Integrating real-time multi-resolution scanning and machine learning for Conformal Robotic 3D Printing in Architecture

Robotic 3D printing applications are rapidly growing in architecture, where they enable the introduction of new materials and bespoke geometries. However, current approaches remain limited to printing on top of a flat build bed. This limits robotic 3D printing’s impact as a sustainable technology: opportunities to customize or enhance existing elements, or to utilize complex material behaviour are missed. This paper addresses the potentials of conformal 3D printing and presents a novel and robust workflow for printing onto unknown and arbitrarily shaped 3D substrates. The workflow combines dual-resolution Robotic Scanning, Neural Network prediction and printing of PETG plastic. This integrated approach offers the advantage of responding directly to unknown geometries through automated performance design customization. This paper firstly contextualizes the work within the current state of the art of conformal printing. We then describe our methodology and the design experiment we have used to test it. We lastly describe the key findings, potentials and limitations of the work, as well as the next steps in this research.

Download Full-text

Enhancing Stock Movement Prediction with Adversarial Training

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/810 ◽

2019 ◽

Cited By ~ 8

Author(s):

Fuli Feng ◽

Huimin Chen ◽

Xiangnan He ◽

Ji Ding ◽

Maosong Sun ◽

...

Keyword(s):

Stock Price ◽

State Of The Art ◽

Stochastic Variable ◽

Stock Prediction ◽

Movement Prediction ◽

Neural Network Prediction ◽

Adversarial Training ◽

Network Prediction ◽

Near Future ◽

New Machine

This paper contributes a new machine learning solution for stock movement prediction, which aims to predict whether the price of a stock will be up or down in the near future. The key novelty is that we propose to employ adversarial training to improve the generalization of a neural network prediction model. The rationality of adversarial training here is that the input features to stock prediction are typically based on stock price, which is essentially a stochastic variable and continuously changed with time by nature. As such, normal training with static price-based features (e.g. the close price) can easily overfit the data, being insufficient to obtain reliable models. To address this problem, we propose to add perturbations to simulate the stochasticity of price variable, and train the model to work well under small yet intentional perturbations. Extensive experiments on two real-world stock data show that our method outperforms the state-of-the-art solution [Xu and Cohen, 2018] with 3.11% relative improvements on average w.r.t. accuracy, validating the usefulness of adversarial training for stock prediction task.

Download Full-text

An integrated approach to pipeline burial in the 21st century – The current state-of-the-art

Frontiers in Offshore Geotechnics III ◽

10.1201/b18442-47 ◽

2015 ◽

pp. 417-422 ◽

Cited By ~ 1

Author(s):

A Maconochie ◽

J Kennedy ◽

J Oliphant

Keyword(s):

21St Century ◽

State Of The Art ◽

Integrated Approach ◽

Current State

Download Full-text

The changing face of additive manufacturing

Journal of Manufacturing Technology Management ◽

10.1108/jmtm-12-2016-0182 ◽

2017 ◽

Vol 28 (1) ◽

pp. 10-17 ◽

Cited By ~ 26

Author(s):

Ian Gibson

Keyword(s):

Additive Manufacturing ◽

3D Printing ◽

Design Methodology ◽

State Of The Art ◽

Personal Perspective ◽

Numerous Application ◽

Content Type ◽

The Past ◽

Current State ◽

The Future

Purpose The purpose of this paper is to discuss the current state-of-the-art in additive manufacturing, more commonly known as 3D printing, from the business perspectives. The primary drivers behind the development of the associated technologies are considered along with features that limit growth. Design/methodology/approach The approach is a personal perspective, based on approximately 25-years study of the development of the associated technologies and applications. Findings The discussion has found that the technology is still growing healthily, but with an understanding that there are numerous application areas that should be considered separately. Some areas are significantly more mature than others and success in some areas does not guarantee success in others. Originality/value This viewpoint has been prepared for the current state-of-the-art and can be compared with earlier viewpoints to see how things may have changed in the past. This should be of value to those interested to explore how the technology has developed in recent times and how it may move into the future.

Download Full-text

Balloons, airships and kites – lighter than air: past, present and future

The Aeronautical Journal ◽

10.1017/s0001924000002384 ◽

2008 ◽

Vol 112 (1133) ◽

pp. 421-429 ◽

Cited By ~ 1

Author(s):

J. Folkes

Keyword(s):

Personal Experience ◽

State Of The Art ◽

Past History ◽

New Materials ◽

Long Distance ◽

The Past ◽

Hot Air ◽

Current State ◽

History Of ◽

Technical Innovations

Abstract One hundred years on from the advent of aeronautics at Queen Mary, University of London, developments in lighter than air technology have progressed at a somewhat slower pace than the technology for heavier than air. Innovations afforded by the ‘discovery’ of helium, the development of the modern day hot air balloon and the application of new materials have all contributed to today’s technical innovations. A review is given of the past history of lighter than air, a note is made of the current state of the art and a brief overview of future applications is discussed. The author’s personal experience in long distance gas balloon flights is mentioned.

Download Full-text

TRANSITION FROM TRADITIONAL COB CONSTRUCTION TO 3D PRINTING OF CLAY HOMES

Journal of Green Building ◽

10.3992/jgb.16.4.3 ◽

2021 ◽

Vol 16 (4) ◽

pp. 3-28

Author(s):

Amnah Y. Alqenaee ◽

Ali M. Memari ◽

Maryam Hojati

Keyword(s):

3D Printing ◽

State Of The Art ◽

Cementitious Materials ◽

Earth Construction ◽

Current State ◽

Time Period ◽

Open Time ◽

Specific Objective ◽

Computer Controlled ◽

Advanced Computer

ABSTRACT 3D printing of cementitious material can provide an affordable, sustainable, and optimized approach for the construction of homes, without compromising quality or craftsmanship. While most of the current research and development efforts in this field are focused on cement-based concrete printing, this paper focuses on the current state-of-the-art literature review of designing and developing a sustainable clay-based mixture design that mainly includes clay, sand, straw, lime, and water. The goal of this paper is to bridge the gap between typical traditional earth construction, specifically cob construction, and emerging 3D printing of cementitious materials. The specific objective of this paper is to offer some possible changes in the typical cob mixture so that it can be used for 3D printing of clay-based mixtures with sufficient flowability, buildability, strength, and open time (i.e., the time period between printing of one layer and printing of another layer deposited on a layer below). The paper describes typical clay-based mixtures and their traditional process and then specifies the challenges in going from traditional cob construction to advanced computer-controlled robotic 3D printing.

Download Full-text

Advances on the Fragmentation-Energy Fan Concept and the Swebrec Function in Modeling Drop Weight Testing

Minerals ◽

10.3390/min11111262 ◽

2021 ◽

Vol 11 (11) ◽

pp. 1262

Author(s):

Finn Ouchterlony ◽

José A. Sanchidrián ◽

Ömürden Genç

Keyword(s):

State Of The Art ◽

Data Sets ◽

New Materials ◽

Fragmentation Energy ◽

Current State ◽

Drop Weight ◽

Weight Test ◽

Swebrec Function ◽

Drop Weight Test ◽

Straight Lines

The breakage index equation (BIE), or t10 model from drop weight testing (DWT) data for rocks and ores is used in the design of crushers and mills. Such models are becoming increasingly difficult to visualize as the number of variables increases. The so-called double fan BIE, combined with the Swebrec distribution’s accurate description of the sieving curves, is applied to the modelling of drop-weight test fragmentation. The key parameters are geometric properties visible in the fan plot; slopes of straight lines and their point of convergence. The ability of the double fan BIE to reproduce DWT data had been previously established for 8 rocks with 480 DWT data sets. Here the fidelity of the double fan BIE is further evaluated for 18 new materials, based on 281 data sets. The fidelity of the double fan BIE with three fan lines is on par with the fidelity of the current state-of-the-art models for the new materials. Besides the breakage index equation, the new double fan BIE’s t10 equation produces, without additional parameters or fitted constants, the general breakage surface equation tn for an arbitrary n value as a bonus. The specific sieving curve for any combination of particle size and impact energy is also contained in the same formula. The result is an accurate, compact and transparent model.

Download Full-text

3D printing for enhanced drug delivery: current state-of-the-art and challenges

Drug Development and Industrial Pharmacy ◽

10.1080/03639045.2020.1801714 ◽

2020 ◽

Vol 46 (9) ◽

pp. 1385-1401 ◽

Cited By ~ 1

Author(s):

Melissa Wallis ◽

Zaisam Al-Dulimi ◽

Deck Khong Tan ◽

Mohammed Maniruzzaman ◽

Ali Nokhodchi

Keyword(s):

Drug Delivery ◽

3D Printing ◽

State Of The Art ◽

Current State

Download Full-text

Behavioral Genetics: Concepts for Research and Practice in Language Development and Disorders

Journal of Speech Language and Hearing Research ◽

10.1044/jshr.3805.1126 ◽

1995 ◽

Vol 38 (5) ◽

pp. 1126-1142 ◽

Cited By ~ 14

Author(s):

Jeffrey W. Gilger

Keyword(s):

Language Development ◽

Behavioral Genetics ◽

State Of The Art ◽

Genetic Research ◽

Great Promise ◽

Behavioral Genetic ◽

Fine Grained ◽

Future Goals ◽

Current State ◽

Research Designs

This paper is an introduction to behavioral genetics for researchers and practioners in language development and disorders. The specific aims are to illustrate some essential concepts and to show how behavioral genetic research can be applied to the language sciences. Past genetic research on language-related traits has tended to focus on simple etiology (i.e., the heritability or familiality of language skills). The current state of the art, however, suggests that great promise lies in addressing more complex questions through behavioral genetic paradigms. In terms of future goals it is suggested that: (a) more behavioral genetic work of all types should be done—including replications and expansions of preliminary studies already in print; (b) work should focus on fine-grained, theory-based phenotypes with research designs that can address complex questions in language development; and (c) work in this area should utilize a variety of samples and methods (e.g., twin and family samples, heritability and segregation analyses, linkage and association tests, etc.).

Download Full-text