Mercury Emission Control via Neural Network Setpoint Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional steam generating units face challenges in effectively reducing mercury emissions, particularly elemental mercury, due to the limitations of existing air pollution control equipment, which often require costly sorbent injection and can contaminate fly ash, leading to increased operational costs and unsalable fly ash.
Innovation Solution
A predictive model and control system using artificial intelligence and advanced control techniques to optimize mercury emissions, incorporating a neural network-based dynamic model that updates setpoints for manipulated variables to maximize mercury oxidation while maintaining carbon in ash limits, thereby reducing elemental and total mercury emissions efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-generated harmful factors
If sorbent injection is used to reduce mercury emissions, then mercury removal efficiency is improved, but operational costs increase and fly ash becomes contaminated
Solution Approach 1:
The patent uses an intermediary substance (sorbent material such as activated carbon or halogenated compounds) injected into the flue gas stream to facilitate mercury removal. This intermediary mediates between the harmful mercury emissions and the fly ash, allowing mercury to be captured without permanently contaminating the fly ash, thereby resolving the contradiction between emission reduction and fly ash usability
Solution Approach 2:
The patent changes the chemical parameters of the flue gas by injecting sorbent materials that alter the speciation of mercury, converting elemental mercury to oxidized forms that are more easily captured. This parameter change enables effective mercury removal while the sorbent materials are designed to minimize fly ash contamination, thus resolving the technical contradiction
2Object-generated harmful factors
If sorbent injection is used to reduce mercury emissions, then mercury removal efficiency is improved, but operational costs increase
Solution Approach 1:
The patent employs relatively inexpensive sorbent materials such as activated carbon or halogenated compounds that can be injected in controlled amounts into the flue gas stream. These materials serve their purpose of capturing mercury and then are disposed of with the fly ash, providing a cost-effective solution for mercury removal without requiring expensive continuous operation or regeneration systems
Solution Approach 2:
The patent optimizes the dosage and injection timing of sorbent materials to achieve effective mercury removal at minimum operational cost. By carefully controlling the amount of sorbent injected and the conditions under which it reacts with mercury, the system achieves cost-effective emission control
3Object-generated harmful factors
If conventional APC equipment is used for mercury removal, then some mercury is removed, but elemental mercury removal is insufficient
Solution Approach 1:
The patent fundamentally changes the chemical parameter of mercury speciation in the flue gas by injecting sorbent materials that oxidize elemental mercury to oxidized mercury forms. This parameter change transforms the mercury from a difficult-to-capture elemental form to an easily captureable oxidized form, thereby significantly improving removal effectiveness while working within existing APC equipment
Solution Approach 2:
The injected sorbent materials act as intermediaries that facilitate the oxidation and capture of elemental mercury. These intermediaries enable the existing APC equipment to effectively remove mercury by first transforming the mercury into a more captureable form, thereby resolving the insufficiency of conventional equipment for elemental mercury removal
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system provides a cost-effective and efficient mercury emission control method that does not contaminate fly ash, avoiding corrosion and ensuring the fly ash remains usable, while effectively reducing mercury emissions from coal-fired steam generating units.
Implementation Method 1
A predictive model and control system using artificial intelligence and advanced control techniques to optimize mercury emissions, incorporating a neural network-based dynamic model
Implementation Method 2
updates setpoints for manipulated variables to maximize mercury oxidation while maintaining carbon in ash limits, thereby reducing elemental and total mercury emissions efficiently
Data Source
AI summary
A method and apparatus for estimating and/or controlling mercury emissions in a steam generating unit. A model of the steam generating unit is used to predict mercury emissions. In one embodiment of the invention, the model is a neural network (NN) model. An optimizer may be used in connection with the model to determine optimal setpoint values for manipulated variables associated with operation of the steam generating unit.