โ Scribed by Zhenkai Liu; Lihui Wang
No coin nor oath required. For personal study only.
Today, feature-based process planning has been popular in academia and industry with its ability to rigorously integrate design and manufacturing. To date, research on feature sequencing is mainly focused on using expert systems or knowledge-based systems, geometric based approaches, unsupervised-learning or artificial neural network, and genetic algorithms. The approach presented in this paper, however, is a hybrid one using both knowledge-based rules and geometric reasoning rules. In addition to feature sequencing rules formulation, our research contributions consist of: (1) determining machining precedence constraints by a set of defined knowledge-based rules, (2) grouping machining features into setups based on tool approaching directions, and (3) sequencing features within each setup through geometric reasoning. The sequence of materials (features) to be removed depends on two types of interactions: adjacent interaction and volumetric interaction. A set of rules for geometric reasoning is therefore developed to generate feature sequence. The developed approach has been implemented as the Sequence Generator module in a Distributed Process Planning system and is validated through a case study.
๐ SIMILAR VOLUMES
We describe a hybrid feature recognition method for machining features that integrates three distinct feature recognition methods: graph matching, cell-based maximal volume decomposition, and negative feature decomposition using convex decomposition. Each of these methods has strengths and limitatio
Monitoring of machining processes is a classic and yet unsolved problem in manufacturing engineering. This paper introduces a new method of feature extraction and feature assessment using a wavelet packet transform for monitoring of machining processes. First, the principles of wavelet transforms ar