Beyond typologies, beyond optimization: Exploring novel structural forms at the interface of human and machine intelligence

2020 ◽  
pp. 147807712094306
Author(s):  
Karla Saldana Ochoa ◽  
Patrick Ole Ohlbrock ◽  
Pierluigi D’Acunto ◽  
Vahid Moosavi

This article presents a computer-aided design framework for the generation of non-standard structural forms in static equilibrium that takes advantage of the interaction between human and machine intelligence. The design framework relies on the implementation of a series of operations (generation, clustering, evaluation, selection, and regeneration) that allow to create multiple design options and to navigate in the design space according to objective and subjective criteria defined by the human designer. Through the interaction between human and machine intelligence, the machine can learn the nonlinear correlation between the design inputs and the design outputs preferred by the human designer and generate new options by itself. In addition, the machine can provide insights into the structural performance of the generated structural forms. Within the proposed framework, three main algorithms are used: Combinatorial Equilibrium Modeling for generating of structural forms in static equilibrium as design options, Self-Organizing Map for clustering the generated design options, and Gradient-Boosted Trees for classifying the design options. These algorithms are combined with the ability of human designers to evaluate non-quantifiable aspects of the design. To test the proposed framework in a real-world design scenario, the design of a stadium roof is presented as a case study.

2020 ◽  
Vol 22 (1) ◽  
pp. 285-307 ◽  
Author(s):  
Elishai Ezra Tsur

Microfluidic devices developed over the past decade feature greater intricacy, increased performance requirements, new materials, and innovative fabrication methods. Consequentially, new algorithmic and design approaches have been developed to introduce optimization and computer-aided design to microfluidic circuits: from conceptualization to specification, synthesis, realization, and refinement. The field includes the development of new description languages, optimization methods, benchmarks, and integrated design tools. Here, recent advancements are reviewed in the computer-aided design of flow-, droplet-, and paper-based microfluidics. A case study of the design of resistive microfluidic networks is discussed in detail. The review concludes with perspectives on the future of computer-aided microfluidics design, including the introduction of cloud computing, machine learning, new ideation processes, and hybrid optimization.


2019 ◽  
Vol 2019 ◽  
pp. 1-12
Author(s):  
Saeed Mesgari ◽  
Mehrdad Bazazzadeh ◽  
Alireza Mostofizadeh

This study deals with the application of optimization in Finocyl grain design with ballistic objective functions using a genetic algorithm. The classical sampling method is used for space filling; a level-set method is used for simulating the evaluation of a burning surface of the propellant grain. An algorithm is developed beside the level-set code that prepares the initial grain configuration using a computer-aided design (CAD) to export generated models to the level-set code. The lumped method is used to perform internal ballistic analysis. A meta-model is used to surrogate the level-set method in an optimization design loop. Finally, a case study is done to verify the proposed algorithm. Observed results show that the grain design method reduced the design time significantly, and this algorithm can be used in designing any grain type.


Author(s):  
N. J. Kalish ◽  
J. K. Davidson ◽  
Jami J. Shah ◽  
Jiten V. Shah

Abstract A novel combination of mathematical tools underlies a method to lower cost of the first fixture-setup required to finish-machine surfaces on large castings or weldments where components will be attached. The computer-aided design (CAD) model, tolerance specifications, process plan, and design of the fixture, including configuration of the locators, are given. The math tools are used to build algorithms for a digital model, the Setup-Map© (S-Map©), that predictively captures all allowable locator adjustments needed to position and orient each part in its fixture before machining begins. The S-Map in this paper is generated for a case-study design, a cast valve-body with two to-be-machined (TBM) features, but the math tools are general so the same methods could be applied directly, or easily adapted, to other designs and fixture schemes. Geometric variations at the TBM features are represented with Tolerance-Maps© (T-Maps©) that are constructed with higher-dimensional linear half-spaces. The T-Maps are shifted to be aligned with, and offset from, one-sided simulated envelopes derived from scans of corresponding features on each casting. Linear programming identifies the setup-point that is chosen to most evenly distribute the required amount of machining over all the TBM features. Inverse kinematics of parallel robots is used to convert the setup-point to custom settings at the fixture locators for each casting. The half-space construction enables the identification of TBM features that have insufficient material and require repair. The algorithms were validated with 13 castings.


Author(s):  
Giovanni Berselli ◽  
Pietro Bilancia ◽  
Luca Luzi

Abstract The use of integrated Computer Aided Design/Engineering (CAD/CAE) software capable of analyzing mechanical devices in a single parametric environment is becoming an industrial standard. Potential advantages over traditional enduring multi-software design routines can be outlined into time/cost reduction and easier modeling procedures. To meet industrial requirements, the engineering education is constantly revising the courses programs to include the training of modern advanced virtual prototyping technologies. Within this scenario, the present work describes the CAD/CAE project-based learning (PjBL) activity developed at the University of Genova as a part of course named Design of Automatic Machines, taught at the second level degree in mechanical engineering. The PjBL activity provides a detailed overview of an integrated design environment (i.e. PTC Creo). The students, divided into small work groups, interactively gain experience with the tool via the solution of an industrial design problem, provided by an engineer from industry. The considered case study consists of an automatic pushing device implemented in a commercial machine. Starting from a sub-optimal solution, the students, supervised by the lecturers, solve a series of sequential design steps involving both motion and structural analysis. The paper describes each design phase and summarizes the numerical outputs. At last, the results of the PjBL activity are presented and commented by considering the opinions of all the parties involved.


Author(s):  
David Veisz ◽  
Essam Z. Namouz ◽  
Shraddha Joshi ◽  
Joshua D Summers

AbstractThis paper presents a preliminary comparison between the role of computer-aided design (CAD) and sketching in engineering through a case study of a senior design project and interviews with industry and academia. The design team consisted of four senior level mechanical engineering students each with less than 1 year of professional experience are observed while completing an industry sponsored mechanical engineering capstone design project across a 17 week semester. Factors investigated include what CAD tools are used, when in the design process they are implemented, the justification for their use from the students' perspectives, the actual knowledge gained from their use, the impact on the final designed artifact, and the contributions of any sketches generated. At each design step, comparisons are made between CAD and sketching. The students implemented CAD tools at the onset of the project, generally failing to realize gains in design efficiency or effectiveness in the early conceptual phases of the design process. As the design became more concrete, the team was able to recognize clear gains in both efficiency and effectiveness through the use of computer assisted design programs. This study is augmented by interviews with novice and experienced industry users and academic instructors to align the trends observed in the case study with industry practice and educational emphasis. A disconnect in the perceived capability of CAD tools was found between novice and experienced user groups. Opinions on the importance of sketching skills differed between novice educators and novice industry professionals, suggesting that there is a change of opinion as to the importance of sketching formed when recent graduates transition from academia to industry. The results suggest that there is a need to emphasize the importance of sketching and a deeper understanding as to the true utility of CAD tools at each stage of the design process.


1995 ◽  
Vol 5 (2) ◽  
pp. 3341-3344 ◽  
Author(s):  
M. Khalaf ◽  
S. Whiteley ◽  
T. Van Duzer

2011 ◽  
Vol 214 ◽  
pp. 60-64
Author(s):  
Rui Lin Lin

This study aimed to perform a case study of the artworks colored using mixed media by applying qualitative methods. The teacher and the students wrote the story and completed the storyboard through interactive discussion teaching. With the knowledge of the properties of current painting papers and media used for coloring, the teacher was able to guide the students to choose paper of better quality, and select proper mixed media to create their artworks, so that the picture book could be richer and more delicate. Furthermore, documentary analysis was performed with current documents related to picture books to provide the students references for their artworks. Finally, the students were guided to process their graphs and arrange the layout using computer software, to complete a picture book artwork colored using mixed media by both hand-drawing and computer graphing and this study.


Sign in / Sign up

Export Citation Format

Share Document