Abstract
In the process of modern mechanical product design, retrieval and reuse of the pre-existed 3D CAD models would greatly save time and cost. Mechanical models, as artificial models, are mainly composed of regular surfaces, and the function of the models is to constrain mechanical movements. The purpose of retrieval is to reuse the functions of models designed by predecessors. To mine the functions contained in mechanical models, this paper proposes an original function dimension (FD)-based engineering shape matching method. Firstly, the function vector of each face making up the model is defined according to its use, machining or assembly method. Then the vectors are grouped to form the FDs of the model by using parallel relation which describes the function dimension of the model. The similarity between CAD models can be obtained by weighting the similarity between the matched FDs using area and angle. Based on FDs, the performance of model retrieval can be improved to facility functional reuse from geometric similarity. We validate the FD-based 3D model retrieval method using the popular ESB database and one novel multi-modal dataset. Extensive experiments show the superiority of the proposed method through comparisons. It has better retrieval accuracy and higher efficiency (3 × 109 models/second). Moreover, to the best of our knowledge, the novel engineering 3D object dataset that we contribute is closest to real engineering models presently.
Similar content being viewed by others
References
Akgül CB, Sankur B, Yemez Y, Schmitt F (2009) 3D model retrieval using probability density-based shape descriptors. IEEE Trans Pattern Anal Mach Intell 31(6):1117–1133
Bai J, Gao SM, Tang WH, Liu YS, Guo S (2010) Design reuse oriented partial retrieval of CAD models. Comput Aided Des 42(12):1069–1084
Bhatti UA, Yu ZY, Yuan LW, Zeeshan Z, Nawaz SA, Bhatti M, Mehmood A, Ul Ain Q, Wen L (2020) Geometric algebra applications in geospatial artificial intelligence and remote sensing image processing. IEEE Access 8:155783–155796
Bhatti UA, Yuan LW, Yu ZY, Nawaz SA, Mehmood A, Bhatti MA, Zeeshan QU, Nizamani MM (2020) Zeeshan, Xiao SJ. Predictive data modeling using sp-kNN for risk factor evaluation in urban demographical healthcare data. J Med Imag Health In 11(1):7–14
Bhatti UA, Yu ZY, Li J, Nawaz SA, Mehmood A, Zhang K, Yuan LW (2020) Hybrid watermarking algorithm using Clifford algebra with Arnold scrambling and chaotic encryption. IEEE Access 8:76386–76398
Bhatti UA, Yu ZY, Hasnain A, Nawaz SA, Yuan LW, Wen L, Bhatti MA (2022) Evaluating the impact of roads on the diversity pattern and density of trees to improve the conservation of species. Environ Sci Pollut R 29(10):14780–14790
Biasotti S, Cerri A, Bronstein A, Bronstein M (2014) Quantifying 3D shape similarity using maps: Recent trends, applications and perspectives. In Eurographics 2014 - State of the Art Reports
Bruno IJ, Kemp NM, Artymiuk PJ, Willett P (1997) Representation and searching of carbohydrate structures using graph-theoretic techniques. Carbohydr Res 304:61–67
Bustos B, Keim DA, Saupe D, Schreck T, Vranic DV (2005) Feature-based similarity search in 3D object databases. ACM Comput Surv 37(4):345–387
Cheng H-C, Lo C-H, Chu C-H, Kim YS (2011) Shape similarity measurement for 3D mechanical part using D2 shape distribution and negative feature decomposition. Comput Ind 62(3):269–280
Daras P, Zarpalas D, Axenopoulos A, Tzovaras D, Strintzis MG (2006) Three-dimensional shape-structure comparison method for protein classification. IEEE-ACM Trans Comput Biol Bioinform 3(3):193–207
Darom T, Keller Y (2012) Scale-invariant features for 3-D mesh models. IEEE Trans Image Process 21(5):2758–2769
Fish N, van Kaick O, Bermano A, Cohen-Or D (2016) Structure-oriented networks of shape collections. ACM Trans Graph 35(6) 171:1–14
Gao Y, Tang J, Hong R, Yan S, Dai Q, Zhang N, Chua TS (2012) Camera constraint-free view-based 3-D object retrieval. IEEE Trans Image Process 21(4):2269–2281
Gao Z, Zhang Y, Zhang H, Guan WL, Feng D, Chen SY (2022) Multi-level view associative convolution network for view-based 3D model retrieval. IEEE T Circ Syst Vid 32(4):2264–2278
Gao HH, Xiao JS, Yin YY, Liu T, Shi JG (2022) A mutually supervised graph attention network for few-shot segmentation: the perspective of fully utilizing limited samples. IEEE T Neur Net Lear:1–13. https://doi.org/10.1109/TNNLS.2022.3155486
Gao HH, Fang DQ, Xiao JS, Hussain W, Kim JY (2022) CAMRL: a joint method of channel attention and multidimensional regression loss for 3D object detection in automated vehicles. IEEE T Intell Transp:1–15. https://doi.org/10.1109/TITS.2022.3219474
Giannini F, Lupinetti K, Monti M (2017) Identification of similar and complementary subparts in B-rep CAD models. J Comput Inf Sci Eng 17(4):041004
Goodall S, Lewis PH, Martinez K, Sinclair PAS, Giorgini F, Addis M, Boniface MJ, Lahanier C, Stevenson J (2004) Sculpter: Multimedia retrieval for museums. In Proc. Third Int’l Conf. Image and Video Retrieval. pp 638-646
Gunn TG (1982) The mechanization of design and manufacturing. Sci Am 247(3):114–130
Han ZP, Mo R, Yang HC, Hao L (2018) Module partition for mechanical CAD assembly model based on multi-source correlation information and community detection. J Adv Mech Des Syst Manuf 12(1): JAMDSM0023
Huangfu ZM, Zhang SS, Yan LH (2017) A method of 3D CAD model retrieval based on spatial bag of words. Multimed Tools Appl 76(6):8145–8173
Iyer N, Jayanti S, Lou K, Kalyanaraman Y, Ramani K (2005) Three-dimensional shape searching: state-of-the-art review and future trends. Comput Aided Des 37(5):509–530
Jackson C, Buxton M (2007) The design reuse benchmark report: seizing the opportunity to shorten product development. Aberdeen Group, Boston
Jakovljevic Z, Puzovic R, Pajic M (2015) Recognition of planar segments in point cloud based on wavelet transform. IEEE Trans Ind Inform 11(2):342–352
Jayanti S, Kalyanaraman K, Iyer N, Ramani K (2006) Developing an engineering shape benchmark for CAD models. Comput Aided Des 38(9):939–953
Jing H, Huang MF, Li C (2019) 3D mechanical models retrieval based on combined histograms for rapid product design. Appl Mech Mater 16-19:65–69
Kastenmüller G, Kriegel HP, Seidl T (1998) Similarity search in 3D protein databases. In Proceedings of German conference on bioinformatics (GCB’98). Cologne, Germany
Kim H, Cha M, Mun D (2017) Shape distribution-based approach to comparing 3D CAD assembly models. J Mech Sci Technol 31(12):5627–5638
Kim H, Cha M, Mun D (2017) Shape distribution-based retrieval of 3D CAD models at different levels of detail. Multimed Tools Appl 76(14):15867–15884
Leila Z, Omar E, Dieter R (2016) A framework for similarity recognition of CAD models. J Comput Des Eng 3(3):274–285
Li M, Zhang YF, Fuh JYH, Qiu ZM (2009) Toward effective mechanical design reuse: CAD model retrieval based on general and partial shapes. J Mech Design 131(12):124501
Li PJ, Ma HD, Ming AL (2011) Non-rigid 3D model retrieval using multi-scale local features. Proceedings of the 19th ACM international conference on Multimedia, 11. pp 1425–1428
Lin X, Zhu KP, Wang QG (2018) Three-dimensional CAD model matching with anisotropic diffusion maps. IEEE Trans Ind Inform 14(1):265–274
Liu YJ, Luo X, Joneja A, Ma CX, Fu XL, Song DW (2013) User-adaptive sketch-based 3-D CAD model retrieval. IEEE Trans Autom Sci Eng 10(3):783–795
Liu A, Nie W, Gao Y, Su Y (2016) Multi-modal clique-graph matching for view-based 3D model retrieval. IEEE Trans Image Process 25(5):2103–2116
Liu AA, Guo FB, Zhou HY, Yan CG, Gao Z, Li XY, Li WH (2022) Domain-adversarial-guided siamese network for unsupervised cross-domain 3-D object retrieval. IEEE T Cybernetics 52:13862–13873. https://doi.org/10.1109/TCYB.2021.3139927
Llewelyn AI (1989) Review of CAD/CAM. Comput Aided Des 21(5):297–302
Lun ZL, Kalogerakis E, Sheffer A (2015) Elements of style: Learning perceptual shape style similarity. ACM Trans Graph 34(4) 84:1–14
Lupinetti K, Pernot JP, Monti M, Giannini F (2019) Content-based CAD assembly model retrieval: survey and future challenges. Comput Aided Des 113(8):62–81
Machalica D, Matyjewski M (2019) CAD models clustering with machine learning. Arch Mech Eng 66(2):133–152
Orio N, Zanuttigh P, Cortelazzo GM (2004) Content-based retrieval of 3D models based on multiple aspects. In Multimedia Signal Processing. 2004 IEEE 6th Workshop on
Osada R, Funkhouser T, Chazelle B, Dobkin D (2002) Shape distributions. ACM Trans Graph 21(4):807–832
Pope A (1994) Model-based object recognition: A survey of recent research. Technical report 94–04, Department of Computer Science, University of British Columbia
Proceedings of the thirteenth text retrieval conference. (2004) http://trec.nist.gov/pubs/trec13/appendices/CE.MEASURES.pdf
Rowe J, Razdan A, Collins D, Panchanathan S (2001) A 3D digital library system: Capture, analysis, query, and display. In Proceedings of 4th international conference on digital libraries
Schulz A, Shamir A, Baran I, Levin DIW, Sitthi-Amorn P, Matusik W (2017) Retrieval on Parametric Shape Collections. ACM Trans Graph 36(1):1–11
Tangelder JWH, Veltkamp RC (2008) A survey of content based 3D shape retrieval methods. Multimed Tools Appl 39:441–471
Tao SQ (2018) 3D CAD model retrieval based on the softassign quadratic assignment algorithm. Multimed Tools Appl 77(13):16249–16265
Ullman DG (1997) The mechanical design process, second edition. McGraw-Hill, New York
Wang P, Li Y, Zhang J, Yu JF (2016) An assembly retrieval approach based on shape distributions and earth Mover's distance. Int J Adv Manuf Technol 86(9–12):2635–2651
Wu YH, Tian L, Li CG (2013) High efficient methods of content-based 3D model retrieval. Chin J Mech Eng-En 26(2):248–256
Zarpalas D, Daras P, Axenopoulos A, Tzovaras D, Strintzis MG (2007) 3D model search and retrieval using the spherical trace transform. EURASIP J Adv Signal Process 1:23912
Zhang C, Zhou G (2019) A view-based 3D CAD model reuse framework enabling product lifecycle reuse. Adv Eng Softw 127:82–89
Zhang J, Pang JZ, Yu JF, Wang P (2018) An efficient assembly retrieval method based on Hausdorff distance. Robot Comput-Integr Manuf 51:103–111
Zhuang T, Zhang XT, Hou ZX, Zuo WM, Liu Y (2017) A novel 3D CAD model retrieval method based on vertices classification and weights combination optimization. Math Probl Eng 2017:6049750–6049712
Acknowledgments
This work was supported by Unveiling and Commanding Science and Technology Project of Liaoning Province (No.2021JH1/10400093), National Key R&D Program of China (2022YFC3006004).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sun, C., Xiong, W., Wang, H. et al. Design reuse oriented retrieval of mechanical 3D model using function dimension matching. Multimed Tools Appl 82, 24521–24545 (2023). https://doi.org/10.1007/s11042-023-15102-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15102-9