Optimal Structure Research Articles

Numerical Modeling and Structure Optimization for Magnetic Levitation Planar Machine Using PCB Coils

Magnetically levitated (ML) systems that incorporate PCB coils represent a growing trend in precision machining, valued for their controllable current flow and high fill factor. The size of modern power devices is decreasing to enhance power density, minimize parasitic inductance, and reduce power losses. However, due to the high resistance of PCB coils, managing heat generation has become a significant area of study. This paper seeks to optimize PCB coil design to minimize power loss and control peak temperatures in ML systems, using a numerical model. An improved magnetic node model is employed to construct the magnetic fields of an ML system. The proposed optimization method considers the interdependencies among parameters to reduce overall power loss from coil resistance and switching losses in the H-bridge circuit, while enhancing heat dissipation efficiency in steady-state operation. A heuristic multi-objective optimization algorithm is employed to optimize the design of the ML actuator. The optimization process initially focuses on the PCB coils, with the magnet size held constant. Once the optimal coil parameters are identified, the magnet volume is optimized. By integrating a theoretical analysis with simulation, this approach effectively addresses the optimization challenges and achieves the desired performance for the ML actuator. Coils and magnets are constructed based on the optimized design and tested by the magnetic field simulation software Radia, confirming the feasibility of the approach. The method was also applied to a different type of ML system for comparison, demonstrating the universality of the proposed strategy. In this optimization effort, the maximum temperature reduction reached an impressive 50 °C

Power system optimization dispatch for energy conservation and emission reduction

This paper examines the optimization of power system dispatching with a focus on energy conservation and emission reduction. Through analyzing current situations and challenges, it aims to propose effective strategies and methods to achieve efficient power system operation while protecting the environment. The article commences by detailing China's advancements and obstacles in energy conservation and emission reduction within its power system. It addresses issues such as the variability of renewable energy sources, efficiency constraints in thermal power generation units, the intricate nature of the power grid infrastructure, and the novel challenges introduced by reforms in the electricity market. Subsequently, the paper presents four major strategies: priority dispatching of clean energy, flexible dispatching of thermal power units, power grid structure optimization, and market mechanism introduction. Research findings, when integrated with practical case studies, demonstrate that the utilization of virtual power plants and advanced dispatching systems can markedly enhance the capacity for clean energy consumption, decrease the operational duration of thermal power units and the intensity of carbon emissions, while simultaneously improving the overall efficiency of power systems. This research holds significant importance for promoting green and sustainable development in the power industry

Optimization of high-dimensional expensive multi-objective problems using multi-mode radial basis functions

Numerous surrogate-assisted evolutionary algorithms are developed for multi-objective expensive problems with low dimensions, but scarce works have paid attention to that with high dimensions, i.e., generally more than 30 decision variables. In this paper, we propose a multi-mode radial basis functions-assisted evolutionary algorithm (MMRAEA) for solving high-dimensional expensive multi-objective optimization problems. To improve the reliability, the proposed algorithm uses radial basis functions based on three modes to cooperate to provide the qualities and uncertainty information of candidate solutions. Meanwhile, bi-population based on competitive swarm optimizer and genetic algorithm are applied for better exploration and exploitation in high-dimensional search space. Accordingly, an infill criterion based on multi-mode of radial basis functions that comprehensively considers the quality and uncertainty of candidate solutions is proposed. Experimental results on widely-used benchmark problems with up to 100 decision variables demonstrate the effectiveness of our proposal. Furthermore, the proposed method is applied to the structure optimization of the blended-wing-body underwater glider (BWBUG) and gets impressive solutions.

Discovery of Brain-Penetrative Negative Allosteric Modulators of NMDA Receptors Using FEP-Guided Structure Optimization and Membrane Permeability Prediction.

N-Methyl-d-aspartate (NMDA) receptors, a subtype of ionotropic glutamate receptors in the central nervous system (CNS), have garnered attention for their role in brain disorders. Specifically, GluN2A-containing NMDA receptors have emerged as a potential therapeutic target for the treatment of depressive disorders and epilepsy. However, the development of GluN2A-containing NMDA receptor-selective antagonists, represented by N-(4-(2-benzoylhydrazine-1-carbonyl)benzyl)-3-chloro-4-fluorobenzenesulfonamide (TCN-201) and its derivatives, faces a significant challenge due to their limited ability to penetrate the blood-brain barrier (BBB), hampering their in vivo characterization and further advancement. In this study, we reported a series of 2-((5-(phemylamino)-1,3,4-thiadiazol-2-yl)thio)-N-(cyclohexylmethyl)acetamide derivatives, achieved through a structure-guided optimization strategy using free energy perturbation (FEP) and BBB permeability estimation. Through systematic exploration of various phenyl substitutions, compound 1f emerged as a standout compound, demonstrating substantially enhanced inhibitory activity compared with the lead compound TCN-213. Compound 1f not only displayed satisfactory BBB permeability but also showed antidepressant-like potency in the hydrocortisone-induced zebrafish depression-like model. All results position it as a promising candidate for developing innovative therapeutics for NMDA receptor-related disorders.

The impact of digital intelligence on energy-intensive firms’ green transformation

Abstract The green transformation of energy-intensive firms is expected to make an outstanding contribution to global carbon neutrality. Digital intelligence, the new phase of digitalization, has injected fresh momentum into corporate green development. Most previous studies focused on the green effect of digitalization using statistical data from listed firms, and failed to make detailed exploration on the impact of digital intelligence on energy-intensive firms' green transformation based on survey data. Based on empowerment theory and technology-organization-environment theory, this study proposed a three-dimensional concept of digital intelligence, including digital intelligence technology, digital intelligence organization and digital intelligence environment. Using survey data from 348 energy-intensive firms in China, this paper employed the structural equation modeling and bootstrap test to investigate the influence of digital intelligence on energy efficiency transformation and green emission transformation, and the mediating effect of energy management. The results indicate that digital intelligence technology, digital intelligence organization and digital intelligence environment promote energy efficiency and green emission of energy-intensive firms. Energy management is the key to the green transformation of energy-intensive firms in the context of digital intelligence. Specifically, energy saving literacy, energy audit, and energy use structure optimization play the positive mediating effects between digital intelligence and energy-intensive firms’ green transformation. It is worth noting that the mediating effect of energy saving literacy between digital intelligence environment and energy-intensive firms' green transformation is insignificant. These findings provide policy and practice references for the government and practitioners in energy-intensive industries to leverage digital intelligence to promote green sustainability.

A comprehensive study on the sandwich stacking structures of antiferroelectric/ferroelectric doped hafnium oxide

In this paper, the combinations of sandwich stacking structures of antiferroelectric/ferroelectric doped hafnium oxide are systematically explored. The sandwich stacking ferroelectric capacitors with the optimal structure (2 nm ferroelectric HZO/4 nm antiferroelectric HZO/2 nm ferroelectric HZO) exhibit high remanent polarization (2Pr = 48 μC/cm2), low coercive field (1.15 MV/cm), and excellent retention ability (8% degraded Pr after 105 s) at a low operating voltage of 1.8 V. The endurance of this structure has also been enhanced to over 1010 cycles, compared with the control group of 8 nm ferroelectric HZO (∼109 cycles). This study provides a promising solution for the application of the embedded FeRAM and advanced silicon technology nodes with low-power consumption.

Cooperative co-evolution deep echo state network for time series prediction

Abstract The deep echo state network demonstrates strong predictive performance in time series tasks, but inter-layer weight optimization and reservoir structure design are still challenging tasks. To address this, we propose the cooperative co-evolutionary deep echo state network (CCEDESN). Firstly, inspired by the hierarchical structure of the brain, we introduce a modular hierarchical design. Each layer of the reservoir contains multiple sub-reservoirs, with central neurons in each sub-reservoir interacting with those in other sub-reservoirs to enhance information processing. Secondly, an advanced cooperative co-evolutionary algorithm is proposed to simultaneously optimize the layer connection weights and hyperparameters of the deep echo state network. We evaluate the CCEDESN model on the Mackey-Glass system, sunspot data, and Apple stock opening prices. The experimental results show that the CCEDESN model achieves superior prediction accuracy compared to other models.

The biomechanical effects of treating double-segment lumbar degenerative diseases with unilateral fixation through interlaminar fenestration interbody fusion surgery: a three-dimensional finite element study

BackgroundTransforaminal lumbar interbody fusion (TLIF) surgery has become increasingly popular in the surgical treatment of lumbar degenerative diseases. The optimal structure for stable double-segment fixation remains unclear.ObjectiveTo compare the biomechanical changes of unilateral fixation versus bilateral fixation in patients with lumbar degeneration undergoing double-segment TLIF surgery, and to explore the stability and feasibility of unilateral double-segment fixation.MethodsA three-dimensional finite element model of L3-5 was established based on CT data from a recruited young male volunteer, and the model was validated to have reasonable predictive capability. Surgical procedures were simulated by adjusting bony structures to create models of unilateral and bilateral fixation for double-segment TLIF. Under a pure moment of 10 Nm, range of motion (ROM), extension, lateral bending, axial rotation movements, as well as stresses on interbody fusion devices, internal fixation, and endplates were recorded and compared.ResultsUnilateral fixation was fixed on the left side, with both groups performing flexion, extension, left lateral flexion, right lateral flexion, left rotation, and right rotation movements. All reconstructed conditions showed decreased motion from L3 to L5. Unilateral fixation had greater lumbar spine range of motion (ROM) in all directions compared to bilateral fixation. The greatest difference between the two occurred during right lateral flexion at the L3-4 segment, measuring 1.78°. During right lateral flexion at the L4-5 segment, the largest difference was 2.29°. Regarding stress on the fusion devices, unilateral fixation models exhibited higher stresses than bilateral fixation models, but no significant differences in stability were found. Terminal plate stress in unilateral posterior fixation was higher during flexion than in the bilateral model, showing a similar trend in stress changes. No significant difference was seen in internal fixation stress between the two groups during two-segment fusion, with the posterior internal fixation stress in unilateral fixation being 1.7 times higher during flexion and 1.9 times higher during left bending compared to bilateral fixation.ConclusionUnilateral fixation in two-segment transforaminal lumbar interbody fusion (TLIF) surgery can increase stability compared to bilateral fixation, with no significant differences observed between the two models. Unilateral two-segment fixation allows for greater lumbar spine mobility than bilateral fixation, albeit with a slight increase in stress on the posterior fixation and fusion devices under the unilateral fixation mode. This provides some biomechanical evidence for selecting surgical approaches for elderly patients who cannot tolerate long surgeries, suggesting that two-segment unilateral fixation may be advisable.Clinical trial numberNot applicable.

Simulation Research on Data Acquisition and Supervisory Control System of Distribution Network Based on Vector Regression Model

With the gradual maturity of deep learning and the Internet of Things, a smart grid is urgently needed to be established. For the intellectualization of the power grid, non-intrusive load monitoring (NILM) technology is the key step of intellectualization. The traditional load monitoring method is an invasive scheme, in which monitoring sensors are usually installed at the output end of each grid load. This method requires a lot of manpower and material resources in terms of equipment installation and maintenance, which is difficult to sustain. Therefore, monitoring electrical appliances are installed at the entrance of the distribution network to decompose the classification and operation status of the individual electrical appliances in the grid. Aiming at the problem of long-term multi-state electrical apparatus monitoring, this paper mainly optimizes the two optimal deep learning models Seq2Seq and WindowGRU based on activation function optimization, regular function optimization and neural network structure optimization. PReLU, Leaky-ReLU and ELU are used and tested. For the optimization based on regular functions, the value of F1-score is 0.9700, which is 0.1534 more than the optimization algorithm Seq2SeqLR in this paper. Meanwhile, it can also reach 0.8100 for other devices, which is 0.2373 more than the nilmTCN designed in this paper. The Recall value of the identification is improved to 0.6673, which is significantly higher than that of other models. It is proved that the research contents of this paper can improve the effective analysis of load energy consumption data, and can minimize unnecessary energy consumption to achieve the purpose of saving electricity.

Efficient Catalysis for Zinc-Air Batteries by Multiwalled Carbon Nanotubes-Crosslinked Carbon Dodecahedra Embedded with Co-Fe Nanoparticles.

The design and fabrication of nanocatalysts with high accessibility and sintering resistance remain significant challenges in heterogeneous electrocatalysis. Herein, a novel catalyst is introduced that combines electronic pumping with alloy crystal facet engineering. At the nanoscale, the electronic pump leverages the chemical potential difference to drive electron migration from one region to another, separating and transferring electron-hole pairs. This mechanism accelerates the reaction kinetics and improves the reaction rate. The interface electronic structure optimization enables the CoFe/carbon nanotube (CNT) catalyst to exhibit outstanding oxygen reduction reaction (ORR) and oxygen evolution reaction (OER) performance. Specifically, this catalyst achieves an ORR half-wave potential (E₁/₂) of 0.895V, outperforming standard Pt/C and RuO₂ electrocatalysts in terms of both specific activity and stability. It also demonstrates excellent electrochemical performance for OER, with an overpotential of only 287mV at a current density of 10mA cm⁻2. Theoretical calculations reveal that the carefully designed crystal facets reduce the energy barrier of the rate-determining steps for both ORR and OER, optimizing O₂ adsorption and promoting the oxygen capture process. This study highlights the potential of developing cost-effective bifunctional ORR-OER electrocatalysts, offering a promising strategy for advancing Zn-air battery technology.

Research on the optimization of drum structure based on virtual prototyping technology

Drums are the core working mechanism of the coal mining machine for coal mining. The structural design level of the drum is crucial for mining efficiency and safety production. Traditional design methods not only have long design cycles and high costs, but also limited design capabilities. This study used computer numerical simulation methods to establish coupled models for drum cutting complex coal seams, which was used to obtain the working performance of drums with different structures. By fitting the comprehensive performance evaluation function of the drum, the optimal structural parameters are obtained through the improved Non-Dominated Sorting Genetic Algorithms (NSGA-II). Taking into account both technical and economic factors, the optimal helix angle is ultimately determined to be 18°, the optimal installation angle is 45°, and the optimal cutting distance is 71 mm. Through experiments, it has been proven that the performance of the optimized drum has significantly improved. Specifically, the average cutting resistance has been reduced by 12.72%, the load fluctuation coefficient has been reduced by 9.81%, the cutting specific energy consumption has been reduced by 2.85%, and the coal loading rate has been increased by 9.59%, providing a reference for the optimization design of the shearer drum structure.

Bayesian predictive system for assessing the damage intensity of residential masonry buildings under the impact of continuous ground deformation

The paper introduces a method for predicting damage intensity in masonry residential buildings situated in mining areas, focusing on the impact of large-scale continuous ground deformation. The research utilizes in situ data collected in a database, encompassing structural and material features, as well as information on maintenance quality and building durability. In addition to this information, the database collected data on the intensity of continuous deformation of the mining area at the location of the building, as well as the range and intensity of damage identified in buildings. The information included in the database was the result of many years of observations of buildings during the disclosure of impacts from mining exploitation and was based on: the results of in-situ building inventory, analysis of available building documentation and information provided by mining companies. The archived data were categorized variables labeled. The transformation of the data to a labeled value was dictated directly by the assumptions of the GOBNILP algorithm. Ultimately, a predictive model, represented by an optimal Bayesian network structure, is established. The optimisation of the network structure is achieved through the adaptation of the GOBNILP Bayesian network learning algorithm from data. This optimisation process is executed through the Gurobi Optimizer. It is worth noting that this interdisciplinary approach represents one of the first applications of such a methodology in the field of civil and environmental engineering. The results obtained can therefore be of significant value given the fact that the methodology of detecting the structure of Bayesian networks from data is still developing intensively in other scientific fields. In the course of the analyses, metric scores are examined, and various network structures are assessed based on their complexity. Great values of classification accuracies over 91% were obtained. This meticulous evaluation allows for the selection of the optimal Bayesian network that best generalises the knowledge acquired during the learning process. The paper also demonstrates the potential application of the obtained model in diagnosing damage causes and predicting future occurrences, highlighting the versatility of the proposed approach for addressing issues in the field.

PC-YOLO11s: A Lightweight and Effective Feature Extraction Method for Small Target Image Detection

Compared with conventional targets, small objects often face challenges such as smaller size, lower resolution, weaker contrast, and more background interference, making their detection more difficult. To address this issue, this paper proposes an improved small object detection method based on the YOLO11 model—PC-YOLO11s. The core innovation of PC-YOLO11s lies in the optimization of the detection network structure, which includes the following aspects: Firstly, PC-YOLO11s has adjusted the hierarchical structure of the detection network and added a P2 layer specifically for small object detection. By extracting the feature information of small objects in the high-resolution stage of the image, the P2 layer helps the network better capture small objects. At the same time, in order to reduce unnecessary calculations and lower the complexity of the model, we removed the P5 layer. In addition, we have introduced the coordinate spatial attention mechanism, which can help the network more accurately obtain the spatial and positional features required for small targets, thereby further improving detection accuracy. In the VisDrone2019 datasets, experimental results show that PC-YOLO11s outperforms other existing YOLO-series models in overall performance. Compared with the baseline YOLO11s model, PC-YOLO11s mAP@0.5 increased from 39.5% to 43.8%, mAP@0.5:0.95 increased from 23.6% to 26.3%, and the parameter count decreased from 9.416M to 7.103M. Not only that, we also applied PC-YOLO11s to tea bud datasets, and experiments showed that its performance is superior to other YOLO-series models. Experiments have shown that PC-YOLO11s exhibits excellent performance in small object detection tasks, with strong accuracy improvement and good generalization ability, which can meet the needs of small object detection in practical applications.

Germanium oxidation state and substitution mechanism in Ge-rich sphalerite from MVT deposits: constraints from X-ray absorption fine structure (XAFS) and geometry optimization

Germanium oxidation state and substitution mechanism in Ge-rich sphalerite from MVT deposits: constraints from X-ray absorption fine structure (XAFS) and geometry optimization

A new tool for shape and structure optimization of soft materials.

A new tool for shape and structure optimization of soft materials.

Can “energy-saving and emission reduction” demonstration city pilot alleviate carbon inequality in Chinese cities?

As a pivotal element in China’s pursuit of a sustainable development model, green fiscal policies have become increasingly important amid the exacerbation of global climate conditions. Regrettably, little attention has been paid to comprehending the carbon allocation effects of the implementation of these policies. This study focuses on the “National Comprehensive Demonstration City of Energy Saving and Emission Reduction Fiscal Policy” (ESER policy) as the focal point of analysis. Using a multi-period difference-in-differences model, we assessed the implications of ESER policies on carbon inequality. This study further explored asymmetry, mechanism effects, and heterogeneity. Our empirical findings demonstrate that the ESER policy directly reduced carbon inequality by 11.4% in the demonstration cities. This conclusion withstood rigorous testing, including parallel trend assessments, robustness analyses, and endogeneity diagnostics. Moreover, the ameliorative implications of the ESER policy on carbon inequality in demonstration cities are predominantly realized by facilitating cleaner production technological innovation, end-of-pipe treatment technological innovation, industrial structure rationalization, and industrial structure optimization. Furthermore, the ameliorative implications of the ESER policy on carbon inequality were conspicuous in the upper quantiles. Finally, the urban magnitude, geographical location, resource endowment, and innovation foundation of a demonstration city exert diverse influences on policy implementation. These empirical results provide valuable guidance for the Chinese government in formulating climate policies with a focus on carbon equity considerations.

Spatial-temporal Evolution and Influencing Factors of Land Use Carbon Emissions in Shandong Province

Exploring the spatial-temporal evolution characteristics of land use carbon emissions and their influencing factors is of great significance for the optimization of land use structure, the formulation of emission reduction policies, and the development of a regional low-carbon economy. Based on land cover and energy consumption data, a multi-parameter land use carbon emission accounting system was constructed to calculate land use carbon emissions in Shandong Province. Moreover, the spatial-temporal evolution and influencing factors of land use carbon emissions were analyzed based on the Gini coefficient and logarithmic mean Divisia index. The results indicated that ① From 2000 to 2020, construction land, woodland, and water area showed a generally increasing trend, while cropland, grassland, and unused land area showed a decreasing trend. The spatial change in land use types was mainly concentrated in the conversion of cropland into construction land （1.09×104 km2）. ② In the study period, carbon emissions from land use in Shandong Province increased from 52.70 million tons to 352.97 million tons, and the annual growth rate decreased from 13.40% to 7.28%, construction land was the primary carbon source, and cropland sequestered carbon. ③ Land use carbon emissions showed significant spatial imbalance at a grid level （Gini > 0.5）, with an overall spatial pattern of "high in the east" and "low in the west." ④ Economic development was the dominant leading factor for the growth of carbon emissions from land use in Shandong Province （contribution rate of 121.33%）, followed by the construction land area effect （33.39%）, while energy structure （-11.12%）, energy efficiency （-20.16%）, and population size effects （-23.44%） limited the increase in carbon emissions.

Toward mass adoption of electric vehicles: policy optimisation under different infrastructure investment scenarios

Mass adoption of electric vehicles (EVs) is seen as a key solution for environmental degradation and a low-carbon economy. To promote EV adoption, the government's should choose the most efficient subsidy scheme from three options: a pure purchase subsidy for consumers, a pure infrastructure subsidy for automakers, or a combination of both. This study models the interactions among the government, automakers, and consumers using a Stackelberg game to identify the optimal subsidy structure, considering supply chain structures and infrastructure investments. Our findings show that a pure subsidy is optimal only when the supplier invests in charging infrastructure. However, if the automaker invests in infrastructure, a combination of both subsidies becomes beneficial. The government’s subsidy strategy depends on the adoption target and infrastructure investment costs. A combined policy is optimal when both the target and costs are high; otherwise, a pure subsidy is more cost-effective. Additionally, we find a complementary relationship between government subsidies and competition. Competition within the EV supply chain reduces the need for large subsidies, helping alleviate the government’s financial burden. Finally, while the most cost-effective subsidy scheme may be efficient in reducing costs, it can lead to poor economic performance and lower profits in certain cases.

Design, Synthesis, and Antibacterial Activity of Novel Sulfone Derivatives Containing a 1,2,4-Triazolo[4,3-a]Pyridine Moiety.

To develop antibacterial agents with a novel mechanism of action, a series of sulfone compounds containing a 1,2,4-triazolo[4,3-a]pyridine were designed and synthesized by progressive molecular structure optimization. The antibacterial activities of some derivatives against the four plant pathogens Xanthomonas oryzae pv. oryzae (Xoo), Xanthomonas oryzae pv. oryzicola (Xoc), Xanthomonas axonopodis pv. citri (Xac), and Pseudomonas syringae pv. actinidiae (Psa) were evaluated. Among them, compound K3 demonstrated significant antibacterial activities against Xoo, Xoc, and Xac, with EC50 values of 1.5, 1.7, and 4.9 mg/L, respectively. In the greenhouse, compound K3 exhibited a protective activity of 44.49% and a curative activity of 42.51% against rice bacterial leaf blight, which notably surpassed the traditional agents thiodiazole-copper (24.65% and 23.35%) and bismerthiazol (34.69% and 30.78%). Furthermore, compound K3 can inhibit the growth of pathogenic bacteria by inhibiting a variety of virulence factors (extracellular polysaccharides, biofilms, and motile and extracellular enzymes.). It also induced the production of reactive oxygen species (ROS) by the pathogens, leading to their death. Transcriptomic analysis revealed that K3 impacts rice biosynthesis, biofilm formation, and metabolic processes, enhancing the plant's self-defense biochemical processes and affecting carbohydrate transport and metabolism to resist pathogen invasion. Therefore, the inhibition of virulence factors as a strategy for controlling difficult-to-treat plant bacterial diseases presents a promising approach to the discovery of novel antibacterial candidates.

Mechanical performance and ANN-based prediction of Co-Cr dental alloys with gyroid cellular structures produced by LPBF technology

Gyroid structures exhibit significant potential in the fields of lightweight structural design, heat transfer, energy absorption, and biological applications. The use of gyroid for implants in dentistry is currently not sufficiently widespread. The research encompasses design, compression testing, cellular investigation using a digital microscope, and the application of artificial neural networks (ANNs) using data gained from the compression test. The ANN study and the test phase in which gyroid geometries are addressed by dental three-point bending tests are novel in this field. In the field of dentistry, this study compares the usability of five distinct gyroid design characteristics, including one model without a gyroid structure. During the testing, we found that the m1 model had an average maximum strength of 600 N, while the m3 model achieved 230 N. The remaining models achieved an approximate strength of 200 N. In the mechanical performance evaluation of the samples, a 40% weight reduction was achieved. An ANN model has been developed to predict the force experienced by gyroid structures under certain deformations depending on the infill ratio. This model was trained with data obtained from a three-point bending test. Using grid search and Monte Carlo cross-validation, the optimal multilayer perceptron structure was determined to have 12 neurons in the hidden layer, a mini-batch size of 8, and a learning rate of 0.0001. The Adam optimization algorithm was used to train the ANN model, which was constructed using the TensorFlow library. Evaluation metrics were used to test the model’s performance, and the results showed strong generalization capability and high accuracy with coefficient of determination ( R2) of 0.997, mean squared error (MSE) of 3.337E-05 kN2, root mean square error of (RMSE) 0.005777 kN, and mean absolute error (MAE) of 0.003633 kN on the test dataset.