scholarly journals Neural Network-Based Formula for the Buckling Load Prediction of I-Section Cellular Steel Beams

Computers ◽  
2018 ◽  
Vol 8 (1) ◽  
pp. 2 ◽  
Author(s):  
Miguel Abambres ◽  
Komal Rajana ◽  
Konstantinos Tsavdaridis ◽  
Tiago Ribeiro
Keyword(s):  
Neural Network ◽  
Computing Time ◽  
Design Guidelines ◽  
Design Tool ◽  
Buckling Load ◽  
Steel Beams ◽  
Efficient Design ◽  
Load Prediction ◽  
Element Analysis ◽  
Parametric Finite Element Analysis

Cellular beams are an attractive option for the steel construction industry due to their versatility in terms of strength, size, and weight. Further benefits are the integration of services thereby reducing ceiling-to-floor depth (thus, building’s height), which has a great economic impact. Moreover, the complex localized and global failures characterizing those members have led several scientists to focus their research on the development of more efficient design guidelines. This paper aims to propose an artificial neural network (ANN)-based formula to precisely compute the critical elastic buckling load of simply supported cellular beams under uniformly distributed vertical loads. The 3645-point dataset used in ANN design was obtained from an extensive parametric finite element analysis performed in ABAQUS. The independent variables adopted as ANN inputs are the following: beam’s length, opening diameter, web-post width, cross-section height, web thickness, flange width, flange thickness, and the distance between the last opening edge and the end support. The proposed model shows a strong potential as an effective design tool. The maximum and average relative errors among the 3645 data points were found to be 3.7% and 0.4%, respectively, whereas the average computing time per data point is smaller than a millisecond for any current personal computer.

scholarly journals Neural Network-based formula for the buckling load prediction of I-section cellular steel beams

2018 ◽  
Author(s):  
Miguel Abambres ◽  
Komal Rajana ◽  
Konstantinos Tsavdaridis ◽  
Tiago Ribeiro
Keyword(s):  
Neural Network ◽  
Computing Time ◽  
Design Guidelines ◽  
Design Tool ◽  
Buckling Load ◽  
Steel Beams ◽  
Efficient Design ◽  
Load Prediction ◽  
Element Analysis ◽  
Parametric Finite Element Analysis

Cellular beams are an attractive option for the steel construction industry due to their versatility in terms of strength, size, and weight. Further benefits are the integration of services thereby reducing ceiling-to-floor depth (thus, building’s height), which has a great economic impact. Moreover, the complex localised and global failures characterizing those members have led several scientists to focus their research on the development of more efficient design guidelines. This paper aims to propose an artificial neural network (ANN)-based formula to estimate the critical elastic buckling load of simply supported cellular beams under uniformly distributed vertical loads. The 3645-point dataset used in ANN design was obtained from an extensive parametric finite element analysis performed in ABAQUS. The independent variables adopted as ANN inputs are the following: beam’s length, opening diameter, web-post width, cross-section height, web thickness, flange width, flange thickness, and the distance between the last opening edge and the end support. The proposed model shows a strong potential as an effective design tool. The maximum and average relative errors among the 3645 data points were found to be 3.7% and 0.4%, respectively, whereas the average computing time per data point is smaller than a millisecond for any current personal computer.

scholarly journals Neural Network-Based Formula for the Buckling Load Prediction of I-Section Cellular Steel Beams

2018 ◽  
Author(s):  
Miguel Abambres ◽  
Komal Rajana ◽  
Konstantinos Tsavdaridis ◽  
Tiago Ribeiro
Keyword(s):  
Neural Network ◽  
Buckling Load ◽  
Steel Beams ◽  
Load Prediction

Analysis, Design, and Optimization of Thermal In-Plane Microactuator—Chevron Type

2011 ◽  
Vol 8 (3) ◽  
pp. 102-109
Author(s):  
K.B. Puneeth ◽  
K.N. Seetharamu
Keyword(s):  
Neural Network ◽  
Mechanical Response ◽  
Thermal Response ◽  
Structural Response ◽  
Design Tool ◽  
Thermal Actuator ◽  
Coupled Models ◽  
Element Analysis ◽  
Design And Optimization ◽  
Analysis Design

A predictive model of thermal actuator behavior has been developed and validated that can be used as a design tool to customize the performance of an actuator to a specific application. Modeling thermal actuator behavior requires the use of two sequentially or directly coupled models, the first to predict the temperature increase of the actuator due to the applied voltage and the second to model the mechanical response of the structure due to the increase in temperature. These models have been developed using ANSYS for both thermal response and structural response. Consolidation of FEA (finite element analysis) results has been carried out using an ANN (artificial neural network) in MATLAB. It is seen that an ANN can be successfully employed to interpolate and predict FEA results, thus avoiding necessity of running FEA code for every new case. Furtheroptimization of geometry for maximum actuation length has been carried out using a GA (genetic algorithm) in MATLAB. The results of the GA were verified against the ANN and FEA results.

scholarly journals Investigation of ANN Architecture for Predicting Load-Carrying Capacity of Castellated Steel Beams

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Thuy-Anh Nguyen ◽  
Hai-Bang Ly ◽  
Van Quan Tran
Keyword(s):  
Yield Stress ◽  
Carrying Capacity ◽  
Design Guidelines ◽  
Steel Beams ◽  
Load Carrying Capacity ◽  
Ann Model ◽  
Efficient Design ◽  
Vertical Projection ◽  
Geometrical Properties ◽  
Load Carrying

Castellated steel beams (CSB) are an attractive option for the steel construction industry thanks to outstanding advantages, such as the ability to exceed large span, lightweight, and allowing flexible arrangement of the technical pipes through beams. In addition, the complex localized and global failures characterizing these structural members have led researchers to focus on the development of efficient design guidelines. This paper aims to propose an artificial neural network (ANN) model with optimal architecture to predict the load-carrying capacity of CSB with a scheme of the simple beam bearing load located at the center of the beam. The ANN model is built with 9 input variables, which are essential parameters equivalent to the geometrical properties and mechanical properties of the material, such as the overall depth of the castellated beam, the vertical projection of the inclined side of the opening, the web thickness, the flange width, the flange thickness, the width of web post at middepth, the horizontal projection of inclined side of the opening, the minimum web yield stress, and the minimum flange yield stress. The output variable is the load-carrying capacity of the CSB. With the optimal ANN architecture [9-1-1] containing one hidden layer, the performance of the ANN model is evaluated based on statistical criteria such as R2, RMSE, and MAE. The results show that the optimal ANN model is a highly effective predictor of the load-carrying capacity of the CSB with the best value of R2 = 0.989, RMSE = 3.328, and MAE = 2.620 for the testing part. The ANN model seems to be the best algorithm of machine learning for predicting the CSB load-carrying capacity.

Parametric Studies of Effects of Solder Bump Pitch, Package Size, and Molding Compound and Substrate Thicknesses on Warpage of PBGA Packages

2014 ◽  
Vol 2014 (1) ◽  
pp. 000044-000049
Author(s):  
Sungbum Kang ◽  
I. Charles Ume
Keyword(s):  
Solder Bump ◽  
Electronic Devices ◽  
Design Guidelines ◽  
Element Analysis ◽  
Molding Compound ◽  
Factors Affecting ◽  
Package Design ◽  
Plastic Ball ◽  
Package Size ◽  
Parametric Finite Element Analysis

Plastic ball grid array (PBGA) is one of the most widely used types of chip packages in various electronic devices such as network servers, microcontrollers, and memory devices. As the demand for higher performance electronic devices grows, the I/O densities of PBGA packages are increasing while requiring superior reliability. Warpage induced during the reflow assembly process is one of the crucial factors affecting the thermo-mechanical reliability of PBGA packages; therefore, accurate warpage prediction is an important task for package design processes. In this study, the effects of four geometric factors (the solder bump pitch, package size, and molding compound and substrate thicknesses) of the PBGA package on its warpage are assessed by using parametric finite element analysis. The correlation between PBGA warpage and the four factors is studied using the regression method. These results are expected to provide design guidelines for in-house PBGA designers.

Development of Bolted Flange Design Tool Based on Artificial Neural Network

2019 ◽  
Vol 141 (5) ◽  
Author(s):  
Alper Yıldırım ◽  
Ahmet Arda Akay ◽  
Hasan Gülaşık ◽  
Demirkan Çoker ◽  
Ercan Gürses ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Finite Element ◽  
Design Tool ◽  
Finite Element Analyses ◽  
Element Analysis ◽  
Flange Connection ◽  
Design Variables ◽  
Artificial Neural ◽  
Bolted Flange

Finite element analysis (FEA) of bolted flange connections is the common methodology for the analysis of bolted flange connections. However, it requires high computational power for model preparation and nonlinear analysis due to contact definitions used between the mating parts. Design of an optimum bolted flange connection requires many costly finite element analyses to be performed to decide on the optimum bolt configuration and minimum flange and casing thicknesses. In this study, very fast responding and accurate artificial neural network-based bolted flange design tool is developed. Artificial neural network is established using the database which is generated by the results of more than 10,000 nonlinear finite element analyses of the bolted flange connection of a typical aircraft engine. The FEA database is created by taking permutations of the parametric geometric design variables of the bolted flange connection and input load parameters. In order to decrease the number of FEA points, the significance of each design variable is evaluated by performing a parameter correlation study beforehand, and the number of design points between the lower and upper and bounds of the design variables is decided accordingly. The prediction of the artificial neural network based design tool is then compared with the FEA results. The results show excellent agreement between the artificial neural network-based design tool and the nonlinear FEA results within the training limits of the artificial neural network.

scholarly journals Moment Resisting Connection with Curved Endplates: Behaviour Study

2021 ◽  
Vol 11 (4) ◽  
pp. 1520
Author(s):  
Andrej Mudrov ◽  
Antanas Šapalas ◽  
Gintas Šaučiuvėnas ◽  
Kęstutis Urbonas
Keyword(s):  
Experimental Tests ◽  
Steel Beams ◽  
Initial Stiffness ◽  
Flat Plates ◽  
Element Analysis ◽  
Hollow Section ◽  
Moment Resisting ◽  
The Moment ◽  
Circular Hollow Section ◽  
Parametric Finite Element Analysis

This article provides a behaviour analysis of moment resisting joints with curved endplates. This is a new type of connection that can be used for joining steel beams to the circular hollow section (CHS) columns by means of bolts. Some researchers apply the Eurocode model without considering the differences in calculation schemes and assumptions, such as by using the general model of an equivalent T-stub in tension. Consequently, many of the existing behaviour studies are somewhat misleading, thus there is a need for further research. Apart from the absence of analytical methods that are devoted to predicting the initial stiffness and strength of the curved T-stub, other technical difficulties were encountered, such as gaps between the endplate and the column, as well as the initial pre-loading force of the bolts. In the previous studies, endplates were manufactured by rolling flat plates to the precise curvature which resulted in firm contact. In contrast, in this study, endplates were manufactured from a standard CHS tube, which led to significant initial gaps. Meanwhile, in terms of preloading force, it was found that it affected the moment resistance of the joint. This paper discusses problems associated with ongoing researches and presents experimental tests of the two connections. The obtained results were further used in the parametric finite element analysis (FEA) to determine the effect of the gaps and preloading force of the bolts on the moment resistance and initial rotational stiffness of the joint. The results indicate that the behaviour of curved plated connections is exceedingly complex and that the preloading force is the key factor, therefore, it should be controlled.

scholarly journals Research on Buckling Load Prediction of Composite Stiffened Plates Based on BP Neural Network

2020 ◽  
Vol 1576 ◽  
pp. 012032
Author(s):  
Chengcheng Zhao ◽  
Junqing Yin ◽  
Yongdang Chen ◽  
Jinyu Gu ◽  
Haotian Du ◽  
...  
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Buckling Load ◽  
Stiffened Plates ◽  
Load Prediction

scholarly journals Development of Bolted Flange Design Tool Based on Finite Element Analysis and Artificial Neural Network

2015 ◽  
Author(s):  
Alper Yildirim ◽  
Ahmet Arda Akay ◽  
Hasan Gulasik ◽  
Demirkan Coker ◽  
Ercan Gurses ◽  
...  
Keyword(s):  
Neural Network ◽  
Finite Element Analysis ◽  
Artificial Neural Network ◽  
Finite Element ◽  
Structural Analysis ◽  
Design Tool ◽  
Design Parameters ◽  
Element Analysis ◽  
Non Linear ◽  
Bolted Flange

In bolted flange connections, commonly utilized in aircraft engine designs, structural integrity and minimization of the weight are achieved by the optimum combination of the design parameters utilizing the outcome of many structural analyses. Bolt size, the number of bolts, bolt locations, casing thickness, flange thickness, bolt preload, and axial external force are some of the critical design parameters in bolted flange connections. Theoretical analysis and finite element analysis (FEA) are two main approaches to perform structural analysis of bolted flange connections. Theoretical approaches require the simplification of the geometry and are generally oversafe. In contrast, finite element analysis is more reliable but at the cost of high computational power. In this paper, a methodology is developed for iterative analyses of bolted flange that utilizes artificial neural network approximation of a database formed with more than ten thousand non-linear analyses with contact algorithm. In the design tool, a structural analysis database is created by taking permutations of the parametric variables. The number of intervals for each variable in the upper and lower range of the variables is determined with the parameters correlation study in which the significance of parameters are evaluated. The prediction of the ANN based design tool is then compared with FEA results and the theoretical approach of ESDU. The results show excellent agreement of the ANN based design tool with the actual non-linear finite element analysis results within the training limits of the ANN.

Sign in / Sign up

Export Citation Format

Share Document