scholarly journals An Artificial Intelligence–Assisted Design Method for Topology Optimization without Pre-Optimized Training Data

2021 ◽  
Vol 11 (19) ◽  
pp. 9041
Author(s):  
Alex Halle ◽  
Lucio Flavio Campanile ◽  
Alexander Hasse
Keyword(s):  
Topology Optimization ◽  
Input Data ◽  
Design Method ◽  
Design Procedure ◽  
Computational Effort ◽  
Training Data ◽  
Geometry Design ◽  
Random Input Data ◽  
Degree Of Filling ◽  
Initial Process

Engineers widely use topology optimization during the initial process of product development to obtain a first possible geometry design. The state-of-the-art method is iterative calculation, which requires both time and computational power. This paper proposes an AI-assisted design method for topology optimization, which does not require any optimized data. An artificial neural network—the predictor—provides the designs on the basis of boundary conditions and degree of filling as input data. In the training phase, the so-called evaluators evaluate the generated geometries on the basis of random input data with respect to given criteria. The results of those evaluations flow into an objective function, which is minimized by adapting the predictor’s parameters. After training, the presented AI-assisted design procedure generates geometries that are similar to those of conventional topology optimizers, but require only a fraction of the computational effort. We believe that our work could be a clue for AI-based methods that require data that are difficult to compute or unavailable.

Efficient Post-Tensioned Slab Design Informed Through Topology Optimization

2019 ◽  
Author(s):  
Mark Sarkisian ◽  
Eric Long ◽  
Alessandro Beghini ◽  
Rupa Garai ◽  
David Shook ◽  
...  
Keyword(s):  
Topology Optimization ◽  
Design Method ◽  
Design Procedure ◽  
Optimization Method ◽  
High Rise ◽  
Load Paths ◽  
Novel Approach ◽  
Optimal Load ◽  
Construction Documents ◽  
Post Tensioned

<p>Post-tensioned (PT) flat-plate gravity framing systems are highly efficient and reduce embodied carbon, improve construction speed, and reduce seismic mass when compared to conventional reinforced concrete framing systems. While efficiency is especially apparent in multi-span applications with regular orthogonal support arrangement, single-span or irregular support applications are common in high-rise buildings.</p><p>A novel approach to determining PT tendon arrangements has been applied to several buildings informed by topology optimization results. Topology optimization is an optimization method which determines optimal load paths in a finite element continuum. By orienting PT tendons along the optimal load paths suggested by topology optimization, several applications have consistently demonstrated reductions in post-tensioned tendon quantities while the amount of mild reinforcement is maintained unchanged. Many of the observed tendon layouts do not follow traditional uniform/banded layouts. Also, the deflection performance is enhanced since tendons are placed in a manner consistent with the load demands.</p><p>This new design method has been applied to three buildings and coordinated with construction teams. This presentation will discuss the design procedure which was developed through construction documents as applied to three buildings.</p>

scholarly journals Sensitivity Analysis of Rigid Pavement Design Based on Semi-Empirical Methods: Romanian Case Study

Symmetry ◽  
2021 ◽  
Vol 13 (2) ◽  
pp. 168
Author(s):  
Costel Pleșcan ◽  
Elena-Loredana Pleșcan ◽  
Mariana D. Stanciu ◽  
Marius Botiș ◽  
Daniel Taus
Keyword(s):  
Input Data ◽  
Design Method ◽  
Design Procedure ◽  
Plain Concrete ◽  
Empirical Method ◽  
Traffic Volume ◽  
Pavement Design ◽  
Mountainous Area ◽  
Rigid Pavement ◽  
Pavement Structures

Due to the intensive process of road construction or rehabilitation of pavement caused by an increase in traffic volume, in the field of rigid pavement design and research in Romania, we can say that there is a need to improve the design method. In the last decade, more and more researchers have been concerned about climate change and the increase in traffic volume; hence, there is a need for a renewal of the climatological, as well as traffic, databases because these are part of the input data for the design process. The design method currently used in Romania for jointed plain concrete pavement design is NP081/2002. The limitation of the data and the lack of lifetime estimation of structural and functional performance are the main aspects that need to be addressed in the new design procedure. The Mechanistic–Empirical Pavement Design (MEPDG) method offers the possibility of the design of pavement structures by estimating the structural and functional performances. This paper aims to obtain a comparative study of these two methods for the analysis of the input data collected from the field corresponding to the three failure criteria, while the symmetry of the characteristics of the material and their asymmetrical thicknesses are compared, thus contributing to the design of viable and long-lasting pavement structures using a rigid pavement with the specific characteristics of the mountainous area in northeastern Romania on the national road DN17 Suceava—Vatra Dornei. The novelty of this study consists of the implementation of the mechanistic–empirical method MEPDG instead of the old NP081/2002 method used in Romania.

scholarly journals Surrogate-Based Optimization of Horizontal Axis Hydrokinetic Turbine Rotor Blades

Energies ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 4045
Author(s):  
David Menéndez Arán ◽  
Ángel Menéndez
Keyword(s):  
Turbine Blade ◽  
Design Method ◽  
Optimization Method ◽  
Turbine Rotor ◽  
Computational Effort ◽  
Rotor Blades ◽  
Linear Functions ◽  
Cavitation Inception ◽  
Hydrokinetic Turbine ◽  
Blade Geometry

A design method was developed for automated, systematic design of hydrokinetic turbine rotor blades. The method coupled a Computational Fluid Dynamics (CFD) solver to estimate the power output of a given turbine with a surrogate-based constrained optimization method. This allowed the characterization of the design space while minimizing the number of analyzed blade geometries and the associated computational effort. An initial blade geometry developed using a lifting line optimization method was selected as the base geometry to generate a turbine blade family by multiplying a series of geometric parameters with corresponding linear functions. A performance database was constructed for the turbine blade family with the CFD solver and used to build the surrogate function. The linear functions were then incorporated into a constrained nonlinear optimization algorithm to solve for the blade geometry with the highest efficiency. A constraint on the minimum pressure on the blade could be set to prevent cavitation inception.

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

scholarly journals A Two-Round Optimization Design Method for Aerostatic Spindles Considering the Fluid–Structure Interaction Effect

2021 ◽  
Vol 11 (7) ◽  
pp. 3017
Author(s):  
Qiang Gao ◽  
Siyu Gao ◽  
Lihua Lu ◽  
Min Zhu ◽  
Feihu Zhang
Keyword(s):  
Optimal Design ◽  
Optimization Design ◽  
Design Method ◽  
Fluid Structure Interaction ◽  
Design Procedure ◽  
Design Parameters ◽  
Geometrical Parameters ◽  
Fluid Structure ◽  
Structure Interaction ◽  
Aerostatic Spindle

The fluid–structure interaction (FSI) effect has a significant impact on the static and dynamic performance of aerostatic spindles, which should be fully considered when developing a new product. To enhance the overall performance of aerostatic spindles, a two-round optimization design method for aerostatic spindles considering the FSI effect is proposed in this article. An aerostatic spindle is optimized to elaborate the design procedure of the proposed method. In the first-round design, the geometrical parameters of the aerostatic bearing were optimized to improve its stiffness. Then, the key structural dimension of the aerostatic spindle is optimized in the second-round design to improve the natural frequency of the spindle. Finally, optimal design parameters are acquired and experimentally verified. This research guides the optimal design of aerostatic spindles considering the FSI effect.

scholarly journals A Shape Optimization Method for Part Design Derived from the Buildability Restrictions of the Directed Energy Deposition Additive Manufacturing Process

Designs ◽  
2020 ◽  
Vol 4 (3) ◽  
pp. 19
Author(s):  
Andreas K. Lianos ◽  
Harry Bikas ◽  
Panagiotis Stavropoulos
Keyword(s):  
Topology Optimization ◽  
Additive Manufacturing ◽  
Energy Deposition ◽  
Design Method ◽  
Current Trend ◽  
Internal Stresses ◽  
Material Distribution ◽  
Load Case ◽  
Design Elements ◽  
Industrial Sectors

The design methodologies and part shape algorithms for additive manufacturing (AM) are rapidly growing fields, proven to be of critical importance for the uptake of additive manufacturing of parts with enhanced performance in all major industrial sectors. The current trend for part design is a computationally driven approach where the parts are algorithmically morphed to meet the functional requirements with optimized performance in terms of material distribution. However, the manufacturability restrictions of AM processes are not considered at the primary design phases but at a later post-morphed stage of the part’s design. This paper proposes an AM design method to ensure: (1) optimized material distribution based on the load case and (2) the part’s manufacturability. The buildability restrictions from the direct energy deposition (DED) AM technology were used as input to the AM shaping algorithm to grant high AM manufacturability. The first step of this work was to define the term of AM manufacturability, its effect on AM production, and to propose a framework to estimate the quantified value of AM manufacturability for the given part design. Moreover, an AM design method is proposed, based on the developed internal stresses of the build volume for the load case. Stress tensors are used for the determination of the build orientation and as input for the part morphing. A top-down mesoscale geometric optimization is used to realize the AM part design. The DED Design for Additive Manufacturing (DfAM) rules are used to delimitate the morphing of the part, representing at the same time the freeform mindset of the AM technology. The morphed shape of the part is optimized in terms of topology and AM manufacturability. The topology optimization and AM manufacturability indicator (TMI) is introduced to screen the percentage of design elements that serve topology optimization and the ones that serve AM manufacturability. In the end, a case study for proof of concept is realized.

AN INDEPENDENT ACTIVE BALANCER FOR PLANAR MECHANISMS

2007 ◽  
Vol 31 (2) ◽  
pp. 167-190 ◽  
Author(s):  
Zhang Ying ◽  
Yao Yan-An ◽  
Cha Jian-Zhong
Keyword(s):  
Working Conditions ◽  
Design Method ◽  
Design Procedure ◽  
Vibration Absorber ◽  
Planar Mechanisms ◽  
Dynamic Balancing ◽  
Joint Coupling ◽  
Design Requirements ◽  
Novel Concept ◽  
Two Degree Of Freedom

This paper proposed a novel concept of active balancer for dynamic balancing of planar mechanisms. Somewhat similar to a vibration absorber, the active balancer is designed as an independent device, which is placed outside of the mechanism to be balanced and can be installed easily. It consists of a two degree-of-freedom (DOF) linkage with two input shafts, one of which is connected to the output shaft of the mechanism to be balanced by a joint coupling, and the other one is driven by a controllable motor. Flexible dynamic balancing adapted to different working conditions can be achieved by varying speed trajectories of the control motor actively. A design method is developed for selecting suitable speed trajectories and link parameters of the two DOF linkage of the balancer to meet various design requirements and constraints. Numerical examples are given to demonstrate the design procedure and to verify the feasibility of the proposed concept.

scholarly journals Novel Robust Design Method of Multilayer Optical Coatings

ISRN Optics ◽  
2012 ◽  
Vol 2012 ◽  
pp. 1-6 ◽  
Author(s):  
Suyong Wu ◽  
Xingwu Long ◽  
Kaiyong Yang
Keyword(s):  
Robust Design ◽  
Optimization Design ◽  
Design Method ◽  
Analytical Calculation ◽  
Design Procedure ◽  
Deposition Process ◽  
Practical Significance ◽  
Optical Coatings ◽  
Optical Films ◽  
Robust Design Method

We present a novel fast robust design method of multilayer optical coatings. The sensitivity of optical films to production errors is controlled in the whole optimization design procedure. We derive an analytical calculation model for fast robust design of multilayer optical coatings. We demonstrate its effectiveness by successful application of the robust design method to a neutral beam splitter. It is showed that the novel robust design method owns an inherent fast computation characteristic and the designed film is insensitive to the monitoring thickness errors in deposition process. This method is especially of practical significance to improve the mass production yields and repetitive production of high-quality optical coatings.

Structural topology optimization of bridge girders in cable supported bridges

2018 ◽  
Author(s):  
Mads Baandrup ◽  
Ole Sigmund ◽  
Niels Aage
Keyword(s):  
Topology Optimization ◽  
Large Scale ◽  
Design Method ◽  
Optimization Method ◽  
Bridge Girders ◽  
Structural Topology ◽  
Box Girders ◽  
Box Girder ◽  
Fine Mesh ◽  
Further Development

<p>This work applies a ultra large scale topology optimization method to study the optimal structure of bridge girders in cable supported bridges.</p><p>The current classic orthotropic box girder designs are limited in further development and optimiza­ tion, and suffer from substantial fatigue issues. A great disadvantage of the orthotropic girder is the loads being carried one direction at a time, thus creating stress hot spots and fatigue problems. Hence, a new design concept has the potential to solve many of the limitations in the current state­ of-the-art.</p><p>We present a design method based on ultra large scale topology optimization. The highly detailed structures and fine mesh-discretization permitted by ultra large scale topology optimization reveal new design features and previously unseen eff ects. The results demonstrate the potential of gener­ ating completely different design solutions for bridge girders in cable supported bridges, which dif­ fer significantly from the classic orthotropic box girders.</p><p>The overall goal of the presented work is to identify new and innovative, but at the same time con­ structible and economically reasonable, solutions tobe implemented into the design of future cable supported bridges.</p>

Sign in / Sign up

Export Citation Format

Share Document