Fluid flow in fractures partially filled with porous media is commonly encountered in engineering and scientific research, yet understanding of its nonlinear seepage characteristics remains limited. ...In this study, we employed 2D numerical simulations, utilizing the Navier-Stokes and Darcy-Brinkman-Forchheimer equations to model free and seepage flow in unfilled and filled fracture regions, respectively. By conducting free-seepage flow coupling simulations, we systematically investigated the effects of filling degree, shape, and porous media properties (intrinsic permeability and porosity) on fluid motion characteristics in partially filled fractures. Our results reveal that filling media reduces the main flow region width and enhances nonlinear seepage development, with the non-Darcy effect becoming more pronounced as the filling degree increases and permeability decreases. Due to the influence of the filling medium, the location of the maximum velocity in the fracture is not at the center of the smallest free-flow channel, but rather in a region further back from that position. With the increase of inertia effect, the recirculation zone (RZ) exhibits a complex evolution influenced by the permeability characteristics, with high-permeability filling media initially increasing RZ volume before decreasing (or no RZ is formed), while low-permeability media leads to a gradual increase in RZ volume. Moreover, we developed a novel nonlinear seepage model to evaluate non-Darcy effects in partially filled fractures, incorporating viscous and inertial permeabilities (with R2 = 0.942, 0.988) obtained via gene expression programming (GEP) based on 432 data sets (from 12,528 simulations).
This study presents two approaches (i.e., the material point method (MPM) and gene expression programming (GEP)) for prediction of landslide runout. The MPM was modified based on a strain-softening ...constitutive model. A collapse test and physical model test were conducted to verify the suitability of the modified MPM. The sensitivity analysis was performed to investigate the importance of the softening parameters on the motion characteristics and final accumulation state. In addition, a predictive equation for prediction of the maximum horizontal distance was proposed based on GEP, with the coefficient of determination of 0.8825. The effects of the maximum vertical distance, landslide volume and landslide posture on the maximum horizontal distance were quantitatively analyzed. Moreover, the GEP model was verified by comparison with other machine learning approaches. Finally, taking the Jiweishan landslide as an example, the simulation and prediction results obtained from the MPM and GEP approaches were compared. The results show that the two are both within a reasonable range, with the errors of 14.1% and 10.6%, respectively.
Fiber-reinforced polymer (FRP) is widely used in the field of structural engineering, for example, as a confining material for concrete. The ultimate conditions (i.e., compressive strength and ...ultimate axial strain) are key factors that need to be considered in the practical applications of FRP-confined concrete cylinders. However, the prediction accuracy of existing confinement models is low and cannot provide an effective reference for practical applications. In this paper, a database containing experimental data of 221 FRP-confined normal concrete cylinder specimens was collected from the available literature, and eleven parameters such as the confining stress, stiffness ratio and strain ratio were selected as the input parameters. Then, a promising machine learning algorithm, i.e., group method of data handling (GMDH), was applied to establish a confinement model. The GMDH model was compared with nine existing models, and the prediction results of these models were evaluated by five comprehensive indicators. The results indicated that the GMDH model had higher prediction accuracy and better stability than existing confinement models, with determination coefficients of 0.97 (compressive strength) and 0.91 (ultimate axial strain). Finally, a convenient graphical user interface (GUI) was developed, which can provide a quick and efficient reference for engineering design and is freely available.
In order to achieve the goal of carbon neutralization, hydrogen plays an important role in the new global energy pattern, and its development has also promoted the research of hydrogen fuel cell ...vehicles. The air supply system is an important subsystem of hydrogen fuel cell engine. The increase of air supply can improve the output characteristics of a fuel cell, but excessive gas supply will destroy the pressure balance of the anode and cathode. In the actual operation of a proton-exchange membrane fuel cell, considering the load change, it is necessary not only to ensure the stability of reactor pressure but also to meet the rapid response of inlet pressure and flow in the process of change. Therefore, the coordinated control of the two is the key to improving fuel cell output performance. In this paper, the dynamic model of the intake system is built based on the mechanism and experimental data. On this basis, the double closed-loop proportion integration differentiation (PID) control and feedforward compensation decoupling PID control are carried out for the air supply system, respectively. Then, the fuzzy neural network decoupling control strategy is proposed to make up for the shortcomings that the double closed-loop PID cannot achieve decoupling and the feedforward compensation decoupling does not have adaptability. The results show that the fuzzy neural network control can realize the decoupling between air intake flow and pressure and ensure that the air intake flow and pressure have a good follow-up, and the system’s response speed is fast.
Fischer–Tropsch (F–T) fuel, synthesized from coal-to-liquid (CTL), is an alternative fuel with clean and efficient characteristics. In this study, a surrogate fuel model was developed, including ...n-dodecane (n-C12H26) and iso-octane (i-C8H18), which represents the n-alkane and iso-alkane in F–T fuel synthesized from CTL, respectively. The proportions of the components in the surrogate fuel are determined by the characteristics of the practical fuel, including cetane number (CN), C/H ration and component composition. For the establishment of the skeletal mechanism model, firstly, based on a two-step direct relationship graph (DRG) and the computational singular perturbation (CSP) importance index method, a reduced model of n-dodecane was developed involving 159 species and 399 reactions, while the detailed n-dodecane mechanism consists of 1279 species and 5056 reactions. Then, the n-dodecane skeletal mechanism was constructed based on a decoupling methodology, involving the skeletal C12 mechanism from the reduced mechanism, a C2-C3 sub mechanism and a detailed H2/CO/C1 sub mechanism. Finally, the skeletal mechanism for the F–T surrogate fuel was developed, including the n-dodecane skeletal mechanism and an iso-octane macromolecular skeletal mechanism. The final mechanism for the F–T diesel surrogate fuel consists of 169 species and 406 reactions. The n-dodecane skeletal mechanism and iso-octane skeletal mechanism were validated on various fundamental experiments, including the ignition delay in shock tubes, the primary species concentrations in jet-stirred reactors and the premixed laminar flame over wide operating conditions, which show great agreement between the predictions and measurements. Moreover, an F–T surrogate fuel mechanism was employed to simulate the combustion characteristics of an engine using computational fluid dynamics (CFD). The results show that the mechanism can predict the performance of F–T fuel combustion in engine accurately.
This paper presents two artificial intelligence techniques (e.g., gene expression programming (GEP) and random forest (RF)) for predicting the bond strength of near-surface-mounted (NSM) ...fiber-reinforced polymer (FRP) strips or rods bonded to concrete. Experimental data from 145 direct pullout tests collected from the literature and five parameters, namely, the bond length, FRP axial rigidity, groove depth-to-width ratio, epoxy tensile strength, and concrete compressive strength, were used to develop the GEP and RF models. A comparison was conducted between the proposed GEP and RF models and two existing empirical models, namely, Seracino’s model and Zhang’s model, and six statistical indices were used to evaluate the performance of these four models. The results show that the proposed GEP and RF models had higher coefficient of determination (R2) values and lower root mean squared error (RMSE), mean absolute error (MAE), root relative squared error (RRSE), mean absolute percentage error (MAPE), and integral absolute error (IAE) values than the two existing empirical models. Finally, a detailed parametric study was conducted to investigate the influence of each input variable on the bond strength. The results showed that the bond strength increased with increasing bond length, FRP axial rigidity, groove depth-to-width ratio, and concrete compressive strength, while the epoxy tensile strength had little effect on the bond strength.
Vehicles are subject to a variety of road unevenness and random road excitations that potentially cause the vehicle to undergo a significant amount of energy dissipation, while compromising energy ...efficiency. This paper focuses on designing a novel piezoelectric energy harvester and aims to assess the energy harvesting potential, from the vehicle suspension, under random and pulse road excitations. To describe the energy harvesting process, a dual‐mass suspension system vibration model of a light electric logistics vehicle, equipped with a piezoelectric energy harvester, is developed. Various parameters, such as driving speed, ratio of the moment arms of the lever, and piezoelectric material cross‐sectional area, are included in the model, for basic harvesting energy. The root mean square (RMS) value of harvested power, in the case of random road, is up to 18.83 W, while the maximum respective value, in the case of pulse road, is 102.24 W and is obtained at 30 km/h. The harvested electricity is very valuable and useful, as it can be used to power automotive electrical equipment. The results of this paper provide an important reference frame for future research, related to energy harvesting from vehicle suspension.
Design a novel piezoelectric energy harvester to harvesting the vibration energy and build its analytical model. The accuracy and credibility of the model were verified based on on‐field experimentations of a light vehicle. Analyze the influence of relevant factors on generated electric power.
An efficient and widely tunable Si-prism-array coupled terahertz-wave parametric oscillator (TPO) with a very narrow linewidth is demonstrated by using a shallow surface cross-pump configuration. The ...shallow surface cross-pumping form was realized by totally reflect the pump beam at the THz-wave exit surface. Widely THz-wave tuning range of 0.6–3.9 THz is realized with a 1-mm diameter pump, and the high-frequency end even reached 5.5 THz with a 2-mm diameter pump to increase the nonlinear gain length. The measured Stokes linewidth was 0.07 nm, which is compressed by 70% for that of the conventional TPOs. The highest THz-wave output energy of 2.4 μJ was achieved at 2 THz under 15 mJ pumping, corresponding to an energy conversion efficiency of 1.6 × 10
−4
. The mechanism of the frequency-selection effect in cross-pumped stimulated polariton scatterings was discussed by calculating the single-pass parametric gain for different phase mismatches.
The coefficient of permeability is the most important parameter for characterizing the permeability characteristics of soil. In this study, a database of the coefficient of permeability (k) for soils ...was compiled firstly, including effective size (d10), mean grain size (d50), the particle diameters at the cumulative percent content of 60% (d60) and void ratio (e), which can reflect the impact of the particle size distribution characteristics. Gene expression programming (GEP), was employed to develop a predictive equation of k, which is convenient for engineering application. The GEP model was compared with eight empirical models and other artificial intelligence models (i.e., random forest (RF) and group method of data handling (GMDH)). The results show that the GEP model and RF model have the highest accuracy, followed by GMDH model and empirical models. Then, the sensitivity analysis was conducted. According to the results, k increases with increasing d10, d50 and e; the effective size d10 has the largest influence on k, followed by d50 and e, which indicates that fine particle content has the control effect on seepage and the effect of soil gradation parameters on k is greater than that of void ratio. Additionally, the SHAP and PDP analysis were conducted to investigate the feature importance and conditional expectation of each feature. The feature importance order is d10 > d50 > e > d60, and the SHAP values of d10, d50 and e increase with the increase of them, while the SHAP value of d60 is basically unchanged.
Abstract
Background
The lint percentage of seed cotton is one of the most important parameters for evaluating seed cotton quality and affects its price. The traditional measuring method of lint ...percentage is labor-intensive and time-consuming; thus, an efficient and accurate measurement method is needed. In recent years, classification-based deep learning and computer vision have shown promise in solving various classification tasks.
Results
In this study, we propose a new approach for detecting the lint percentage using MobileNetV2 and transfer learning. The model is deployed on a lint percentage detection instrument, which can rapidly and accurately determine the lint percentage of seed cotton. We evaluated the performance of the proposed approach using a dataset comprising 66 924 seed cotton images from different regions of China. The results of the experiments showed that the model with transfer learning achieved an average classification accuracy of 98.43%, with an average precision of 94.97%, an average recall of 95.26%, and an average F1-score of 95.20%. Furthermore, the proposed classification model achieved an average accuracy of 97.22% in calculating the lint percentage, showing no significant difference from the performance of experts (independent-sample
t-
test,
t
= 0.019,
P
= 0.860).
Conclusion
This study demonstrated the effectiveness of the MobileNetV2 model and transfer learning in calculating the lint percentage of seed cotton. The proposed approach is a promising alternative to traditional methods, providing a rapid and accurate solution for the industry.