Bayesian Networks for Set-Based Collaborative Design

2009 ◽  
Author(s):  
David Shahan ◽  
Carolyn C. Seepersad
Keyword(s):  
Bayesian Networks ◽  
Design Process ◽  
Collaborative Design ◽  
Design Space ◽  
Expert Knowledge ◽  
Hill Climbing ◽  
Local Networks ◽  
Design Problems ◽  
Potential Benefits ◽  
Aerial Vehicle

A set-based approach to collaborative design is presented, in which Bayesian networks are used to represent promising regions of the design space. In collaborative design exploration, complex multilevel design problems are often decomposed into distributed subproblems that are linked by shared or coupled parameters. Collaborating designers often prefer conflicting values for these coupled parameters, resulting in incompatibilities that require substantial iteration to resolve, extending the design process lead time without guarantee of achieving a good design. In the proposed approach to collaborative design, each designer builds a locally developed Bayesian network that represents regions of interest in his design space. Then, these local networks are shared and combined with those of collaborating designers to promote more efficient local design space search that takes into account the interests of one’s collaborators. The proposed method has the potential to capture a designer’s preferences for arbitrarily shaped and potentially disconnected regions of the design space in order to identify compatible or conflicting preferences between collaborators and to facilitate a compromise if necessary. It also sets the stage for a flexible and concurrent design process with varying degrees of designer involvement that can support different designer strategies such as hill-climbing or region identification. The potential benefits are the capture of expert knowledge for future use as well as conflict identification and resolution. This paper presents an overview of the proposed method as well as an example implementation for the design of an unmanned aerial vehicle.

scholarly journals Bayesian Network Classifiers for Set-Based Collaborative Design

2010 ◽  
Author(s):  
David Shahan ◽  
Carolyn C. Seepersad
Keyword(s):  
Design Process ◽  
Collaborative Design ◽  
Probability Distributions ◽  
Design Problems ◽  
Fuzzy Membership Functions ◽  
Domain Specific ◽  
Bayesian Network Classifiers ◽  
Complex Design ◽  
Data Points ◽  
Aerial Vehicle

Complex design problems are typically decomposed into smaller design problems that are solved by domain-specific experts who must then coordinate their solutions into a satisfactory system-wide solution. In set-based collaborative design, collaborating engineers coordinate themselves by communicating multiple design alternatives at each step of the design process. The goal in set-based collaborative design is to spend additional resources exploring multiple options in the early stages of the design process, in exchange for less iteration in the latter stages, when iterative rework tends to be most expensive. Several methods have been proposed for representing sets of designs, including intervals, surrogate models, fuzzy membership functions, and probability distributions. In this paper, we introduce the use of Bayesian networks for capturing sets of promising designs, thereby classifying the design space into satisfactory and unsatisfactory regions. The method is compared to intervals in terms of its capacity to accurately classify satisfactory design regions as a function of the number of available data points. A simplified, multilevel design problem for an unmanned aerial vehicle is presented as the motivating example.

scholarly journals Bayesian Network Classifiers for Set-Based Collaborative Design

2012 ◽  
Vol 134 (7) ◽  
Author(s):  
David W. Shahan ◽  
Carolyn Conner Seepersad
Keyword(s):  
Bayesian Network ◽  
Collaborative Design ◽  
Design Problem ◽  
Design Space ◽  
Expert Knowledge ◽  
Optimization Techniques ◽  
Domain Specific ◽  
Bayesian Network Classifiers ◽  
New Information ◽  
Engineering Design Problems

Complex engineering design problems are often decomposed into a set of interdependent, distributed subproblems that are solved by domain-specific experts. These experts must resolve couplings between the subproblems and negotiate satisfactory, system-wide solutions. Set-based approaches help resolve these couplings by systematically mapping satisfactory regions of the design space for each subproblem and then intersecting those maps to identify mutually satisfactory system-wide solutions. In this paper, Bayesian network classifiers are introduced for mapping sets of promising designs, thereby classifying the design space into satisfactory and unsatisfactory regions. The approach is applied to two example problems—a spring design problem and a simplified, multilevel design problem for an unmanned aerial vehicle (UAV). The method is demonstrated to offer several advantages over competing techniques, including the ability to represent arbitrarily shaped and potentially disconnected regions of the design space and the ability to be updated straightforwardly as new information about the satisfactory design space is discovered. Although not demonstrated in this paper, it is also possible to interface the classifier with automated search and optimization techniques and to combine expert knowledge with the results of quantitative simulations when constructing the classifiers.

A Multi-Expert System for Sheet Metal Part Design

1991 ◽  
Author(s):  
William R. D. Wilson ◽  
Jyhwen Wang
Keyword(s):  
Expert System ◽  
Sheet Metal ◽  
Design Process ◽  
Heuristic Search ◽  
Collaborative Design ◽  
Expert Knowledge ◽  
Object Oriented ◽  
Sheet Metal Parts ◽  
Heuristic Search Methods ◽  
Representation Scheme

Abstract A multi-expert system approach for the design of sheet metal parts, and its implementation is described. The system uses a frame-based, object-oriented representation scheme to model the part design as well as the expert knowledge. To facilitate the collaborative design process, a blackboard architecture is used. Heuristic search methods that guide the collaborative design process are presented. The advantages offered by such a multi-expert system are also discussed.

scholarly journals Creating tools for inquiry-based mathematics learning from technological pedagogical content knowledge perspectives: Collaborative design approach

2018 ◽  
Vol 34 (4) ◽  
Author(s):  
Zhiming Yan ◽  
Ching Sing Chai ◽  
Hyo-Jeong So
Keyword(s):  
Preservice Teachers ◽  
Pedagogical Content Knowledge ◽  
Content Knowledge ◽  
Design Process ◽  
Collaborative Design ◽  
Expert Knowledge ◽  
Technological Pedagogical Content Knowledge ◽  
Practicing Teachers ◽  
Pedagogical Content ◽  
Technology Tools

This study employed the technological pedagogical content knowledge (TPACK) framework to guide the collaborative design process between preservice and practicing teachers. The teams designed technological pedagogical mathematics tools (TPMTs) for inquiry-based learning based on the syllabi for secondary mathematics. The content of the chat messages of preservice and practicing teachers was coded with different dimensions of TPACK to unpack the process of how the teams arrived at critical design decisions. The TPMTs were further evaluated by 30 practicing mathematics teachers, with respect to three criteria: (1) technology tools and curriculum goals, (2) technology tools and teaching activities, and (3) the fit between pedagogy and technology. The content analysis revealed that the collaborative design process involved three clear stages, demarcated by the different versions of the TMPTs: replacement, enhancement, and transformation. Practicing teachers’ pedagogical content knowledge played a crucial role in the design of pedagogically sound tools, and for refining the initial TPACK of preservice teachers. The subsequent evaluations supported the positive pedagogical values of the TPMTs. Overall, this study contributes to TPACK research with a case where the collaborative design process with distributed expert knowledge can be synthesised to create pedagogically sound technological tools for mathematics.

Enumeration of Architectures With Perfect Matchings

2016 ◽  
Author(s):  
Daniel R. Herber ◽  
Tinghao Guo ◽  
James T. Allison
Keyword(s):  
Design Process ◽  
Design Space ◽  
Perfect Matching ◽  
Search Algorithm ◽  
Perfect Matchings ◽  
Architecture Design ◽  
Tree Search ◽  
Colored Graph ◽  
Design Problems ◽  
Tree Search Algorithm

In this article a class of architecture design problems is explored with perfect matchings. A perfect matching in a graph is a set of edges such that every vertex is present in exactly one edge. The perfect matching approach has many desirable properties such as complete design space coverage. Improving on the pure perfect matching approach, a tree search algorithm is developed that more efficiently covers the same design space. The effect of specific network structure constraints and colored graph isomorphisms on the desired design space is demonstrated. This is accomplished by determining all unique feasible graphs for a select number of architecture problems, explicitly demonstrating the specific challenges of architecture design. Additional applications of this work to the larger architecture design process is also discussed.

A Model of Collaborative Design Decision Making Using Timed Petri-Net

2006 ◽  
Author(s):  
Zhiqiang Chen ◽  
Zahed Siddique
Keyword(s):  
Decision Making ◽  
Design Process ◽  
Petri Net ◽  
Collaborative Design ◽  
Process Model ◽  
Design Decision ◽  
Design Problems ◽  
Design Variables ◽  
And Performance ◽  
Improved Design

This paper presents a Petri-net process model that captures the dependency relationships of design decision making and information exchanges among multiple design problems in a distributed environment. The Model of Distributed Design (MDD) allows quantitative representation of a collaborative design process in which designers from multiple disciplines can effectively work together. The MDD is developed based on the Petri-net graph, which allows various performance analysis to be performed to evaluate and improve a collaborative design process. In this paper, the compromise Decision Support Problem (c-DSP) formulation is used to describe the design problems and the Petri-net is utilized to explicitly describe the propagation of shared design variables and the interactions. The applicability of the model is demonstrated through an example design problem that requires collaboration among four design disciplines. The design processes based on the example are modeled and then analyzed to obtain process features and performance evaluations. Based on the analysis results, an improved design process is given which shortens the design time.

Sequential Sampling With Kernel-Based Bayesian Network Classifiers

2011 ◽  
Author(s):  
David Shahan ◽  
Carolyn C. Seepersad
Keyword(s):  
Bayesian Network ◽  
Collaborative Design ◽  
Design Space ◽  
Sequential Sampling ◽  
Space Filling ◽  
Training Set ◽  
Design Problems ◽  
Sampling Schemes ◽  
Domain Specific ◽  
Bayesian Network Classifiers

Complex design problems are typically decomposed into smaller design problems that are solved by domain-specific experts who must then coordinate their solutions into a satisfactory system-wide solution. In set-based collaborative design, collaborating engineers coordinate themselves by communicating multiple design alternatives at each step of the design process. Previous research has demonstrated that classifiers can be a communication medium for facilitating set-based collaborative design because of their ability to divide a design space into satisfactory and unsatisfactory regions. The proposed kernel-based Bayesian network (KBN) classifier uses a set of example designs of known acceptability, called the training set, to create a map of the satisfactory region of the design space. However, previous implementations used deterministic space-filling sampling sequences to choose the training set of designs. The shortcoming of deterministic space-filling sampling schemes is that they do not adapt to focus the samples on regions of interest to the design team (exploitation) or, alternatively, on regions in which little information is known (exploration). In this paper, we introduce the use of KBN classifiers as the basis for sequential sampling strategies that can be exploitive, exploratory, or any combination thereof.

Causing a Stir

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Camilo POTOCNJAK-OXMAN
Keyword(s):  
Design Process ◽  
Collaborative Design ◽  
Entrepreneurial Activity ◽  
Design Team ◽  
Design Processes ◽  
Early Stages

Stir was a crowd-voted grants platform aimed at supporting creative youth in the early stages of an entrepreneurial journey. Developed through an in-depth, collaborative design process, between 2015 and 2018 it received close to two hundred projects and distributed over fifty grants to emerging creatives and became one of the most impactful programs aimed at increasing entrepreneurial activity in Canberra, Australia. The following case study will provide an overview of the methodology and process used by the design team in conceiving and developing this platform, highlighting how the community’s interests and competencies were embedded in the project itself. The case provides insights for people leading collaborative design processes, with specific emphasis on some of the characteristics on programs targeting creative youth

scholarly journals Integrating Theory in Co-design: An Abductive Approach

2021 ◽  
Vol 29 (1) ◽  
pp. 66-77
Author(s):  
Erin Hurley ◽  
Timo Dietrich ◽  
Sharyn Rundle-Thiele
Keyword(s):  
Social Cognitive Theory ◽  
Design Process ◽  
Social Marketing ◽  
Social Cognitive ◽  
Cognitive Theory ◽  
Expert Knowledge ◽  
Future Research ◽  
Abductive Inference ◽  
Design Framework ◽  
Research Recommendations

Co-design empowers people, giving them a voice in social marketing program design; however, approaches have mostly excluded expert knowledge. An abductive approach to co-design allows for inclusion of expert knowledge, providing theoretical guidance while simultaneously investigating user views and ideas extending understanding beyond known effective approaches. We use the seven-step co-design framework and outline how an abductive inference can be applied to co-design. Social cognitive theory constructs were integrated into the seven-step co-design process. The abductive approach to co-design was tested in two co-design sessions involving 40 participants. Findings demonstrate that theory can be successfully integrated into the seven-step co-design process through utilization of theory-mapped activity cards. This article provides guidance on how theory can be incorporated into ideation and insight generation. Limitations and future research recommendations are provided.

scholarly journals Configuration Study of Electric Helicopters for Urban Air Mobility

Aerospace ◽  
2021 ◽  
Vol 8 (2) ◽  
pp. 54
Author(s):  
Julia A. Cole ◽  
Lauren Rajauski ◽  
Andrew Loughran ◽  
Alexander Karpowicz ◽  
Stefanie Salinger
Keyword(s):  
Conceptual Design ◽  
Urban Areas ◽  
Design Space ◽  
Design Method ◽  
Urban Air ◽  
Main Rotor ◽  
Potential Benefits ◽  
Compound Helicopter ◽  
Configuration Changes

There is currently interest in the design of small electric vertical take-off and landing aircraft to alleviate ground traffic and congestion in major urban areas. To support progress in this area, a conceptual design method for single-main-rotor and lift-augmented compound electric helicopters has been developed. The design method was used to investigate the feasible design space for electric helicopters based on varying mission profiles and technology assumptions. Within the feasible design space, it was found that a crossover boundary exists as a function of cruise distance and hover time where the most efficient configuration changes from a single-main-rotor helicopter to a lift-augmented compound helicopter. In general, for longer cruise distances and shorter hover times, the lift-augmented compound helicopter is the more efficient configuration. An additional study was conducted to investigate the potential benefits of decoupling the main rotor from the tail rotor. This study showed that decoupling the main rotor and tail rotor has the potential to reduce the total mission energy required in all cases, allowing for increases in mission distances and hover times on the order of 5% for a given battery size.

Sign in / Sign up

Export Citation Format

Share Document