Files in this item
|(no description provided)|
|Title:||Knowledge Based Approach to Checking Designs for Conformance With Standards|
|Author(s):||Elam, Steven Lee|
|Doctoral Committee Chair(s):||Lopez, Leonard|
|Department / Program:||Civil Engineering|
|Degree Granting Institution:||University of Illinois at Urbana-Champaign|
|Abstract:||The engineering computing community has been slow to develop intelligent standards processing methodologies. To pave the way for the advancement of automated standards processing systems, it is necessary to develop formalized models of design standards and of the peripheral knowledge used in the design and checking processes.
Most of the standards processing systems that do currently exist have portions of standards embedded within their software which generates problems related to misinterpretation of standards, program inflexibility, and maintenance.
The solution used in this investigation is the separation of standards and all related knowledge from the application system and provide them as declarative data. The objectives of this investigation are (1) to examine the process of checking designs for conformance with governing design standards and to identify the various types of knowledge involved; (2) to formalize the types of knowledge identified and to develop models that represent and functionally separate these bodies of knowledge; and (3) to produce a prototype automated standards processing environment that operates on these models and checks designs for conformance with governing standards.
This investigation identifies the types of knowledge used in the checking process and develops formal models that functionally separate them.
The SASE decision table and classifier tree model are used to represent design standards. Production rule models are developed to represent the remaining expert knowledge which contain complex heuristic reasoning. Network inferencing techniques are developed to operate on the knowledge models.
A prototype system called SICAD (Standards Interfaces in Computer Aided Design) has been implemented to illustrate the principals expressed in this investigation. The system allows the types of knowledge to be developed as separate knowledge bases. The system has a blackboard architecture and uses control rules to regulate system operation. Mappings provided by the knowledge engineer establish the links between knowledge bases and between data items and external sources of data (data base functions). The ability of the system to easily obtain data from data bases is a major contribution to standards processing technology. The system has the ability to explain why it is asking for data and how data item values were produced.
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1988.
|Date Available in IDEALS:||2014-12-15|
This item appears in the following Collection(s)
Dissertations and Theses - Civil and Environmental Engineering
Graduate Dissertations and Theses at Illinois
Graduate Theses and Dissertations at Illinois