CGI > Case Studies > Driving Predictive Maintenance into ThyssenKrupp Elevators

Driving Predictive Maintenance into ThyssenKrupp Elevators

CGI Logo
 Driving Predictive Maintenance into ThyssenKrupp Elevators - IoT ONE Case Study
Technology Category
  • Analytics & Modeling - Machine Learning
  • Analytics & Modeling - Predictive Analytics
  • Infrastructure as a Service (IaaS)
  • Platform as a Service (PaaS) - Data Management Platforms
Applicable Industries
  • Equipment & Machinery
Applicable Functions
  • Maintenance
Use Cases
  • Predictive Maintenance
The Customer
ThyssenKrupp Elevator (TKE)
About The Customer
ThyssenKrupp Elevator (TKE) Americas is the largest producer of elevators in the Americas, providing and maintaining more than one million elevators around the world.
The Challenge

TKE had a number of initiatives underway around the world to enable remote monitoring of its elevators. However, none of the solutions provided the data and insight required to move from a traditional reactive maintenance approach to one that is predictive and even preemptive, and all were challenged by information overload issues that limited their value. TKE wanted a solution that would enable it to anticipate and quickly resolve maintenance issues for the majority of the 1.2 million elevators it services across the globe.

The Solution

CGI’s development team built a pilot, cloud-based elevator monitoring system using Microsoft’s Azure-based Intelligent System Service (ISS), Microsoft’s Azure Maching Learning, HDInsight and our own Intelligent Enterprise Framework (IEF), which facilitates the rapid deployment of IoT applications. Integrated with TKE’s elevator sensors, the system harnesses data from each sensor, processes the data using business rules defined by TKE, and generates rich data insight using predictive analytics. The resulting insight is then made available to supervisors and site technicians via two different user interfaces in the form of maintenance alerts, instructions and recommendations. Feedback from users is integrated within the system, enabling it to become more accurate over time. CGI worked with Microsoft to develop predictive data models using Microsoft’s Machine Learning Azure service. Years of historical data from elevators across North America were analysed to generate sequence mappings of alarms to identify the root causes of faults. he system was implemented for a small number of elevators run by TKE in the Seattle, Washington area in the summer of 2014. The pilot project was a success, enabling TKE to reduce elevator downtime and improve resource planning, cost forecasting and maintenance scheduling. In turn, TKE has been able to provide a more competitive offering to its customers.

Data Collected
Downtime, Maintenance Requirements, Maintenance Work Orders, Per-Unit Maintenance Costs
Operational Impact
  • [Process Optimization - Predictive Maintenance]
    Strong predictive analytics that generate rich, valuable insight, enabling more proactive, predictive and pre-emptive maintenance
  • [Efficiency Improvement - Production Uptime]
    Reduced downtime
  • [Efficiency Improvement - Maintenance]
    Improved cost forecasting, resource planning and maintenance scheduling

Case Study missing?

Start adding your own!

Register with your work email and create a new case study profile for your business.

Add New Record

Related Case Studies.

Contact us

Let's talk!
* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.