Data and predictive maintenance to optimise operational efficiency and service quality at Keolis

How Keolis harnesses data and predictive maintenance to optimize operational efficiency and service quality

Data and predictive maintenance to optimise operational efficiency and service quality at Keolis
Share on
PostedNOV. 1, 2022
Words byKeolis
All the mobility authorities served by Keolis face one key challenge: ensuring the best quality service for passengers. As it expands its use of data and AI, Keolis is delivering concrete solutions to improve the performance of several forms of mobility through predictive maintenance. By significantly reducing vehicle and infrastructure downtime, Keolis is improving the quality of service for passengers.

Helping transit operators improve their planning with predictive maintenance

Can data predict the future? This is what predictive maintenance aims to do. As onboard sensors increase the volume of data being collected and artificial intelligence optimizes the use of data, predictive maintenance is becoming an essential counterpart to traditional preventive and curative maintenance. It enables a more agile approach – continuous and in real time – while limiting the need for expensive curative maintenance operations.

In Boston, for example, trains equipped with sensors record vibrations, measure the temperature of trains and detect door malfunctions. This data is centralized and analyzed in real time by predictive maintenance software. AI thus makes it possible to anticipate potential incidents and take action before they occur.

Another example is the Keolis Group’s Citadis project in Lyon. This portal collects all the operating data of the city’s tramways and uploads it to the server when trams return to the depot. This data then helps the operator anticipate breakdowns and accelerate decision-making.

The result? Firstly, optimized service thanks to repairs and replacements of parts being carried out in advance, thus reducing the risk of vehicles breaking down and bottlenecks developing. Secondly, reduced vehicle downtime and more efficient scheduling of maintenance operations for technicians.

Analysis of maintenance data.

Predictive, preventive, curative: three types of maintenance

Predictive maintenance: This type of maintenance takes place before any breakdown or malfunction occurs and aims to keep equipment in good working order to reduce the risk of incidents or breakdowns. It also guarantees compliance with safety regulations. Predictive maintenance is based on an analysis of the condition of parts, machinery and production equipment.

Preventive maintenance (systematic or conditional): Systematic preventive maintenance is performed at fixed intervals through regular equipment inspections with the aim of replacing components and parts before they wear out. Conditional preventive maintenance consists in monitoring critical indicators concerning the condition of equipment and making any necessary changes to avoid potential malfunctions or breakdowns.

Curative maintenance: This consists simply in repairing an observed breakdown or malfunction.

Maintenance 4.0, which is based on 3 levels, offers a complete and digitalized approach.

Maintenance 4.0 adapted to connected vehicles

This approach relies on connected vehicles that transmit information in real time. For this reason, Keolis has partnered with STRATIO to integrate their remote diagnosis tool into buses and trams. Collaborating with STRATIO makes it possible to provide three levels of maintenance:

- traditional curative maintenance, as needed.

- preventive maintenance based on monitoring several critical indicators to trigger early alerts: engine temperature, battery level and condition, the condition of brakes, etc.

- predictive maintenance using artificial intelligence to anticipate malfunctions before any sign of weakness appears and generate qualified alerts to launch maintenance operations. For example: predicting the end of battery life.

Keolis' partnership with STRATIO has made it possible to integrate remote diagnosis tools into buses and coaches.
© kmg design

The platform allows operators to adopt a comprehensive maintenance 4.0 approach (including all three levels of maintenance) and offers several advantages:

- improved scheduling of technical inspections by anticipating breakdowns and other problems.

- the ability to plan required maintenance operations in advance based on identified warning signs.

- improved efficiency of the entire maintenance process ahead of vehicle inspection.

- reduced vehicle downtime during maintenance.

- optimized equipment lifespan, especially for batteries, which are essential for the growing number of electric vehicles in the bus fleets operated by Keolis.

Digital predictive maintenance to help maintenance technicians

Digitizing predictive maintenance helps to optimize the operations carried out by maintenance technicians and keep the maximum number of vehicles available for use.

In Dubai, for example, Keolis has set up a remote assistance system that allows an expert to take control of a technician's mobile device in the event of a problem.

In Australia, Keolis Melbourne has installed sensors on the pantographs of its trams to measure wear on the overhead contact lines (OCL) and provide geolocated data to maintenance teams. This automated process makes operations safer and helps technicians avoid dangerous situations, especially during the night. It also allows these measurements to be performed during the day, without interrupting passenger service.

The digitized forms used by several Keolis subsidiaries also allow technicians to take readings directly on a tablet and access the necessary technical documentation and maintenance data for the equipment. These applications allow technicians to focus on tasks with higher added value, such as analyzing reports or optimizing the alerts that trigger predictive maintenance operations.

The digitalization of predictive maintenance optimizes and secures the interventions of maintenance technicians, and improves the availability of vehicles.

In Australia, Keolis Melbourne has installed sensors on the pantographs of its streetcars to provide geolocation data to maintenance teams.