Applied sciences

Archive of Mechanical Engineering


Archive of Mechanical Engineering | 2019 | vol. 66 | ahead of print |


Similarity assessment between 3D models is an important problem in many fields including medicine, biology and industry. As there is no direct method to compare 3D geometries, different model representations (shape signatures) are developed to enable shape description, indexing and clustering. Even though some of those descriptors proved to achieve high classification precision, their application is often limited. In this work, a different approach to similarity assessment of 3D CAD models was presented. Instead of focusing on one specific shape signature, 45 easy-to-extract shape signatures were considered simultaneously. The vector of those features constituted an input for 3 machine learning algorithms: the random forest classifier, the support vector classifier and the fully connected neural network. The usefulness of the proposed approach was evaluated with a dataset consisting of over 1600 CAD models belonging to 9 separate classes. Different values of hyperparameters, as well as neural network configurations, were considered. Retrieval accuracy exceeding 99% was achieved on the test dataset.

Go to article

Editorial office


Prof. Janusz Frączek, Warsaw University of Technology, Poland


Editorial Board

Prof. Krzysztof Arczewski, Warsaw University of Technology, Poland

Prof. Janusz T. Cieśliński, Gdańsk University of Technology, Poland

Prof. Antonio Delgado, LSTM University of Erlangen-Nuremberg, Germany

Prof. Peter Eberhard, University of Stuttgart, Germany

Prof. Jerzy Maciej Floryan, The University of Western Ontario, Canada

Prof. Tadeusz Ryszard Fodemski, Technical University of Lodz, Poland

Prof. Zenon Mróz, Institute of Fundamental Technological Research, Polish Academy of Sciences, Poland

Prof. Andrzej J. Nowak, Silesian University of Technology, Poland

Dr. Andrzej F. Nowakowski, The University of Sheffield, United Kingdom

Prof. Jerzy Sąsiadek, Carleton University, Canada

Prof. Jacek Szumbarski, Warsaw University of Technology, Poland

Prof. Tomasz Wiśniewski, Warsaw University of Technology, Poland

Prof. Günter Wozniak, Chemnitz University of Technology, Germany


Assistant to the Editor

Małgorzata Broszkiewicz, Warsaw University of Technology, Poland


Editorial Advisory Board

Prof. Alberto Carpinteri, Politecnico di Torino, Italy

Prof. Fernand Ellyin, University of Alberta, Canada

Prof. Feng Gao, Shanghai Jiao Tong University, P.R. China

Prof. Emmanuel E. Gdoutos, Democritus University of Thrace, Greece

Prof. Gregory Glinka, University of Waterloo, Ontario, Canada

Prof. Andrius Marcinkevicius, Vilnius Gedeminas Technical University, Lithuania

Prof. Manuel José Moreira De Freitas, Instituto Superior Tecnico, Portugal

Prof. Andrzej Neimitz, Kielce University of Technology, Poland

Prof. Masateru Ohnami, Ritsumeikan University, Kyoto, Japan

Prof. Thierry Palin-Luc, Arts et Métiers ParisTech, Institut Carnot Arts, France

Prof. Andre Pineau, Centre des Matériaux, Ecole des Mines de Paris, France

Prof. Narayanaswami Ranganathan, LMR, Ecole Polytechnique de l'Université de Tours, France

Prof. Jan Ryś, Cracow University of Technology, Poland

Prof. Adelia Sequeira, Technical University of Lisbon, Portugal,

Prof. Józef Szala, University of Technology and Life Sciences in Bydgoszcz, Poland

Prof. Edmund Wittbrodt, Gdańsk University of Technology, Poland

Prof. Jens Wittenburg, Karlsruhe Institute of Technology, Germany

Prof. Stanisław Wojciech, University of Bielsko-Biała, Poland


Language Editor

Lech Śliwa, Institute of Physiology and Pathology of Hearing, Warsaw, Poland




Editorial Office:

Institute of Aeronautics and Applied Mechanics, Warsaw University of Technology

Nowowiejska 24, Room 132, 00-665 Warsaw, Poland

Phone:  (+48) 22 234 7448, fax: (+48) 22 628 25 87,


Instructions for authors

About the Journal
Archive of Mechanical Engineering is an international journal publishing works of wide significance, originality and relevance in most branches of mechanical engineering. The journal is peer-reviewed and is published both in electronic and printed form. Archive of Mechanical Engineering publishes original papers which have not been previously published in other journal, and are not being prepared for publication elsewhere. The publisher will not be held legally responsible should there be any claims for compensation. The journal accepts papers in English.

Archive of Mechanical Engineering is an Open Access journal. The journal does not have article processing charges (APCs) nor article submission charges.

Original high quality papers on the following topics are preferred:

  • Mechanics of Solids and Structures,
  • Fluid Dynamics,
  • Thermodynamics, Heat Transfer and Combustion,
  • Machine Design,
  • Computational Methods in Mechanical Engineering,
  • Robotics, Automation and Control,
  • Mechatronics and Micro-mechanical Systems,
  • Aeronautics and Aerospace Engineering,
  • Heat and Power Engineering.

All submissions to the AME should be made electronically via Editorial System - an online submission and peer review system at:

More detailed instructions for Authors can be found there.

This page uses 'cookies'. Learn more