Efficient Gas Research Articles

Modeling of a Biomass Cogeneration Plant from a Gasification Process

In recent decades, growing energy demand, coupled with concerns about climate change, has led to the exploration of sustainable energy sources. Among these, biomass gasification stands out as a promising method for generating heat and power. This research delves into the potential impact of biomass gasification within the global energy landscape, focusing particularly on its application in cogeneration plants. Utilizing Aspen Plus software V10, this study undertook the modeling and optimization of a biomass cogeneration plant. Through simulation, it was found that a biomass flow rate of 5 kg/s yielded 6.172 MW of power output. Additionally, the study revealed several key factors that influence power generation: increasing biomass and airflow rates, increasing gasification temperature, and reducing water flow rate. By doubling the biomass flow rate to 10 kg/s and increasing the temperature to 800 °C, power generation increases by 41.75%. Moreover, the study demonstrates that Portuguese municipal waste is an efficient source of energy production, with higher cold gas and overall efficiencies compared to forest and vine-pruning residues.

Efficient-safe gas extraction in the superimposed stress strong-outburst risk area: Application of a new hydraulic cavity technology

Coal and gas outbursts pose significant risk in coal mining, especially in high-stress areas. The F15-22080 haulage roadway of the No. 8 Mine, known for its high outburst risk with superimposed stress, presents challenges such as low permeability and frequent borehole outbursts during gas extraction. To address these issues, this study introduced an innovative, efficient, and safe gas extraction technique paired with an air-hydraulic drilling integrated anti-outburst platform. The stress and outburst characteristics of the roadway reservoir were analyzed using FLAC3D simulation and experimental testing, leading to the classification of the reservoir into the general stress area (GSA) and superimposed stress area (SSA). Focusing on the SSA, the borehole outburst mechanism was investigated. Building on these insights, a comprehensive gas zoning control plan for extraction was developed. In the GSA with low risk of borehole outburst, hydraulic cavity boreholes were directly implemented to boost extraction efficiency and minimize construction costs. In the SSA, a multistep collaborative extraction strategy was adopted. This strategy involved an initial "air-flushing conventional borehole pre-extraction" step to prevent borehole outbursts, followed by a "hydraulic cavity borehole strengthening-extraction" step to ensure efficient gas extraction. The fluid-solid coupling model consistent with the gas flow around boreholes was established, and the extraction effects of the regional control plan were simulated and analyzed using COMSOL, thereby establishing the construction parameters. The successful field application of this technique, evidenced by data from gas extraction and roadway excavation, validates the effectiveness of it.

Surrogate-assisted constrained hybrid particle swarm optimization algorithm for propane pre-cooled mixed refrigerant LNG process optimization

The propane pre-cooled mixed refrigerant (C3MR) process is one of the most widely used and efficient natural gas liquefaction processes. However, optimization of this process involves various design and operational constraints, complex thermodynamics, and hence nonconvex in nature. Therefore, it's computationally expensive, often involving trial and error approaches. Existing optimization algorithms often possess flaws such as insufficient accuracy and premature convergence, leading to suboptimal solutions that may violate essential process constraints. This article proposes a novel method to optimize the C3MR process that handles the computational complexity, meets the constraints, and achieves feasible solutions quickly. The proposed method includes modified feasibility-based constraint handling and radial basis function network-assisted surrogate modeling and optimization, where the power consumption is optimized using a hybrid of the particle swarm optimization (PSO) and social learning PSO algorithm. The proposed algorithm achieves the optimum power consumption (121109.31 kW), which is 21.5 % less than the base case (154200 kW). The optimization results are compared with similar optimization algorithms, where the proposed algorithm outperformed the other algorithm regarding optimal solution, convergence, and speed. The results from this study are compared to previous studies from the literature, which validate the accuracy and applicability of the proposed method.

Experimental and modeling study of medical waste based on plasma gasification

Plasma gasification melting (PGM) provides reliable disposal of toxic medical waste with a low heating value, which is capable of converting waste into energy. This study investigates the performance of experiments on plasma gasification for the treatment of chemical-pharmaceutical medical waste (CPMW) with an air medium. A comparative analysis is performed for gasification characteristics at three reactor temperatures (1000, 1400, and 1800 °C). Moreover, a thermodynamic equilibrium model is developed to assess performance features such as syngas yield, high heating value, and cold gas efficiency in the gasification temperature range of 1000–1800 °C. A comparison of the experiment and computational outcomes shows a good agreement. The results show that the quality of syngas and heating value is improved by increasing the temperature of the plasma gasifier so that at 1800 °C, H2, CO, and higher heating value (HHV) are obtained as 41 %, 37 %, and 10 MJ/Nm3, respectively. The obtained syngas is a clean fuel with low sulfur-containing and nitrogen-containing. The experimental results provide an extensive comprehension of CPMW gasification in a plasma reactor and consider a possibility for hydrogen and energy production.

Influence of Yttria content in YSZ: An evaluation of water-based SPS coatings and spark plasma sintered pellets

The inherent phase instability of the state-of-the-art 7–8 mol% partially stabilised Yttria-Stabilised Zirconia (YO1.5, 8 YSZ, tetragonal) under a molten CMAS attack lacks the technological readiness needed to increase the gas inlet temperatures for more thermally efficient gas turbine engines. In this study, the concentration of Yttria in YSZ was systemically increased to impart CMAS resistance and their applicability via emerging Suspension Plasma Sprayed (SPS) coatings and Spark Plasma Sintered (SpPS) pellets under simulated conditions was evaluated. The fully stabilised higher Yttria YSZ compositions (21.4 mol% and 50.2 mol%, cubic) severely restricted the CMAS infiltration and interaction areas, with the later composition forming an apatite layer and the trans-granular cracking and chipping of YSZ into layers reduced with an increase in Yttria content. However, their application into water-based SPS coatings resulted in a complete coating failure following the high-temperature CMAS tests. During Furnace Cycling Test (FCT) tests, the 8 YSZ coating survived 34 thermal cycles compared to just one on the 50.2 mol% YSZ coatings. The premature delamination of the higher Yttria coating seems to have been caused by the spallation associated with horizontal cracks within the coating. The YSZ composition could be modified into CMAS-resistant chemistry; however, their applicability as a functioning TBC with inherent microstructural features, such as the Dense Vertically Cracked (DVC) coating strategy examined in this study, requires new coating design strategies that impart sustainable thermal cycling performance.

Harnessing NOx emission management: A virtual sensor model for natural gas power generation engines with active pre-chamber

This paper presents a NOx Sensor machine learning model for a highly efficient 2MW power generation lean burn gas engine with an active pre-chamber. As gas power generation continues to evolve, engine efficiency and the accurate measurement of NOx emissions has taken on greater importance. However, the working life of existing NOx sensors pales in comparison to the lifecycle of an engine. This paper studies a series of machine learning NOx sensor models and carries out a comparative analysis. We introduce a predictive analytics model used for monitoring the emissions of active pre-chamber gas engines. This real deployment aims to detect the deviations in emissions across an entire fleet of gas engines, even when no physical sensors are installed in the engines. Finally, a model has been implemented that allows the prediction of NOx values, in engines that did not have them initially, with a 5–10 % precision. For example, with NOx at 120 ppm, the virtual sensor provides values close to +-10 ppm. It has been observed that such features as the setpoint value of the active pre-chamber gas pressure, in a lean burn gas engine with active pre-chamber, are among those parameters that have the greatest impact on the model estimation.

Modulating pore microenvironment in a robust ionic porous polymer for efficient propyne/propylene separation

Developing highly selective and stable adsorbents for capturing trace propyne from propylene to produce polymer-grade propylene is of great significance but challenging. Porous organic polymers with high stability are promising for propyne removal, but display trade-off effect between capacity and selectivity. Here, we report a novel ionic porous polymer with stable structure and well-tuned pore microenvironment featured abundant microporosity and inorganic anions, which realized efficient propyne/propylene separation. Gas adsorption experiments demonstrate excellent propyne/propylene selectivity (43) and boosted diffusion performance. Meanwhile, polymer-grade propylene (≥99.5 %) could be obtained with the highest productivity (5.7 mol kg−1) among porous organic polymers. Molecular simulations reveal the high-density anions in P(Ph4Im-Br-DVB) enable effective discrimination of propyne from propylene with hydrogen-bonding like interactions. This work highlights how pore microenvironment tuning in porous organic polymers can realize the efficient gas separation.

Performance of novel carbonate-based CO2 post-combustion capture process

A novel carbonate-based CO2 capture process was developed at VTT, and proof-of-concept was tested using a bench scale device. The process has closed-loop, carbonate liquid, and the captured CO2 is released at under-pressure. The temperature is around 65 °C, which enables, for example, utilisation of waste heat streams in process integrations. The process performance and its parameters were tested using 8 w-% sodium carbonate liquid with simulated gases, real flue gases and biogas. Also, the absorption mass transfer kinetics and suitable flow parameters of the invented microbubble generator were assessed. The device has successfully and continuously run for tens of hours, and the typical CO2 capture rate between 72 and 84 % were performed at the liquid pH value of 9.3, using a near-atmospheric pressure process. Mass transfer rates kLa for carbonate liquid and air were between 0.14 and 0.34 s−1, which indicates efficient gas absorption, enabling size reduction of the device size.

Bimetallic metal-organic framework aerogels supported by aramid nanofibers for efficient CO2 capture

The excessive CO2 emission has gained global attentions due to its potential effects on climate change, plant nutrition deterioration, and human health and safety. Metal-organic frameworks (MOFs) featured with high specific surface area, adjustable pore size, and tailorable morphology have been widely applied for CO2 capture. However, some drawbacks of poor mechanical stability and uneven distribution of mesopores limit their further applications. Herein, we demonstrate a one-step synthesis of bimetallic center framework (OSSBCF) and pore reconstruction (PRC) strategy to prepare the hierarchical porous Zn/Co-ZIF@ANF aerogels. This unique design achieves the construction of efficient gas transfer channels and creates massive micropores with abundant Lewis basic adsorption sites. Benefiting from theses merits, the bimetallic Zn/Co-ZIF@ANF aerogels demonstrate high MOFs loading mass of 47.51 wt%, high specific surface area of 686.39 m2g−1, and large porosity of 99.31 %. Moreover, the bimetallic Zn/Co-ZIF@ANF aerogels exhibit an enhanced CO2 adsorption capacity of 5.99 mmol/g and CO2/N2 adsorption selectivity of 35 at 25 °C and 1 bar. The CO2 capacity of bimetallic Zn/Co-ZIF@ANF aerogels keep up to 95.19 % after ten cycles of CO2 adsorption, indicating the excellent long-term recycle stability. Therefore, this study provides a promising strategy to engineer hierarchical porous bimetallic MOF aerogels toward practical CO2 capture.

Deciphering the dynamic structural evolution of oxygen vacancies enriched SrFe12O19 for efficient reverse water gas shift reaction

The Reverse Water-Gas Shift (rWGS) reaction is recognized as a potentially promising pathway to serve the dual purpose, possible shifting of CO2 from a linear economy to a circular and positive economic impact in the current industrial process. This study is engaged to develop a series of oxygen vacancies enriched M−type strontium hexaferrite (SrFe12O19) catalysts via doping of transition metals like Cu, Zn, Co, and Ni for the rWGS reaction. Cu-doped SrFe12O19 exhibited 100 % CO selectivity and a CO production rate of 2850 mmol h−1 gcat-1, at a comparatively lower temperature (500 °C), outpacing the performance of almost all non-precious metal-based catalytic systems. Moreover, the catalyst was active without the requirement of the H2 pre-reduction procedure and displayed remarkable stability tested up to 200 h without any significant deactivation, making it more industrially relevant. The characterization of as-prepared catalysts indicates the enrichment of oxygen vacancies and reducibility after the involvement of the dopant in the SrFe12O19 system. The formation of various iron species (Fe3O4, Fe3C, and Fe5C2) was revealed by the in-situ studies and post-reaction characterizations of the catalyst system, and their relative amounts were significantly affected by the nature of doping elements, which subsequently influenced the CO selectivity. The dynamic structural evolution and surface-adsorbedspecies were identified usingin-situ Raman and DRIFTS studies. Finally, the structure–activity relationship was rationalized through not only several ex-situ/in-situ characterization techniques but also an in-detailed Density functional theory (DFT) study.

Exploring enhanced CFC gas adsorption on Pt decorated graphene-modified sheets: A density functional theory investigation

The potential of Pt-decorated graphene and Pt-decorated graphene doped with N and S as efficient absorbent and gas sensors for chlorofluorocarbons (CFCs) is examined here using density functional theory (DFT) calculations. Pt-decorated graphene is an incredible material with many applications being investigated because of its amazing properties. We study the structural properties, charge transfer, interaction distance, and orbital hybridization in both pristine and graphene-doped with N and S. We perform extensive electronic investigations that include evaluations of the density of states, frontier molecular orbitals, and non-covalent interactions to gain a deeper knowledge of the interactions of the CFC molecules. Our findings reveal a physisorption interaction between CFC molecules and Pt-decorated graphene, which yields an adsorption energy of −0.50 eV. However, Pt-decorated graphene and Pt-decorated graphene doped with N and S exhibit adsorption energies of −0.70 eV and −0.55 eV, respectively, signifying chemisorption behaviour. It suggests that this material can be used as a CFC gas sensor.

Rapid Classification and Diagnosis of Gas Wells Driven by Production Data

Conventional gas well classification methods cannot provide effective support for gas well routine management, and suffer from poor timeliness. In order to guide the on-site operation in liquid loading gas wells and improve the timeliness of gas well classification, this paper proposes a production data-driven gas well classification method based on the LDA-DA (Linear Discriminant Analysis–Discriminant Analysis) combination model. In this method, considering the requirements of routine management, gas wells are evaluated from two aspects: liquid drainage capacity (LDC) and liquid production intensity (LPI), and are classified into six types. Domain knowledge is used to perform the feature engineering on the on-site production data, and five features are set up to quantitatively evaluate the gas well and to create classification samples. On this basis, in order to specify the optimal data processing flow to establish the gas well classification map, four linear dimensionality reduction techniques, LDA, PCA, LPP, and ICA, are used to reduce the dimensionality of original classification samples, and then, four classical classification algorithms, NB, DA, KNN, and SVM, are trained and evaluated on the low-dimensional samples, respectively. The results show that the LDA space achieves the optimal sample separation and is chosen as the decision space for gas well classification. The DA algorithm obtains the top performance, i.e., the highest Average Macro F1-score of 95.619%, in the chosen decision space, and is employed to determine the classification boundaries in the decision space. At this point, the LDA-DA combination model for sample data processing is developed. Based on this model, gas well classification maps can be established by data mining, and the rapid evaluation and diagnosis of gas wells can be achieved. This method realizes instant and efficient production data-driven gas well classification, and can provide timely decision-making support for gas well routine management. It introduces new ideas for performing gas well classification, expanding the content and scope of the classification work, and presenting valuable insights for further research in this field.

Performance evaluation of red mud-based oxygen carriers in the chemical looping gasification of wet sludge rich in iron

A high-performance and low-cost oxygen carrier (OC) is the key for industrialization of chemical looping gasification (CLG) technology for sludge treatment. In this work, four OCs (RM_15 %CuO, RM_10 %CuO, RM, RM_POC) were prepared in an industrial-scale granulation equipment. The red mud was composited by mixing with different amounts of CuO and MnO2, then subjecting to different calcination temperatures. Firstly, the oxygen decoupling and oxygen carrying capacities of the OCs were compared using 5% H2 as the reducing agent. RM_15%CuO and RM_POC showed excellent oxygen release capabilities, with oxygen release loss of −1.99 % for RM_15%CuO. The catalytic gasification performances of RM_15%CuO and RM_POC were evaluated in a lab-scale fluidized bed reactor with wet sludge as the feedstock. Both OCs were able to maintain the H2 concentration of over 44.6% and no less than 79.2% sludge gasification efficiency after 30 cycles. However, the H2 content was clearly higher in case of RM_POC. SEM-EDS was used to analyze the influence of sludge ash, rich in Fe, on the performance of two OCs after the fluidized bed operation. The results showed that the sludge ash sample with more than 20% Fe2O3 could transfer its lattice oxygen to assist OC and prevent the in-situ segregation of Fe phase in the POC surface. However, the inhibitory effect of RM_15%CuO was much lower. The degradation performance of RM_POC carrier was slower and thus the H2 content was higher. This performance evaluation provides a theoretical guide for chemical looping gasification of sludge in future with an idea of mixed ratio of recycling sludge ash to the RM_POC.

Simulations on coal water slurry gasification by molecular dynamics method with ReaxFF.

Coal water slurry (CWS) is a new type of liquid coal product with low pollution, which is mainly used in the chemical industry to produce syngas (CO + H2). It is of great significance to study the microscopic mechanism of CWS gasification reaction for improving the efficiency of coal gasification. In this paper, the method of molecular dynamics based on reaction force fields (ReaxFF-MD) is used to study the gasification process of CWS/O2 system at different temperatures. The results show that, in the range of 1600-2400 K, the macromolecular network structure of lignite is decomposed into a large number of small molecular structures and a small number of light tar free radical fragments, and the types and quantities of reaction products increased rapidly. At 2400-4000 K, the free radical fragments of light tar are further decomposed and reacted with gasification agents, but the types and quantities of reaction products have little change. At 3600 K, a full gasification reaction occurred in the system, and the content of syngas is the highest. The model was established and optimized by Materials Studio (MS) software. Based on ReaxFF-MD method, Lammps software was used to simulate the gasification process of CWS/O2 system, and the reaction force field files containing C, H, O, N, and S element were used. By calculating the activation energy of gasification reaction, the rationality of the model and calculation method was illustrated. The post-processing of the results was implemented using OVITO, ChemDraw software, and self-programmed Python scripts.

Energy efficiency and greenhouse gas emission reduction potential of solar PV and biomass-based systems for a food processing plant

The industrial sector is one of the most energy-intensive sectors, with a share of nearly 38 % (156 EJ) of all energy used globally in 2020. Historical energy demand and consumption data from a poultry processing plant have been analyzed to lower greenhouse gas emissions (GHG) and reliance on traditional energy sources. The study includes energy, economic, and emissions analyses for (a) solar photovoltaic (PV) systems, (b) biomass fuels, and (c) coal-fired with wood. Fixed, single, and two-axis tracking solar PV systems that are company-owned and funded by banks are considered. The historical energy consumption data of the plant shows that 52.36 % of energy demand is met by electrical energy and 47.63 % by thermal energy. The yearly electricity demand is 9,938 MWh, costs $1,192,560, and emits 5117.6 tCO2. Thermal energy demand is based on an annual use of 898 tonnes of coal and 71.6 tonnes of liquefied petroleum gas (LPG), which costs $ 143,681 and emits 2977.7 tonnes of carbon dioxide (tCO2). Feasibility of 1.3 MW, fixed axis company-owned, solar PV plant shows an annual electricity production of 1876 MWh, GHG emission reduction of 965.9 tCO2 with a payback period of 3.4 years. Biomass system delivers yearly fuel cost savings of $25,724, reducing 2784 tCO2 with a 1.9-year payback period. Co-firing biomass offers a 3.58 % fuel cost saving and 557 tCO2 with a 0.93-year payback period. It concluded that the wood fuel feedstock biomass option is most suitable renewable energy resource for such large-scale poultry facilities.

UV activated formaldehyde gas sensing based on gold decorated ZnO@ In2O3 hollow nanospheres at room temperature

Using uniform carbon nanospheres as sacrificial templates, gold nanoparticle-modified ZnO@ In2O3 hollow nanospheres with controlled dimensions and porous architectures were successfully synthesized through water bath, hydrothermal and chemical reduction methods. Gas sensing evaluation revealed that the Au-decorated ZnO@ In2O3 hollow nanostructures exhibited a dramatically amplified response up to 14.8 when exposed to 10 ppm formaldehyde analyte at room temperature. Furthermore, multifaceted performance benefits of Au-decorated ZnO@ In2O3 over single-phase ZnO, Au-ZnO, ZnO@ In2O3 heterojunction-based composites were observed, including excellent selectivity towards formaldehyde even in complex gas mixtures; tremendous sensitivity enhancement stemming from synergies between efficient gas diffusion through hollow heterojunction nanospheres and accelerated surface reactions at catalytically-active Au sites; and rapid, fully-reversible response/recovery time of 32 s and 42 s, respectively. In-depth investigations were conducted into the fundamental sensing mechanisms enabling formaldehyde detection using AC impedance spectroscopy, in situ diffuse reflectance Fourier transform infrared spectroscopy (DRIFTS), and density functional theory (DFT) computational modeling analyses.

An optimised cell for in situ XAS of gas diffusion electrocatalyst electrodes

The quality of in situ XAS of electrochemical systems is highly sensitive to electrode disturbances, such as gas evolution and gas consumption at an electrolyte / catalyst interface. A novel in situ spectro‐electrochemical X‐ray absorption spectroscopy cell is presented as a new tool for the characterisation of gas evolving and consuming electrocatalysts at high overpotentials. By utilising a thin, porous membrane with efficient electrolyte and gas circulating loops, an improved three phase interface that enabled efficient gas supply and minimised the interference from bubble formation. X‐ray absorption spectroscopy measurements were conducted in fluorescence mode with three experiments selected to demonstrate the cell’s performance. The first two reactions; an in‐situ study of a highly active amorphous iridium oxide catalyst during the oxygen evolution reaction and an in‐situ study of copper oxide during the carbon dioxide reduction reaction are used to exemplify the XAS data quality achieved under operational conditions. Thirdly, a detailed XAS investigation of a highly dispersed platinum catalyst during the oxygen reduction reaction is presented, along with comparative data in nitrogen. These measurements show the retention of oxygen on the surface of the platinum metal particles down to 0.48 V (vs. RHE), well below the platinum oxide reduction peak.

Mesoporous CdO/CdGa2O4 microsphere for rapidly detecting triethylamine at ppb level

Developing fast, accurate and sensitive triethylamine gas sensors with low detection limits is paramount to ensure the safety of workers and the public. However, sensors based on single metal oxide materials still suffer from drawbacks such as low response sensitivity and long response and recovery times. To address these challenges, in this work, a series of mesoporous CdO/CdGa2O4 microspheres were synthesized. We optimized the sensor's sensing performance to triethylamine by fine-tuning the ratio of CdO to CdGa2O4. Among them, CdO:3CdGa2O4-based sensor demonstrates a rapid response time of 2 s to detect 100 ppm of triethylamine, with a high response value of 211 and exceptional selectivity. Furthermore, it exhibits a low detection limit of 20 ppb for triethylamine, making it suitable for practically testing fish freshness. Crucially, electron transfer between the heterojunctions increases the chemically adsorbed oxygen on the materials’ surface, thereby enhancing the sensor's response sensitivity to triethylamine. This discovery provides new insights and methodologies for the design of highly efficient triethylamine gas sensors.

MOF-derived metal oxide (Cu, Ni, Zn) gas sensors with excellent selectivity towards H2S, CO and H2 gases

Metal-organic framework (MOF)-derived metal oxides blend the sensing properties of metal oxides with MOF porosity, enhancing gas sensing capabilities. In this study, M-MOFs (M = Cu, Ni and Zn) were synthesized and then calcined at different temperatures to obtain their corresponding metal oxides (CuO, NiO and ZnO). The synthesis method incorporated novel approaches to enhance sensor performance, such as optimizing calcination temperatures for improved selectivity. Structural and morphological analyses confirmed the high surface area and porosity of the metal oxide materials, facilitating efficient gas adsorption and promoting enhanced sensor response. Gas sensing studies revealed significantly enhanced performance of MOF-derived metal oxides over M-MOFs, strongly influenced by calcination temperature. Moreover, CuO, NiO and ZnO MOF-derived metal oxides showed improved selectivity towards H2S, CO and H2 gases, respectively. This study demonstrates that tuning MOF and calcination parameters can tailor sensor selectivity effectively.

Reservoir properties inversion using attention-based parallel hybrid network integrating feature selection and transfer learning

The inversion of subsurface reservoir properties is of profound significance to the oil and gas energy development and utilization. The strong heterogeneity and complex pore structure of underground reservoirs pose a challenge to efficient oil and gas energy development and utilization across the world, which increases the necessity of developing an efficient reservoir properties inversion method. However, traditional model-driven methods are confronted with the challenges of strong nonlinearity and geological heterogeneity. Moreover, previous studies rarely emphasized the importance of nonlinear feature selection and transfer learning (TL). Aiming to address the research gaps, a reservoir properties inversion method was proposed by combining random forest (RF) feature selection, bidirectional temporal convolutional network (BiTCN), bidirectional gated recurrent units (BiGRU) network, multi-head attention (MHA) mechanism and TL strategy. First, the RF was used to screen the features with significant correlation with the target reservoir properties. Thereafter, combining BiTCN and BiGRU network to leverage their complementary strengths, a parallel dual branch feature learning network was constructed to learn richer geological information from logging data. Meanwhile, MHA was introduced to fuse the output features of the dual network structure. Finally, the fused features were passed through the fully connected module to output the inversion results. TL was used to associate the correlation between reservoir properties and model inversion to improve the inversion performance. The application results with actual field data showed that the proposed method was accurate and robust in reservoir properties inversion. This study can provide a new way for reliable reservoir properties inversion and promote the application of artificial intelligence in data-driven energy science.