Published research / software

Moment–rotation prediction.

Inspect a full connection-response estimate without rebuilding the regression workflow.

Supplied workflow for numerical evidence, database analysis, prediction, interpretation and GUI development. Publication · 10.1007/s11709-025-1162-y

Role: Research author · credited developer
Period: 2025
Methods: Curve fitting · ML
Status: Published research / software

Engineering software / Desktop interface

A defined input.
An inspectable decision.

For connection engineers

Inspect a full connection-response estimate without rebuilding the regression workflow.

01 / INPUT

Set the engineering case

End-plate dimensions, bolt diameter and spacing, and beam/column second moments of area

02 / OUTPUT

Inspect the result

Stiffness, resistance parameters and a moment–rotation curve

03 / DECISION

Compare the next options

Compare stiffness and moment capacity across candidate joints.

Technical basis

Curve fitting · ML

Validation evidence

Personally credited EEP/FEP interfaces and the published four-parameter model study.

Current scope

The two interface variants form one tool family. A predicted curve is not a tested joint.

Public deployment has not been verified. The supplied interface and source establish the implementation shown.

Engineering record

Scope, method and evidence.

One connection-response tool across EEP/FEP versions. Authorship does not imply every FE model or physical test was personally produced.

01Engineering question

Inspect a full connection-response estimate without rebuilding the regression workflow.

Context: Structural steel.

02Role and documented scope

Research author · credited developer

03Methods and evidence

The research represents moment–rotation response through a four-parameter curve formulation and compares machine-learning models for the connection-response task. EEP/FEP versions belong to one tool family, rather than separate application counts.

Supplied research files support the scope shown. Authorship is distinguished from personal ownership of every dataset, test or model; an interface is not proof of current deployment.

Publication record · 10.1007/s11709-025-1162-y

04Interpretation and limitations

No universal accuracy, engineering approval or field benefit is inferred from a selected output. Model domains and independent checks must be established for a new assignment.

Research supporting this project