nil0y-dey/co2-laser-engraving-pmma

How nil0y-dey/co2-laser-engraving-pmma works

This repository is research code for predicting PMMA groove width and depth from CO₂ laser parameters, with uncertainty-aware quality decisions. Users provide the experimental dataset and run independent scripts for five-model comparison, feature diagnostics, optimizer sensitivity, or quality-gate validation. The principal result is the conformal-calibrated GPR surrogate; it also supports SHAP and PDP/ICE analysis. README descriptions establish the shared experiment protocol and generated outputs; sampled code confirms model training, calibration, and gate evaluation. The scripts are standalone rather than a single shared runtime pipeline.

Main entry points: data_template.csv Experimental Data · results Experiment Outputs · gpr.py GPR Surrogate · quality_gating.py Quality Gate

Components 12

Surrogate Models

GPR Surrogate src/gpr.py
SVR Baseline src/svr.py
MLP Baseline src/mlp.py
Random Forest src/random_forest.py
Polynomial Ridge src/polynomial_ridge.py

GPR Analysis

Conformal Calibration src/gpr.py
SHAP PDP ICE src/gpr.py

Validation Studies

Quality Gate src/quality_gating.py
GWO Sensitivity src/gwo_sensitivity.py
Feature Diagnostics src/vif_analysis.py

Data and Results

Experimental Data data/data_template.csv
Experiment Outputs results

Connections 19

Experimental Data → GPR Surrogate: trains from README.md
Experimental Data → SVR Baseline: trains from README.md
Experimental Data → MLP Baseline: trains from README.md
Experimental Data → Random Forest: trains from README.md
Experimental Data → Polynomial Ridge: trains from README.md
GPR Surrogate → Conformal Calibration: calibrates predictions README.md
GPR Surrogate → SHAP PDP ICE: analyzes predictions README.md
Experimental Data → Quality Gate: evaluates against src/quality_gating.py
Experimental Data → GWO Sensitivity: loads for analysis src/gwo_sensitivity.py
Experimental Data → Feature Diagnostics: loads for diagnostics src/vif_analysis.py
Conformal Calibration → Quality Gate: informs decisions README.md
GPR Surrogate → Experiment Outputs: writes outputs README.md
SVR Baseline → Experiment Outputs: writes outputs README.md
MLP Baseline → Experiment Outputs: writes outputs README.md
Random Forest → Experiment Outputs: writes outputs README.md
Polynomial Ridge → Experiment Outputs: writes outputs README.md
Quality Gate → Experiment Outputs: writes outputs README.md
GWO Sensitivity → Experiment Outputs: writes outputs src/gwo_sensitivity.py
Feature Diagnostics → Experiment Outputs: writes outputs src/vif_analysis.py

Drawn by GitDiagram on November 15, 2026 from the repository's file tree, README and source files. Read as Markdown ·