在有限元素分析中實體網格直接影響其準確度與分析時間，而手動建立實體網格是目前相當耗時的技術之一。塑膠薄殼元件是射出成型當中常見的模型，薄殼元件中包含許多凸起物，凸起物又可以再細分成肋、管、柱以及其他較為複雜支撐結構等，若使用四面體網格自動建立網格，這些特徵容易造成品質下降的問題，因此若能事先將凸起物辨識出來，個別進行網格建立，則可以改善網格品質。在傳統模具設計當中，分模線、模仁設計往往依賴經驗豐富的工程師設計，造成設計上較為耗時且困難。在實務上模具溫度將影響到產品生成的品質，如果模溫不均會造成產品翹曲、縫合線、凹痕和短射等問題。因此本研究發展自動特徵辨識的技術，針對薄殼元件自動辨識凸起特徵，辨識過程中紀錄凸起物之關聯性，作為後續網格建立以及設計變更上的參考資訊。本研究的內外面辨識也進一步應用於分模線辨識上，可找出分模線、母模面、公模面，以改善傳統分模上設計困難與耗時的問題。;Solid meshes affect the accuracy and efficiency of the analysis and simulation. However, Solid mesh generation is usually a time-consuming process. Thin-wall plastic parts exist in many products and are frequently manufactured by injection molding. The inner surface of a thin-wall part involves many functional and structural features design, such as ribs, tubes and complex supporting structure. If we use tetrahedron meshes to generate these features, it usually results in poor quality mesh. The purpose of this study was to develop a method for the detection of protrusion features on thin-wall plastic parts. In the proposed algorithm, the inner and outer faces of a part model were recognized first, then auxiliary faces, including transitional, wall and bottom faces, were next recognized. In designing a model, the generation of the parting line is one of the most time consuming processes. The model designer may find it difficult to determine the parting line and parting surface. The purpose of this study was to recognize parting line, core surfaces and cavity surfaces.
