Institute for Systems Research

Permanent URI for this communityhttp://hdl.handle.net/1903/4375

Browse

Author: search.filters.author.Gupta, Sandeep K.Subject: search.filters.subject.feature extraction

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    "Manufacturing-Operation Planning Versus AI Planning
    (1995) Nau, D.S.; Gupta, Sandeep K.; Regli, W.C.; ISR
    Although AI planning techniques can potentially be useful in several manufacturing domains, this potential remains largely unrealized. Many of the issues important to manufacturing engineers have not seemed interesting to AI researchers---but in order to adapt AI planning techniques to manufacturing, it is important to address these issues in a realistic and robust manner. Furthermore, by investigating these issues, AI researchers may be able to discover principles that, are relevant for AI planning in general.

    As an example, in this paper we describe the techniques for manufacturing-operation planning used in IMACS (Interactive Manufacturability Analysis and Critiquing System). We compare and contrast them with the techniques used in classical AI planning systems, and point out that some of the techniques used in IMACS may also be useful in other kinds of planning problems.

  • Thumbnail Image
    Item
    Generation of Alternative Feature-Based Models and Precedence Orderings for Machining Applications
    (1992) Gupta, Sandeep K.; Nau, D.S.; ISR
    For machining purposes, a part is often considered to be a feature-based model (FBM), i.e., a collection of machining features. However, often there can be several different FBM's of the same part. These models correspond to different sets of machining operations, with different precedence constraints. Which of these sets of machining operations is best depends on several factors, including dimensions, tolerances, surface finishes, availability of machine tools and cutting tools, fixturability, and optimization criteria. Thus, these alternatives should be generated and evaluated.

    In this paper we present the following results: 1. We give general mathematical definitions of machining features and FBMs.

    2. We present a systematic way to generate the alternative FBMs for a part, given an initial FBM for the part.

    3. For each FBM, interactions among the features will impose precedence constraints on the possible orderings in which these features can be machined. We show how to generate these precedence constraints automatically for each interpretation.

    4. We show how to organize the above precedence constraints into a time-order graph that represents all feasible orderings in which the features can be machined, and examine the time-order graph to see if it is consistent. If it is not consistent, then there is no way to machine this particular interpretation.

    This work represents a step toward our overall approach of developing ways for automatically generating the alternative ways in which a part can be machined, and evaluating them to see how well they can do at creating the desired part. We anticipate that the information provided by this analysis will be useful both for process planning and concurrent design.

  • Thumbnail Image
    Item
    Concurrent Evaluation of Machinability during Product Design
    (1992) Gupta, Sandeep K.; Nau, D.; Zhang, G.M.; ISR
    This paper presents a new methodology of evaluating the machinability of a machined part during the design state of the product development cycle, so that problems related to machining can be recognized and corrected while the product is being designed. Our basic approach is to perform a systematic evaluation of machining alternatives throughout each step in the design stage. This involves three basic steps: (1) generate alternative interpretations of the design as different collection of machinable features, (2) generate the various possible sequences of machining operations capable of producing each interpretation, and (3) evaluate each operations sequence, to determine the relevant information on achievable quality and associated costs. The information provided by this analysis can be used not only to give feedback to the designer about problems that might arise with the machining, but also to provide information to the manufacturing engineer about alternative ways in which the part might be machined.