Failure Analysis and Classification of Brake and Pneumatic Systems in Rolling Stock: A Comprehensive Approach to Enhancing Maintenance Efficiency

Abstract

This study is an excellent formulation of the way to improve the reliability and the maintenance efficiency of the rolling stock, and the central point of this is the brake and pneumatic systems, which are the key to the safety and effective railway operation. A dual-analytical approach can be created that means combining a Microsoft Excel-based dashboard and VBA to manage a systematic data entry and visualization with predictive modelling using the RapidMiner and machine learning algorithms, including Support Vector Machine (SVM) and Decision Tree. With an analysis of more than 38,000 failure notifications showing that most of the notifications concerned service failure alerts, especially in emergency braking mechanisms, it should be clear that proactive maintenance management should be adopted. The predictive models had a great success rate in terms of determining the high-risk parts and maintenance schedules. The main suggestions are the introduction of digital inventory structures, standardization of failure maintenance forms, and connection to the predictive tools that will allow data-driven choices. These results are used towards the creation of stronger, less expensive, and sustainable railway maintenance.