Modeling mercury speciation in combustion flue gases using support vector machine: prediction and evaluation
Bingtao Zhao1, Zhongxiao Zhang, Jing Jin
1School of Energy and Power Engineering, University of Shanghai for Science and Technology, 516 Jungong Road, Shanghai 200093, China. zhaobingtao@usst.edu.cn
Journal of Hazardous Materials
|September 30, 2009
Summary
This study introduces a Support Vector Machine (SVM) model to accurately predict mercury speciation in coal combustion flue gases. The SVM model outperforms traditional methods, offering a powerful tool for environmental analysis.
Area of Science:
- Environmental Science
- Chemical Engineering
- Computational Chemistry
Background:
- Mercury emissions from coal combustion pose a significant global environmental challenge.
- Understanding mercury speciation (elemental, oxidized, particulate) and concentration in flue gas is crucial for effective control.
- Complex nonlinear relationships exist between coal properties, operating conditions, and mercury emission characteristics.
Purpose of the Study:
- To develop and validate an advanced computational model for simulating mercury speciation and concentration in coal combustion flue gases.
- To compare the performance of the proposed model against conventional Multiple Nonlinear Regression (MNR) and Artificial Neural Network (ANN) models.
- To analyze the correlations between coal properties, operating conditions, and mercury chemical forms using the developed model.
Main Methods:
- Implementation of a Support Vector Machine (SVM) model integrated with a dynamically optimized search technique and cross-validation.
- Training and testing the SVM model using simulation data of mercury speciation and concentration.
- Comparative performance evaluation based on prediction accuracy, generalization capability, mean squared error (MSE), and correlation coefficient (R).
Main Results:
- The SVM model demonstrated superior prediction performance compared to MNR and ANN models.
- Achieved a mean squared error of 0.0095 and a correlation coefficient of 0.9164 for the testing dataset.
- Analysis using the SVM model revealed significant correlations between coal properties, operating conditions, and mercury speciation.
Conclusions:
- Support Vector Machine (SVM) provides a powerful and accurate alternative approach for modeling mercury speciation in coal combustion flue gases.
- The developed SVM model enhances the understanding of factors influencing mercury emissions, aiding in environmental management strategies.
- Accurate simulation of mercury speciation is vital for addressing the global environmental problem of mercury pollution from coal power plants.
Related Concept Videos
01:19Gas Chromatography: Types of Detectors-II
In gas chromatography, different detectors are employed to meet specific analytical needs. These detectors are often categorized based on their detection mechanisms and the types of compounds they are best suited to analyze. Thermal Conductivity Detectors (TCD), Flame Ionization Detectors (FID), and Electron Capture Detectors (ECD) represent common categories, each with unique operating principles and applications. However, beyond these, several other detectors are designed for more specialized...
01:25Atomic Absorption Spectroscopy: Atomization Methods
Atomic Absorption Spectroscopy (AAS) atomizes samples through flame atomization or electrothermal atomization. Flame atomization typically involves a nebulizer and spray chamber assembly to combine the sample with a fuel–oxidant mixture, creating a fine aerosol mist that enters a burner. Typically, the fuel and oxidant are combined in an approximately stoichiometric ratio. However, for atoms that are easily oxidized, a fuel-rich mixture may be more advantageous. Only about 5% of the aerosol...
01:02Flame Photometry: Overview
Flame photometry, also known as flame emission spectrometry, is a technique used for the qualitative and quantitative analysis of elements present in a sample using a flame as the source of excitation energy. The concept of flame photometry was realized in the early 1860s by Kirchhoff and Bunsen, who discovered that specific elements emit characteristic radiation when excited in flames. The first instrument developed for this purpose was used to measure sodium (Na) in plant ash using a Bunsen...
01:16Flame Photometry: Lab
In a flame photometer, when a solution like potassium chloride is aspirated into the flame, the solvent evaporates, leaving behind dehydrated salt. This salt dissociates into free gaseous atoms in their ground state. Some of these atoms absorb energy from the flame, leading to their excitation. The excited atoms return to the ground state, emitting photons at characteristic wavelengths. Because only electronic transitions are involved, the resulting emission lines are very narrow. The intensity...
01:29Atomic Fluorescence Spectroscopy
Atomic fluorescence spectroscopy (AFS) is an analytical technique that involves the electronic transitions of atoms in a flame, furnace, or plasma being excited by electromagnetic (EM) radiation. When these atoms absorb energy, they become excited and subsequently release energy as they return to their original state. This emitted light, or "fluorescence," is observed at a right angle to the incident beam. Both absorption and emission processes transpire at distinct wavelengths, which are...
01:14Gas Chromatography–Mass Spectrometry (GC–MS)
Gas chromatography–mass spectrometry (GC–MS) is the combination of analytical techniques of gas chromatography and mass spectrometry in a single instrument for analyzing a mixture of compounds. The gas chromatograph separates the compounds in the mixture, and the mass spectrometer analyzes each compound separately to determine the molecular masses and molecular structures.
A gas chromatograph consists of a long, narrow capillary column with a polysiloxane coating on the inner wall. The coating...
A gas chromatograph consists of a long, narrow capillary column with a polysiloxane coating on the inner wall. The coating...