Generating Machine Learning Datasets on Damage Identification Using Finite Element Bridge Model

Hidetaka Saomoto; Takashi Miyamoto

doi:10.2208/jscejseee.78.4_i_10

January 1, 2022Journal of Japan Society of Civil Engineers Ser A1 (Structural Engineering & Earthquake Engineering (SE/EE))Open Access

Generating Machine Learning Datasets on Damage Identification Using Finite Element Bridge Model

View Full Paper

Ask AI

Bookmark

Share

Key Points

To establish standardized benchmark datasets for bridge damage identification using finite element simulation to support machine learning evaluation in civil engineering.
Generated four distinct dataset cases for structural damage estimation using finite element analysis of a bridge model.
Trained and evaluated 19 machine learning algorithms across the synthetic datasets using the coefficient of determination (R²) as the primary metric.
Datasets modeling single-member damage yielded R² values ranging from 0.5 to 1.0 across the 19 algorithms, establishing an appropriate baseline benchmark.
Datasets modeling two-member damage resulted in R² values of 0.5 or lower for approximately half of the structural members, representing a more challenging benchmark.

Implication

Computational benchmark study evaluates finite element bridge datasets across 19 machine learning algorithms, highlighting distinct difficulty tiers for structural damage identification.

Abstract

No abstract yet. The journal hasn't published one we can show.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Saomoto et al. (2022) studied this question.

synapsesocial.com/papers/6a7e93d0358787acda4f7730 https://doi.org/10.2208/jscejseee.78.4_i_10

View Full Paper

Ask AI

Bookmark

Share

Generating Machine Learning Datasets on Damage Identification Using Finite Element Bridge Model

Key Points

Implication

Abstract

Discussion

Cite This Study

Generating Machine Learning Datasets on Damage Identification Using Finite Element Bridge Model

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

More related papers

More from Journal of Japan Society of Civil Engineers Ser A1 (Structural Engineering & Earthquake Engineering (SE/EE))

Keep reading

More related papers

More from Journal of Japan Society of Civil Engineers Ser A1 (Structural Engineering & Earthquake Engineering (SE/EE))