Machine learning framework for predicting ESDD on high-voltage glass insulators with SHAP-based feature optimization

Ali Ahmed Salem, Waleed M Hamanah, Abdullah S Algamili, Salem Mgammal Al-Ameri, Samir Al-Gailani · 2026

Read Machine learning framework for predicting ESDD on high-voltage glass insulators with SHAP-based feature optimization by Ali Ahmed Salem, Waleed M Hamanah, Abdullah S Algamili, Salem Mgammal Al-Ameri, Samir Al-Gailani (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0354892.txt.

Description

Ali Ahmed Salem and co-authors predict how badly pollution coats high-voltage glass insulators, a grime layer that can trigger flashovers and outages. Utilities measure coating severity with a salt-density score, but testing is slow and manual. Four learning models were trained on several hundred records spanning fifteen weather and operating features, tuned two ways, and then interrogated with an explanation method that ranks which features drive each prediction.

A smooth probabilistic model won on accuracy under every tuning style. Keeping only the top ten ranked features beat using five or all fifteen, sharpening accuracy while trimming complexity. Salem and colleagues present the trimmed, explainable models as tools grid crews can actually audit before trusting them with maintenance decisions.

Catalog record

CREATORAli Ahmed Salem, Waleed M Hamanah, Abdullah S Algamili, Salem Mgammal Al-Ameri, Samir Al-Gailani
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE65618
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0354892

Browse the full library · About the Tower of Babel