Advances in Engineering Software最新文献

{"title":"A novel dual-channel deep neural network for tunnel boring machine slurry circulation system data prediction","authors":"Rui Zhu ,&nbsp;Qingchao Sun ,&nbsp;Xuezhi Han ,&nbsp;Huqiang Wang ,&nbsp;Maolin Shi","doi":"10.1016/j.advengsoft.2024.103853","DOIUrl":"10.1016/j.advengsoft.2024.103853","url":null,"abstract":"<div><div>The slurry circulation system is a crucial component of the Slurry Pressure Balance Tunnel Boring Machine (SPB TBM),with the pressure and flow at the inlet and outlet sections pipelines significant parameters for SPB TBMs.Accurate prediction of these parameters is essential for maintaining face pressure and preventing surface settlement or heave, providing a reference for TBM control adjustments.This research proposes a novel Dual-channel Hybrid Model based on Variational Mode Decomposition and Self-attention Temporal Convolutional Networks (DHM-VSATCN) to address this issue.This multi-input multi-output model is designed to forecast pressure and flow in slurry pipelines accurately.This method encompasses several key components, including data preprocessing,signal decomposition, an enhanced dual-channel deep learning model,a loss function, and evaluation metrics to ensure prediction accuracy. Validation of the model using a real SPB TBM operation dataset demonstrates that the model achieves excellent performance for five pressure and flow rate parameters, with low Mean Absolute Errors (MAE) ranging from 0.0032 to 4.01,<em>R</em>² values above 0.95, and Mean Absolute Percentage Errors (MAPE) consistently below 0.23 %. The comparative analysis highlights the superior performance of the proposed DHM-VSATCN method over models such as SVR, XGB, FTS, ARIMA, RNN, LSTM and iTransformer. Furthermore,in the context of multi-output prediction problems,the proposed dual-channel modeling strategy not only ensures prediction accuracy but also reduces training time compared to existing modeling strategies. The proposed DHM-VSATCN achieves an all-MAPE of only 0.7253 % across five parameters,with a model training time of just 1212.8 s.Therefore, this method is an effective solution for predicting TBM performance and offers valuable insights for other engineering scenarios requiring the prediction of multiple related outputs using the same input.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"201 ","pages":"Article 103853"},"PeriodicalIF":4.0,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182912","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}

{"title":"Filling gaps in MODIS NDVI data using hybrid multiple imputation–Machine learning and DINCAE techniques: Case study of the State of Hawaii","authors":"Trang Thi Kieu Tran ,&nbsp;Sayed M. Bateni ,&nbsp;Hamid Mohebzadeh ,&nbsp;Changhyun Jun ,&nbsp;Manish Pandey ,&nbsp;Dongkyn Kim","doi":"10.1016/j.advengsoft.2024.103856","DOIUrl":"10.1016/j.advengsoft.2024.103856","url":null,"abstract":"<div><div>Normalized difference vegetation index (NDVI) data are vital for monitoring vegetation dynamics and health. However, NDVI time-series data obtained via remote sensing often contain missing values due to factors such as cloud cover, snow, and hardware failures. To address this problem and fill gaps in NDVI data from the Moderate Resolution Imaging Spectroradiometer (MODIS), this study combines the multiple imputations by chained equations (MICE) model with three machine learning techniques: Knearest neighbor, multilayer perceptron (MLP), and boosted regression tree. Additionally, the data interpolating convolutional auto-encoder (DINCAE), a recently proposed imputation method, is employed for imputation and comparison. The performance of all these models is evaluated using MODIS NDVI data from Oahu, Hawaii for training and validation. Synthetic scenarios with gap sizes of 20 %, 40 %, 60 %, and 80 % are created to assess the models’ feasibility for each gap size. Furthermore, all models are tested using data from Hawaii Island and Maui. Results indicate that the MICE-MLP model achieves the highest accuracy in imputing missing NDVI values on Oahu, with root mean square error (RMSE) values of 0.1028, 0.1112, and 0.1224 for missing ratios of 20 %, 40 %, and 60 %, respectively. Similarly, MICE-MLP outperforms other models using Hawaii Island and Maui data at gap sizes below 80 %. While the DINCAE model demonstrates superior accuracy at an 80 % gap size, its computational speed is slower than MICE-MLP. Overall, the findings underscore the robustness and accuracy of the MICE-MLP model in imputing missing NDVI data, making it a reliable alternative to existing methods.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"201 ","pages":"Article 103856"},"PeriodicalIF":4.0,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182911","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}

{"title":"Modeling reinforced concrete structures under fire conditions in GiD-OpenSees: Framework, validations, and implications","authors":"Anand Kumar ,&nbsp;P. Ravi Prakash ,&nbsp;Mhd. Anwar Orabi","doi":"10.1016/j.advengsoft.2024.103855","DOIUrl":"10.1016/j.advengsoft.2024.103855","url":null,"abstract":"<div><div>This paper presents modifications to the OpenSees for fire source code and the GiD-OpenSees interface to facilitate finite element (FE) macro modeling of reinforced concrete (RC) structural frames under fire conditions. In the FE framework, RC frames are discretized by 1-D line elements, and their cross-sections are further discretized by 2-D FE mesh. The mechanical analysis is configured for 1-D line elements, whereas the heat transfer analysis handles 2-D FE meshes. New material models (<em>DamagePlastictyConcreteECT</em> and <em>DPMsteelECT</em>) are developed based on the EN1992-1-2 stress–strain relations, and they explicitly consider transient creep (concrete), damage-plasticity (concrete), and plasticity (steel). Such an approach enables precise modeling of irreversible strain components, especially during strain reversal conditions. The existing GiD-OpenSees interface is extended to implement the new material models, FE framework, and automated thermo-mechanical analysis. Six numerical examples are presented, which include experimental validations and a comparison study against standard structural fire simulation software SAFIR. The results show that the developed framework is able to trace the structural response under fire to a high level of fidelity and robustly traverses strain-reversal conditions.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"201 ","pages":"Article 103855"},"PeriodicalIF":4.0,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182910","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}

{"title":"Optimal Tool Path Planning in Five-Axis Flank Milling for Cylindrical Cutters using Surrogate Models and Multi-Level Space Reduction Techniques","authors":"Jin Yi ,&nbsp;Chi-Lung Kuo ,&nbsp;Kai-Wen Tien ,&nbsp;Chih-Hsing Chu","doi":"10.1016/j.advengsoft.2024.103854","DOIUrl":"10.1016/j.advengsoft.2024.103854","url":null,"abstract":"<div><div>Precise error control in 5-axis flank milling of complex surfaces through optimal tool path planning is a challenging task. The solution process usually involves a large number of decision variables in a highly nonlinear search space. The performance of previous meta-heuristic algorithms on this problem has been unsatisfactory, largely due to the curse of dimensionality. This paper proposes a computational scheme for generating optimal tool paths based on multi-level space reduction techniques integrated with surrogate models. A global model is first constructed to offer an approximation to the actual solution landscape that facilitates quick identification of a potential global optimal area. Next, a local model is created around the optimal area to estimate more accurate solutions. This two-step process can repeat for multiple iterations until a satisfactory solution is achieved. We compare how different surrogate modeling methods and sampling techniques influence the optimization process based on the scheme. Test results on representative surfaces show that it outperforms other methods in terms of both solution quality and search efficiency. This work provides an effective approach for enhancing geometric accuracy in five-axis flank milling.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"201 ","pages":"Article 103854"},"PeriodicalIF":4.0,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182909","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}

{"title":"Fast parametric modeling of visualized simulation and design for tracked vehicle system","authors":"Pingxin Wang ,&nbsp;Xiaoting Rui ,&nbsp;Junjie Gu ,&nbsp;Kai Huang ,&nbsp;Lei Zhou ,&nbsp;Min Jiang","doi":"10.1016/j.advengsoft.2024.103852","DOIUrl":"10.1016/j.advengsoft.2024.103852","url":null,"abstract":"<div><div>The burgeoning demand for efficient and accurate design methodologies in the engineering domain has been accentuated by the complexities inherent in the development of tracked vehicle systems. Despite the advent of virtual prototyping and computer-aided design technologies, challenges persist in achieving rapid parametric modeling of these systems, particularly due to their intricate assembly requirements and dynamics simulations. This paper develops a novel fast parametric modeling plugin for the simulation and design of tracked vehicle systems. It integrates advanced visualization techniques and an automatic assembly algorithm. Utilizing the open-source Open CASCADE library, the developed plugin facilitates sophisticated manipulations of 3D models. Leveraging an integrated Python console editor, the Python scripts are seamlessly converted into Open Inventor scripts and are rendered via the Coin3D engine. Ultimately, the model is displayed within the Qt graphical user interface framework. The key finding is the creation of the automatic assembly algorithm, which starts from an individual track link and automatically constructs a continuous track assembly. The case studies illustrate the systematic application of the parametric modeling technology in the dynamic modeling and optimization of a representative tracked vehicle, highlighting the plugin's efficiency and the accuracy. By employing a Particle Swarm Optimization algorithm to optimize the geometric parameters of wheels and tracks, the vehicle vibration has been reduced. The unique value of this paper lies in its contribution to the field of vehicle engineering through the provision of a robust parametric modeling tool that enhances the efficiency of virtual simulation and design processes.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"201 ","pages":"Article 103852"},"PeriodicalIF":4.0,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182908","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}

{"title":"A remedy to mitigate tensile instability in SPH for simulating large deformation and failure of geomaterials","authors":"Tapan Jana,&nbsp;Subhankar Pal,&nbsp;Amit Shaw,&nbsp;L.S. Ramachandra","doi":"10.1016/j.advengsoft.2024.103848","DOIUrl":"10.1016/j.advengsoft.2024.103848","url":null,"abstract":"<div><div>Large deformation analysis in geomechanics plays an important role in understanding the nature of post-failure flows and hazards associated with landslides under different natural calamities. In this study, a SPH framework is proposed for large deformation and failure analysis of geomaterials. An adaptive B-spline kernel function in combination with a pressure zone approach is proposed to counteract the numerical issues associated with tensile instability. The proposed algorithm is validated using a soil cylinder drop problem, and the results are compared with FEM. Finally, the effectiveness of the proposed algorithm in the successful removal of tensile instability and stress noise is demonstrated using the well-studied slope failure simulation of a cohesive soil vertical cut.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"201 ","pages":"Article 103848"},"PeriodicalIF":4.0,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182907","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}

{"title":"A proposed innovative approach for predicting the torsional moment capacity of half-shaft based on static FEM","authors":"Junlou Li ,&nbsp;Yipo Kang ,&nbsp;Jianjiao Deng ,&nbsp;Xuandong Li ,&nbsp;Youlong Zhang ,&nbsp;Bo Yan","doi":"10.1016/j.advengsoft.2024.103851","DOIUrl":"10.1016/j.advengsoft.2024.103851","url":null,"abstract":"<div><div>The torsional moment capacity of the automotive half-shaft is a crucial design parameter, and the utilization of induction hardening can enhance this capability. This paper presents the development of a comprehensive static finite element simulation model and a three-layer gradient distribution model of material property for the half-shaft based on its actual heat treatment state. A torque prediction model was developed for the torsional moment capacity of the half-shaft based on the torque-angle curve derived from the static finite element analysis. This model accurately and quickly predicts the torque value at which the half-shaft will break during the torsional test. In contrast with the current continuum damage mechanics method, this approach requires a reduced number of material factors and has a lower computing cost. Furthermore, the accuracy of the prediction results in three distinct groups of half-shafts reaches 94 %, 97 %, and 99.6 %. This approach can provide guidance for the design and enhancement of half-shafts, potentially replacing or minimizing the need for torsion testing of automotive half-shafts. It has the potential to minimize the duration of the product development cycle and lower the associated costs. It can also be applied to different drive shafts, demonstrating excellent adaptability and extensive applicability.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"201 ","pages":"Article 103851"},"PeriodicalIF":4.0,"publicationDate":"2024-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182906","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}

{"title":"Efficient dual-level parallelism solutions for OpenFOAM-based discrete unified gas kinetic scheme","authors":"Feifei Zhang ,&nbsp;Yunlan Wang ,&nbsp;Rui Zhang ,&nbsp;Jie Guo ,&nbsp;Tianhai Zhao ,&nbsp;Sha Liu ,&nbsp;Congshan Zhuo ,&nbsp;Chengwen Zhong","doi":"10.1016/j.advengsoft.2024.103840","DOIUrl":"10.1016/j.advengsoft.2024.103840","url":null,"abstract":"<div><div>The Discrete Unified Gas Kinetic Scheme (DUGKS) is an efficient framework for solving gas kinetic equations, crucial in areas such as aerospace, microfluidics, and vacuum technologies. However, the existing dugksFoam solver (Zhu et al., 2017), developed on OpenFOAM, suffers from low parallel efficiency and high computational costs. This paper focuses on enhancing the efficiency of the dugksFoam solver through optimisations specific for memory access, communication, and computation. Two innovative process-thread hybrid parallel algorithms are proposed, combining dual-level parallelism tailored to the characteristics of the DUGKS algorithm and modern HPC cluster architectures. Algorithm 1 utilises process-level parallelism for physical space partitioning and thread-level parallelism for velocity-space partitioning, while Algorithm 2 swaps these parallel levels. Multiple validation cases were conducted to verify the accuracy of the algorithms. Both algorithms demonstrate significant performance improvements over the existing dugksFoam solver. Algorithm 1 is suitable for small-scale parallelism, and Algorithm 2 achieves linear speedup on 1024 cores, excelling in large-scale parallel scenarios.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"201 ","pages":"Article 103840"},"PeriodicalIF":4.0,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182905","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}

{"title":"CFD analysis and design of bypass dual throat nozzle for high-performance fluidic thrust vectoring","authors":"Chanho Park ,&nbsp;Woochan Lee ,&nbsp;Seongim Choi","doi":"10.1016/j.advengsoft.2024.103827","DOIUrl":"10.1016/j.advengsoft.2024.103827","url":null,"abstract":"<div><div>The purpose of the study is to investigate detailed flow properties of the bypass dual throat nozzle (BDTN) for fluidic thrust vectoring, and to find an optimal geometry to maximize its performance. The performance metrics of the BDTN are defined as the thrust efficiency and flow deflection angle at the nozzle exit. Given the nozzle pressure ratio (NPR), secondary flows injected from the bypass duct of the nozzle create circulatory flows in the nozzle cavity, produce complex interactions of shock and expansion waves, and deflect the directions of the exit flows. To identify key parameters for the BDTN performance, a sensitivity study is carried out using the traditional finite difference method as well as the AI-assisted Shapley additive explanation methods with respect to geometric variables of the BDTN. For the design optimization, a total of eight geometric parameters were chosen including an upstream convergent angle (<span><math><msub><mrow><mi>θ</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span>), a bypass injection angle (<span><math><msub><mrow><mi>θ</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span>), cavity divergence and convergence angles (<span><math><msub><mrow><mi>θ</mi></mrow><mrow><mn>3</mn></mrow></msub></math></span> and <span><math><msub><mrow><mi>θ</mi></mrow><mrow><mn>4</mn></mrow></msub></math></span>), upstream and downstream throat diameters (<span><math><msub><mrow><mi>d</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span> and <span><math><msub><mrow><mi>d</mi></mrow><mrow><mn>3</mn></mrow></msub></math></span>), bypass channel diameter (<span><math><msub><mrow><mi>d</mi></mrow><mrow><mn>4</mn></mrow></msub></math></span>), and cavity divergence length (<span><math><msub><mrow><mi>l</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span>). Those parameters were varied by 10<span><math><mo>∼</mo></math></span>20 % of the baseline values to create more than 100 random BDTN geometries which were solved by the full CFD analysis. The multi-variate Gaussian process regression (GPR) model was developed by training the data as a surrogate model to the CFD analysis of arbitrary BDTN shape during the design iteration. Multi-objective optimization was conducted to generate the Pareto optimal front of multiple design candidates for maximum deflection angle and thrust values. The optimum BDTN geometry produced a deflection angle increased up to 13 %, while thrust value was slightly increased from that of the baseline by less than 1%. The approach provides a foundation for future research into adaptive nozzle designs responsive to real-time flow conditions, potentially expanding the applications of fluidic thrust vectoring.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"201 ","pages":"Article 103827"},"PeriodicalIF":4.0,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182903","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}

{"title":"Robustness of hybrid light gradient boosting for concrete creep compliance prediction","authors":"Viet-Linh Tran ,&nbsp;Duc-Kien Thai ,&nbsp;Jin-Kook Kim","doi":"10.1016/j.advengsoft.2024.103831","DOIUrl":"10.1016/j.advengsoft.2024.103831","url":null,"abstract":"<div><div>Concrete creep is one of the most crucial factors in concrete. A reliable prediction of concrete creep is vital for safe concrete structure design and maintenance. However, the theoretical and empirical models are convoluted and unreliable due to the complex time-dependent behavior of concrete creep. This study collects a comprehensive experimental database from the literature to develop a hybrid machine learning model that combines grey wolf optimizer (GWO) and light gradient boosting (LGB), namely GWO-LGB, for predicting precisely concrete creep compliance (<em>J_creep</em>). Three widely used empirical models and six baseline ensemble machine learning models are adopted to evaluate the efficacy of the developed hybrid GWO-LGB mode. The comparative results reveal that the hybrid GWO-LGB model produces more accuracy in predicting the <em>J_creep</em> than other models. In addition, the Shapley Additive exPlanations (SHAP) method is used to investigate the influence of input parameters on the <em>J_creep</em>. Finally, a web tool is created to apply the hybrid GWO-LGB model readily to predict the <em>J_creep</em> with new input data without cumbersome programming.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"201 ","pages":"Article 103831"},"PeriodicalIF":4.0,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182904","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}