Last updated on September 19th, 2023


Failure prediction analytics for Nissan


  • Build a vehicle component failure prediction system
  • Display real-time status of engine health and predicted time to failure


The difficulty in predicting exact rate of component degredation made it challenging to accurately predict driving distance until engine failure.

Key Results

A prototype of predictive failure analytics was built and demonstrated

Drivers were able to view real-time engine health and predicted distance to failure


When an older vehicle has high mileage, its parts will eventually need significant maintenance or replacement. Nissan wanted to monitor the condition of critical vehicle parts so they could notify their customers how much longer they could drive before a possible breakdown.

Nissan sought out Acerta’s experience building on-road anomaly detection systems. This experience has given Acerta an edge in understanding the data and machine learning algorithms required to create a prototype.

The project was undertaken with funding from the Ontario Vehicle Innovation Network.

Solution Process

In our prototype, we designed a model to determine engine condition and estimated the remaining driving distance to engine failure. We monitored critical engine components: the air injector, air by fuel sensor, and air flow meter. 

Previous attempts to develop similar technology had used two different methods: one using mechanically-driven “dynatest” data and one using an AI-driven model with only on-road data.  

In this project, we combined both data sets to predict the remaining distance a vehicle could drive before a failure would occur. This was especially challenging because classical approaches could not predict the exact rate of component degradation. To counter this, additional data was gathered from a fleet of pre-production vehicles driven by Nissan employees.  


A prototype of the engine failure detection system was constructed and installed in a Nissan Rogue. The project culminated in an on-road demonstration where stakeholders gathered in Waterloo, Ontario, to witness the technology firsthand.


“Nissan recognizes the strength in Ontario’s thriving automotive ecosystem combined with expertise in AI and manufacturing. We worked with Acerta to accelerate the development of this new technology for our vehicles to bring future tangible benefits to our customers, and we’re excited to continue our partnership.”
Kazuhiro Doi
Kazuhiro Doi
Nissan Corporate Vice President and Alliance Global VP Research Division
"We were excited to develop predictive analytics for Nissan to improve passenger safety, reduce unexpected repairs, and help Nissan customers save money. We’re grateful for the support that this project received from the Government of Ontario through OVIN. "
Greta Cutulenco
Greta Cutulenco
Acerta Analytics CEO and Co-founder

Use AI and machine learning to solve your complex data problems.

How can we Help?

Contact Info

Automate root cause analysis and predict defects in real time

How is that possible?