← Search

Data · dataset · 2026

Training and testing data for damaged beam with multiple boundary conditions

Listed in Teesside University Research Data Repository

This dataset contains analytically, numerically, and experimentally generated data used for the training and validation of machine learning models for structural damage identification in beam-like structures under multiple boundary conditions.

Description

The database includes the first six bending-mode Relative Frequency Shifts (RFS) calculated for various crack locations, crack severities, and support configurations. Beam dimensions and material properties L [m] B[m] H[m] A[m^2] I[m^4] ρ [kg/m^3] E [Pa] 1 0.03 0.005 0.00015 3.125E-10 7850 2E+11 The analytical training dataset was generated by iteratively repositioning the crack along the beam with a step of Δ(x/L) = 0.002 and varying the crack depth from a = 0.2 mm to a = 2 mm with an increment of Δa = 0.2 mm, for ten boundary condition configurations: romanian A–A english H–H (hinged–hinged), A–G eng.

H–S (hinged–sliding), A–L eng. H–F (hinged–free), G–G eng. S–S (sliding–sliding), G–L eng.

Read the rest (4 more)

S–F (sliding–free) , C–A eng. C–H (clamped–hinged) , C–G eng. C–S (clamped–sliding), ΖÎ, eng.

C–C (clamped–clamped), ΖL eng. C–F (clamped–free), and L–L eng. F–F (free–free).

Symmetric mirrored cases were excluded to reduce redundancy. In total, the training set contains 39,904 scenarios. The numerical testing dataset includes 160 Finite Element Method (FEM) simulated damage scenarios generated in ANSYS using the same beam geometry and material properties.

The experimental dataset contains measured natural frequencies and corresponding RFS values obtained from laboratory tests on S355JR steel beams under C–F (cantilever) and C–C (clamped–clamped) boundary conditions with cracks of 1 mm depth on specified position relative to the left end of the beam. The dataset can be used for: boundary condition classification; crack localization; crack severity estimation; benchmarking machine learning and Structural Health Monitoring (SHM) algorithms.

Links

Where it is published

Catalogue records · 1

Topics

From keywords
Computer Science & AI · Earth & Environmental Science · Engineering · Humanities · Life Sciences · Machine learning · Medicine & Health · Social Science
Provenance · 1 source records, 13 field assertions
SourceKeyLast seenRaw
Teesside University Research Data Repositoryoai:data.mendeley.com/d76b73ft36.212 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
concepts[field].anzsrc:group:4611mapping · researchdata tees ac ukvocabulary-mapper@1.0.0keywords['Machine Learning']
concepts[field].local:field:computer-science-aimapping · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
concepts[field].local:field:earth-environmentalmapping · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
concepts[field].local:field:engineeringmapping · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
concepts[field].local:field:humanitiesmapping · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
concepts[field].local:field:life-sciencesmapping · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
concepts[field].local:field:medicine-healthmapping · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
concepts[field].local:field:social-sciencemapping · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
descriptionsource · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0/metadata/dc/description
licensesource · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0/metadata/dc/rights
publication_datesource · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0
titlesource · researchdata tees ac ukconnector:researchdata_tees_ac_uk@1.0.0/metadata/dc/title