Jul 15, 2022
No image
Completed
Predictive Maintenance Solution for EV Charging Company
$10,000+
4-6 months
United States
2-5
Service categories
Service Lines
Artificial Intelligence
Big Data
Cloud Consulting
Domain focus
Automotive
Energy & Utilities
Challenge
After years of successful collaboration on software solution development, the global company specializing in producing EV charging station management solutions has reached out to us to solve the business challenge of maintaining their charging stations in top condition and reducing downtimes. Together, we agreed on building an ML-powered solution for predictive maintenance (PdM) that should allow the company to mitigate the risk of the EV chargers breaking down abruptly.
After years of successful collaboration on software solution development, the global company specializing in producing EV charging station management solutions has reached out to us to solve the business challenge of maintaining their charging stations in top condition and reducing downtimes. Together, we agreed on building an ML-powered solution for predictive maintenance (PdM) that should allow the company to mitigate the risk of the EV chargers breaking down abruptly.
Solution
The Intelliarts team did detailed analysis of historical data received from EV chargers via OCPP protocol to get insights into how the customer could automate the charging station health state labeling. We also researched ways to improve the state diagnosis data quality and the data missing to build the PdM solution. The anomaly detection analysis helped us better understand which anomaly behavior usually results in the EV charger outages
Based on the results of the research phase, we instructed the company on additional raw data to be collected; what format to store this raw data in to provide predictive power to ML models; how to automate data labeling; and how to build proper cold storage on top of AWS S3 to preserve massive amounts of historical data for the future PdM solution
The Intelliarts team did detailed analysis of historical data received from EV chargers via OCPP protocol to get insights into how the customer could automate the charging station health state labeling. We also researched ways to improve the state diagnosis data quality and the data missing to build the PdM solution. The anomaly detection analysis helped us better understand which anomaly behavior usually results in the EV charger outages
Based on the results of the research phase, we instructed the company on additional raw data to be collected; what format to store this raw data in to provide predictive power to ML models; how to automate data labeling; and how to build proper cold storage on top of AWS S3 to preserve massive amounts of historical data for the future PdM solution
Results
Based on the specific recommendations from our data science team, the software development team proceeded with implementing the data collection pipeline, building storage for raw data, and collecting the missing data. As soon as the customer collects additional EV charger diagnosis data in the suggested format, we plan to move forward with creating the PdM solution we initially planned.
Based on the specific recommendations from our data science team, the software development team proceeded with implementing the data collection pipeline, building storage for raw data, and collecting the missing data. As soon as the customer collects additional EV charger diagnosis data in the suggested format, we plan to move forward with creating the PdM solution we initially planned.