Yield Of Pyrolysis Products Research Articles

Effect of moisture content on pyrolysis product yield from lignite and lignite-peanut shell mixtures using slow pyrolysis

ABSTRACT The conversion of biomass-coal mixtures into energy using thermal conversion systems offers a more environmentally sustainable alternative to conventional coal consumption. A reactor with an internal compartment is proposed to improve the pyrolysis performance of lignite coal and mixtures of lignite coal with peanut shells. The study investigates lignite coal with varying moisture contents and peanut shell proportions (0%, 10%, 25%, and 50%) at a temperature of 500°C, using a heating rate of 0.1°C/s. The results indicated that dry mixtures demonstrated higher overall productivity compared to wet mixtures, particularly in terms of charcoal production. The weight of charcoal increased by 4.83%, 4.71%, 4.02%, and 2.61% across the mixtures. The total conversion rates for dry mixtures were 24.59%, 29.27%, 34.36%, and 40.44%, while for wet mixtures, the conversion rates were 29.42%, 33.98%, 38.38%, and 43.05%, respectively. The results revealed that moisture content during pyrolysis significantly influenced the productivity of lignite and lignite-peanut shell mixtures. The conversion rates in dry mixtures were lower compared to those in wet mixtures. The novelty of this work lies in its pioneering investigation of the impact of moisture on the slow pyrolysis of Turkish lignite mixed with peanut shells. It offers novel insights into optimizing the thermal conversion process for these materials by uniquely examining the effects of moisture on productivity and conversion rates.

Upgrading vacuum residue in a supercritical CO2 environment with polypropylene and steam: Insights into products distribution and characterization of liquid products

The pyrolysis of vacuum residue (VR) using polypropylene (PP) under supercritical carbon dioxide (scCO2) conditions represents a novel approach to converting this abundant and difficult-to-process feedstock into lighter liquid products. In this paper, a set of experiments was performed to analyze the impact of scCO2, PP and steam on the yields of pyrolysis products (i.e., liquid, gas and coke) and characteristics of the liquid fractions. The findings indicated notable improvements when scCO2 was used instead of subcritical CO2 in the pyrolysis of VR with PP. These included decreased viscosity and improved API gravity, alongside increased maltene yield and reduced coke yield. Furthermore, the inclusion of PP markedly elevated the quality of the obtained liquid, whereas steam + scCO2 primarily affected the product distribution by raising the yield of coke and gas fractions. VR pyrolysis under scCO2 conditions at 380 °C, 8 MPa, PP/VR ratio of 0.23 for 60 min in a batch system, without the use of catalyst, resulted in the highest liquid yield of 83.7 ± 1.9 wt%, and minimum coke yield of 9.8 ± 1.3 wt%. Under these conditions, the upgraded liquid consisted of 75.2 wt% light and middle distillates with boiling points below 350 °C. Additionally, the proportion of oxygenates in the pyrolysis oil reduced by 60.5 %, improving its heating value. Moreover, adding PP to the upgrading process resulted in a higher proportion of isoparaffins, cycloparaffins, and aromatics, coupled with a decrease in olefins, aligning the liquid specifications more closely with fuel standards.

CO-PROCESSING OF COTTON SOAPSTOCK, COAL DUST AND POLYMER WASTE BY PYROLYSIS METHOD

The work is aimed at solving the problems of rational consumption of secondary raw materials on the basis of carbon-containing waste of industries, saturation of the market with additional products and protection of the environment from the toxic effects of waste. Aim of work: the study of the co-pyrolysis process of gossypol resin (GR) from cotton soapstock of "Shymkentmay" JSC, coal dust (CD) of Kulan deposit and plastics waste (PW) in N2 medium. The methodology of work included the establishment of optimal modes of the process, determination of yield, composition and properties of pyrolysis products. Analysis of pyrolysis products by IR spectroscopy, XRD, chromatomass spectrometry. Study of the component composition of liquid pyrolysis products by the method of extraction separation in Soxhlet apparatus into oils, asphaltenes and resins. Assessment of perspectivity of co- pyrolytic processing of carbon-containing wastes from different industries for industrial development. Results and discussion. The optimum temperature of GR pyrolysis (T=450 ⁰С) was established, at which the yield of liquid product was on average 33.01 wt.%, gas yield – 60.33 wt.%, yield of solid residue – 6.65 wt.%. The co-pyrolysis of GR and CD at 1:1 ratio and T=500 ⁰C in N2 atmosphere was investigated for the first time. A high yield of liquid product – 47.34 wt.%, low gas formation – 2.31 wt.% and a large amount of solid residue – 50.34 wt.% were observed, which is apparently due to the formation of coal semicoke and coke. The process of co- pyrolysis of GR, CD with D=90 μm and PW (PE:HPPP – 1:1) at the ratio of 1:1:1 and temperatures of 500 ⁰С-700 ⁰С in N2 atmosphere was investigated for the first time. It is shown that the main contribution to the formation of liquid products in the given temperature regimes is made by GR and PW. Conclusion. Co-processing of carbon-containing wastes was found to be of interest and practical importance, both in terms of obtaining marketable products and maintaining a safe ecology.

Study on biomass and polymer catalytic co-pyrolysis product characteristics using machine learning and shapley additive explanations (SHAP)

Biomass and polymer catalytic co-pyrolysis can convert waste into higher-quality fuels, thereby reducing the use of fossil fuels to some extent. However, this process is an extremely complex thermochemical conversion, influenced by numerous factors such as feedstock properties, operational variables, and catalyst. Currently, experimental methods require substantial time and resource investment. Machine learning (ML) can fit and match input and output features based on existing data, achieving extremely high accuracy in the co-pyrolysis process. This study applies advanced ML models to study the biomass and polymer catalytic co-pyrolysis process, with a focus on the yield of pyrolysis products and the variations of the oxygen-containing components in the pyrolysis oil. The best-performing model is used for feature analysis of the correlation between inputs and outputs, based on game theory SHAP analysis. The results indicate a significant negative correlation between the polymer addition ratio and the generation of oxygen-containing components during the co-pyrolysis process. The addition of catalysts promotes the generation of pyrolysis gas during co-pyrolysis but suppresses the yield of pyrolysis oil. Additionally, catalysts significantly inhibit the formation of oxygenates in the pyrolysis oil. The XGBR model shows the highest performance in predicting pyrolysis oil yield, achieving R2 values of 0.98 during training phase and 0.91 during testing phase. The GBR model performs well in predicting the oxygenate composition of pyrolysis oil from small datasets.

Research on the co-pyrolysis of biomass and coal

Abstract Co-pyrolysis of biomass and coal has attracted much attention as a potential energy conversion technology. In this paper, the significant effects of n-hexane insoluble substance (INS) on tar, water, and coke residue yields were analyzed in depth using statistical analysis. With INS and mixing ratio as independent variables, multivariate analysis of variance (ANOVA) was used to comprehensively investigate the effects of the interaction between the two on the yields of different pyrolysis products, revealing the significant interaction between different pyrolysis products. The genetic algorithm was used to establish an optimization model to optimize the mixing ratios of the co-pyrolysis, and the considerable differences between the experimental and theoretically calculated values of the product yields of the co-pyrolysis compounds were analyzed by statistical tests, and subgroup analyses were carried out to determine the specific differences under different mixing ratios. CNN prediction model was established, and model optimization confirmed the differences between the experimental and theoretically calculated values for different pyrolytic coupling ratio-specific ratios by data validation and subgroup analysis. The further extension and optimization of the model provide a new theoretical basis and idea for further research on the co-pyrolysis of biomass and coal, which can help to improve the energy conversion efficiency and product quality.

Machine learning-based prediction model for the yield of nitrogen-enriched biomass pyrolysis products: Performance evaluation and interpretability analysis

The process optimization and control of nitrogen-rich biomass pyrolysis technology is crucial. This technology effectively converts agricultural waste into high-value energy products. The aim of this study is to develop an accurate model for predicting the yield of nitrogen-rich biomass pyrolysis products using machine learning techniques. The goal is to improve both the yield and quality of the products. This study uses machine learning techniques to develop an accurate model for predicting the yield of three-phase products from nitrogen-rich biomass pyrolysis. The goal is to optimize the biomass energy conversion process. The study builds a dataset containing 468 samples. This dataset comprehensively characterizes the chemical, elemental, and industrial properties of biomass, as well as the pyrolysis operating parameters. Models with high prediction accuracy are achieved by comparing various machine learning algorithms. These algorithms include Random Forest, GBDT, SVR, and ANN. Fine feature selection and hyper-parameter tuning are used to enhance the performance. In particular, the optimized GBDT model achieves a performance of MSE of 10.04 and R² of 0.92 in cross-validation. SHAP value analysis is used to further interpret the prediction results of the model. Sensitivity analysis, conducted through Monte Carlo simulation, identifies key features that have a high impact on the target value. Additionally, two-feature partial correlation analysis reveals the importance and dependence of the model features. This provides crucial technical support and a scientific basis for the industrial application of biomass energy and the optimization of the pyrolysis process.

Distribution and characterization of products obtained from pyrolysis of cooked food waste- Impact of heating rate

This work offers a comprehensive investigation of the pyrolysis products—liquid, gas, and solid derived from cooked food waste (CFW) at different heating rates (15–100 °C/min). The heating rate significantly influenced the yield of pyrolysis products. The maximum yield of bio-oil (oil + aqueous) was achieved at a heating rate of 50 °C/min, py-gas at 100 °C/min, and biochar at 15 °C/min. The yields were 34 wt% for bio-oil, 30 wt% for py-gas, and 32 wt% for biochar. Analysis of the bio-oil revealed significant proportions of fatty acids (Methyl-methyltetradecanoate) and esters (Oleic acid ethyl ester), constituting 25 %, and 26 % at 15 °C/min but declining with increasing heating rates. Another ester (9-Octadecenoic acid methyl ester) was found across all heating rate with highest concentration of 33 % at 100 °C/min. Aliphatic hydrocarbons (Octane, Dodecene, Heptadecane, Tetradecyne, Undecane, Dimethylhepta-1,3-triene, Tetradecane, Nonadecane), constituted highest concentration of 12 % at 25 °C/min and aromatic hydrocarbons (Toluene) showed maximum presence of 4 % at 50 °C/min. The aqueous phase showcased cyclic nitrogenated compounds (Piperidine), anhydrosugars (DGP), and furanics (Furanmethanol), with the highest concentrations of 46 %, 12 %, and 38 %, respectively observed at 100 °C/min. Instantaneous py-gas analysis indicated an elevated presence of CO2 and CO in the initial pyrolysis stages (up to 70 min) followed by higher H2 in the latter stages (>70 min). While increasing heating rates (15–100 °C/min) boosted cumulative fractions of CO2 and CO, the highest H2 fraction was observed at 50 °C/min. The proximate and ultimate analysis of biochars indicated increased ash, fixed carbon, HHV and H/C compared to raw CFW. The surface area and morphology were positively influenced by an increase in heating rate, resulting in a microporous biochar having maximum surface area of 340.6 m2/g at 50 °C/min.

Characteristics of granulated activated carbon from a mixture of plant raw material waste

Relevance. The need to increase the use of renewable energy sources in the economy to reduce the harmful effects on the environment. Aim. To assess the possibility of obtaining by the thermochemical method high-quality carbon adsorbents from a granular mixture of various wastes of plant origin. Objects. Samples of illiquid lumpy birch wood, walnut shells, sunflower seed husks, flax fires, anthracite coal. Methods. Physical experiments: conductive pyrolysis, water-steam activation and differential thermal analysis. The ash content and moisture content of the samples were determined according to SS R 56881-2016 and SS 33503-2015. Nitrogen adsorption isotherms were measured using a NOVA-1200e analyzer. The equilibrium activity for toluene was determined according to SS 8703-74, the adsorption activity for iodine was determined according to SS 6217-74. The determination of the density of the granules was carried out according to SS 15139-69. Results. The authors have established rational parameters for obtaining carbon adsorbents from granules of vegetable raw materials. The specific yield of pyrolysis products of a mixture of vegetable raw materials with pyrolysis resin was determined. The specific yield of carbonization products of the granular compacted mass showed an increase of 25% in comparison with the non-compacted mixture of vegetable raw materials. Rational parameters for obtaining activated carbon with the highest adsorption capacity are granules with a density of 1200 kg/m3 with a degree of burnout of the carbonization product of 70%. It was established that the obtained samples of adsorbents from granules of plant raw materials have high adsorption characteristics comparable to activated carbons obtained from fossil raw materials.

Energy potential of plant and animal biomass using in relation to its thermal processing

Relevance. The need for effective utilization of biomass waste generated in significant quantities. Pyrolysis, accompanied by exothermic reactions, is a promising way of biomass processing. Aim. Assessment of the possibility of covering the thermal costs of plant and animal biomass pyrolysis due to heat release during decomposition. Methods. Proximate and ultimate analysis of biomass are determined according to certified methods. Thermal analysis of the studied raw materials was carried out on a Netzsch STA 449 F5 Jupiter synchronous thermal analyzer with an integrated gas analyzer QMS 403 Aeolos; quantitative yield of pyrolysis products was determined according to GOST 3168-93, gas composition was established using the gas analyzer TEST-1 (БОНЭР, Russia). Results and conclusions. According to the results of thermal analysis, it was found that pyrolysis of plant (pine nut shells) and animal (cattle manure) biomass is accompanied by exothermic reactions associated with the organic part decomposition in the temperature range 240–700°C. The value of heat release of exothermic reactions during pine nut shell destruction is 1.39 MJ/kg, a similar value during manure decomposition is 0.31 MJ/kg. This amount of heat allows you to fully cover the thermal costs of pine nut shell pyrolytic processing, the share of covering the thermal costs of manure pyrolysis is ∼30%. An additional source of heat is pyrolysis gaseous products with energy potential equal to 3.28 and 1.58 MJ of thermal energy per 1 kg of processed pine nut shells and manure, respectively.

Preliminary strategy and product analysis of microwave pyrolysis of waste printed circuit board

AbstractIn this study, microwave pyrolysis of waste printed circuit boards (WPCBs) was carried out in an inert atmosphere, and the effects of pyrolysis temperature and nitrogen flow rate on the yield and composition of pyrolysis products were investigated. With the increase of pyrolysis temperature, the yield of liquid product increases gradually, and the yield of solid product decreases gradually. At 600°C, the yield of each phase tends to be stable. When the temperature continues to rise, the content of H2 and CO decreases, and the content of C6 ~ C9 in the liquid product decreases. Microwave heating promotes the pyrolysis of brominated epoxy resin, which helps to improve the recovery rate of valuable substances and reduce the environmental impact of waste treatment. This study demonstrates that the microwave pyrolysis of WPCBs in nitrogen atmosphere has great potential in the green recovery process.

Bio-oil production from the catalytic pyrolysis of raw and torrefied corn waste by using MgO and CaO catalysts

Abstract This research investigates the influence of torrefaction and catalytic pyrolysis of raw corn waste (RCW) to upgrade the quality of bio-oil. RCW was torrefied at 280°C for 16 mins to produce torrefied corn waste (TCW). Natural basic oxides (CaO and MgO) catalysts were selected because of inexpensive and high catalytic performance. Pyrolysis experiments were conducted in a bench-scaled bubbling fluidized bed reactor at 500°C. The effects of torrefaction and the presence of a catalyst on the pyrolysis product both yield and composition were investigated. The results from non-catalytic pyrolysis revealed that TCW pyrolysis gave 15 wt.% lower in oil yield, and about 6.8 wt.% lower in gas yield but the char yield was approximately 22 wt.% higher compared to the pyrolysis of RCW. Considering the effect of catalyst, the yield of bio-oil reduced slightly, while the yield of char and gas increased compared to non-catalytic pyrolysis for both RCW and TCW. The bio-oil composition derived from TCW pyrolysis contained more phenolic and aromatic compounds and significantly lower oxygenated compounds when compared to that of RCW pyrolysis. Moreover, with the presence of the catalysts, the bio-oil composition and HHVs of bio-oil was also improved.

Research on Catalytic Reaction of Cotton Straw Pyrolysis Based on Model Compounds

The study starts from the clean conversion of desulfurized ash and biomass resources, based on correlation analysis and Langmuir-Hinshelwood model, studies the components of cotton stalk pyrolysis products and describes the mechanism and effects of desulfurized ash as a catalyst in the pyrolysis process. Regression analysis, support vector machine, and other methods are used to predict the yield or output of pyrolysis products, which is of great significance for the efficient utilization and sustainable development of cotton stalks. The study found that desulfurized ash significantly promoted the thermal decomposition of cotton stalks, increased the pyrolysis gas yield and lower heating value, increased the production of hydrogen-rich gas in the pyrolysis gas, and reduced the production of carbon oxides. Through the study of model compounds, it was found that desulfurized ash has different catalytic effects on the process of cellulose and lignin components in cotton stalks generating pyrolysis gas.

Analytical evaluation of the performance of pyrolysis-gasification (Py-Gs) combination within hybrid thermochemical-biological biorefinery

Thermochemical treatments like pyrolysis and gasification, were proposed to circumvent hydrolysis bottleneck of conventional 2nd generation biorefineries. Within this big-picture, the target of this article was to establish the type and amount of bioavailable matter that can be obtained through intermediate pyrolysis of biomass followed by gasification of biochar. To establish the amount of “chemical energy” partitioned among different products’ chemical oxygen demand (COD), which is proportional to higher heating value (HHV) and often utilized for biological systems, was applied for the evaluation of thermochemical conversion of a lignocellulosic feedstock (fir wood). The most abundant product of intermediate pyrolysis was biochar, which retains from 33 % to 40 % of feedstock COD (with temperatures starting from 450 °C). The yield of water-soluble pyrolysis products (WS) slightly increases from 24 % at 450 °C to 27 % at 650 °C, whereas the yield of WI increases considerably with the same temperature. Pyrolysis temperature showed a minor effect on the composition of WS as revealed by GC-MS analysis of main compounds and size exclusion chromatography. Preliminary gasification experiments, performed at 850 °C under CO2 atmosphere, provided gasification rates for different biochars, which was equal to 0.004, 0.005, 0.006 min−1 for biochars obtained at 650, 550, and 450 °C respectively. Syngas obtained from gasification of 450 °C and 550 °C biochar was almost tar-free, whereas gasification of 650 °C biochar yielded a detectable amount of tars (0.4 %). Increasing the gasification temperature to 950 °C sharply increases the gasification rate of biochar obtained at 450 °C, allowing to obtain 55% conversion yield. Within the scope of hybrid thermochemical-biological (HTB) processes, the obtained results show that intermediate pyrolysis, when coupled with subsequent 950 °C CO2 gasification of biochar, can deliver 64% of chemical energy (by COD basis) of the lignocellulosic feedstock as bioavailable constituents, which are defined to syngas and WS based on recent biological studies. Whereas downstream fermentation can process syngas and WS materials in an effective way, such yields could surpass the holocellulose-targeted methods based on hydrolysis.

Data-driven analysis of product interactions during biomass pyrolysis

Pyrolysis technology, crucial for sustainable energy in light of the energy crisis and environmental concerns, was studied using a model compound method involving desulfurization ash with cotton straw and a model compound. This study focused on the catalytic effects of desulfurization ash on the pyrolysis product formation from cotton straw. Key findings include a negative correlation between tar yield and the yields of carbon, water, and syngas, but a positive correlation with other pyrolysis products. Specifically, in the DFA/CE combination, tar and carbon yields were positively correlated, but negatively correlated with syngas and water yields. In DFA/LG, however, tar yield negatively correlated with water and carbon yields. Analysis using visual charts indicated that the H2 yield in DA/CS significantly fluctuated and positively correlated with the mixing ratio. In DFA/CE, a negative correlation existed between H2 yield and the combination ratio. For DFA/LG, the trends of CO and CH4 were consistent with C2H6 and H2, with a stable C2H6 rate and CO positively correlating with CO2. The Lilliefors test, ANOVA, and Spearman's correlation coefficient revealed no significant difference in the yields of pyrolysis products and gases between CE and LG under the same desulfurization ash proportions.

TRANSFORMING WASTE MANAGEMENT: EVALUATION OF A FIXED BED BATCH-TYPE PYROLYSIS PLANT UTILIZING SCRAP TIRES IN BANGLADESH

This study assesses the efficacy of a fixed bed batch-type pyrolysis plant utilizing scrap tires as feedstock for waste management in Bangladesh. Pyrolysis presents a promising approach to address the mounting challenge of tire disposal by converting scrap tires into valuable products such as fuel oil, carbon black, and steel wire. The research encompasses the design, fabrication, and performance evaluation of the pyrolysis plant under local operational conditions. Through comprehensive testing and analysis, key performance indicators including pyrolysis efficiency, product yield, and environmental impact are assessed. The findings offer insights into the feasibility and sustainability of pyrolysis-based waste management solutions in Bangladesh, with implications for addressing broader environmental and energy challenges.

Elevating Sustainability and Profitability: Non-Precious Metal Nano Catalysts for Maximizing Yield and Calorific Value in Asphalt Pyrolysis

Pyrolysis has proven to be a promising method for converting complex organic materials such as asphalt into high-value products. In an effort to increase the economic efficiency of this process, we investigated the use of non-precious metal nano catalysts for asphalt pyrolysis. Non-precious metal nano catalysts were chosen because of their potential to increase reaction rates and optimize product yields. This research involves the preparation of non-precious metal nano catalysts and their implementation in the asphalt pyrolysis process. The temperature and pyrolysis time variables are varied to determine optimal conditions. The results showed that the use of non-precious metal nano catalysts resulted in a significant increase in the yield of pyrolysis products, with the highest yield reaching 50.78%. In addition, the calorific value of the resulting product also increased to 10684 calories per gram. The main advantage of this research is the emphasis on economic aspects. The use of non-precious metal nano catalysts effectively increases the efficiency of the pyrolysis process, leading to higher product yields and greater calorific values. Thus, the use of non-precious metal nano catalysts makes a positive contribution in reducing production costs on an industrial scale. These findings provide new insights in the development of pyrolysis technology that is sustainable and economical and encourages a wiser use of natural resources through the use of bitumen and other complex organic materials.

Understanding the impact of molecular structure on the formation of stable intermediates during the pyrolysis of monoalkylated cyclohexanes in a shock tube

Alkylcyclohexanes are common constituents of conventional jet fuels and are expected to be a vital molecular subclass in next-generation, sustainable aviation fuels (SAFs). In an effort to advance the current understanding of the combustion chemistry of these species at engine-relevant conditions, we measured the time-resolved evolution of key stable intermediates during the pyrolysis of cyclohexane (CH) and four monoalkylated cyclohexanes: methylcyclohexane (MCH), ethylcyclohexane (ECH), propylcyclohexane (PCH), and butylcyclohexane (BCH), using laser absorption spectroscopy (LAS) in a shock tube. These experiments were conducted using 2 % Fuel/Argon test mixtures at a nominal pressure of 2 atm over the temperature range 1150–1530 K. Simultaneous tracking of the mole fraction time histories of methane, ethylene, and larger alkenes (>C2) provided new, valuable insight into the high-temperature reactivity of the five fuels studied. Studying all five fuels under similar test conditions enabled us to observe clear trends in the yields of different pyrolysis products with varying molecular structure, specifically increasing the number of carbon atoms in the alkyl chain. The fuel structure effects investigated in this work are instrumental in characterizing the pyrolysis product distribution, and thereby the overall combustion behavior of cyclohexane derivatives with longer (>C4) alkyl chains. We believe the multi-wavelength speciation data presented in this work can significantly contribute towards the development of robust, simplified, and fuel-specific kinetic models for monoalkylated cyclohexanes.

Study on the yield of cotton straw pyrolysis products based on nonlinear prediction and grey predictive analysis

Study on the yield of cotton straw pyrolysis products based on nonlinear prediction and grey predictive analysis

Theoretical and Experimental Demonstration of Advantages of Microwave Peat Processing in Comparison with Thermal Exposure during Pyrolysis

A series of theoretical and experimental studies was carried out with the aim of a direct comparison of the thermal and microwave destruction of peat during pyrolysis. Different heating mechanisms in these processes were investigated in the framework of simulations conducted using a commercial 3D software package, CST Studio Suite, to define their specific features. Based on these simulations, identical reactors were constructed exploiting an electric element and a microwave complex as a heat source, and an experimental technique was developed that allows these processes to be correctly compared under similar conditions. Using these reactors based on different heat sources, comparative experiments on peat pyrolysis were performed, and the results of the theoretical analysis were confirmed. As a result, the advantages of microwave exposure were demonstrated to achieve a more uniform and deep fragmentation of peat, increase the reaction rate and reduce the processing time, with high energy efficiency accompanying this method. As part of the experiments, the yield of pyrolysis products was analyzed. During the microwave destruction of peat, a high gas output (up to 27%) was obtained, which allows for a further increase in the efficiency of this processing method when burning these gases. The conducted elemental analysis showed an increase in the percentage of carbon from about 50% to 78% after microwave processing, which can become a raw material for obtaining effective environmentally friendly sorbents. The prospects for creating industrial microwave complexes for processing organic materials are discussed.

Product prediction of fixed-bed coal pyrolysis using a fusion model

Here, a proactively optimized fusion model (FM) for predicting the product yield of coal pyrolysis was developed. Eight coal characteristics (including pyrolysis temperature and proximate and ultimate analyses) were chosen as input parameters. Multiple linear regression (MLR), support vector machine (SVM), and random forest (RF) models were applied as the base models to form the FM. Sixty sets of experimental data from the literature were used for training and testing the base models. Different learning weights are assigned to the base models according to their predictive performance. The FM proactively improve the model outputs by means of the dynamical learning weight results. The coefficient of determination (R2) and the root-mean-squared error (RMSE) derived from the FM model were better than those of the base models. Moreover, the maximum relative error between the experimental data and model outputs was just 0.37%. These results suggest that FMs can be used to develop better predictive models for the yields of co-pyrolysis products. The FM proactively optimized the outputs base on learning weight algorithm and had better predicted performance than base models with less data.