Abstract
Based on neural network principle, and the information obtained with FEM (finite element method) simulation, the expert system described as an open adaptive expert system was proposed. It is planned to possess the following desirable features: automatic process planning for H-shaped forgings; optimization of technological process; prediction of defects; providing information for die designer and CAD/CAE/CAM system. The expert system has the following technical features: (1) simulation information is extracted with FEM and organized by neural network for the generation of knowledge base; (2) the system has the function of self-learning; it is convenient for acquiring knowledge base; (3) each rule is expressed digitally; so it is convenient to organize and manage the knowledge base; and it is easy to complete preform and final forging design; (4) the system is also different from existing expert system in that numerical computation instead of logic is used; (5) the system is made up of a BP network group; so it can realize automatic forging process planing, optimization of technological process, prediction of defects, etc.
| Original language | English |
|---|---|
| Pages (from-to) | 161-162 |
| Number of pages | 2 |
| Journal | Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University |
| Volume | 14 |
| Issue number | 1 |
| State | Published - Feb 1996 |
| Externally published | Yes |