Sinter Production Research Articles

Intelligent Optimization and Impact Analysis of Energy Efficiency and Carbon Reduction in the High-Temperature Sintered Ore Production Process

The coordinated optimization of energy conservation, efficiency improvement, and pollution reduction in the sintering production process is vital for the efficient and sustainable development of the sintering department. However, previous studies have shown shortcomings in the multi-objective collaborative optimization of sintering systems and the quantification of pollutant impacts. To address these, this paper proposes a multi-objective optimization method integrated with the NSGA-III algorithm and establishes an integrated system optimization model for sintered ore production and high-temperature waste heat recovery. The results demonstrate significant improvements: energy utilization efficiency increased by 0.67%, energy consumption decreased by 17.3 MJ/t, production costs were reduced by 11.45 CNY/t, and the emissions of CO2, SO2, and NOx were reduced by 0.464 kg/t, 0.034 kg/t, and 0.008 kg/t, respectively. Additionally, the study identified optimal configuration parameters and analyzed the quantitative impact of several key factors on multiple indicators. The results also show that reducing the water content of the mixture, decreasing the middling coal content in the fuel, and increasing the thickness of the material layer are effective strategies to reduce energy consumption and pollutant emissions in the sintering process. Overall, implementing these optimizations can bring significant economic and environmental benefits to the steel industry.

Sintering Behavior of Molybdenite Concentrate During Oxidation Roasting Process in Air Atmosphere: Influences of Roasting Temperature and K Content

Sintering is a common phenomenon, which often takes place during the oxidation roasting process of molybdenite concentrate in multiple-hearth furnaces. The occurrence of sintering phenomena has detrimental effects on the product quality and the service life of the furnace. In this work, the influence of two key factors (roasting temperature and K content) on the sintering behavior is investigated using molybdenite concentrate as the raw material. Different technologies such as XRD, FESEM-EDS, and phase diagrams are adopted to analyze the experimental data. The results show that the higher the roasting temperature is, the greater the mass loss and the more serious the sintering degree will be. The results also show that with the increase in K content, the mass loss of the raw material is first increased and then decreased, while its sintering degree is still gradually increased. The sintering products obtained during the oxidation roasting process are often tightly combined with the bottom of the used crucible with a smooth and dense surface structure, while their internal microstructures are very complicated, which not only includes numerous MoO3 species, but also unoxidized MoS2, Mo sub-oxide, SiO2, and a variety of molybdates. Among them, both MoO3 and molybdates can be easily dissolved into the ammonia solution, leading to a residue mainly composed of SiO2 and CaMoO4. This study also finds that the sintering phenomenon is caused by the increase in local temperature and the formation of various low-melting-point eutectics. It is suggested that decreasing the roasting temperature and K content, especially the K content, are effective methods for reducing the sintering degree of molybdenite concentrate during the oxidation roasting process.

Structural Characteristics of Active Quicklime Flux and Optimization of Quasiparticle Granulation Performance in Thick‐Bed Sintering

The deterioration of sintering bed permeability is an important factor that hinders thick‐bed sintering. Flux is one of the key factors that determines the bonding degree of quasiparticles. Selecting high‐quality flux is an effective way to improve both the permeability and thickness of the sintering bed. Herein, the hydration activity of quicklime flux is used as a criterion to assess quality. Two types of quicklimes with different activity levels are selected for comparative analysis in three aspects: microstructure, sinter quasiparticle granulation performance, and the sinter mineralization process. The experimental results show that active quicklime has a higher CaO content and fewer impurities. The small and dense CaO particles give active quicklime significant advantages in raw material granulation and sinter mineral formation. The application of active quicklime can effectively improve the permeability of the sintering bed; notably, the drying fines’ removal rate decreases from 22.81% to 2.42% with an increase in the ratio of active quicklime addition. However, this affects the average particle size of quasiparticles. To address this issue, solutions are determined by adjusting the condition parameters. It is concluded that active quicklime plays an important role in enhancing the permeability of the sintering bed during thick‐bed sintering production.

Method of obtaining and possibility of using of new complex fertilizers from flotation sludge – potassium-magnesium ore processing wastes

The results of research on properties of cinders obtained by high-temperature roasting of clay-salt waste (sludge) after processing K-Mg ores are presented. Cinders are used as complex fertilizers, ameliorant components and microelement fertilizers. Secondary wastes, after extraction of Pd, Pt, Ag from burnt sludge (cinder), consist of sludge after deslagging of crushed cinder and “tails” after sand enrichment. Mixing these products, moistening, granulating and sintering forms result in a sintering product (CP) that is ready for application as complex fertilizer, ameliorating additive and microfertilizer. A study of the chemical composition and composition of impurities of cinders and CP was carried out. The identity of the composition of cinders and CP has been established. Tests with cinders and CP as a complex of fertilizers, ameliorants and microfertilizers were carried out. The research was carried out on the experimental field of Perm Agricultural Research Institute, on sod-podzolic heavy loamy soil formed on the deluvium of Permian clays, this soil represents up to 70% of the arable lands of the Perm region, the studied crop was potato. The yield of potato when applying cinder as an ameliorant additive was higher by 6.05 t/ha compared to the control (the use of traditional fertilizers provided an increase of 3.56 t/ha). For the first time determination of chemical composition including trace elements studies was fulfilled in potato tubers from unfertilized variants, plots fertilized with traditional fertilizers and plots fertilized with cinders. Two components of tubers – peel and pulp – were analyzed using a mass spectral method, with decomposition in a closed system (autoclave). Most of the elements were characterized by a higher content in the peel (almost an order of magnitude) compared to the pulp. An inverse relationship was observed for P and S, their content was higher in pulp than in peel. In the variant with the use of cinder, a higher content of microelements, especially rare-earths elements, was observed compared to the control. A method for processing sludge to extract Pd, Pt, Ag, results in secondary wastes, that can be used as complex slow-release fertilizers, ameliorating additives and microelement-containing fertilizers.

Prediction of SO2, NOx and PM in the sintering process based on deep learning

The accurate prediction of SO2, NOx and PM emissions in the iron ore sintering process could adjust the desulfurization and denitrification operation in time. The study presented an integrated prediction model for SO2, NOx and PM in sintering flue gas. Gradient boosting decision tree, recurrent neural network, gated recurrent unit were chosen as sub-models to predict SO2, NOx and PM by comparing different regression prediction models, which were then combined to form an integrated prediction model (MMEP). The box plots, empirical mode decomposition algorithm, Pearson correlation coefficient and maximum information coefficient to select independent variables for the predictive model. The MMEP model had an overall accuracy greater than 0.82, as verified by production data, which could provide guidance for on-site sintering production.

Calcined colemanite as an additive for iron ore sintering process

During sintering process, iron ores, fluxes and coke are agglomerated into a desirable blast furnace feed. The degrading iron ore quality and environmental norms has forced sinter producers to look for additives which can improve the sintering process efficiency. For the current work, use of calcined colemanite as an additive was studied by adding it from 0% to 4% within the sinter raw blend through lab-scale pot trials. During the sintering process, calcined colemanite forms a Calcium Borosilicate (Ca11B2Si4O22) phase at temperature above 400 °C which latter gets dissociated within the liquid melt thus increasing the liquid slag formation. Increasing calcined colemanite up to 2% increases tumbler index from 56.27% to 61.67%, decreasing thereafter to 55.33% at 4% of calcined colemanite. The sinter yield (+5 mm) is also found to be maximum of 89.39% at 2% of calcined colemanite. An increase in calcined colemanite from 0% to 4% increases sintering time from 20 to 26 min, decreasing the overall sinter productivity from 2.35 to 1.99 t/m2/h. Before integrating calcined colemanite within the sintering process at plant scale, its cost and efficacy must be considered. An alternate approach can be combining it with an organic binder where the two can complement each other in providing the required sinter properties.

Reduction of carbon emission in iron sintering process based on hot air sintering technology

Reducing carbon dioxide (CO2) emissions in the iron and steel industry plays a crucial role in addressing global climate change. One significant technological solution for reducing CO2 emissions in iron and steel production is the recycling of waste heat. Hot air sintering has the potential to decrease CO2 emissions from flue gas by reusing hot flue gas in the production process. This can result in a reduction in the consumption of fossil fuels. Usually, the relationship between the hot air temperature and the carbon content determines the CO2 emission reduction effect. In order to meet the demand for reducing CO2 emissions, this paper thoroughly investigates the mechanism of CO2 reduction by hot air sintering through sintering pot experiments. It precisely establishes the correlation between hot air temperature and carbon content, and suggests strategies for effectively managing hot air sintering based on scientific principles. The results show that hot air sintering achieves a reduction in CO2 emissions by enhancing fuel combustion heat utilization and heat substitution. On the one hand, the heat of the sinter bed surface layer is increased, which improves the mineralization conditions and increases the sintered mineral quantity and quality, thus reducing the CO2 emission by 4.4%; on the other hand, the waste heat is returned to the sinter bed to replace part of the fuel combustion heat, thus reducing the CO2 emission by 17.7%. The experimental results show that the best carbon reduction effect is achieved at a hot air temperature of 300 °C and a solid fuel ratio of 4.7% (labelled T300-C47), which reduces carbon emissions by 17.7% and improves the quality of the sintered minerals. Combined with the actual production, in the range of 200–300 °C hot air, by increasing the hot air temperature to replace the solid fuel with equal heat can realize the hot air sintering to reduce CO2 emissions and improve the sintering production. The research provides theoretical guidance for the clean production of iron and steel sintering and energy saving and carbon reduction.

Application of coalbed methane assisted iron ore sintering: Injection effect, pollutant abatement and economic evaluation

Hydrogen-rich gas injection, which has garnered widespread attention from academia and industry, is an effective method for reducing CO2 emissions during the sintering process and for improving sinter quality. Coalbed methane (CBM) is a cost-effective and reliable hydrogen-rich gas resource in China. In this study, we investigated the injection effect of CBM in assisting iron ore sintering. Additionally, we determined the appropriate injection parameters by systematic sintering pot tests and compared it with coke oven gas (COG). The impacts of CBM injection on pollutant abatement and combustion efficiency were analyzed based on the variations in the sintering flue gas composition, and a comprehensive economic evaluation was conducted. The results showed that injecting 0.51 vol% CBM between 5 and 13 min after ignition with 0.3 wt% coke breeze ratio reduction could significantly improve the sintering index and the uniformity of heat distribution within the sinter bed. Excessive injection would affect the bed permeability. CBM took advantage over COG at a gas–solid heat transfer ratio of 1:1.28. The four-stage cascade mode with a gradient of 0.18 vol% and the intermittent mode with an intermittent time of 0.5 min could optimize the injection effect. However, the cascade mode performed better. Besides, injecting CBM increased the emission reduction rates of CO and NOx and improved combustion efficiency by 5.72%, 4.47%, and 1.46%, respectively. Overall, the cost-savings were CNY 2.19 per ton sinter, and the annual production cost could be reduced by approximately CNY 6.71 million for a 265 m2 sintering machine. The profits achieved because of CBM injection can be further improved by increasing the bed permeability and mixed injecting with other gas media. This study provides an effective path for green transformation of sintering production.

Characterisation of iron ore sinter products with varying binary basicity (CaO/SiO2) from 1.5 to 2.7

Characterisation of iron ore sinter products with varying binary basicity (CaO/SiO₂) from 1.5 to 2.7

Исследование железоматричных композитов с карбидным упрочнением, полученных спеканием механоактивированных смесей титанидов железа с углеродом

Introduction. The addition of dispersed solid particles of refractory compounds (carbides, borides, silicides) to the structure of alloy is a widely used effective way to increase the wear resistance of steels and alloys. Composites with a matrix of iron-based alloys (steel and cast iron) strengthened by titanium carbide particles are of great practical interest. The main structural characteristics, which define hardness and wear resistance of the composites, are volume fraction, dispersion and morphology of the particles of the strengthening carbide phase. The structure of composites depends on the method of its preparation. The methods of powder metallurgy combined with preliminary mechanical activation of powder mixtures have become widespread. It is previously established that in mechanically activated powder mixtures of FTi35S5 ferrotitanium, consisting of 82 % of (Fe,Al)2Ti phase, and P-803 carbon black, a reaction occurs with the formation of a composite consisting of a steel binder and titanium carbide. The synthesis reaction of carbides occurs in a solid-phase mode at combustion’s temperatures of 900–950 °C. Therefore, there is no coarsening of the structure due to the growth of carbide particles, which is typical for reactions in the presence of a liquid phase. FTi35S5 alloy contains a plenty of impurities (silicon, aluminum and etc). The purpose of the work is to investigate the phase composition and structure of the products of the interaction of Fe2Ti and FeTi iron titanides with carbon under the conditions of reaction sintering of mechanically activated powder mixtures and to determine the possibility of synthesizing iron-matrix composites strengthened with submicron titanium carbide particles. Research methods. The structure and phase composition of sintered compacts from mechanically activated powders were studied by optical metallography, X-ray diffraction (XRD) and scanning electron microscopy (SEM) using determination of the elemental composition by energy-dispersive X-ray spectroscopy (EDX). Experimental technique. The reaction mixtures were prepared using intermetallic powders obtained by vacuum sintering of compacts from iron and titanium powder mixtures of 2Fe+Ti and Fe+Ti compositions. Carbon black was added to the intermetallic powders to convert all the titanium containing in the intermetallic compounds into carbide. The titanides – carbon black mixtures were processed by an Activator 2S planetary ball mill for 10 min milling time at a rotation speed of 755 rpm (40g). The mechanically activated mixtures were cold compacted into cylindrical samples with a diameter of 20 mm, which were sintered in vacuum at а temperature of 1,200 °C and an isothermal holding time of 60 minutes. Results and discussion. According to the results of X-ray diffraction analysis, almost all titanium contained in iron titanides reacts with carbon to form carbide and reduced iron. The sintering products of compacts of both compositions contain target phases: titanium carbide with a slight shift from the equiatomic ratio and α-iron, which has the lattice parameters close to the reference data, and also a few of other phases. The titanium carbide particles in the iron binder were identified on the back-scattered electron (BSE) images due to the tonal contrast: the heavy iron appears darker against the carbide, which is composed of lighter elements. According to EDX analysis, the relative content of titanium and carbon in the carbide particles indeed corresponds to the composition of non-stoichiometric titanium carbide. Conclusion. The composites including titanium carbide and α-iron binder were obtained by sintering of iron titanides and carbon (carbon black) mechanically activated powder mixtures. The granules of composite powders obtained by crushing of sintered compacts are of interest as feedstocks for wear-resistant coatings and additive technologies, as well as for manufacturing of dense materials by other compaction methods: spark plasma sintering (SPS) or hot pressing (HP).

Batch Sintering of FeO·OH and Fe2O3 Blends: Chemical and Metallurgical Characterization

A sample of goethite iron ore sinter feed (G_SF) was employed as a raw material in a sintering bed. This sample partially replaced hematite sinter feed (H_SF), which is currently used as raw material in a sintering plant in the state of Minas Gerais, Brazil. This substitution did not adversely affect the chemical and metallurgical proprieties of the sinter mix product, provided that the utilization of G_SF was kept below 30% in weight. Despite the higher proportion of fines in G_SF, the presence of argillaceous minerals in the sample led to an improvement in the granulation index (GI) of the sinter mix product. The GI value increased from 68.4 to 82.7% for the experiments conducted without the presence of goethite ore and with 40% of goethite ore in the sintering mix, respectively. Consequently, the qualities of both the process and the produced sinter product were not compromised. The raw materials and the various sinters produced were characterized through X-ray fluorescence (XRF) and X-ray diffraction (XRD), as well as thermal gravimetric analysis (TGA). The XRD results were used to perform a quantitative assessment of the mineral phase using the Rietveld method (RM). This technique allowed for the determination of goethite content in the studied sample, which was 35.5%. Finally, the incorporation of G_SF in the sintering bed led to a 20% reduction in the cost of raw materials.

Application of the Fuller–Thompson equation in sinter blend design to increase sinter productivity

Sintering is an important phase of the iron-making chain, as it allows the usage of finer iron ore particles in the blast furnace whilst still maintaining furnace performance. An on-going challenge for sinter plants is to obtain higher productivity from their sinter blends, or maintain sinter productivity whilst using more financially attractive iron ores. One of the most effective means to reduced blend cost is to use a higher proportion of concentrated iron ores in the blend. The key characteristic of concentrated ores is that they have a finer particle size distribution (PSD) than traditional sinter feeds and are widely known to negatively impact sinter bed permeability and sinter productivity. In this study, various iron ore blends were used to demonstrate the effect that the PSD of the sinter blend has on granulation and subsequent sintering process parameters during laboratory-scale sintering. Particular focus was applied to the impact of the PSD of the layering material in blend (−0.5 mm). Cold bed superficial gas velocity (SGV) was correlated to the spread of the PSD within the layers around granule nuclei. Widening the PSD spread within the layer increased cold SGV due to a narrowing in the spread of the granule size distribution (GSD) and increase in mean granule diameter. The Fuller–Thompson (FT) blend exhibited increased SGV during sintering (hot SGV) which led to shorter sintering times. This was a result of an enhanced ‘hot SGV efficiency’ (a measure for the ratio of hot SGV to cold SGV) over what was anticipated based on the trend with mean granule diameter. Complete industrial blends were compared with blends designed to the FT equation at varying proportions of layering particles in the blends (−0.5 mm). At equal proportions of layering particles in the blends, the FT blends exhibited increased cold and hot SGV by up to 20% and 25%, respectively, and led to a maximum 10% decrease in sintering time. Further, blends designed to the FT equation enabled the incorporation of 4 wt-% more layering particles and still exhibited similar cold SGV, hot SGV and sintering times to the industrial blends.

Advancing into Millimeter Wavelengths for IoT: Multibeam Modified Planar Luneburg Lens Antenna with Porous Plastic Material

This paper introduces an innovative antenna design utilizing a cylindrical dielectric Luneburg lens tailored for 60 GHz Internet of Things (IoT) applications. To optimize V-band communications, the permittivity of the dielectric medium is strategically adjusted by precisely manipulating the physical porosity. In IoT scenarios, employing a microstrip dipole antenna with an emission pattern resembling cos10 enhances beam illumination within the waveguide, thereby improving communication and sensing capabilities. The refractive index gradient of the Luneburg lens is modified by manipulating the material’s porosity using air holes, prioritizing signal accuracy and reliability. Fabricated with polyimide using 3D printing, the proposed antenna features a slim profile ideal for IoT applications with space constraints, such as smart homes and unmanned aerial vehicles. Its innovative design is underscored by selective laser sintering (SLS), offering scalable and cost-effective production. Measured results demonstrate the antenna’s exceptional performance, surpassing IoT deployment standards. This pioneering approach to designing multibeam Luneburg lens antennas, leveraging 3D printing’s porosity control for millimeter-wave applications, represents a significant advancement in antenna technology with scanning ability between −67 and 67 degrees. It paves the way for enhanced IoT infrastructure characterized by advanced sensing capabilities and improved connectivity.

Changes in Microscale Liquid Formation in Lump and Sinter Mixed Burden Softening and Melting Tests with the Addition of Hydrogen

With the movement toward hydrogen-enriched blast furnace operation to lower greenhouse gas emissions, ferrous burden design must be reconsidered to optimize furnace permeability. Increasing the ratio of direct charge lump ore in the ferrous burden also presents an opportunity to lessen the emissions associated with the production of sinter and pellets. Under traditional blast furnace conditions, lump ore usage is improved by mixing it with the sinter in the burden to promote their favorable high-temperature interactions (both chemical and physical). As such, mechanistic changes to the interaction must be understood to optimize burden design, including for future operations with hydrogen addition. In this study, liquid formation in both the metallic and oxide components of ferrous burdens is microscopically investigated. Oxide liquid and solid phase stability at the interfaces of dissimilar burdens are visualized using a novel mapping technique, and metallic iron is etched to reveal microstructures indicative of carbon. Results indicate that the inclusion of hydrogen promotes the gas carburization of metallic iron in sinter, but not lump. It was concluded that mixed burden softening and melting performance with hydrogen addition were improved through the addition of lump in two ways: the highly metallic lump particles provide structural support for the collapsing sinter bed and also suppress the formation of early liquid slag from the sinter.Graphical

PENGUJIAN KEAUSAN ALUMUNIUM MATRIX KOMPOSIT DIPERKUAT DENGAN KARBON NANOTUBE

Wear testing of engineering materials is an important aspect in evaluating their performance and durability. This study aims to investigate the wear-resistant ability of aluminum composites reinforced with carbon nanotubes (CNTs). The composite manufacturing process was carried out by infiltrating CNTs into the aluminum matrix through powder metallurgy method. Tests were conducted using two methods, namely pressing and sintering with temperature variations of 0oC (non sintering), 400oC, 500oC, 600oC and 700oC. The results showed that the specific wear value on the specimen obtained the best value at a sintering temperature of 400oC with a value of 0.003632850 mm3/kg.m and the highest value at a sintering temperature of 700oC with a value of 0.042771207 mm3/kg.m. And the wear rate on the specimen obtained the best value at a sintering temperature of 400oC with a value of 0.447887285 mm3/s and the highest value at a sintering temperature of 700oC with a value of 1.155387594 mm3/s. This shows that the addition of temperatures greater than 400oC has a major influence on the specific wear value and wear rate of sintering products. In addition, this method is also a reference for further researchers in developing aluminum carbon nanotube technology to obtain optimal results.

An integrated approach to improve the quality of solid fuel in sintering production by improving the DChG 900.700 four-roll crusher

An integrated approach to improve the quality of solid fuel in sintering production by improving the DChG 900.700 four-roll crusher

Relevance vector machine with hybrid kernel-based soft sensor via data augmentation for incomplete output data in sintering process

A ratio of CO and CO2 (CO/CO2) is a key indicator of sintering carbon consumption, which is difficult to be determined in real-time. Therefore, the establishment of its soft sensing model is of great practical significance. This paper proposes a novel CO/CO2 soft sensing model with incomplete output data based on relevance vector machine with hybrid kernel via data augmentation. First, a least absolute shrinkage and selection operator is employed for determining key input variables of the model, and an automatic fuzzy clustering framework is used to automatically identify multiple operating modes. Then, a relevance vector machine with hybrid kernel method is presented to model each operating mode separately. Meanwhile, considering the problem of incomplete input and output data, data augmentation is applied in modeling to enhance the model performance. Finally, the soft sensing model of CO/CO2 is formed. Experimental results and analyses using actual production data coming from the sintering production process demonstrate that the prediction performance and accuracy of the proposed model outperform some existing algorithms.

Exploring the use of iron ore and pellet dusts in sinter production: A comprehensive evaluation

Exploring the use of iron ore and pellet dusts in sinter production: A comprehensive evaluation

ПОВЫШЕНИЕ ЭФФЕКТИВНОСТИ ИСПОЛЬЗОВАНИЯ ЭЛЕКТРОЭНЕРГИИ НА ГОРНЫХ ПРЕДПРИТИЯХ

The paper presents the results of a comprehensive energy audit at the nickel plant, one of the structural divisions of MMC Norilsk Nickel. A structural diagram of the plant's power supply is presented, the dynamics of electricity consumption is shown, showing that the main electricity consumption at the enterprise goes to the production of nickel (69% from the sinter and 21% from the Nadezhda Metallurgical Plant). Analysis of the dynamics of changes in electricity consumption for the main technological processes of nickel production from sinter shows a pronounced dependence of changes in the volume of electricity consumption for the production of sinter and smelting in ore-thermal furnaces. An analysis of the operation of electric drives with voltages of 0.4 kV and 6 kV is presented, for which the load parameters of the most powerful motors in the technological shops of the enterprise were recorded. It has been established that in order to increase the efficiency of energy use, as well as to reduce the influence of the electric drive on the load losses of the supply network, it is necessary to consider: the possibility of replacing individual, most unloaded motors with motors of lower power or the use of frequency control of the performance of process equipment...

A novel deep learning method for on-line monitoring of grate bar defects in sintering machine system

The defective grate bars at the bottom of the sintering machine system pose a serious safety risk to steel enterprises. Cracking and missing of these grate bars lead to severe production accidents and economic losses. Implementation of an efficient defect monitoring system plays a crucial role in ensuring continuous and stable sintering production. This paper presents a novel on-line grate bar defects monitoring method to address the following two key challenges. Firstly, a light-weight location model called Multi Scale Separated Convolutional Attention Network-LiteSeg (MSSCAN-LiteSeg) is proposed to identify the optimal shooting position of the moving trolley and simultaneously segment the horizontal and vertical grate bars. By separating the attention calculation into independent channel spaces, MSSCAN-LiteSeg can effectively handle the imbalanced sample distributions. Secondly, an innovative few-shot segmentation network named Response Forgetting Attention-Hypercorrelation Squeeze Network (RFA-HSNet) is proposed for defect detection by employing a "Forgetting-Enhancing-Recalling" method. Extensive experiments have demonstrated that our method can achieve a precision rate of 93.3% and provide a satisfactory performance in the on-line grate bar defects monitoring system.