Authors: Assistant Professor M.Pradeepthi, J. Divya
Abstract: Ensuring the safety, reliability, and sustainability of modern railway and powerline systems has become increasingly important due to the rapid growth of transportation networks and energy infrastructure. Continuous monitoring of operational conditions, timely fault detection, accurate current load prediction, and efficient signal management are essential for preventing failures, reducing maintenance costs, and improving overall system performance. Recent advancements in Machine Learning (ML) have enabled intelligent predictive models that can analyze large volumes of operational data and support automated decision-making for critical infrastructure. This paper presents a machine learning-based framework for improving the safety and sustainability of railway and powerline systems through predictive analytics and intelligent monitoring. The proposed methodology utilizes Decision Tree (DT), K-Nearest Neighbor (KNN), Random Forest (RF), Gradient Boosting (GB), Reinforcement Learning (RL), and Time Series Analysis (TSA) to perform safety diagnostics, current load forecasting, and railway signal efficiency optimization. Synthetic datasets representing railway operational parameters and powerline conditions are employed to train and evaluate the predictive models. Comprehensive experimental analysis is conducted using multiple performance measures, including Accuracy, Precision, Recall, F1-score, and confusion matrix-based evaluation. The results demonstrate that ensemble-based machine learning techniques provide superior predictive performance for infrastructure monitoring while enabling reliable fault detection and operational forecasting. The proposed framework offers an intelligent decision-support solution that enhances infrastructure safety, optimizes maintenance planning, improves energy efficiency, and contributes to the sustainable operation of railway and powerline systems.
