Stiffened Cold-Formed Steel (CFS) sections often exhibit intricate nonlinear behaviors attributable to factors such as flexure effects and excessive slenderness. Traditional design methodologies, including the direct stiffness method, may inadequately capture these subtleties, potentially resulting in conservative or suboptimal designs. This study aimed to evaluate the performance of various machine learning algorithms, including simple and ensemble models, to predict the bending capacity of stiffened and unstiffened cold-formed beams in pure bending. A parametric study was conducted based on verified finite element analysis, and the machine learning algorithms were utilized to develop a unified capacity prediction method. The performance of six classical machine learning algorithms and four ensemble models were compared. The findings demonstrate that ensemble models, including AdaBoost, Gradient Boosting, Random Forest, and Extra Trees, outperform simple machine learning models in predicting the bending capacity of CFS beams. Moreover, introducing the stacking ensemble technique, using six different base models selectively, resulted in better performance than the individual baseline models. The approach addressed the nonlinearity pattern in the dataset caused by the flexure effect and excessive slenderness. The study suggests that adopting the proposed numerical and machine learning techniques could be a reliable method for predicting the structural behaviour and conducting cost-effective design of CFS beams, compared to the traditional analytical methods.
加劲冷弯型钢 (CFS) 截面通常会因挠曲效应和过长的细长度等因素而表现出复杂的非线性行为。包括直接刚度法在内的传统设计方法可能无法充分捕捉这些微妙之处，从而可能导致保守或次优设计。本研究旨在评估各种机器学习算法的性能，包括简单模型和集合模型，以预测加劲和非加劲冷弯梁在纯弯曲情况下的抗弯能力。在验证有限元分析的基础上进行了参数研究，并利用机器学习算法开发了统一的承载力预测方法。比较了六种经典机器学习算法和四种集合模型的性能。研究结果表明，在预测 CFS 梁的抗弯能力方面，包括 AdaBoost、梯度提升、随机森林和 Extra Trees 在内的集合模型优于简单的机器学习模型。此外，引入堆叠集合技术，有选择地使用六个不同的基础模型，比单个基线模型的性能更好。该方法解决了数据集中由挠曲效应和过度细长引起的非线性模式。研究表明，与传统的分析方法相比，采用拟议的数值和机器学习技术是预测 CFS 梁结构行为和进行经济有效设计的可靠方法。
{"title":"Evaluation of machine learning techniques for capacity prediction of cold-formed steel beams subjected to bending","authors":"Ayman Hamdallah, Antti Niemi, Ahmed Abdullah","doi":"10.23998/rm.144743","DOIUrl":"https://doi.org/10.23998/rm.144743","url":null,"abstract":"Stiffened Cold-Formed Steel (CFS) sections often exhibit intricate nonlinear behaviors attributable to factors such as flexure effects and excessive slenderness. Traditional design methodologies, including the direct stiffness method, may inadequately capture these subtleties, potentially resulting in conservative or suboptimal designs. This study aimed to evaluate the performance of various machine learning algorithms, including simple and ensemble models, to predict the bending capacity of stiffened and unstiffened cold-formed beams in pure bending. A parametric study was conducted based on verified finite element analysis, and the machine learning algorithms were utilized to develop a unified capacity prediction method. The performance of six classical machine learning algorithms and four ensemble models were compared. The findings demonstrate that ensemble models, including AdaBoost, Gradient Boosting, Random Forest, and Extra Trees, outperform simple machine learning models in predicting the bending capacity of CFS beams. Moreover, introducing the stacking ensemble technique, using six different base models selectively, resulted in better performance than the individual baseline models. The approach addressed the nonlinearity pattern in the dataset caused by the flexure effect and excessive slenderness. The study suggests that adopting the proposed numerical and machine learning techniques could be a reliable method for predicting the structural behaviour and conducting cost-effective design of CFS beams, compared to the traditional analytical methods.","PeriodicalId":52331,"journal":{"name":"Rakenteiden Mekaniikka","volume":"29 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141923372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rashid Hajivand Dastgerdi, Arif Khan, K. Kazemi, Michal Kowalski, Agnieszka Malinowska
The direct shear test is a fundamental method in geotechnical engineering that provides crucial soil shear strength parameters, including cohesion (c) and the angle of internal friction (ϕ). These parameters play a pivotal role in structural design, slope stability assessment, and soil stability evaluation. However, achieving a uniform normal stress distribution within the shear box remains a challenging task, which can result in inaccuracies in test results. This study investigates the impact of shear box shape, specifically comparing circular and square configurations, on the outcomes of the direct shear test. The findings reveal that the choice of lower or upper box movement has a minimal effect on test results. Moreover, circular boxes demonstrate superior normal stress distribution, leading to reduced variations in comparison to square boxes. Wall friction effects lead to lower shear capacity measurements, with circular boxes yielding higher shear levels when contrasted with square boxes. Additionally, the soil along the sides and corners of the specimen experiences diminished shear stress due to reduced normal stress. This research contributes significantly to our comprehension of how shear box shape influences the determination of shear strength parameters in direct shear tests, ultimately enhancing the reliability of geotechnical engineering assessments.
{"title":"Numerical investigation of box shape effects on soil direct shear test","authors":"Rashid Hajivand Dastgerdi, Arif Khan, K. Kazemi, Michal Kowalski, Agnieszka Malinowska","doi":"10.23998/rm.142264","DOIUrl":"https://doi.org/10.23998/rm.142264","url":null,"abstract":"The direct shear test is a fundamental method in geotechnical engineering that provides crucial soil shear strength parameters, including cohesion (c) and the angle of internal friction (ϕ). These parameters play a pivotal role in structural design, slope stability assessment, and soil stability evaluation. However, achieving a uniform normal stress distribution within the shear box remains a challenging task, which can result in inaccuracies in test results. This study investigates the impact of shear box shape, specifically comparing circular and square configurations, on the outcomes of the direct shear test. The findings reveal that the choice of lower or upper box movement has a minimal effect on test results. Moreover, circular boxes demonstrate superior normal stress distribution, leading to reduced variations in comparison to square boxes. Wall friction effects lead to lower shear capacity measurements, with circular boxes yielding higher shear levels when contrasted with square boxes. Additionally, the soil along the sides and corners of the specimen experiences diminished shear stress due to reduced normal stress. This research contributes significantly to our comprehension of how shear box shape influences the determination of shear strength parameters in direct shear tests, ultimately enhancing the reliability of geotechnical engineering assessments.","PeriodicalId":52331,"journal":{"name":"Rakenteiden Mekaniikka","volume":"76 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141922303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sami Kreivi, Teemu Kuivaniemi, A. Mäntylä, J. Vaara, Jaakko Istolahti, Pasi Halla-aho, Antti-Jussi Vuotikka, T. Frondelius
The big end bearing of a connecting rod is one of the most highly loaded bearings in marine engines. This paper presents a feasibility study and optimization of the geometrical parameters of a bush-cut bronze bearing for connecting rods in large-bore marine engines. An accurate simulation workflow was developed and carried out in Abaqus to analyze whether a new simple and cost-saving alternative for manufacturing big end bearings would be possible. The simulations showed that aluminium bronze is feasible regarding stress and yielding. However, improvements were needed to increase the radial contact pressure and decrease the compressive tangential stress peaks on the ends of the split bearing. The optimized design parameters included the outer diameter and thickness of the bearing, the thickness of the cutting blade, and the cut angle. Especially the combination of optimized blade thickness and cut angle generated promising results. The findings of this study provide valuable insights and design principles for bearing design processes.
{"title":"Feasibility and optimization of a bush-cut aluminium bronze big end bearing: a simulation-based study","authors":"Sami Kreivi, Teemu Kuivaniemi, A. Mäntylä, J. Vaara, Jaakko Istolahti, Pasi Halla-aho, Antti-Jussi Vuotikka, T. Frondelius","doi":"10.23998/rm.132039","DOIUrl":"https://doi.org/10.23998/rm.132039","url":null,"abstract":"The big end bearing of a connecting rod is one of the most highly loaded bearings in marine engines. This paper presents a feasibility study and optimization of the geometrical parameters of a bush-cut bronze bearing for connecting rods in large-bore marine engines. An accurate simulation workflow was developed and carried out in Abaqus to analyze whether a new simple and cost-saving alternative for manufacturing big end bearings would be possible. The simulations showed that aluminium bronze is feasible regarding stress and yielding. However, improvements were needed to increase the radial contact pressure and decrease the compressive tangential stress peaks on the ends of the split bearing. The optimized design parameters included the outer diameter and thickness of the bearing, the thickness of the cutting blade, and the cut angle. Especially the combination of optimized blade thickness and cut angle generated promising results. The findings of this study provide valuable insights and design principles for bearing design processes.","PeriodicalId":52331,"journal":{"name":"Rakenteiden Mekaniikka","volume":" 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139143297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artikkelissa tarkastellaan sekaformulaation ja elementtimenetelmän soveltamista tasomuodonmuutostapauksessa Galerkin-pienimmän neliön keinoa käyttäen. Täysin kokoonpuristumattoman aineen lisäksi käsitellään erityisesti myös yleistä kokoonpuristuvaa tapausta. Ainemallina on isotrooppinen Hooken laki. Numeerisissa sovelluksissa käytetään kolmisolmuista kolmioelementtiä. Suoritetaan vertailua puhtaalla siirtymäformulaatiolla saatuihin tuloksiin. Sensitointiparametrin arvon määritystapa kuvataan.
{"title":"Sekaformulaatio, tasomuodonmuutostila ja kolmisolmuinen kolmioelementti","authors":"Jouni Freund, E-M. Salonen","doi":"10.23998/rm.136079","DOIUrl":"https://doi.org/10.23998/rm.136079","url":null,"abstract":"Artikkelissa tarkastellaan sekaformulaation ja elementtimenetelmän soveltamista tasomuodonmuutostapauksessa Galerkin-pienimmän neliön keinoa käyttäen. Täysin kokoonpuristumattoman aineen lisäksi käsitellään erityisesti myös yleistä kokoonpuristuvaa tapausta. Ainemallina on isotrooppinen Hooken laki. Numeerisissa sovelluksissa käytetään kolmisolmuista kolmioelementtiä. Suoritetaan vertailua puhtaalla siirtymäformulaatiolla saatuihin tuloksiin. Sensitointiparametrin arvon määritystapa kuvataan.","PeriodicalId":52331,"journal":{"name":"Rakenteiden Mekaniikka","volume":" 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139142115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A damage-plasticity model for tensile failure analyses of brittle materials is developed. The stress states leading to a failure (inelastic strains and damage) are indicated by a rounded approximation of the Rankine criterion. This approximation is expressed in terms of the stress invariants avoiding thus the need of coordinate transformations and eigenvalue solutions required by the classical Rankine criterion. The model is formulated with the effective stress space approach, i.e. the return mapping is first performed in the global effective stress space and then the damage update is performed independently of the plasticity part. The model is consistently linearized, and, finally, some demonstrative simulations of a tensile test on a rock-like material are carried out.
{"title":"A damage-plasticity model for brittle materials based on an approximation of Rankine type of failure criterion","authors":"T. Saksala, R. Kouhia","doi":"10.23998/rm.137249","DOIUrl":"https://doi.org/10.23998/rm.137249","url":null,"abstract":"A damage-plasticity model for tensile failure analyses of brittle materials is developed. The stress states leading to a failure (inelastic strains and damage) are indicated by a rounded approximation of the Rankine criterion. This approximation is expressed in terms of the stress invariants avoiding thus the need of coordinate transformations and eigenvalue solutions required by the classical Rankine criterion. The model is formulated with the effective stress space approach, i.e. the return mapping is first performed in the global effective stress space and then the damage update is performed independently of the plasticity part. The model is consistently linearized, and, finally, some demonstrative simulations of a tensile test on a rock-like material are carried out.","PeriodicalId":52331,"journal":{"name":"Rakenteiden Mekaniikka","volume":" 40","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139144903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, a recursion formula is given for the integer power of a second-order tensor in 3D Euclidean space. It can be used in constitutive modelling for approximating failure or yield surfaces with corners, and it is demonstrated for the case of Rankine failure criterion. Removing corners provides clear advantages in computational plasticity. We discuss the consequences of the approximation errors for failure analyses of brittle and quasi-brittlematerials.
{"title":"A recursion formula for the integer power of a symmetric second-order tensor and its application to computational plasticity","authors":"R. Kouhia, T. Saksala","doi":"10.23998/rm.137537","DOIUrl":"https://doi.org/10.23998/rm.137537","url":null,"abstract":"In this paper, a recursion formula is given for the integer power of a second-order tensor in 3D Euclidean space. It can be used in constitutive modelling for approximating failure or yield surfaces with corners, and it is demonstrated for the case of Rankine failure criterion. Removing corners provides clear advantages in computational plasticity. We discuss the consequences of the approximation errors for failure analyses of brittle and quasi-brittlematerials.","PeriodicalId":52331,"journal":{"name":"Rakenteiden Mekaniikka","volume":" 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139143333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artikkelissa johdetaan lineaarisesti kimmoisan ortotrooppisen materiaalimallin konstitutiivinen yhtälö invarianttiteorian avulla koordinaatistoriippumattomassa muodossa. Ortotrooppinen symmetriaryhmä määritellään kolmen ortogonaalisen yksikkövektorin avulla. Ortotrooppisen aineen invarianttikanta koostuu seitsemästä invariantista, joiden avulla jännitys-energian tai vastaavasti venymäenergian lausekkeet voidaan konstruoida. Materiaaliparametrien termodynaamiset rajoitteet ja kimmokertoimien monotonisuusehdot johdetaan. Esimerkkeinä tarkastellaan balsapuuta, douglaskoivua, sekä reiden ja säären tiivisluun parametreja.
{"title":"Ortotrooppinen lineaarikimmoinen materiaalimalli","authors":"Reijo Kouhia, Kari Kolari","doi":"10.23998/rm.137490","DOIUrl":"https://doi.org/10.23998/rm.137490","url":null,"abstract":"Artikkelissa johdetaan lineaarisesti kimmoisan ortotrooppisen materiaalimallin konstitutiivinen yhtälö invarianttiteorian avulla koordinaatistoriippumattomassa muodossa. Ortotrooppinen symmetriaryhmä määritellään kolmen ortogonaalisen yksikkövektorin avulla. Ortotrooppisen aineen invarianttikanta koostuu seitsemästä invariantista, joiden avulla jännitys-energian tai vastaavasti venymäenergian lausekkeet voidaan konstruoida. Materiaaliparametrien termodynaamiset rajoitteet ja kimmokertoimien monotonisuusehdot johdetaan. Esimerkkeinä tarkastellaan balsapuuta, douglaskoivua, sekä reiden ja säären tiivisluun parametreja.","PeriodicalId":52331,"journal":{"name":"Rakenteiden Mekaniikka","volume":"70 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139147395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：