ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

DEVELOPMENT OF AN INTELLIGENT SYSTEM FOR OPTIMIZATION OF BLANKING DIE DESIGN PARAMETERS SELECTION

Journal: International Journal of Civil Engineering and Technology (IJCIET) (Vol.8, No. 9)

Publication Date:

Authors : ; ;

Page : 238-243

Keywords : Artificial Intelligence; Recommended Dimensional Tolerances; Short-Run Tooling; Blanking Dies; Fine-Blanked Parts; Trimming Allowances.;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Selection of optimum parameters for blanking die design is an important activity in stamping industries. Developing a Knowledge Based system is proposed that can elicit recommendations in selecting optimum die design parameters. Conventional die design method involves numerous considerations, calculations, tables and mainly depends on the ability of taking decision by process planners and die designers. This arrangement facilitates interfacing of die design with drafting and can be loaded in a PC. The proposed system is developed using rule based system approach of AI. It utilizes interfacing of AutoCAD and Auto LISP for automation of selection of blanking die design parameters. The system comprises four modules. Recommended Dimensional Tolerances for sheet-metal blanks produced with short-run tooling, recommended dimensional tolerances for sheet-metal blanks produced with blanking dies, recommended tolerances for fine-blanked parts, recommended trimming allowances are the four parameters considered in this system. The modules were developed based on information from manufacturing standards, industrial catalogues, brochures and best of industrial practices. Hence for the given input condition, the system generates an optimum parametric output on the screen during its execution. The system is flexible and can be upgraded depending upon both specific shop floor requirements and development of new technology solutions. The application of the proposed system is demonstrated through a sample run of four modules for a real time industrial component. Key words:

Last modified: 2018-04-10 23:02:42