Reinforcement Learning for Structural Control

Adam, Bernard; Smith, Ian F. C.

doi:10.1061/(asce)0887-3801(2008)22:2(133)

Cited by 56 publications

(26 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, the field of machine learning is divided into three subdomains: supervised learning, unsupervised learning, and reinforcement learning [21]. Briefly, supervised learning requires training with labeled data which has inputs and desired outputs.…”

Section: Definition and Classification Of Machine Learningmentioning

confidence: 99%

A survey of machine learning for big data processing

Qiu

Ding

et al. 2016

EURASIP J. Adv. Signal Process.

641

361

View full text Add to dashboard Cite

There is no doubt that big data are now rapidly expanding in all science and engineering domains. While the potential of these massive data is undoubtedly significant, fully making sense of them requires new ways of thinking and novel learning techniques to address the various challenges. In this paper, we present a literature survey of the latest advances in researches on machine learning for big data processing. First, we review the machine learning techniques and highlight some promising learning methods in recent studies, such as representation learning, deep learning, distributed and parallel learning, transfer learning, active learning, and kernel-based learning. Next, we focus on the analysis and discussions about the challenges and possible solutions of machine learning for big data. Following that, we investigate the close connections of machine learning with signal processing techniques for big data processing. Finally, we outline several open issues and research trends.

show abstract

Section: Definition and Classification Of Machine Learningmentioning

confidence: 99%

A survey of machine learning for big data processing

Qiu

Ding

et al. 2016

EURASIP J. Adv. Signal Process.

641

361

View full text Add to dashboard Cite

show abstract

“…The values for this configuration are inspired from previous research [27][28][29]. The parameter of interest is alone varied while the values for other parameters are left unchanged from the base configuration.…”

Section: Design Using Parametric Analysis and Traditional Designmentioning

confidence: 99%

Design of tensegrity structures using parametric analysis and stochastic search

Rhode-Barbarigos

Jain

Kripakaran

et al. 2009

Engineering with Computers

View full text Add to dashboard Cite

Tensegrity structures are lightweight structures composed of cables in tension and struts in compression. Since tensegrity systems exhibit geometrically nonlinear behavior, finding optimal structural designs is difficult. This paper focuses on the use of stochastic search for the design of tensegrity systems. A pedestrian bridge made of square hollow-rope tensegrity ring modules is studied. Two design methods are compared in this paper. Both methods aim to find the minimal cost solution. The first method approximates current practice in design offices. More specifically, parametric analysis that is similar to a gradient-based optimization is used to identify good designs. Parametric studies are executed for each system parameter in order to identify its influence on response. The second method uses a stochastic search strategy called Probabilistic Global Search Lausanne (PGSL). Both methods provide feasible configurations that meet civil engineering criteria of safety and serviceability. Parametric studies also help in defining search parameters such as appropriate penalty costs to enforce constraints while optimizing using stochastic search. Traditional design methods are useful to gain an understanding of structural behavior. However, due to the many local minima in the solution space, stochastic search strategies find better solutions than parametric studies.

show abstract

“…Fest et al (2004) employed telescopic struts to investigate the active control behavior of a five-module tensegrity structure. In several studies, biomimetic properties of active tensegrity structures have been studied (Adam and Smith 2008;Domer 2003;Domer and Smith 2005). These structures were not deployable.…”

Section: Introductionmentioning

confidence: 99%

Deployment of a Tensegrity Footbridge

2015

View full text Add to dashboard Cite

Deployable structures are structures that transform their shape from a compact state to an extended in-service position. Structures composed of tension elements that surround compression elements in equilibrium are called tensegrity structures. Tensegrities are good candidates for deployable structures since shape transformations occur by changing lengths of elements at low energy costs. Although the tensegrity concept was first introduced in 1948, few full-scale tensegrity-based structures have been built. Previous work has demonstrated that a tensegrity-ring topology is potentially a viable system for a deployable footbridge. This paper describes a study of a near-full-scale deployable tensegrity footbridge. The study has been carried out both numerically and experimentally. The deployment of two modules (one half of the footbridge) is achieved through changing the length of five active cables. Deployment is aided by energy stored in low stiffness spring elements. Self-weight significantly influences deployment, and deployment is not reproducible using the same sequence of cable-length changes. Active control is thus required for accurate positioning of front nodes in order to complete deployment through joining both sides at center span. Additionally, testing and numerical analyses have revealed that the deployment behavior of the structure is non-linear with respect to cable-length changes. Finally, modelling the behavior of the structure cannot be done accurately using friction-free and dimensionless joints. Similar deployable tensegrity structures of class two and higher are expected to require simulation models that include joint dimensions for accurate prediction of nodal positions.

show abstract

Reinforcement Learning for Structural Control

Cited by 56 publications

References 25 publications

A survey of machine learning for big data processing

A survey of machine learning for big data processing

Design of tensegrity structures using parametric analysis and stochastic search

Deployment of a Tensegrity Footbridge

Contact Info

Product

Resources

About