在現今工業產業中，藉由資料庫搜索CAD模型是一項重要的技術，可以利用此項技術減少產品開發與製造過程中花費的時間。本研究的主要目的是開發比對CAD模型與資料庫相似性的演算法，以CAD模型上的幾何資訊比較模型相似性。透過辨識CAD模型上的各種特徵，建立個別的幾何資料，並比較不同CAD模型上相對應特徵的資料，進而計算出相似性，達到比較CAD模型的目的。本研究最主要的貢獻為開發自動比對模型相似性的演算法，利用其他研究所開發的特徵辨識演算法，進一步計算出CAD模型上需要比較的資料，最終比較兩個CAD模型的相似性。同時透過本研究的演算法，也可以將CAD模型需比對的資料記錄為文字檔，並依此建立為資料庫。當有一個新的待測模型，僅需計算待測模型上需進行比對的資料，即可與資料庫中所有CAD模型自動計算出相似性，並選出相似性較高的模型。本研究使用10個待測模型與資料庫進行自動化比對，測試並分析其結果，以驗證本研究提出方法的可行性。

Searching similarity of CAD models nowadays becomes an important technology for industries. This technology can reduce time and cost consuming significantly in product design and manufacture. The main purpose of this study is to develop an algorithm that can find the similarity between a CAD model and those on a database by comparing geometric information. Our study starts by recognizing features on CAD models and calculating individual geometric information on every feature. After we obtain the geometric information for two CAD models, we compare several attributes of the same type of features. Finally, we can compute the similarity of two CAD models. The primary contribution of this study is developing an algorithm and procedure to search the similarity between a CAD model and those on the database. This algorithm is combined with a feature recognition algorithm, developed in our lab, to obtain the data required for the similarity study between two CAD models. This algorithm can also be used for generating the database of CAD models for similarity analysis. Whenever we have a new query CAD model, we need to compute its geometric information. We can then compare it with that of each CAD model on the database automatically and obtain a similarity result. Finally, the algorithm can yield a CAD model with the highest rate of similarity. Ten query CAD models were tested and the results were analyzed, which verifies the feasibility of the proposed method.

[1] C. F. You and Y. L. Tsai, “3D solid model retrieval for engineering reuse based on local feature correspondence”, The International Journal of Advanced Manufacturing Technology, Vol. 46, No. 5-8, pp. 649-661, 2010.
[2] C. Y. Ip, D. Lapadat, L. Sieger and W. C. Regli, “Using shape distributions to compare solid models”, In Proceedings of the Seventh ACM Symposium on Solid Modeling and Applications, pp. 273-280, 2002.
[3] C. H. Chu and Y. C. Hsu, “Similarity assessment of 3D mechanical components for design reuse”, Robotics and Computer-Integrated Manufacturing, Vol. 22, No. 4, pp. 332-341, 2006.
[4] D. McWherter, M. Peabody, A. C. Shokoufandeh and W. Regli, “Database techniques for archival of solid models”, In Proceedings of the Sixth ACM Symposium on Solid Modeling and Applications, pp. 78-87, 2001.
[5] M. El-Mehalawi and R. A. Miller, “A database system of mechanical components based on geometric and topological similarity. Part II: indexing, retrieval, matching, and similarity assessment”, Computer-Aided Design, Vol. 35, No. 1, pp. 95-105, 2003.
[6] A. Elinson, D. S. Nau and W. C. Regli, “Feature-based similarity assessment of solid models”, In Proceedings of the Fourth ACM Symposium on Solid Modeling and Applications, pp. 297-310, 1997.
[7] N. Iyer, S. Jayanti, K. Lou, Y. Kalyanaraman and K. Ramani, “Three-dimensional shape searching: state-of-the-art review and future trends’’, Computer-Aided Design, Vol. 37, No. 5, pp. 509-530, 2005.
[8] K. Lupinetti, F. Giannini, M. Monti and J. P. Pernot, “Content-based multi-criteria similarity assessment of CAD assembly models”, Computers in Industry, Vol. 112, pp. 103-111, 2019.
[9] T. L. Sun, “Shape similarity assessment of polyhedral parts based on boundary models”, International Journal of Production Research, Vol. 38, No. 18, pp. 4655-4670, 2000.
[10] H. P. Kriegel, P. Kroger, Z. Mashael, M. Pfeifle, M. Potke and T. Seidl, “Effective similarity search on voxelized CAD objects”, In Eighth International Conference on Database Systems for Advanced Applications, pp. 27-36, 2003.
[11] H. J. Rea, J. R. Corney, D. E. Clark, J. Pritchard, M. L. Breaks and R. A. MacLeod, “Part-sourcing in a Global Market”, Concurrent Engineering, Vol. 10, No. 4, pp. 325-333, 2002.
[12] J. Y. Lai, P. P. Song, A. S. Hsiao, Y. C. Tsai and C. H. Hsu, “Recognition and classification of protrusion features on thin-wall parts for mold flow analysis”, Engineering with Computers, pp. 1-22, 2019.
[13] F. Rahutomo, T. Kitasuka, and M. Aritsugi, “Semantic cosine similarity”, In the 7th International Student Conference on Advanced Science and Technology ICAST, Vol. 4, No. 1, p. 1, 2012.
[14] D. Sinwar and R. Kaushik, “Study of Euclidean and Manhattan distance metrics using simple k-means clustering”, International Journal for Research in Applied Science and Engineering Technology, Vol. 2, No. 5, pp. 270-274, 2014.
[15] H. W. Kuhn, “The Hungarian method for the assignment problem”, Naval Research Logistics Quarterly, Vol. 2, No. 1‐2, pp. 83-97, 1955.
[16] Rhinoceros, Website: http://www.rhino3d.com, Accessed 4 June 2021.
[17] OpenNURBS, Website: http://www.rhino3d.com/tw/opennurbs, Accessed 4 June 2021.