Conference Paper

Research and Application on Typical Process Knowledge Discovery in Mechanical Manufacturing Enterprise

Northwestern Polytech. Univ., Xi'an
DOI: 10.1109/WKDD.2008.67 Conference: Knowledge Discovery and Data Mining, 2008. WKDD 2008. International Workshop on
Source: IEEE Xplore


The source and composing of process planning knowledge is analyzed based on the state of art in discrete mechanical manufacturing enterprise. On the basis of the widely application of computer aided process planning system (CAPP) in mechanical manufacturing enterprise, the concept of process planning knowledge discovery (PPKD) is proposed for product process planning database. CAPPFramework (a CAPP development platform that is developed by Northwestern Polytechnical University supported by China) is taken as a basic development platform, the technology architecture of process planning knowledge discovery is founded based on object-oriented model driven technology, and the process planning knowledge discovery script is designed. Elementary application research in typical process summarization is described in detail. The technology of PPKD has been used in mechanical manufacturing enterprise to support the automatically knowledge acquisition in CAPP system, and it shows good application effect.

2 Reads
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Procedures are a common knowledge form in process industries such as refineries. A typical refinery captures hundreds of procedures documenting actions that operators must follow. Maintaining the action-knowledge contained in these procedures is important because it represents a key organizational asset that can be leveraged to minimize the threat of accidents. We develop an approach that extracts services from these operator procedures. The paper describes the heuristics underlying this approach, illustrates its application, and discusses implications.
    Full-text · Conference Paper · Jan 2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: Computer-Aided Process Planning (CAPP) plays a significant role in modern manufacturing system, and knowledge-based CAPP system is one of the predominant trends of its development. How to discover and acquire valuable process knowledge from the existing process data by applying data mining methodology is always the key technology and bottleneck issue for improving the application level of knowledge-based CAPP systems. As an important knowledge of process flow, typical process routes have a vital influence on the accuracy and efficiency of part family oriented process planning. In this paper, a novel approach for elicitation of typical process routes through the combination of granular computing theory and bioinformatics technology is put forward. The sequence alignment technology in bioinformatics is used to establish the best alignment between two process routes, based on which their distance is exactly calculated. According to the distances between process routes to be analysed, the neighborhood-based granulation method in granular computing theory is applied to construct a series of process information granular layers with different granularity so as to acquire typical process routes from process information granules contained in an optimal granular layer. Two application examples not only adequately validate the applicability and effectiveness of the proposed approach, but also fully demonstrate its advantages in the quality and efficiency of typical process routes elicitation.
    No preview · Article · Oct 2015 · Engineering Applications of Artificial Intelligence