This application is an AI-based system capable of recognizing and analyzing handwritten sketches of engineering beam diagrams, producing a set of common plots.

This program allows users to upload their hand-drawn engineering sketches of beam diagrams and receive a thorough analysis encompassing six plots. These plots include a visualization of model structure, a visualization of applied loads, a visualization of model deformation, an axial force distribution, a shear force distribution, and a bending moment distribution. Complete correctness cannot be guaranteed, so users should thoroughly verify all results.

This software is accessible as a web application on MecSimCalc, a cloud computing platform developed at the University of Alberta, thanks to the work of Malcolm Kamgang. All source code, developed primarily by Isaac Joffe, is available at https://github.com/mqp2259/CV4BeamAnalysis.

When using this application, please cite this paper:

@article{joffe2024cv,
  AUTHOR = {Joffe, Isaac and Qian, Yuchen and Talebi-Kalaleh, Mohammad and Mei, Qipei},
  TITLE = {A Computer Vision Framework for Structural Analysis of Hand-Drawn Engineering Sketches},
  JOURNAL = {Sensors},
  VOLUME = {24},
  YEAR = {2024},
  NUMBER = {9},
  ARTICLE-NUMBER = {2923},
  URL = {https://www.mdpi.com/1424-8220/24/9/2923},
  PubMedID = {38733029},
  ISSN = {1424-8220},
  ABSTRACT = {Structural engineers are often required to draw two-dimensional engineering sketches for quick structural analysis, either by hand calculation or using analysis software. However, calculation by hand is slow and error-prone, and the manual conversion of a hand-drawn sketch into a virtual model is tedious and time-consuming. This paper presents a complete and autonomous framework for converting a hand-drawn engineering sketch into an analyzed structural model using a camera and computer vision. In this framework, a computer vision object detection stage initially extracts information about the raw features in the image of the beam diagram. Next, a computer vision number-reading model transcribes any handwritten numerals appearing in the image. Then, feature association models are applied to characterize the relationships among the detected features in order to build a comprehensive structural model. Finally, the structural model generated is analyzed using OpenSees. In the system presented, the object detection model achieves a mean average precision of 99.1%, the number-reading model achieves an accuracy of 99.0%, and the models in the feature association stage achieve accuracies ranging from 95.1% to 99.5%. Overall, the tool analyzes 45.0% of images entirely correctly and the remaining 55.0% of images partially correctly. The proposed framework holds promise for other types of structural sketches, such as trusses and frames. Moreover, it can be a valuable tool for structural engineers that is capable of improving the efficiency, safety, and sustainability of future construction projects.},
  DOI = {10.3390/s24092923}
}