Traditional Finite Element Analysis Research Articles

Graph Neural Network Graph Embedding Optimization Method for Vascular Stress Prediction

This study focuses on the accurate prediction of vascular stress by using graph neural network, and innovatively proposes a graph embedding method adapted to vascular structure. By comparing with the traditional finite element vertex diagram representation, and deeply analyzing various key factors affecting vascular stress, the efficiency and accuracy of this method are fully verified, which provides potential technical support for vascular mechanics research and related disease diagnosis. In biomedical engineering, vascular stress analysis is very important for the diagnosis and treatment of cardiovascular diseases. Although the traditional finite element analysis is accurate, it has high calculation cost and poor adaptability in the face of complex vascular geometry, material nonlinearity and diverse loads. In this study, an innovative vascular graph embedding method is proposed, and different segments of blood vessels are regarded as vertices to build models, which effectively reduces complexity. GraphSAGE algorithm is used to predict stress, and compared with the traditional finite element vertex graph representation, research is carried out. Comprehensively consider the geometric changes of blood vessels, curvature, uneven pipe diameter and branch structure; Simulating the nonlinearity of materials under physiological and pathological conditions; Set boundary conditions such as vascular end fixation, elastic support and freedom; Covers uniform, concentrated and dynamic blood flow loads. Experiments show that the new method has obvious advantages, the memory occupation of GPU is reduced to about 2%, and the training time is reduced to 4%. Its GraphSAGE model is accurate in stress prediction, and the average accuracy of the maximum von Mises stress is 92.3%. This achievement shows the potential of graph neural network and new graph embedding method in vascular stress analysis, which can provide key support for the research and treatment of vascular diseases and strongly promote the development of biomechanics and medical engineering.

Slope Calculation Analysis Based on Arbitrary Polygonal Hybrid Stress Elements Considering Gravity

This article proposes an arbitrary polygonal hybrid stress element considering gravity. It derives an arbitrary polygonal hybrid stress element considering gravity alone for slope stability related engineering analysis. In the stability analysis of slopes, slope disasters caused by gravity erosion have recently become an urgent problem to be solved through engineering. The traditional finite element analysis of slope stability faces problems such as a large number of divided elements and slow calculation efficiency. By introducing high-order stress fields through stress hybridization elements, accurate results can be simulated using a small number of elements. When dividing the mesh, most of the cell shapes are asymmetric, and the shape of the cell can be any polygon, which can simulate the geometric shape of complex slopes well and more accurately calculate the stress distribution in different parts, thus accurately simulating the stability situation in engineering. By comparing with the corresponding commercial software MARC 2020, the effectiveness and efficiency of the element were verified. It has been proven that any polygonal hybrid stress element has the advantage of flexible mesh division, which can obtain high-order stress fields and stress concentration phenomena with fewer elements. Applying this element to practical problems of slopes in engineering has also achieved good calculation results.

The development of mortar method for the non-conforming multi-patch elastic problems in isogeometric analysis

Abstract Isogeometric Analysis (IGA) leverages Non-Uniform Rational B-Splines (NURBS) for complex geometries, offering an attractive alternative to traditional Finite Element Analysis (FEA). However, connecting NURBS patches in IGA often requires non-conforming interfaces. The Mortar method addresses this challenge by efficiently coupling such interfaces in solving Partial Differential Equations (PDEs). This work presents a novel development of the Mortar method tailored explicitly for non-conforming multi-patch elastic problems in IGA. We introduce a novel formulation for the coupling coefficient within the Mortar method, ensuring accurate solution transfer across non-matching interfaces. The efficient implementation of this method in the IGA framework is also presented. The effectiveness of the proposed method is demonstrated through numerical examples, showcasing its ability to handle complex geometries with significant computational speedup compared to conforming patches. Validation is performed using established benchmark problems in linear elasticity. Finally, we discuss the advantages and limitations of the proposed Mortar method, highlighting its potential for practical engineering applications. We also identify promising avenues for future research in this area. This work contributes significantly to developing robust IGA techniques for complex engineering problems involving multi-patch domains. It provides a valuable resource for researchers and practitioners seeking efficient solutions for elastic analysis using IGA.

MainModelingStr: A Structural Dynamic Nonlinear Analysis Framework with Adaptive Beam-Column Finite Elements

This study introduces a new method for nonlinear structural analysis of buildings using high-order Hermitian interpolation function matrices for Timoshenko elements. This method aims to improve the accuracy of traditional beam-column finite element analyses by using higher-order shape function polynomials. Thus, a p-adaptive procedure is employed to address the potential issues of increased complexity and round-off error associated with higher-order functions. The study uses a technique for removing outliers in the p-adaptive method, which is more consistent with the theoretical approach. Moreover, a novel strategy based on the generalized alpha method is applied to reduce even more convergence problems, allowing its parameters to adapt in each instant of the time-history analysis. These adaptive parameters permit setting a low tolerance error and avoiding changing these parameters manually in time-consuming analyses. The efficiency of using fourth-order beam-column elements is also investigated. Finally, the importance of the proposed method is demonstrated through examples of building analyses, which is the base of a proposed software called MainModelingStr.

Enhancing Prediction Performance and Generalizing for Transverse Behavior of Unidirectional Composites via Strategic Input Feature Augmentation

AbstractThis study proposes an efficient method for analyzing complex fracture patterns in the cross‐sections of unidirectional (UD) composites, influenced by the volume fraction (VF) and fiber arrangement, and for predicting the corresponding transverse mechanical responses. Traditional finite element (FE) analysis incurs high computational costs when evaluating responses for every configuration. To address this, deep learning (DL), particularly convolutional neural networks (CNNs), have been applied, but these approaches have typically focused on limited VF spaces, leading to large data requirements and reduced prediction accuracy for new configurations. In this research, a novel DL approach is introduced that can be effectively extended to broader VF spaces by integrating low‐cost, physically insightful auxiliary features as multi‐modal inputs. Specifically, the Mori–Tanaka (MT) feature and stress concentration factor (SCF) are selected as auxiliary inputs and incorporated them into the conventional CNN model for comparative analysis. The results showed that the model incorporating the MT feature significantly improved extrapolation performance in unseen VF spaces while maintaining robust predictive performance as the training dataset size increased. In contrast, the SCF feature does not demonstrate similar benefits. These findings illustrate that integrating advanced features like the MT feature into the DL model can offer more effective and versatile solutions for predicting material properties.

Towards a real-time simulation of elastoplastic deformation using multi-task neural networks

This study introduces a surrogate modeling framework merging proper orthogonal decomposition, long short-term memory networks, and multi-task learning, to accurately predict elastoplastic deformations in real-time. Superior to single-task neural networks, this approach achieves a mean absolute error below 0.40% across various state variables, with the multi-task model showing enhanced generalization by mitigating overfitting through shared layers. Moreover, in our use cases, a pre-trained multi-task model can effectively train additional variables with as few as 20 samples, demonstrating its deep understanding of complex scenarios. This is notably efficient compared to single-task models, which typically require around 100 samples. Significantly faster than traditional finite element analysis, our model accelerates computations by approximately a million times, making it a substantial advancement for real-time predictive modeling in engineering applications. While it necessitates further testing on more intricate models, this framework shows substantial promise in elevating both efficiency and accuracy in engineering applications, particularly for real-time scenarios.

Impact of layer orientation and interlayer inhomogeneity on the bending properties of plain weave CFRP laminates

AbstractPlain weave carbon fiber reinforced polymer (CFRP) laminates have garnered widespread attention in the aerospace and automotive industries due to their exceptional mechanical properties and lightweight structure. During the production of laminates, the thickness of each layer is often nonuniform. In traditional finite element analysis (FEA), the laminates are usually assumed to be uniformly layered, which can introduce some errors. Thus, there is room for improvement in prediction accuracy. This study explores the bending performance of plain weave CFRP laminates at different orientation angles of the layers, employing both experimental and FEA. In contrast to traditional methods, using images of weave structures captured by metallographic microscopy to create the representative volume element (RVE) model can improve the precision of FEA. Bending tests are conducted on specimens with orientation angles at 0° and 45°, while the bending modulus for orientation angles at 15° and 30° are predicted through FEA methods. This research enhances the accuracy of the mechanical performance analysis of plain weave CFRP laminates and also uncovers the relationship between the bending modulus changes and the orientation angles. It provides a theoretical foundation and guidance for optimizing the structural design and improving the mechanical properties of woven laminates.Highlights Investigated plain weave CFRP laminate mechanics via homogenization. Microscopy‐based RVE model improves FEM bending modulus prediction. Effects of orientation angles on plain weave CFRP laminate bending performance.

PROSTHESIS REPAIR OF ORAL IMPLANTS BASED ON ARTIFICIAL INTELLIGENC`E FINITE ELEMENT ANALYSIS

PROSTHESIS REPAIR OF ORAL IMPLANTS BASED ON ARTIFICIAL INTELLIGENC`E FINITE ELEMENT ANALYSIS

Prediction of axial compressive capacity and interpretability analysis of web perforated Σ-shaped cold-formed steel

Prediction of axial compressive capacity and interpretability analysis of web perforated Σ-shaped cold-formed steel

Symmetrical Short-Circuit Behavior Prediction of Rare-Earth Permanent Magnet Synchronous Motors

Since the advent of rare-earth permanent magnet (PM) materials, PM synchronous machines (PMSMs) have become popular in power generation, industrial drives, and e-mobility. However, rare-earth PMs in PMSMs are prone to temperature- and operation-related irreversible demagnetization. Additionally, faults can endanger components like inverters, batteries, and mechanical structures. Designing a fault-tolerant machine requires considering these risks during the PMSM design phase. Traditional transient finite element analysis is time-consuming, but fast analytical simulation methods provide viable alternatives. This paper evaluates methods for analyzing dynamic three-phase short-circuit (3PSC) events in PMSMs. Experimental measurements on a PMSM prototype serve as benchmarks. The results show that accounting for machine saturation reduces discrepancies between measured and predicted outcomes by 20%. While spatial harmonic content and sub-transient reactance can be neglected in some cases, caution is required in other scenarios. Eddy currents in larger machines significantly impact 3PSC dynamics. This work provides a quick assessment based on general machine parameters, improving fault-tolerant PMSM design.

Strength Lab AI: a mixture-of-experts deep learning approach for limit state analysis and design of monolithic and laminate structures made of glass

The demand for transparent building envelopes, particularly glass facades, is rising in modern architecture. These facades are expected to meet multiple objectives, including aesthetic appeal, durability, quick installation, transparency, and both economic and ecological efficiency. At the heart of facade design, particularly for structural glass elements, lies the assurance of structural integrity for ultimate and serviceability limit states with a requisite level of reliability. However, current structural engineering assessments for glass and glass laminate designs, especially in the geometrically non-linear setting, are time-consuming and require significant expertise. This study develops a customized Mixture-of-Experts (MoE) neural network architecture to overcome current limitations. It calibrates it on synthetically generated stress and deformation data obtained via parametrized Finite-Element-Analysis (FEA) of glass and glass laminate structures under both geometrically linear and nonlinear conditions for several joint support and loading conditions. Our findings reveal that the MoE model outperforms baseline models in predicting laminate deflections and stresses, offering a substantial increase in computational efficiency, compared to traditional linear and non-linear FEA, at high accuracy. The MoE is integrated within a novel web-based glass design and verification tool called Strength Lab AI and provided to the engineering public for future use. These results have profound implications for advancing engineering practice, offering a robust tool for the intricate structural design and analysis of glass and glass laminate structures.

Application of a novel machine learning model for the prediction and optimization of anti-blast performance of sandwich honeycomb blast walls

Application of a novel machine learning model for the prediction and optimization of anti-blast performance of sandwich honeycomb blast walls

Optimal Design of an Interior Permanent Magnet Synchronous Motor for Electric Vehicle Applications Using a Machine Learning-Based Surrogate Model

This paper presents an innovative design for an interior permanent magnet synchronous motor (IPMSM), targeting enhanced performance for electric vehicle (EV) applications. The proposed motor features a double V-shaped rotor structure with irregular ferrite magnets embedded in the slots between the permanent magnets. This design significantly enhances torque performance. Furthermore, a machine learning-based surrogate model is developed by integrating fine and coarse mesh data. Optimized using the Non-dominated Sorting Genetic Algorithm II (NSGA-II), this surrogate model effectively reduces computational time compared to traditional finite element analysis (FEA).

GNN-Based Concentration Prediction With Variable Input Flow Rates for Microfluidic Mixers.

Recent years have witnessed significant advances brought by microfluidic biochips in automating biochemical protocols. Accurate preparation of fluid samples is an essential component of these protocols, where concentration prediction and generation are critical. Equipped with the advantages of convenient fabrication and control, microfluidic mixers demonstrate huge potential in sample preparation. Although finite element analysis (FEA) is the most commonly used simulation method for accurate concentration prediction of a given microfluidic mixer, it is time-consuming with poor scalability for large biochip sizes. Recently, machine learning models have been adopted in concentration prediction, with great potential in enhancing the efficiency over traditional FEA methods. However, the state-of-the-art machine learning-based method can only predict the concentration of mixers with fixed input flow rates and fixed sizes. In this paper, we propose a new concentration prediction method based on graph neural networks (GNNs), which can predict output concentrations for microfluidic mixters with variable input flow rates. Moreover, a transfer learning method is proposed to transfer the trained model to mixers of different sizes with reduced training data. Experimental results show that, for microfluidic mixers with fixed input flow rates, the proposed method obtains an average reduction of 88% in terms of prediction errors compared with the state-of-the-art method. For microfluidic mixers with variable input flow rates, the proposed method reduces the prediction error by 85% on average. Besides, the proposed transfer learning method reduces the training data by 84% for extending the pre-trained model for microfluidic mixers of different sizes with acceptable prediction error.

Numerical method for the form finding and force analysis of non-prestressed cable-membrane structures with mechanism displacement

Numerical method for the form finding and force analysis of non-prestressed cable-membrane structures with mechanism displacement

High fidelity FEM based on deep learning for arbitrary composite material structure

High fidelity FEM based on deep learning for arbitrary composite material structure

Different Soil-Structure Interaction Modelling Strategies for Seismic Analysis of a Masonry Church

ABSTRACT Masonry structures can be damaged different external reasons such as war, flood, earthquake etc. For protecting and transfer to the next generations, these structures can be examined detailed. Finite element analysis has generally been used for the seismic evaluation of masonry structures. The fixed base assumption has been used in traditional finite element analysis of masonry structures. Interacting with the surrounding soil and structure was generally ignored. The seismic behavior of masonry structures is significantly influenced by the soil-structure interaction (SSI). There are various soil structure interaction modelling strategies in the recent studies. In this paper, the dimensions, mechanical properties and material model of the soil are considered constant. One of them had no soil-structure interaction. The others, roller support case, fixed support case, absorbing boundary case, free field columns and Winkler supports. Variations in the seismic response of a historical masonry church were investigated using 4 different SSI models and a fixed base (SSI ignored) model. Nonlinear time history analyses were employed for the finite element analysis. The soil borehole provided the material characteristics of the surrounding soil. According to the analysis results, higher response amplitudes were obtained when SSI was considered.

Numerical Simulation and Influence of Non-Gaussian Vibrations on Flexible Robotic Systems

Random vibration excitation is a standard method for obtaining the dynamic properties of aerospace structures and simulating loading conditions. Shaker-based random excitation and traditional finite element analysis techniques use random vibrations, assuming a Gaussian distribution of excitation impulse magnitudes. While Gaussian signals may sufficiently describe some vibrational environments, many real-world excitations have non-Gaussian distributions. These signals may contain vibrational impulses larger than those observed in a Gaussian signal and could cause damage if not considered. This paper examines the influence of non-Gaussian signals on flexible vs. rigid robotic architectures using NASA JPL’s Pop-Up Flat Folding Explorer Robot (PUFFER) and Cooperative Autonomous Distributed Robotic Explorer (CADRE). The results indicate that flexible systems can be significantly impacted by a non-Gaussian excitation profile and that neither a typical enveloping of a Gaussian excitation nor a superposition of the responses to a worst-case impulse load with the response to a Gaussian signal was sufficient to bound the response due to non-Gaussian excitation. The driving mechanism for increased sensitivity of flexible robotic systems appears to be inertial, and designers may consider shifting the relative flexibility of the system or its constraints to force particular deformation modes or designing hinge mechanisms with increased damping to minimize the influence of non-Gaussian signals on the response of a flexible robotic structure.

An Improved Decoupled Finite Element Analysis Method of Ultra-Large Offshore Wind Turbine Subjected to Combined Wind–Wave Actions

Abstract Owing to the simplification of the wind turbine, it is difficult to accurately simulate the interaction between the rotor system and the supporting structure using the decoupling finite element method. Therefore, when using this method for safety assessment and dynamic response research of the offshore wind turbine (OWT), there is a deviation between the simulation result and the real response of the OWT. In this study, an improved decoupled finite element analysis method is proposed based on a theoretical derivation. A simplified finite element model of a 10 MW jacket OWT with an equivalent substructure was established, and the dynamic response of the OWT under wind and waves was studied. By comparing the results of the fully coupled analysis method and the traditional finite element method, the applicability of the traditional finite element analysis method to the dynamic analysis of an OWT under typical winds and waves is discussed. The limitations of using the traditional finite element method to study or evaluate an OWT complex dynamic system were revealed, and the effectiveness and applicability of the improved method proposed in this study were qualitatively and quantitatively verified. Subsequently, based on the proposed improved decoupled finite element analysis method, a numerical calculation corresponding to a fully coupled test was performed. Compared with the numerical results obtained by the traditional finite element method, the improved decoupled finite element method proposed in this study obtained more consistent results with the fully coupled test.

Optimization Design of Phononic Crystals Based on BPNN‐MPA in Applied Mathematical Analysis

Traditional finite element analysis methods have the problem of expensive and unstable band structure diagram calculation when generating phononic crystals. Therefore, this study combines back propagation neural networks with ocean predator algorithms to optimize the geometric structure of phononic crystals. The results show that the coefficient of determination for the predicted bandgap width and lower bound of Model 3 is 1.00, which is better than the comparison model. However, Models 2 and 5 have poor predictive performance for bandgap width due to overfitting during actual training. Therefore, after using the ocean predator algorithm for hyperparameter adjustment, it is found that the maximum number of failures in the validation set of Model 5 is 30, the number of hidden layer nodes is 30, and after 500 experiments, the average error of the bandgap width is 5.26%, and the average error of the lower bound of the bandgap is 1.33%. The average error of the bandgap width after hyperparameter adjustment is 4.89%, and the average error of the lower bound of the bandgap is 1.21%, both of which are effectively reduced and better than the comparison model. Overall, the combination model has high computational efficiency and stability in phononic crystal optimization and can be practically applied in the design and optimization of phononic crystal geometric structures.