Identifying Recurring Elevator Faults Across a Growing Fleet

An elevator company was managing a growing installed base across multiple buildings and locations. Although service teams were successfully resolving individual breakdowns, management was finding it difficult to understand which problems were repeatedly affecting the fleet.

The same elevator might experience multiple faults over several months, but service records were maintained separately by technicians and locations. As a result, recurring issues were often treated as individual service calls rather than part of a larger pattern.

Management lacked a consolidated view of questions such as:

Which elevators generate the most faults? Which faults occur repeatedly? Which locations require more maintenance? And which problems are increasing over time?

Without this visibility, maintenance decisions were largely based on individual technician observations and historical service records.

The company implemented an IoT enabled elevator monitoring and analytics platform to bring operational and maintenance data from its installed fleet into a centralized environment.

The platform continuously collected elevator operating information and fault events from connected elevators.

Instead of looking at each service request independently, the company could analyze fault history across individual elevators, buildings, and the wider fleet.

AI driven analytics helped identify recurring patterns and abnormal behavior. Service teams could use this information to distinguish between isolated incidents and elevators that were experiencing repeated problems.

Managers could also compare elevator performance across locations and use historical data to identify assets that required closer attention or preventive maintenance.