A Knowledge-Based Mesh Generation System for Forging Simulation

  • Authors:

  • Osamu Takata;Koukichi Nakanishi;Nariaki Horinouchi;Hiroshi Yano;Tadashi Akashi;Toyohide Watanabe

  • Affiliations:

  • Toyota Central R & D Labs., Inc., Nagakute, Aichi-gun, Aichi-pref., 480-1192, Japan. takata@kis.tytlabs.co.jp;Toyota Central R & D Labs., Inc., Nagakute, Aichi-gun, Aichi-pref., 480-1192, Japan. kou@kis.tytlabs.co.jp;Toyota Central R & D Labs., Inc., Nagakute, Aichi-gun, Aichi-pref., 480-1192, Japan. hor@kis.tytlabs.co.jp;Toyota Motor Corporation, Toyota-cho, Toyota, 471-8571, Japan. h_yano@mail.toyota.co.jp;Toyota Motor Corporation, Toyota-cho, Toyota, 471-8571, Japan. tadao_akashi@mail.toyota.co.jp;Graduate School of Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, 464-8603, Japan. watanabe@nuie.nagoya-u.ac.jp

  • Venue:
  • Applied Intelligence
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

We developed a knowledge-based system GENMAI (Artificial IntelligenceMesh GENerator) to auto-generate two-dimensional structured meshes.GENMAI is easily applicable to various kinds of application domains.Mesh generation is one of the major tasks confronted in computationalsimulation. The quality of generated meshes affects computational accuracy and computing time. Since various kinds of domain knowledge areneeded to generate high quality structured meshes,the knowledge-based approach has been found effective and successful.Before designing GENMAI, we analyzed mesh generation jobsin plastic deformation analysis and computational fluid dynamics.Then, we formulate GENMAI so that it searches feasible plural dividedpatterns combinatorially and selects the best pattern. The characteristics of GENMAI are as follows: the meta-inference mechanism and its knowledge representationare widely applicable to various kinds of application domains; and plural patterns can be efficiently obtained at the same time bya search technique based on global dependency and local dependency.We applied GENMAI to forging simulation and developed AI-FESTE, which integrateda rigid-plastic deformation analysis program andGENMAI. Forging designers can easily decide shapes of a forgingproduct and dies and also plan the forming sequenceusing AI-FESTE. AI-FESTE automates a series of forging analysis operations and shortens the execution time from 1 or 2 day(s) to a few hours.As a result, not only can AI-FESTE shorten the turn-around time, butit can improve the quality of product and die design.