Timber Joints Analysis and Design Using Shape and Graph Grammar-Based Machine Learning Approach - Proposal and Synthetic Dataset Preparation

Aug 3, 2026

Upload by Anda

Timber joints serve as a foundational building-construction technique across cultures, traditionally relying on simple geometry to connect components without adhesives or fixings. The study combines computational design with shape and graph grammar to reinterpret complex timber connections and support machine learning. It proposes a synthetic dataset preparation workflow using shape grammar and graph grammar, including prototype design of shape and graph extraction systems implemented in Topologic within Sverchok and Blender.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Background

Research Aims

Synthetic Data Preparation Approach

Prototype for Shape and Graph Extraction Systems

Graph Extraction for ML Datasets

Results and Discussion

Extracted Graphs and Shape Grammars

Limitations and Future Work

Timber Joints Analysis and Design Using Shape and Graph Grammar-Based Machine Learning Approach Synthetic Data Preparation of Timber Joints’ Shape and Graph Grammar for Machine Learning Application Ho Man Yau1, Theodoros Dounas2, Wassim Jabi3, Davide Lombardi4 1, 2Robert Gordon University, 3Cardiff University, 4Xi'an Jiaotong-Liverpool University 1, [2](2 {h.m.yau | t.dounas}@rgu.ac.uk)[ {h.m.yau](2 {h.m.yau | t.dounas}@rgu.ac.uk)[ |](2 {h.m.yau | t.dounas}@rgu.ac.uk)[ t.dounas}@rgu.ac.uk](2 {h.m.yau | t.dounas}@rgu.ac.uk), [3](3jabiw@cardiff.ac.uk)[jabiw@cardiff.ac.uk](3jabiw@cardiff.ac.uk), [4](4 davide.lombardi@xjtlu.edu.cn)[ davide.lombardi@xjtlu.edu.cn](4 davide.lombardi@xjtlu.edu.cn)[ ](4 davide.lombardi@xjtlu.edu.cn)Timber joints had been applied as one of the primary methods across different cultures of building construction. The technique of crafting timber joints uses simple geometry to connect different components without the need of adhesives or fixings. Digitalisation and computational design method provided a new approach to developing complex timber joint connections. By combining this traditional technique with computational design methods, shape, and graph grammar opened new opportunities in reinterpreting timber joint designs. In this paper, we proposed a timber joints’ synthetic dataset preparation using shape grammar and graph grammar for machine learning applications. The research focused on designing a prototype of a shape grammar extraction system and graph extraction system manually and using Topologic in Sverchok, Blender, with a discussion on how to shape grammar applications help to analysis and create a larger database for future machine learning development of this project. Keywords: Shape grammar, Graph grammar, Timber structures, Parametric design, Machine learning. INTRODUCTION Digitalisation has been introduced to the architecture and building construction industry. The technological advancements opened new opportunities in analysing and designing complex geometrical structures. Machine learning (ML) and Artificial Intelligence (AI) applications have become a trend in computational design methods in architecture, in the section involved data-based could be computerised and automated to enhance design practice (Carta, 2020) . This paper investigates how shape and graph grammar open new opportunities creating a more convenient system for the analysis and design of parametrically-based timber joints. By using shape and graph grammar to analyse parametric timber joints for preparing synthetic datasets for ML application (Figure 1) . Moreover, this paper will propose a prototype that focused on graph extraction in creating synthetic datasets using traditional timber joints. This article is divided into the following sections. In the first section, we deliver the introduction and the background of the research. We review which type of tools are needed for the preparation of the prototype for the graph analysis system. In the second section, we propose a graph grammar extract system that is aimed at analysing and translating parametric timber joints into a graph format. We demonstrate the approach of the algorithm, rules, and method being applied torecreate the timber joints. With a shape grammar extraction system and divided into stages to demonstrate on the method of analysis and extraction of rules used in timber joints. The next section shows and discusses different graphs and shape grammars extracted from the algorithm and shapes grammar-generated timber joints. The last section discusses the method, the limitations of the project, and further work of the research. Figure 1 The overall structure of the project BACKGROUND Timber has been applied as a primary building material across different cultures for centuries (Yen, 2012) . This technique can be traced back to the Hemudu period in China (Fan, 2018) . Traditional timber joints used simple geometry to create tigh

FAQs

Why are timber joints important in building construction?

Timber joints have been used for centuries across different cultures as a primary connection method, relying on geometry to create tightfit interlocks that resist shear and bending stresses.

How does the paper apply shape and graph grammar to timber joints?

The approach analyzes parametrically based timber joints using shape grammar and graph grammar, translating them into graph representations to support downstream synthetic dataset preparation and ML use.

What is the main contribution regarding machine learning datasets?

The paper proposes a method for preparing a synthetic dataset of timber joint shapes and graph grammar structures, implemented via a manually developed prototype using Topologic in Sverchok and Blender.

Aug 3, 2026

Upload by Anda