AI-Powered Decision Support System for Enhancing Railway Asset Management and Reducing Turnaround Time: A Focus on the Northern Division

Abstract

This paper gives the improvement and analysis of a Resource Management System (RMS) aimed toward improving the turnaround performance of railway belongings inside the Delhi Division of Indian Railways. The RMS incorporates superior technology, inclusive of actual-time monitoring, predictive protection, and automated workflows, to cope with full-size challenges in railway asset control. The machine is designed to optimize the supply and efficiency of railway coaches and locomotives, with a specific recognition on reducing Pre-Departure Detention (PDD) instances and improving body of workers education compliance.

The studies evaluate the performance of key metrics inclusive of average turnaround times, asset availability ratios, and PDD times both earlier than and after the implementation of the RMS. The consequences monitor significant improvements: average turnaround times for coaches reduced by way of 37.50% and for locomotives via 32.29%. The availability ratios for coaches and locomotives stepped forward through 20.00% and 21. 43%, respectively. Furthermore, PDD times have been reduced by using 37.50%, while compliance with group of workers education necessities expanded through 38. 46%. The implementation of the RMS also caused a reduction in the quantity of faulty coaches and locomotives, with defects decreasing by using 33.33% and 37.50%, respectively.

These findings highlight the effectiveness of the RMS in enhancing operational performance and asset control inside Indian Railways. The paper concludes by discussing future research guidelines, consisting of the ability integration of synthetic intelligence (AI) and machine getting to know technologies to amplify system talents and enhance performance similarly, while also incorporating user comments to refine the RMS design.