Engineering Analysis with Boundary Elements最新文献_第2页

FO-PINN: A First-Order formulation for Physics-Informed Neural Networks

IF 4.2 2区工程技术

Engineering Analysis with Boundary Elements Pub Date : 2025-02-25 DOI: 10.1016/j.enganabound.2025.106161

Rini Jasmine Gladstone , Mohammad Amin Nabian , N. Sukumar , Ankit Srivastava , Hadi Meidani

{"title":"FO-PINN: A First-Order formulation for Physics-Informed Neural Networks","authors":"Rini Jasmine Gladstone , Mohammad Amin Nabian , N. Sukumar , Ankit Srivastava , Hadi Meidani","doi":"10.1016/j.enganabound.2025.106161","DOIUrl":"10.1016/j.enganabound.2025.106161","url":null,"abstract":"<div><div>Physics-Informed Neural Networks (PINNs) are a class of deep learning neural networks that learn the response of a physical system without any simulation data, and only by incorporating the governing partial differential equations (PDEs) in their loss function. While PINNs are successfully used for solving forward and inverse problems, their accuracy decreases significantly for parameterized systems and higher-order PDE problems. PINNs also have a soft implementation of boundary conditions resulting in boundary conditions not being exactly imposed everywhere on the boundary. With these challenges at hand, we present first-order physics-informed neural networks (FO-PINNs). These are PINNs that are trained using a first-order formulation of the PDE loss function. We show that, compared to standard PINNs, FO-PINNs offer significantly higher accuracy in solving parameterized systems, and reduce time-per-iteration by removing the extra backpropagations needed to compute the second or higher-order derivatives. Additionally, FO-PINNs can enable exact imposition of boundary conditions using approximate distance functions, which pose challenges when applied on high-order PDEs. Through four examples, we demonstrate the advantages of FO-PINNs over standard PINNs in terms of accuracy and training speedup.</div></div>","PeriodicalId":51039,"journal":{"name":"Engineering Analysis with Boundary Elements","volume":"174 ","pages":"Article 106161"},"PeriodicalIF":4.2,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A coupled hydraulic-mechanical-chemical peridynamic model for simulating corrosion-induced failure of unsaturated reinforced concrete under hydraulic pressure 模拟水压作用下非饱和钢筋混凝土腐蚀诱发破坏的水力-机械-化学周流体力学耦合模型

IF 4.2 2区工程技术

Engineering Analysis with Boundary Elements Pub Date : 2025-02-21 DOI: 10.1016/j.enganabound.2025.106177

Shenhua Liu , Weizhong Chen , Jingqiang Yuan

{"title":"A coupled hydraulic-mechanical-chemical peridynamic model for simulating corrosion-induced failure of unsaturated reinforced concrete under hydraulic pressure","authors":"Shenhua Liu , Weizhong Chen , Jingqiang Yuan","doi":"10.1016/j.enganabound.2025.106177","DOIUrl":"10.1016/j.enganabound.2025.106177","url":null,"abstract":"<div><div>Underwater reinforced concrete is vulnerable to chloride corrosion, which reduces the durability of underwater concrete structures. In this paper, by introducing time-varying chloride ion diffusion and non-uniform corrosion expansion failure model, a chemical-hydraulic-mechanical coupling peridynamic model of reinforced concrete corrosion expansion failure process in actual underwater environment is established. The proposed model focuses both on the unsaturated transport process of water and chloride and the corrosion failure of unsaturated reinforced concrete under water pressure. The validity of proposed model is firstly verified by comparing with experimental results and theoretical solutions. Then, the whole process of corrosion expansion failure of underwater reinforced concrete is simulated by using this model. The numerical results show that the developed chemical-hydraulic-mechanical coupling peridynamic model can simulate the penetration of water and chloride in unsaturated concrete and the failure process of concrete caused by chloride corrosion under water pressure. Furthermore, the effects of water pressure on water / chloride ion transport and corrosion expansion damage of underwater reinforced concrete were studied.</div></div>","PeriodicalId":51039,"journal":{"name":"Engineering Analysis with Boundary Elements","volume":"174 ","pages":"Article 106177"},"PeriodicalIF":4.2,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Nonlinear eigenvalue analysis of thermoviscous acoustic problems using an equivalent source method

IF 4.2 2区工程技术

Engineering Analysis with Boundary Elements Pub Date : 2025-02-21 DOI: 10.1016/j.enganabound.2025.106162

Meng-Hui Liang, Chang-Jun Zheng, Yong-Bin Zhang, Liang Xu, Shuai Wang, Chuan-Xing Bi

{"title":"Nonlinear eigenvalue analysis of thermoviscous acoustic problems using an equivalent source method","authors":"Meng-Hui Liang, Chang-Jun Zheng, Yong-Bin Zhang, Liang Xu, Shuai Wang, Chuan-Xing Bi","doi":"10.1016/j.enganabound.2025.106162","DOIUrl":"10.1016/j.enganabound.2025.106162","url":null,"abstract":"<div><div>In this study, a nonlinear eigenvalue solver for the numerical solution of thermoviscous acoustic problems based on the equivalent source method (ESM) is developed. By using the idea of the ESM, the solutions to the thermoviscous formulations are coupled on the surface of the structure through the isothermal and non-slip conditions. The frequency-dependent nature of the transfer matrix in the system equation of ESM gives rise to a nonlinear eigenvalue problem (NLEP), presenting an additional challenge in the eigenvalue analysis. To tackle this issue, the contour integral method is employed to convert the NLEP into a generalized eigenvalue problem (GEVP). This contour integral method is effective for accurately identifying complex acoustic eigenvalues, which are frequently encountered in the context of thermoviscous acoustic problems. Numerical examples are provided to validate the effectiveness and accuracy of the proposed method, while simulations involving acoustic black hole and acoustic-structural interaction demonstrate its potential applicability in engineering applications.</div></div>","PeriodicalId":51039,"journal":{"name":"Engineering Analysis with Boundary Elements","volume":"174 ","pages":"Article 106162"},"PeriodicalIF":4.2,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-scale feature fusion quantum depthwise Convolutional Neural Networks for text classification

IF 4.2 2区工程技术

Engineering Analysis with Boundary Elements Pub Date : 2025-02-19 DOI: 10.1016/j.enganabound.2025.106158

Yixiong Chen , Weichuan Fang

{"title":"Multi-scale feature fusion quantum depthwise Convolutional Neural Networks for text classification","authors":"Yixiong Chen , Weichuan Fang","doi":"10.1016/j.enganabound.2025.106158","DOIUrl":"10.1016/j.enganabound.2025.106158","url":null,"abstract":"<div><div>In recent years, with the development of quantum machine learning, Quantum Neural Networks (QNNs) have gained increasing attention in the field of Natural Language Processing (NLP) and have achieved a series of promising results. However, most existing QNN models focus on the architectures of Quantum Recurrent Neural Network (QRNN) and Quantum Self-Attention Mechanism (QSAM). In this work, we propose a novel QNN model based on quantum convolution. We develop the quantum depthwise convolution that significantly reduces the number of parameters and lowers computational complexity. We also introduce the multi-scale feature fusion mechanism to enhance model performance by integrating word-level and sentence-level features. Additionally, we propose the quantum word embedding and quantum sentence embedding, which provide embedding vectors more efficiently. Through experiments on two benchmark text classification datasets, we demonstrate our model outperforms a wide range of state-of-the-art QNN models. Notably, our model achieves a new state-of-the-art test accuracy of 96.77% on the RP dataset. We also show the advantages of our quantum model over its classical counterparts in its ability to improve test accuracy using fewer parameters. Finally, an ablation test confirms the effectiveness of the multi-scale feature fusion mechanism and quantum depthwise convolution in enhancing model performance.</div></div>","PeriodicalId":51039,"journal":{"name":"Engineering Analysis with Boundary Elements","volume":"174 ","pages":"Article 106158"},"PeriodicalIF":4.2,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The three-dimensional elastoplastic analysis of bi-directional functionally graded materials using a meshfree global radial basis reproducing kernel particle method

IF 4.2 2区工程技术

Engineering Analysis with Boundary Elements Pub Date : 2025-02-18 DOI: 10.1016/j.enganabound.2025.106176

Shaopeng Qin, Deshun Yin, Liangzhu Ma, Baozhi Han, Mingyuan Tian, Xuan Chen

{"title":"The three-dimensional elastoplastic analysis of bi-directional functionally graded materials using a meshfree global radial basis reproducing kernel particle method","authors":"Shaopeng Qin, Deshun Yin, Liangzhu Ma, Baozhi Han, Mingyuan Tian, Xuan Chen","doi":"10.1016/j.enganabound.2025.106176","DOIUrl":"10.1016/j.enganabound.2025.106176","url":null,"abstract":"<div><div>The meshless global radial basis reproducing kernel particle method (GRB-RKPM), constructed based on the global radial basis function and the reproducing kernel particle method (RKPM), is extended to the investigation of the three-dimensional (3D) elastoplastic problem of bi-directional functional gradient materials (BDFGMs). The discrete equations in the incremental form are established based on the Galerkin integral weak formulation of the 3D elastoplastic problem. The solution equations of the GRB-RKPM for the 3D elastoplastic problem of BDFGMs are derived using the incremental tangent stiffness method. The numerical accuracy, convergence, and stability of the GRB-RKPM are analyzed. BDFGMs based on the exponential and Voigt models are employed in the numerical examples. The numerical results demonstrate that the GRB-RKPM is effective in solving the 3D elastoplastic problem of BDFGMs. The computational accuracy of the GRB-RKPM is higher than that of the GRBF, the RKPM and the local radial basis reproducing kernel particle method. The displacement of the 3D elastoplastic of BDFGMs decreases with an increase in the gradient index.</div></div>","PeriodicalId":51039,"journal":{"name":"Engineering Analysis with Boundary Elements","volume":"173 ","pages":"Article 106176"},"PeriodicalIF":4.2,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The selection of shape parameter and fictitious radius for RBF collocation method using the modified Franke formula and effective condition number

IF 4.2 2区工程技术

Engineering Analysis with Boundary Elements Pub Date : 2025-02-18 DOI: 10.1016/j.enganabound.2025.106159

Xinxiang Li , Han Liu

{"title":"The selection of shape parameter and fictitious radius for RBF collocation method using the modified Franke formula and effective condition number","authors":"Xinxiang Li , Han Liu","doi":"10.1016/j.enganabound.2025.106159","DOIUrl":"10.1016/j.enganabound.2025.106159","url":null,"abstract":"<div><div>The shape parameter <span><math><mi>c</mi></math></span> and the fictitious radius <span><math><mi>R</mi></math></span> are important parameters that affect the performance of the polynomial-augmented RBF collocation method (RBFCM) with fictitious centers. It is known that the RBFCM can reduce the accuracy dependency on shape parameter by using extra polynomial constraints. Moreover, we find that calculation inaccuracies exhibit a strong association with the effective condition numbers for various fictitious radii. While there have been some methods for selecting the shape parameter, an approach that allows for the simultaneous selection of <span><math><mi>c</mi></math></span> and <span><math><mi>R</mi></math></span> has not yet been widely researched. In this paper, we propose a systematic method to choose parameters for the polynomial-augmented RBFCM with fictitious centers. The method utilizes the effective condition number to find an appropriate fictitious radius <span><math><mi>R</mi></math></span> and the modified Franke formula to select a good shape parameter <span><math><mi>c</mi></math></span>. Five examples of second and fourth order PDEs in 2D and 3D are presented to demonstrate the effectiveness of the proposed method.</div></div>","PeriodicalId":51039,"journal":{"name":"Engineering Analysis with Boundary Elements","volume":"174 ","pages":"Article 106159"},"PeriodicalIF":4.2,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Total Lagrangian smoothed particle hydrodynamics for large-strain elastoplasticity with particle resolution refinement using an anisotropic Lagrangian kernel

IF 4.2 2区工程技术

Engineering Analysis with Boundary Elements Pub Date : 2025-02-18 DOI: 10.1016/j.enganabound.2025.106173

Jin-Woo Kim, Eung Soo Kim

{"title":"Total Lagrangian smoothed particle hydrodynamics for large-strain elastoplasticity with particle resolution refinement using an anisotropic Lagrangian kernel","authors":"Jin-Woo Kim, Eung Soo Kim","doi":"10.1016/j.enganabound.2025.106173","DOIUrl":"10.1016/j.enganabound.2025.106173","url":null,"abstract":"<div><div>Key features for the versatile industrial applications of smoothed particle hydrodynamics (SPH) are numerical accuracy and stability, computational efficiency, and ease of implementation. To meet these requirements, this study presents a straightforward algorithm to treat large-strain elastoplasticity within Total Lagrangian SPH (TLSPH) framework. In terms of accuracy and stability, the total Lagrangian formulation in SPH completely eliminates tensile instability related to the use of Eulerian kernel functions. This study adopts a multiplicative hyperelastic-based plasticity model, enabling the model to treat from purely elastic to elastoplastic structural deformations. A common strategy of efficient simulations in structural analysis is utilizing predefined local resolution refinement with non-uniform particle spacing. However, within TLSPH framework, numerical accuracy and efficiency of this strategy were not investigated sufficiently. To maintain a proper number of neighboring particles in the presence of non-uniform spacing, an anisotropic kernel and its derivatives are incorporated in SPH approximations. Beyond its inherent stability, TLSPH can offer great convenience for the multi-resolution implementation with minimized computational load, as repeated kernel computations at each time advancement are not required. Several benchmark tests are conducted to validate the proposed TLSPH model with various initial particle distributions, demonstrating good accuracy and robustness while lowering computational load.</div></div>","PeriodicalId":51039,"journal":{"name":"Engineering Analysis with Boundary Elements","volume":"173 ","pages":"Article 106173"},"PeriodicalIF":4.2,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Zonal free element method for solving nonlinear transient heat conduction problems

IF 4.2 2区工程技术

Engineering Analysis with Boundary Elements Pub Date : 2025-02-17 DOI: 10.1016/j.enganabound.2025.106170

Kai Yang, Jia-Bo Han, Wen-Wei Jiang, Zhi-Yuan Zhou, Chen-Hao Tan, Si-Qi Zhang, Yun-Tao Zhou, Hua-Yu Liu, Xiao-Wei Gao

引用次数: 0

A fast approach evaluating origin intensity factors on Neumann boundary in the singular boundary method

IF 4.2 2区工程技术

Engineering Analysis with Boundary Elements Pub Date : 2025-02-15 DOI: 10.1016/j.enganabound.2025.106160

Weiwei Li, Chenchen Yang

{"title":"A fast approach evaluating origin intensity factors on Neumann boundary in the singular boundary method","authors":"Weiwei Li, Chenchen Yang","doi":"10.1016/j.enganabound.2025.106160","DOIUrl":"10.1016/j.enganabound.2025.106160","url":null,"abstract":"<div><div>This study introduces a rapid methodology based on recursive skeletonization factorization (RSF), for the determination of origin intensity factors (OIFs) at Neumann boundaries within the framework of the singular boundary method (SBM). The conventional formula for OIFs, which is derived using the subtracting and adding-back technique (SABT), is reformulated into a matrix-vector product representation. The components of the matrix consist of the fundamental solutions of the double-layer potential that adhere to the governing equations. Consequently, the RSF facilitates the implicit construction of a hierarchically generalized LU decomposition of the matrix, producing decomposition factors that allow for efficient multiplication with any vector. This innovative approach significantly reduces the computational cost associated with the calculation of OIFs, thereby meeting the demands of simulating large-scale problems. Numerical results demonstrate that this method is both accurate and stable, and it is applicable to a variety of problems characterized by irregular geometries.</div></div>","PeriodicalId":51039,"journal":{"name":"Engineering Analysis with Boundary Elements","volume":"173 ","pages":"Article 106160"},"PeriodicalIF":4.2,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Formation mechanism of normal force of a vehicle during the oblique water entry based on multi-phase smoothed particle hydrodynamics

IF 4.2 2区工程技术

Engineering Analysis with Boundary Elements Pub Date : 2025-02-15 DOI: 10.1016/j.enganabound.2025.106156

Jia-Jie Wang , Fu-Ren Ming , Chang Liu , Qing-Sen Zhang , Hao Chen

{"title":"Formation mechanism of normal force of a vehicle during the oblique water entry based on multi-phase smoothed particle hydrodynamics","authors":"Jia-Jie Wang , Fu-Ren Ming , Chang Liu , Qing-Sen Zhang , Hao Chen","doi":"10.1016/j.enganabound.2025.106156","DOIUrl":"10.1016/j.enganabound.2025.106156","url":null,"abstract":"<div><div>The oblique entry process of a vehicle not only generates strong axial forces, but also generates significant normal force due to the asymmetry of air and cavity flows, which poses a great threat to the local and overall strength of the vehicle. This paper employs a multiphase <span><math><mi>δ</mi></math></span>-smoothed particle hydrodynamics (<span><math><mi>δ</mi></math></span>-SPH) method to analyze the flow field evolution and pressure distribution on the vehicle during water entry. Firstly, the accuracy and convergency of numerical model are verified through an oblique water entry case. Furthermore, the normal force formation mechanism is investigated by capturing the pressure evolution on the vehicle. Finally, the influences of half-cone angle and water-entry angle on the normal force during water entry are discussed. The findings indicate that the formation of normal force can be attributed to the hydrodynamic pressure and the aerodynamic pressure difference, which will provide valuable insights for the designs of force reduction and structural safety.</div></div>","PeriodicalId":51039,"journal":{"name":"Engineering Analysis with Boundary Elements","volume":"173 ","pages":"Article 106156"},"PeriodicalIF":4.2,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0