ThyssenKrupp Elevator slashes downtime with predictive maintenance

ThyssenKrupp Elevator implemented AI-powered predictive maintenance to significantly reduce elevator downtime across their global fleet. By leveraging Azure IoT sensors, data were collected on vibration, temperature, and pressure. These data streams were processed via Azure Data Lake and analyzed using Azure Machine Learning to detect anomalies and predict faults before they occurred. When issues arose, Dynamics 365 Field Service was triggered to automate maintenance tasks and coordinate technician dispatch. Power BI provided real-time visibility for operational teams while Copilot streamlined piloting and team adoption. The initiative helped ThyssenKrupp move maintenance from a reactive to a proactive approach, extending equipment lifespans, optimizing resources, and lowering operational costs. Supported by AlfaPeople, the solution is robust and ready to scale across similar industrial deployments. This transformation enabled up to 50% reduction in elevator downtime, improved cost-efficiency, and greatly increased reliability. The process involves close integration between AI analytics and field service automation, allowing proactive identification and resolution of faults, supporting uninterrupted business operations.