Interpretable domain knowledge enhanced machine learning framework on axial capacity prediction of circular CFST columns

TL;DR

This paper presents a domain knowledge integrated neural network framework that significantly improves the accuracy of axial capacity prediction for CFST columns by combining machine learning with engineering insights.

Contribution

It introduces a novel DKNN model that incorporates domain knowledge and advanced feature engineering, achieving over 50% reduction in prediction error compared to existing models.

Findings

Over 50% reduction in MAPE compared to previous models

High robustness in noisy environments

Provides design recommendations based on sensitivity and SHAP analysis

Abstract

This study introduces a novel machine learning framework, integrating domain knowledge, to accurately predict the bearing capacity of CFSTs, bridging the gap between traditional engineering and machine learning techniques. Utilizing a comprehensive database of 2621 experimental data points on CFSTs, we developed a Domain Knowledge Enhanced Neural Network (DKNN) model. This model incorporates advanced feature engineering techniques, including Pearson correlation, XGBoost, and Random tree algorithms. The DKNN model demonstrated a marked improvement in prediction accuracy, with a Mean Absolute Percentage Error (MAPE) reduction of over 50% compared to existing models. Its robustness was confirmed through extensive performance assessments, maintaining high accuracy even in noisy environments. Furthermore, sensitivity and SHAP analysis were conducted to assess the contribution of each effective parameter to axial load capacity and propose design recommendations for the diameter of cross-section, material strength range and material combination. This research advances CFST predictive modelling, showcasing the potential of integrating machine learning with domain expertise in structural engineering. The DKNN model sets a new benchmark for accuracy and reliability in the field.