Skip to main content
search results
Sorry, but nothing matched your search terms. Sorry, but nothing matched your search terms. Sorry, but nothing matched your search terms. Désolé, mais rien ne correspond à vos critères de recherche. Désolé, mais rien ne correspond à vos critères de recherche. Entschuldigung, wir haben nichts zu diesem Suchbegriff gefunden.
Sorry, but we cannot handle your search query now. Please, try again later! Sorry, but we cannot handle your search query now. Please, try again later! Sorry, but we cannot handle your search query now. Please, try again later! Désolé, mais nous ne pouvons pas traiter votre demande. Veuillez réessayer plus tard ! Désolé, mais nous ne pouvons pas traiter votre demande. Veuillez réessayer plus tard ! Entschuldigung, wir können Ihre Suchanfrage zurzeit nicht bearbeiten. Bitte versuchen Sie es später noch einmal.
Search suggestions

case study

Making predictive maintenance chargers and high-voltage batteries for EVs a reality

Share on linkedin
Share on twitter
Share on facebook
Share on print
Key Facts Predictive Maintenance

Challenge : Harnessing auto parts’ data to derive new value

To maintain its excellent brand reputation as an innovator, our client, a global automaker and provider of e-mobility solutions, wanted to launch a new service: predictive maintenance for on-board chargers and high-voltage batteries for EVs.

The client was sending a lot of data (physical, vehicle, emergency call etc.) to a cloud-based platform: it asked Expleo to use this information to predict breakdowns. However, usual time-series and signal processing tools were unusable due to their low sampling rate.

Solution : Out-of-the box thinking

Using its automotive engineering skills in addition to data science, Expleo created a new methodology to use this information to classify failure. Expleo’s data experts designed a Machine Learning (ML) pipeline (Kernel) based on those weak signals to predict if/when the battery will soon break down, with nearly 100% accuracy for on-board chargers’ failure predictions and a similar outcome for batteries.  

Outcome : Mission accomplished

Expleo found an alternative, and innovative, way to define which data can be used to classify failure. To perform this task, Expleo used its automotive engineering skills in addition to data science, combining a physical and data approach: it used error codes to identify the symptoms of failure.

Its global methodology to predictive maintenance is efficient – it will save time and reduce costs. It is also an intelligible way to perform predictive maintenance: since it is based on error codes, we can explain why the algorithm is predicting failure or not and correct the issue (interpretability).

Ultimately, predictive maintenance services will enable customers to have their vehicle serviced if needed rather than risk a breakdown on the road, increasing their satisfaction and thus our client’s brand reputation. 

Client benefits

  • New E-Mobility & Predictive maintenance offering 
  • Ready for production source code 
  • Global methodology for predictive maintenance
  • Vehicle architecture does not need to be altered
  • Final customer satisfaction can be increased by the provision of new and value-adding services 

CUSTOMER SUPPORT & MAINTENANCE

Predictive maintenance

Based on vast amount of data recordings, Expleo offers predictive maintenance support enabling our clients to time their maintenance operations in advance and reduce their maintenance costs.

Let's talk

Like to find out more information on Expleo?

Please fill in the form below and we will get in touch with you shortly.

Thank you.

Thank you for your interest in Expleo. We have received your enquiry and one of our consultants will get in touch with you as soon as possible.