A Physics-Informed Machine Learning Framework for Structural Damage Detection: Integrating Modal Analysis with SHAP-Based Feature Importance

Bibek Pokhrel; Bighyan Awasthi; Aayushma Bohora; Damnee Kumari; Prabesh Kunwar; Brindal Paudel

Article Details

A Physics-Informed Machine Learning Framework for Structural Damage Detection: Integrating Modal Analysis with SHAP-Based Feature Importance

Authors:

Bibek Pokhrel | Bighyan Awasthi | Aayushma Bohora | Damnee Kumari | Prabesh Kunwar | Brindal Paudel

Publisher:

EngiScience Publisher

Main Topics:

Modal frequency analysis

Journal:

Journal of Studies in Civil Engineering Vol.3 Issue 1, pp.74-92

Document Type:

Article

Publication Date:

6/2026

Document Language:

English

Document ID (Org No.):

2001837637

pISSN:

3007-8679

Keywords:

Abstract:

 Structural health monitoring systems increasingly rely on machine learning, yet these models often function as black boxes that obscure the physical meaning of their predictions. This study addresses this gap by developing a novel Frequency Importance Weighted Damage Index (FIWDI) that bridges physics-based modal analysis with interpretable machine learning through SHAP value integration. The framework was validated using the Z-24 Bridge benchmark dataset, where we extracted modal frequencies from 45 test configurations spanning healthy and progressively damaged states. A CatBoost classifier achieved perfect classification accuracy (100%), with SHAP analysis revealing that the fourth vibration mode contributed 34.54% to damage detection—an unexpected finding that challenges conventional assumptions about lower-mode dominance. The FIWDI demonstrated superior sensitivity compared to traditional frequency-based indices. Statistical validation confirmed robustness across environmental variations. This work demonstrates that interpretable machine learning can enhance rather than replace physics-based understanding in structural engineering applications.

Article Details

A Physics-Informed Machine Learning Framework for Structural Damage Detection: Integrating Modal Analysis with SHAP-Based Feature Importance

Authors:

Bibek Pokhrel | Bighyan Awasthi | Aayushma Bohora | Damnee Kumari | Prabesh Kunwar | Brindal Paudel

Publisher:

EngiScience Publisher

Main Topics:

Modal frequency analysis

Journal:

Journal of Studies in Civil Engineering Vol.3 Issue 1, pp.74-92

Document Type:

Article

Publication Date:

6/2026

Document Language:

English

Document ID (Org No.):

2001837637

pISSN:

3007-8679

EngiScience Publisher

Journal of Studies in Civil Engineering

JSCE

jsce

Engineering

Civil

Issues

Article Details

A Physics-Informed Machine Learning Framework for Structural Damage Detection: Integrating Modal Analysis with SHAP-Based Feature Importance

Authors: Bibek Pokhrel | Bighyan Awasthi | Aayushma Bohora | Damnee Kumari | Prabesh Kunwar | Brindal Paudel

Publisher: EngiScience Publisher

Main Topics: Modal frequency analysis

Journal: Journal of Studies in Civil Engineering Vol.3 Issue 1, pp.74-92

Document Type: Article

Publication Date: 6/2026

Document Language: English

Document ID (Org No.): 2001837637

pISSN: 3007-8679

EngiScience Publisher

Journal of Studies in Civil Engineering

JSCE

jsce

Engineering

Civil

Issues

Authors:

Bibek Pokhrel | Bighyan Awasthi | Aayushma Bohora | Damnee Kumari | Prabesh Kunwar | Brindal Paudel

Publisher:

EngiScience Publisher

Main Topics:

Modal frequency analysis

Journal:

Journal of Studies in Civil Engineering Vol.3 Issue 1, pp.74-92

Document Type:

Article

Publication Date:

6/2026

Document Language:

English

Document ID (Org No.):

2001837637

pISSN:

3007-8679