Research on an Automatic Solution Method for Plane Frames Based on Computer Vision

TL;DR

This paper introduces a deep learning-based method to automatically analyze plane frame structures from images, making structural analysis faster and more accessible.

Contribution

A novel integration of computer vision and mechanics to automate structural analysis from schematic images, reducing manual effort and analysis time.

Findings

The detection accuracy of structural primitives reached 99.1%.

The overall solution accuracy of mechanical problems exceeded 90% in the final test set.

Abstract

What are the main findings?
Proposed a structured reconstruction method to bridge visual semantics and mechanics, converting image recognition data into precise inputs for the matrix displacement method.Established a novel rapid analysis method based on visual perception that integrates deep learning with traditional mechanics to automatically generate internal force diagrams.

Proposed a structured reconstruction method to bridge visual semantics and mechanics, converting image recognition data into precise inputs for the matrix displacement method.

Established a novel rapid analysis method based on visual perception that integrates deep learning with traditional mechanics to automatically generate internal force diagrams.

What are the implications of the main findings?
This approach automates the workflow from image input to structural solving, significantly reducing analysis time to seconds by avoiding complex manual modeling.It provides a new technical path for intelligent structural analysis, proving highly effective for teaching demonstrations and quick engineering estimations.

This approach automates the workflow from image input to structural solving, significantly reducing analysis time to seconds by avoiding complex manual modeling.

It provides a new technical path for intelligent structural analysis, proving highly effective for teaching demonstrations and quick engineering estimations.

In the internal force analysis of plane frames, traditional mechanics solutions require the cumbersome derivation of equations and complex numerical calculations, a process that is both time-consuming and error-prone. While general-purpose Finite Element Analysis (FEA) software offers rapid and precise calculations, it is limited by tedious modeling pre-processing and a steep learning curve, making it difficult to meet the demand for rapid and intelligent solutions. To address these challenges, this paper proposes a deep learning-based automatic solution method for plane frames, enabling the extraction of structural information from printed plane structural schematics and automatically completing the internal force analysis and visualization. First, images of printed plane frame schematics are captured using a smartphone, followed by image pre-processing steps such as rectification and enhancement. Second, the YOLOv8 algorithm is utilized to detect and recognize the plane frame, obtaining structural information including node coordinates, load parameters, and boundary constraints. Finally, the extracted data is input into a static analysis program based on the Matrix Displacement Method to calculate the internal forces of nodes and elements, and to generate the internal force diagrams of the frame. This workflow was validated using structural mechanics problem sets and the analysis of a double-span portal frame structure. Experimental results demonstrate that the detection accuracy of structural primitives reached 99.1%, and the overall solution accuracy of mechanical problems in the final test set exceeded 90%, providing a more convenient and efficient computational method for the analysis of plane frames.

Figures