Current Research
We take as a given that engineering groups have devoted a significant software, hardware and human resources investment to a preferred set of software tools and design standards. Nonetheless, for projects that integrate multiple workgroups, the engineering activities must be coordinated across the enterprise.Additionally, knowledge must be shared between multiple enterprises who may not speak the same "language" or understand the peculiarities of design standards adopted by other workgroups.
These issues have led us to design an integration infrastructure that assimilates the design models and CAD tools into a single interface for manipulating design data, processes and dependencies. Unlike traditional CAD interfaces, the one we propose is founded on the metaphor of compound documents, an engineering notebook of sorts. As a result, the system offers a new viewport to the design environment, a conceptual model for design systems which applies the document-based metaphor as an interface to mechanical design. This perspective leads to a model of network design in which the paradigms of active design documentation and product data management merge, to allow the designer to create, browse, explore, pinpoint and manage design information.The primary challenge in applying this model of the network design lies in reducing the complex expressions of associations and design constraints by making appropriate assumptions and simplifications. It is this problem that I focus on in future research in developing context information from the design model, and infer associations to other documents of known content.
Authors: Andy Dong, Frank Moore and Cameron Woods (Autodesk, Inc.) and Alice Agogino
An emerging trend in product design is the de-centralization of the design team. Critical to this enterprise engineering environment is the availability of design information through shared knowledge databases. Such access can also be a significant aid during the re-design of a documented product or the original design of a similar product. We describe a framework for managing CAD-based design information in enterprise-wide networked design environments. By merging the processes of design documentation and design data management through the concept of "smart drawings," we characterize the development of a shared knowledge base for exchanging product information among interdisciplinary design teams. The combination of relational database and document management technology enables the use of the CAD-based information as a single front-end to the design tools and for manipulating design data. The knowledge base is formed by associating CAD models to related documents and embedding significant semantic content in the domain model, rather than in the application programs that use the database. The availability of design information is then accessed through a knowledge repository in a client/server environment. The system is deployed on a test bed consisting of facilities design and management.Accepted to the IFIP WG5.2 Second Workshop on Formal Design Methods for CAD.
Available in PostScript (350 kB), Word 6.0 for Windows (2.0 MB) and Word 5.1a for MacOS (231 kB) format.
Authors: Andy Dong and Alice M Agogino
In design synthesis, engineering prototypes make an ideal representation medium for preliminary designs. Unlike parametric design wherein a pre-specified design is parametrically varied, design synthesis demands artistic creativity and engineering experience to transform the previously known components, relationships and designs into a new form. The process compels the designer to ascertain which prototypes will, in some sense, best satisfy the design task. The challenge in this assignment lies in selecting the "right" design prototype. This selection process typically entails an objective evaluation of different designs that perform the same functions or have similar intended behavior and comparing trade-offs between alternate designs. This paper introduces a multi-objective spectral optimization algorithm for the selection of design prototypes based upon their functional representations. The optimization algorithm returns an index of rank, scoring the functional similarity of the proposed design to the goal design. Two illustrative examples apply the algorithm to the selection of a heat fin and beam.Accepted to the Seventh International ASME Conference on Design Theory and Methodology 1995.
Available in PostScript (300 kB), Word 6.0 for Windows (1.4 MB) and Word 5.1a for MacOS (386 kB) format.
Authors: Andy Dong and Alice M Agogino
An emerging model in concurrent product design and manufacturing is the federation of workgroups across traditional functional "silos." Along with the benefits of this concurrency comes the complexity of sharing and accessing design information. The primary challenge in sharing design information across functional workgroups lies in reducing the complex expressions of associations between design elements. Collaborative design systems have addressed this problem from the perspective of formalizing a shared ontology or product model. We share the perspective that the design model and ontology are an expression of the "meaning" of the design and provide a means by which information sharing in design may be achieved. However, in many design cases, formalizing an ontology before the design begins, establishing the knowledge sharing agreements or mapping out the design hierarchy is potentially more expensive than the design itself. This paper introduces a technique for inducing a representation of the design based upon the syntactic patterns contained in the corpus of design documents. The association between the design and the representation for the design is captured by basing the representation on terminological patterns in the design text. In the first stage, we create a "dictionary" of noun-phrases found in the text corpus based upon a measurement of the content carrying power of the phrase. In the second stage, we cluster the words to discover inter-term dependencies and build a Bayesian belief network which describes a conceptual hierarchy specific to the domain of the design. We integrate the design document learning system with an agent-based collaborative design system for fetching design information based on the "smart drawings" paradigm.Accepted to the Fourth International Conference on Artificial Intelligence in Design. Winner of Best Paper Prize.
Final version available in PostScript (900 kB) ,Word 6.0 for Windows (6.0 MB) and Word 6.0.1 for MacOS (1.6 MB) format. Revised version for Artificial Intelligence in Engineering in Word 6.0 for Windows (6.0 MB) format. Zip format.
Authors: Andy Dong, J Enrique Barreto and Alice M Agogino
Information retrieval (IR) systems interact with users by returning a ranked list of relevant documents in response to a query. Through feedback mechanisms such as relevance feedback and automated keyword expansion, IR systems attempt to guide users in constructing search queries which better represent their information needs. These mechanisms, however, do not offer the user more insight into the content of the documents in the IR database nor do they provide direction as to which search terms might yield better search results in terms of relevance and certainty that the retrieved document contains the information the user intended to retrieve. This paper presents a methodology based on the decision-analytic concept of expected value of perfect information for controlling query augmentation in information retrieval. The system dynamically learns the content of the documents in the database to compute the utility (measured in terms of relevance) of retrieving certain documents in response to queries, where the words in the queries represent the random variables. By computing the expected value of perfect information for each query term, the system either suggests new search terms or suggests that the user terminate the search.
Submitted to the 1997 ACM SIGIR Conference. Draft versions available in MS Word 7.0 for Windows. Please do NOT re-distribute.