Process planning is a highly knowledge-intensive domain. AI-based (Artificial Intelligence) techniques are designed for capturing, representing, organizing, and utilizing knowledge by computers, and hence will be the key technology for process planning. To date, most AI-based approaches used in process planning are some variation of knowledge-based expert systems. Expert systems are successful in medical domain but insufficient for engineering tasks, especially process planning. Another branch of AI is neural networks, which belongs to a family of models that are based on a learning-by-example paradigm. The combination of expert system and neural network techniques will greatly improve the performance of AI in process planning. In this paper, we introduce a knowledge-based connectionist model, which integrates expert system and neural network techniques, for process planning. The performance of a knowledge-based connectionist model is shown via a turning/grinding case, in which the model is used to decide the surface of a rotational part should be turned or ground.
|Number of pages||10|
|State||Published - 1994|
|Event||Proceedings of the 1994 International Mechanical Engineering Congress and Exposition - Chicago, IL, USA|
Duration: Nov 6 1994 → Nov 11 1994
|Conference||Proceedings of the 1994 International Mechanical Engineering Congress and Exposition|
|City||Chicago, IL, USA|
|Period||11/6/94 → 11/11/94|