Query：
学者姓名：喻智
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
Blasting is the primary technical method of mining mineral resources, the accurate prediction of blasting fragmentation after blasting has a key impact on controlling mining operation costs and reducing environmental pollution. To that end, a powerful artificial intelligence (AI) model, named Gaussian Process Regression (GPR), was proposed to predict the mean fragment size (MFS) of broken rock after blasting. To improve the prediction performance of GPR model, the newly bio-inspired Artificial Hummingbirds Algorithm (AHA) was employed to select the optimal hyperparameter's combinations. Additionally, the other regression models including the artificial neural networks (ANN), support vector regression (SVR), and standard GPR, were also developed to compare the prediction performance with the proposed hybrid AHA-GPR model. Two cases collected from Chilean copper mine and an Indian coal mine were used to verify the model performance, mainly using two performance metrics and the Taylor diagram analysis to determine the best prediction model. The AHA-GPR model achieved R-2 values of 0.88 and 0.85, with RMSE values of 11.40 and 9.50 for the Copper mine database, and R-2 values of 0.93 and 0.90, with RMSE values of 0.02 and 0.03 for the Coal mine database. These results demonstrate that the AHA-GPR model outperforms other predictive models, establishing it as the most reliable approach in both case studies. Besides, this AI model-based approach offers researchers and mining engineers an improved approach to predict the rock fragmentation after blasting, facilitating thorough analysis of blasting design before mining operations and enabling precise forecasting of blasting outcomes. Furthermore, the sensitivity analysis further provided essential insights to optimize the blasting designs.
Keyword ：
Artificial intelligence Artificial intelligence Blasting fragmentation Blasting fragmentation Hybrid AHA-GPR model Hybrid AHA-GPR model Mean fragment size Mean fragment size Mines Mines
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yu, Zhi , Du, Lin-Feng , Liu, Jian-Xing et al. Feasibility of a hybrid AHA-GPR model for predicting blasting fragmention in surface mines [J]. | EARTH SCIENCE INFORMATICS , 2025 , 18 (3) . |
| MLA | Yu, Zhi et al. "Feasibility of a hybrid AHA-GPR model for predicting blasting fragmention in surface mines" . | EARTH SCIENCE INFORMATICS 18 . 3 (2025) . |
| APA | Yu, Zhi , Du, Lin-Feng , Liu, Jian-Xing , Zhou, Jian , Li, Chuan-Qi . Feasibility of a hybrid AHA-GPR model for predicting blasting fragmention in surface mines . | EARTH SCIENCE INFORMATICS , 2025 , 18 (3) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The construction of an elastoplastic constitutive model for energy dissipation and crack evolution in rocks is crucial for accurately predicting their failure processes. This study first constructs a theoretical elastoplastic constitutive model by analyzing the mechanical properties of rocks, energy dissipation, and crack evolution under conventional triaxial compression. Subsequently, a three-dimensional finite difference scheme for the theoretical model is derived to implement a numerical algorithm. Finally, using argillaceous siltstone as an example, the validity of the theoretical model and its algorithmic implementation is verified through experimental testing, result analysis, model construction, secondary development, and numerical simulation. The research indicates that the dissipated energy is equal to the integral of the stress-strain curve minus the elastic strain energy, which can be quantitatively described using strength parameters. The volumetric strain of cracks is equal to the plastic volumetric strain, which can be indirectly quantified using the dilation angle. The simulated stress-strain curves closely align with the experimental data, and the simulated dissipated energy and crack volumetric strain are consistent with the theoretical calculations, confirming that the theoretical model effectively captures the nonlinear mechanical behavior, energy dissipation, and crack evolution of rocks.
Keyword ：
crack evolution crack evolution elastoplastic constitutive model elastoplastic constitutive model energy dissipation energy dissipation rock mechanics rock mechanics
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cheng, Lei , Yu, Zhi , Liu, Xinxi . Elastoplastic Constitutive Model for Energy Dissipation and Crack Evolution in Rocks [J]. | APPLIED SCIENCES-BASEL , 2025 , 15 (8) . |
| MLA | Cheng, Lei et al. "Elastoplastic Constitutive Model for Energy Dissipation and Crack Evolution in Rocks" . | APPLIED SCIENCES-BASEL 15 . 8 (2025) . |
| APA | Cheng, Lei , Yu, Zhi , Liu, Xinxi . Elastoplastic Constitutive Model for Energy Dissipation and Crack Evolution in Rocks . | APPLIED SCIENCES-BASEL , 2025 , 15 (8) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Water medium has been widely used in decoupled charge blasting due to its high efficiency of energy transfer. In this study, water-coupling presplit blasting is investigated theoretically and numerically from the essential mechanism of the effect of stress wave parameters (peak pressure Pb, loading rate Lrand attenuation coefficient alpha) on presplitting. According to the propagation and superposition theory of stress waves, the inter-hole tangential stress peak distributions and hole spacings under different stress wave parameters are analytically given. Further, considering the role of stress wave parameters, water-coupling presplit blasting under different in-situ stresses 6s and delay intervals Delta t are investigated with air-coupling presplit blasting as a comparison. Through LS-DYNA, numerical simulations of presplit blasting are carried out to verify the reliability of theoretical analysis and further study their effects on the presplitting. Both the theoretical and numerical results show that the blasting load with higher Pb and lower Lr, alpha, 6s and Delta t favors presplitting. Under the same Pb, the stress superposition range, minimum stress peak and hole spacing of water-coupling presplit blasting are larger than those of air-coupling presplit blasting. The numerical results of the crack pattern also show that lower Lr will change the crack pattern from the crushing zone extension dominated by compression-shear damage to the main crack propagation dominated by tensile damage, and the directionality of presplitting is more pronounced with higher Pb and lower Lr, 6sand Delta t. Compared with air medium, water medium has better performance in the directional effect of presplitting and anti-interference ability to the delay scatter due to its lower Lr.
Keyword ：
Filling medium Filling medium Loading rate Loading rate Numerical simulation Numerical simulation Peak pressure Peak pressure Presplit blasting Presplit blasting
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Huo, Xiaofeng , Yu, Zhi , Qiu, Xianyang et al. Investigation of water-coupling presplit blasting considering the role of stress wave parameters [J]. | ENGINEERING FRACTURE MECHANICS , 2025 , 321 . |
| MLA | Huo, Xiaofeng et al. "Investigation of water-coupling presplit blasting considering the role of stress wave parameters" . | ENGINEERING FRACTURE MECHANICS 321 (2025) . |
| APA | Huo, Xiaofeng , Yu, Zhi , Qiu, Xianyang , Shi, Xiuzhi . Investigation of water-coupling presplit blasting considering the role of stress wave parameters . | ENGINEERING FRACTURE MECHANICS , 2025 , 321 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Underground narrow veins, typically less than 2-3 m thick but rich in precious metals, hold significant economic value. However, the confined free surface in the open stope poses substantial challenges for long-hole blasting, often leading to overbreak and underbreak, emphasising the need for optimising blasting parameters. To address this, understanding the influence of free surface width on blasting performance becomes critical. Therefore, a modified method based on the Scaled Heelan solution was employed to comprehensively investigate this influence, particularly its relationship with burden, velocity of detonation (VOD), and initiation positions. The indicators considered include blasting damage and fragment size distribution. The analysis allows the following conclusions: (1) both the damage volume and the fragment size are positively correlated with the width of the free surface within a certain range; (2) for a fixed free surface width, damage volume and fragment size increase with burden within an appropriate range, but an excessive burden prevents a blasting crater formation; (3) higher VOD does not always result in better fragmentation near the blasthole, and an optimal VOD lies approximately between the velocity of P- and S-wave; (4) the axial damage distribution depends on the initiation position but with minimal impact on radial damage. These findings provide a theoretical basis for burden and spacing design in narrow-vein open stoping and thereby contribute to improved blasting fragmentation efficiency.
Keyword ：
Blasting damage Blasting damage Fragment size distribution Fragment size distribution Free surface width Free surface width Long-hole blasting Long-hole blasting Scaled Heelan solution Scaled Heelan solution Underground narrow veins Underground narrow veins
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Shian , Shi, Xiuzhi , Qiu, Xianyang et al. Influence of free surface width on blasting damage in open stope mining in narrow vein orebodies [J]. | INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES , 2025 , 194 . |
| MLA | Zhang, Shian et al. "Influence of free surface width on blasting damage in open stope mining in narrow vein orebodies" . | INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES 194 (2025) . |
| APA | Zhang, Shian , Shi, Xiuzhi , Qiu, Xianyang , Zong, Chengxing , Yu, Zhi . Influence of free surface width on blasting damage in open stope mining in narrow vein orebodies . | INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES , 2025 , 194 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Rock fragment movement during blasting operations is a major cause of ore and profit losses in hard rock open-pit mines having a complex-orebody. To address this issue, a novel multilayer dig-limit approach, which well considers blast movement in dig-limit optimization, was proposed in this study by combining machine learning techniques and practical heuristic algorithms. First, horizontal and vertical blast-induced rock movement distances were predicted using a supervised learning model. Then, the movement direction of rock fragments was computed based on the initiation sequence. After meshing the blast block into rock units, the blasted muckpile and post-blast ore boundary were determined, providing a good basis for dig-limit determination. Finally, the optimized dig-limit with maximum profit can be calculated using a practical heuristic algorithm. By applying this method in a case study, the ore recovery and economic profit were improved, compared with manually drawn dig-limit method. Additionally, the impact of equipment size, number of layers and powder factor on the application of this method was discussed. The obtained results indicated that ore and profit losses can be reduced with a decreased equipment size, increased number of layers and decreased powder factor. A multilayer dig-limit approach considering blast-induced rock movement and dig-limit optimization was proposed.The multilayer dig-limit approach yields higher ore recovery and economic profit compared to manually drawn dig-limit.Ore losses can be reduced by decreasing the equipment size, increasing the number of layers and decreasing the powder factor.
Keyword ：
Blast-induced rock movement Blast-induced rock movement Complex-orebody open-pit blast Complex-orebody open-pit blast Economic profit Economic profit Multilayer dig-limit optimization Multilayer dig-limit optimization Ore recovery Ore recovery
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yu, Zhi , Shi, Xiu-Zhi , Zhang, Zong-Xian et al. A Multilayer Dig-Limit Approach for Reducing Ore and Profit Losses in an Open-Pit Mine Having Complex Orebody [J]. | ROCK MECHANICS AND ROCK ENGINEERING , 2024 , 57 (9) : 7425-7441 . |
| MLA | Yu, Zhi et al. "A Multilayer Dig-Limit Approach for Reducing Ore and Profit Losses in an Open-Pit Mine Having Complex Orebody" . | ROCK MECHANICS AND ROCK ENGINEERING 57 . 9 (2024) : 7425-7441 . |
| APA | Yu, Zhi , Shi, Xiu-Zhi , Zhang, Zong-Xian , Zhou, Jian , Cai, Xing-Qi , He, Song et al. A Multilayer Dig-Limit Approach for Reducing Ore and Profit Losses in an Open-Pit Mine Having Complex Orebody . | ROCK MECHANICS AND ROCK ENGINEERING , 2024 , 57 (9) , 7425-7441 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The denoising of microseismic signals is a prerequisite for subsequent analysis and research. In this research, a new microseismic signal denoising algorithm called the Black Widow Optimization Algorithm (BWOA) optimized Variational Mode Decomposition (VMD) joint Wavelet Threshold Denoising (WTD) algorithm (BVW) is proposed. The BVW algorithm integrates VMD and WTD, both of which are optimized by BWOA. Specifically, this algorithm utilizes VMD to decompose the microseismic signal to be denoised into several Band-Limited Intrinsic Mode Functions (BLIMFs). Subsequently, these BLIMFs whose correlation coefficients with the microseismic signal to be denoised are higher than a threshold are selected as the effective mode functions, and the effective mode functions are denoised using WTD to filter out the residual low- and intermediate-frequency noise. Finally, the denoised microseismic signal is obtained through reconstruction. The ideal values of VMD parameters and WTD parameters are acquired by searching with BWOA to achieve the best VMD decomposition performance and solve the problem of relying on experience and requiring a large workload in the application of the WTD algorithm. The outcomes of simulated experiments indicate that this algorithm is capable of achieving good denoising performance under noise of different intensities, and the denoising performance is significantly better than the commonly used VMD and Empirical Mode Decomposition (EMD) algorithms. The BVW algorithm is more efficient in filtering noise, the waveform after denoising is smoother, the amplitude of the waveform is the closest to the original signal, and the signal-to-noise ratio (SNR) and the root mean square error after denoising are more satisfying. The case based on Fankou Lead-Zinc Mine shows that for microseismic signals with different intensities of noise monitored on-site, compared with VMD and EMD, the BVW algorithm is more efficient in filtering noise, and the SNR after denoising is higher.
Keyword ：
black widow optimization algorithm black widow optimization algorithm denoising denoising microseismic signal microseismic signal Variational mode decomposition Variational mode decomposition wavelet threshold denoising wavelet threshold denoising
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Rao, Dijun , Huang, Min , Shi, Xiuzhi et al. A Microseismic Signal Denoising Algorithm Combining VMD and Wavelet Threshold Denoising Optimized by BWOA [J]. | CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES , 2024 , 141 (1) : 187-217 . |
| MLA | Rao, Dijun et al. "A Microseismic Signal Denoising Algorithm Combining VMD and Wavelet Threshold Denoising Optimized by BWOA" . | CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES 141 . 1 (2024) : 187-217 . |
| APA | Rao, Dijun , Huang, Min , Shi, Xiuzhi , Yu, Zhi , He, Zhengxiang . A Microseismic Signal Denoising Algorithm Combining VMD and Wavelet Threshold Denoising Optimized by BWOA . | CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES , 2024 , 141 (1) , 187-217 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Evaluation of ground motion induced by underground blasting is a growing concern due to increased mining of large underground deposits. A numerical analysis is first conducted on the wave propagation characteristics, taking into account geological conditions and ground topography, and it is compared to that resulting from open-pit blasts. Then systemic experiments are conducted at two ore blocks in an underground mine. Predictions are made for peak particle velocity (PPV), frequency, and their combination for ground motions, which are then compared to inside rock vibrations induced by the same ore block blasts. Due to traditional inadequate prediction, the response spectral analysis and the normalized pseudo velocity response spectra (NPVRS) are employed to create a novel approach for illustrating ground motions. The results of numerical calculation and experimental analysis allow for the following conclusions: the wave propagation induced by underground blasting along the ground surface is more complex than that from open-pit blasts; the effect of charge weight on ground vibration decreases with a power factor (n) in the scaling attenuation equation lower than 1/3, as opposed to the typically acceptance of n being 1/2 for open-pit blasts and 1/3 for inside rock vibration induced by underground blasting; the frequency significantly drops from inside rock to ground surface; the NPVRS is a reasonable indicator for quantifying ground motions at specific positions with connecting structural responses, the relative displacement in the concerning frequency range of 5-20 Hz is linearly proportional to ground peak amplitudes. A systematic experimental work on surface ground motion induced by underground blastingComparison of inside rock and ground vibration from underground blastingDecreasing effect of charge weight on ground vibration induced by underground blastingNormalized pseudo velocity response spectra (NPVRS) can be simplified as the same at a specific position for effectively predicting ground vibrations
Keyword ：
Ground vibration Ground vibration Inside rock vibration Inside rock vibration Normalized pseudo velocity response spectra (NPVRS) Normalized pseudo velocity response spectra (NPVRS) Prediction method Prediction method Underground blasting Underground blasting
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Gou, Yonggang , Shi, Lizhen , Huo, Xiaofeng et al. Propagation and Prediction of Blasting Vibration on Ground Surface Induced by Underground Mining with Comparison to Vibration Inside Rock [J]. | ROCK MECHANICS AND ROCK ENGINEERING , 2024 , 57 (12) : 10283-10306 . |
| MLA | Gou, Yonggang et al. "Propagation and Prediction of Blasting Vibration on Ground Surface Induced by Underground Mining with Comparison to Vibration Inside Rock" . | ROCK MECHANICS AND ROCK ENGINEERING 57 . 12 (2024) : 10283-10306 . |
| APA | Gou, Yonggang , Shi, Lizhen , Huo, Xiaofeng , Yu, Zhi , Chen, Yumin . Propagation and Prediction of Blasting Vibration on Ground Surface Induced by Underground Mining with Comparison to Vibration Inside Rock . | ROCK MECHANICS AND ROCK ENGINEERING , 2024 , 57 (12) , 10283-10306 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
During the numerical simulation of blasting in jointed rock masses, the accuracy of joint geometric parameters is one of the key factors affecting the numerical results. To facilitate the numerical simulation, most of the previous studies on blasting in jointed rock masses were conducted on regular jointed rocks, which is not conducive to fully revealing the dynamic responses and blast-induced damage characteristics of jointed rock mass. In this study, scanline sampling and borehole sampling were employed to obtain the surface and internal joint structures of the rock bench. To represent the joint geometry, a reconstruction technique for threedimensional (3D) jointed rock masses in LS-DYNA was proposed utilizing MATLAB code. In the process, the elements on joint surfaces were identified and assigned mechanical parameters of joints to construct the 3D jointed rock model, where the geometrical properties of generated joints obey the statistical distribution obtained from the scanline survey. Taking an open-pit limestone mine as an example, a statistical analysis of the 3D distribution of joints was carried out and used to construct a 3D jointed rock numerical model for bench blasting. Comparisons between the bench slope extracted from the numerical model and the actual joint trace mapping from a rock exposure are performed, and the similarity between the two contour plots of joint orientations reaches 91.6 %. For comparison tests, the bench blasting was simulated by an intact rock model and the jointed rock model. The results indicate that the dynamic responses and blastinduced damage characteristics of jointed rocks are significantly affected by the geometry of joints. Compared with the intact rock model, the presence of joints causes stress concentration and local strengthening of rock damage between adjacent joints, which results in a 30.5 % increase in the damage volume. Furthermore, a field blasting test was conducted to analyze the accuracy of the jointed rock model. The results show that the fragment size distributions obtained from the jointed rock numerical model and the filed test are generally consistent, and the error between them in the proportion of rock fragments with a size of 0 similar to 100 mm is only 12.8 %. These findings indicate that the proposed reconstruction method of the jointed rock model is considerably robust for characterizing the joint geometry of in situ rock masses and simulating the bench blasting in jointed rock masses.
Keyword ：
3D model reconstruction 3D model reconstruction Bench blasting simulation Bench blasting simulation Jointed rock mass Jointed rock mass LS-DYNA LS-DYNA Rock fragmentation Rock fragmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Huo, Xiaofeng , Jiang, Yuanjian , Wei, Wenpeng et al. Three-dimensional finite element simulation and reconstruction of jointed rock masses for bench blasting [J]. | SIMULATION MODELLING PRACTICE AND THEORY , 2024 , 135 . |
| MLA | Huo, Xiaofeng et al. "Three-dimensional finite element simulation and reconstruction of jointed rock masses for bench blasting" . | SIMULATION MODELLING PRACTICE AND THEORY 135 (2024) . |
| APA | Huo, Xiaofeng , Jiang, Yuanjian , Wei, Wenpeng , Qiu, Xianyang , Yu, Zhi , Nong, Junnian et al. Three-dimensional finite element simulation and reconstruction of jointed rock masses for bench blasting . | SIMULATION MODELLING PRACTICE AND THEORY , 2024 , 135 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In cold regions, the dynamic compressive strength (DCS) of rock damaged by freeze-thaw weathering significantly influences the stability of rock engineering. Nevertheless, testing the dynamic strength under freeze-thaw weathering conditions is often both time-consuming and expensive. Therefore, this study considers the effect of characteristic impedance on DCS and aims to quickly determine the DCS of frozen-thawed rocks through the application of machine-learning techniques. Initially, a database of DCS for frozen-thawed rocks, comprising 216 rock specimens, was compiled. Three external load parameters (freeze-thaw cycle number, confining pressure, and impact pressure) and two rock parameters (characteristic impedance and porosity) were selected as input variables, with DCS as the predicted target. This research optimized the kernel scale, penalty factor, and insensitive loss coefficient of the support vector regression (SVR) model using five swarm intelligent optimization algorithms, leading to the development of five hybrid models. In addition, a statistical DCS prediction equation using multiple linear regression techniques was developed. The performance of the prediction models was comprehensively evaluated using two error indexes and two trend indexes. A sensitivity analysis based on the cosine amplitude method has also been conducted. The results demonstrate that the proposed hybrid SVR-based models consistently provided accurate DCS predictions. Among these models, the SVR model optimized with the chameleon swarm algorithm exhibited the best performance, with metrics indicating its effectiveness, including root mean square error (RMSE) = 3.9675, mean absolute error (MAE) = 2.9673, coefficient of determination (R2) = 0.98631, and variance accounted for (VAF) = 98.634. This suggests that the chameleon swarm algorithm yielded the most optimal results for enhancing SVR models. Notably, impact pressure and characteristic impedance emerged as the two most influential parameters in DCS prediction. This research is anticipated to serve as a reliable reference for estimating the DCS of rocks subjected to freeze-thaw weathering. (c) 2024 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).
Keyword ：
Characteristic impedance Characteristic impedance Dynamic compressive strength Dynamic compressive strength Freeze-thaw cycle Freeze-thaw cycle Machine learning Machine learning Support vector regression Support vector regression
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhou, Shengtao , Zhang, Zong-Xian , Luo, Xuedong et al. Predicting dynamic compressive strength of frozen-thawed rocks by characteristic impedance and data-driven methods [J]. | JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING , 2024 , 16 (7) : 2591-2606 . |
| MLA | Zhou, Shengtao et al. "Predicting dynamic compressive strength of frozen-thawed rocks by characteristic impedance and data-driven methods" . | JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING 16 . 7 (2024) : 2591-2606 . |
| APA | Zhou, Shengtao , Zhang, Zong-Xian , Luo, Xuedong , Huang, Yifan , Yu, Zhi , Yang, Xiaowei . Predicting dynamic compressive strength of frozen-thawed rocks by characteristic impedance and data-driven methods . | JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING , 2024 , 16 (7) , 2591-2606 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Petroleum reservoirs are often influenced by various flow behaviours including the mixture of gas, water and oil. The gas relative permeability is used to estimate how much of the gas in the reservoir is producible at a given water saturation level. Therefore, the gas relative permeability is a significant parameter to characterize the behaviour of petroleum reservoirs. However, the measurement of gas relative permeability by traditional methods tends to be comparatively expensive and time-consuming. In the recent years, the machine learning techniques provided new alternatives for predicting the gas relative permeability. For this purpose, five new methods were proposed based on kernel extreme learning machine (KELM) technique. Five meta-heuristic algorithms were adopted to tune the model hyper-parameters of KELMs, i.e., butterfly optimization algorithm (BOA), tunicate swarm algorithm (TSA), Multi-verse optimizer (MVO), Golden jackal optimization (GJO) and Harris hawk's optimization (HHO). Five-fold cross validation was used to increase the model generalization. An extensive dataset from the experiments which contain 1024 data were taken to develop models. Four classical statistical indicators were used to measure the model performance, i.e., root mean squared error (RMSE), coefficient of determination (R2), variance accounted for (VAF) and mean absolute error (MAE). In addition, two comprehensive manners, overall evaluation index (GI) and Taylor Diagram, were evaluated to provide overall model assessments. Proposed hybrid KELM models performed better than several other machine learning techniques. BOA-KELM model with swarm size 150 generated the best generalization for the testing set and could be recommended to predict the gas relative permeability with the same inputs used in this study. The detailed performance of BOA-KELM includes: training set (GI:0.1736; R2: 0.9902; RMSE: 0.7477; VAF: 99.0218; MAE: 10.6636), testing set (GI:0.4164; R2: 0.9789; RMSE: 0.5314; VAF: 97.8917; MAE: 4.1706). The mutual information technique was employed to examine the influence of influential factors to the model interpretation and it can be found that the gas saturation had a larger influence on the hybrid KELM models. When it was used as an individual input, the overall prediction decreased but acceptable prediction performance still can be obtained by hybrid KELM models. In the case of the gas saturation to be the only input, the best testing R2 (0.94) could be generated by MVO-KELM which is higher than the R2 from the empirical method named Corey-Brooks model and several other machine learning techniques. The main novelty of this study is that five new machine learning methods were proposed to predict the gas relative permeability and performed better than other empirical or machine learning techniques. Five new methods based on KELM were proposed to predict gas relative permeability in reservoir.Meta-heuristic algorithms were used to tune the hyper-parameters in KELM.BOA-KELM model with swarm size 150 brought the best generalization ability.Hybrid KELM models performed better than other classical and machine learning model for multi-inputs.Mutual information was used to explore the interpretation of inputs.
Keyword ：
Gas relative permeability prediction Gas relative permeability prediction Kernel Extreme Learning Machine Kernel Extreme Learning Machine Meta-heuristic algorithms Meta-heuristic algorithms Mutual information Mutual information Petroleum reservoirs Petroleum reservoirs
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Enming , Zhang, Ning , Xi, Bin et al. Analysis and modelling of gas relative permeability in reservoir by hybrid KELM methods [J]. | EARTH SCIENCE INFORMATICS , 2024 , 17 (4) : 3163-3190 . |
| MLA | Li, Enming et al. "Analysis and modelling of gas relative permeability in reservoir by hybrid KELM methods" . | EARTH SCIENCE INFORMATICS 17 . 4 (2024) : 3163-3190 . |
| APA | Li, Enming , Zhang, Ning , Xi, Bin , Yu, Zhi , Fissha, Yewuhalashet , Taiwo, Blessing Olamide et al. Analysis and modelling of gas relative permeability in reservoir by hybrid KELM methods . | EARTH SCIENCE INFORMATICS , 2024 , 17 (4) , 3163-3190 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
