merits of the proposed DMNN are confirmed on a benchmark and real industrial data of a municipal solid waste incineration (MSWI) process. The problem that the NOx emission of MSWI process is difficult to be accurately predicted due to the sensor limitation is effectively solved.

A steam flare is provided that injects steam, unmixed with air into a waste gas stream at locations where the resulting accelerated steam and waste gas mixture upon exposure to the surrounding air induces a mixture of steam, waste gas and air with improved combustion and effectively complete destruction of the waste gas, and where under low-flow conditions, reduced steam and/or assist gas are required to maintain smokeless operation. The steam is injected via multiple tubes each controlled independently so that steam can normally be flowed via a first tube, and then, when operation loads require, flowed via a second tube. The first and second tubes may be concentric and may be in communication with steam supplies that have different pressures of steam.

Systems and methods for monitoring emissions of a combusted gas are provided. The method includes determining a first net heating value of a flare gas. The method also includes determining a second net heating value of a combustion gas including the flare gas. The second net heating value can be determined based upon the first net heating value and a volumetric flow rate of the flare gas. Based upon the value of the second net heating value, an empirical model or a non-parametric machine learning model can be selected. A combustion efficiency of the combustion gas can be determined using the selected model, the second net heating value, and selected ones of the process conditions and the environmental conditions. Total emissions of the combustion mixture can be further determined from the combustion efficiency and a volumetric flow rate of the combustion gas.

According to an embodiment, a monitoring device, comprising: a sensor for sensing inflow gas information including a component and a concentration of an inflow gas introduced into a regenerative thermal oxidizer (RTO); and a processor for determining residual gas information including a component and a concentration of a residual gas in the RTO by using the inflow gas information, and updating an inflow amount per unit time of the inflow gas according to a risk level of the RTO determined based on the residual gas information, is provided.

Disclosed are novel engineered fuel feed stocks, feed stocks produced by the described processes, methods of making the fuel feed stocks, methods of producing energy from the fuel feed stocks. Components derived from processed MSW waste streams can be used to make such feed stocks which are substantially free of glass, metals, grit and noncombustibles and contain a sorbent. These feed stocks are useful for a variety of purposes including as gasification and combustion fuels. In addition, one or more sorbents can be added to the feed stocks in order to reduce the amount of a variety of pollutants present in traditional fuel and feed stocks, including, but not limited, sulfur and chlorine. Further, these feed stocks with added sorbent can mitigate corrosion, improve fuel conversion, extend power generating plant lifetime, reduce ash slagging, and reduced operating temperature.

Disclosed are novel engineered fuel feed stocks, feed stocks produced by the described processes, methods of making the fuel feed stocks, methods of producing energy from the fuel feed stocks. Components derived from processed MSW waste streams can be used to make such feed stocks which are substantially free of glass, metals, grit and noncombustibles and contain a sorbent. These feed stocks are useful for a variety of purposes including as gasification and combustion fuels. In addition, one or more sorbents can be added to the feed stocks in order to reduce the amount of a variety of pollutants present in traditional fuel and feed stocks, including, but not limited, sulfur and chlorine. Further, these feed stocks with added sorbent can mitigate corrosion, improve fuel conversion, extend power generating plant lifetime, reduce ash slagging, and reduced operating temperature.

A method and system for the conversion of waste into energy in a sealed system where combustion does not take place and the operating pressure prior to the inlet of the steam or power generating equipment is maintained below atmospheric pressure. Destruction of the RDF (refuse derived fuel) is accomplished by subjecting the RDF to a high temperature environment under controlled conditions in a purpose designed and built reactor. The high temperature environment, <5000 C., is achieved through the use of one or more non-transferred plasma torches for generation of plasma gas. The plasma gas exiting the torch and provides the thermal energy for the continual gasification of metallurgic coke configured as a carbon bed in the lower part of the reactor, which acts as a thermal catalyst and this provides the thermal energy for the gasification process.

A thermal reactor for producing usable heat energy by destroying waste including a vessel wherein organic waste upon entering said vessel gasifies as it falls onto a carbon bed and is transformed into a synthesis gas with high heat and kinetic energy that can be harnessed to produce electricity. Inorganic waste upon entering melts as it falls onto the carbon bed and exits via slag ports to form an inert slag. Because there is no oxygen present in the gasification zone, the waste is not combusted and neither furan or dioxin are formed. The waste includes either prepared refuse derived fuel (RDF) or unprepared raw waste or a combination thereof.

In a method for physical and thermochemical treatment of biomass, the biomass moisture content is reduced in a dryer and ammonia (NH.sub.3) is also released from the biomass during drying. The dried biomass is then either pyrolyzed in a pyrolysis reactor and the pyrolysis gas is forwarded to and combusted in a combustion device to form flue gas, or is combusted in a combustion facility unit to form flue gas. In either case the flue gas is fed to a mixer. Oxygen (O.sub.2) is metered to the flue gas in the mixer and is fed directly to the dryer as drying gas. As the drying gas passes through the dryer, the sulfur dioxide (SO.sub.2) contained in the drying gas and/or the sulfur trioxide (SO.sub.3) chemically reacts with the ammonia (NH.sub.3) to form ammonium sulfite ((NH.sub.4).sub.2SO.sub.3) and/or ammonium sulfate ((NH.sub.4).sub.2SO.sub.4). Also a treatment facility physically and thermochemically treats the biomass.