Case study: Analysis of recurring problems with vehicle batteries

Goals

Early detection of impending problems with the power system vehicle

Root cause analysis for emerging warnings about large voltage differences on vehicle batteries

Results

A predictive model has been developed that allows detection of problems with batteries up to 2 hours before the appearance of warnings in the system bus

In a 1.5-month test period 35 of 36 cases of the tested problem (97% effectiveness)

Challenge

The subject of the work was to investigate the problem of repeated SPN104000 and SPN106000 errors on batteries (warning of large voltage differences on batteries). The challenge was to develop a predictive model that would enable early detection of anomalies leading to the above-mentioned errors. In addition, based on the results of the work, Root Cause Analysis (RCA) had to be investigated, identifying signals showing anomalous behavior in periods before the errors appeared.

Solution

A predictive model was developed that allowed early detection of anomalies leading to the appearance of the mentioned errors. In addition, based on the results of the work, Root Cause Analysis (RCA) was carried out, identifying signals showing anomalous behavior in periods before the appearance of errors.

Benefits

The developed predictive model showed more than 97% efficiency in predicting the problem under study (35 out of 36 cases were detected). The average time horizon for the predicted errors was about 45min. At the same time, during the studied period, the model detected 12 additional anomalous periods, which, according to the analysis, show similar signal patterns.

Early information about anomalies in the vehicle power system

Possibility to prepare a replacement vehicle

Additional root cause information for technologists and specialists

About company

ReliaSol is a company established in response to the growing need to increase the efficiency of machines and installations in industry.

We provide software and services that accelerate the digital transformation process. The applications we create combine real data from machines, sensors, event reports and automate drawing conclusions. The result of their work is data visualization, event prediction and monitoring of the optimal operating range of machines and entire production lines.

We will be happy to answer your questions

Reliability Solutions Sp. z o. o.
ul. Królewska 57, 30-081 Kraków, Polska