Fleet monitoring IoT solution: improving driving performance, safety + efficiency.

Fleet Monitoring IoT solution: understand truck health + performance through fleet monitoring.

The solution

Helping fleet managers to overcome these issues requires a combination of near real-time (CANBus, OBD-II and GPS) data, external mapping and maintenance data, and clever algorithms to help pin-point those drivers or vehicles that need attention. For example, we developed a driver efficiency metric, which combined vehicle engine and transmission data with GPS information and fuel prices.

Our Fleet Monitoring IoT solution, built on our all-in-one data, AI + IoT platform, enables truck manufacturers and those responsible for fleet monitoring and management to focus their efforts on improving driver safety, decreasing spend on fuel and maintenance, and reducing overall vehicle downtime.

Defining what data to collect is critical
To develop the new data capture functionality, Rayven firstly investigated the optimal process for extracting data from truck telematic systems. After investigation with the telematics supplier and vehicle manufacturers, we found that extracting data from each vehicle directly via 4G to the cloud was the best way to send data to ensure the minimum loss of data from the trucks to the cloud. This would allow for data to be collected that records:

1. Brake usage - counts and overall distance
2. Clutch usage and gear changes
3. RPM and gear usage
4. Trip speeds and idle times
5. Engine status
6. DEF (e.g. AdBlue) level
7. Coolant temperature
8. Coast distance
9. Fuel consumption in litres and dollars.

Initial goals of the Fleet Monitoring IoT solution
The first goal of this solution was to connect the thousands of trucks to the Rayven cloud and ensure data quality and integrity by providing the following abilities to:

1. Monitor critical operational truck data received from telemetry via a web-based system
2. Define business logic to the application in order to meet the business objectives
3. Provide alarm and alert notifications via email or SMS messages
4. Collect enough historical data to enable the ability to test different logic to diagnose faults
5. Provide the right dashboard to the right user with the right insights across multiple fleets and truck makes
6. Test the application, making sure all of the above goals are met, based on the below solution architecture.

Before go-live, we tested four critical aspects of the Fleet Monitoring IoT solution:

Security
Our integrated data, AI + IoT platform is built with security as a top priority and our proprietary security architecture ensures that data is secure at all points of the environment.

The Fleet Monitoring IoT solution includes data encryption in transit from device-to-cloud, as well as device authentication; security (Bearer) tokens; SSL, AES and RSA encryption; as well as additional device security checks done via automated polling.

Connectivity
Once all the vehicle telemetry was connected and data was flowing via 4G to the cloud through a secure and encrypted transmission path, work was done to test back-filling data which was saved on the edge when the transmission of data wasn’t possible in remote areas.

Data integrity
To ensure the data we being received by our integrated data, AI + IoT platform was current, it was necessary for us to compare the telemetry data with the dashboards and to construct functionality to back-fill data in the event that communication was ever lost. This process is important to ensure data integrity, so that sound business decisions could be made by fleet managers.

Industrial data science
The objective of exploratory data analysis was to create a predictive maintenance machine learning data model, which included:

1. Fleet comparison of the maintenance status of all trucks in the fleet
2. The contribution of hauled-mass to the need for maintenance
3. Alerts and automated reporting of trucks most in need of maintenance
4. Overall fleet health and performance insights
5. Event management of maintenance activity.

What’s next?

We continue to add vehicles to the Fleet Monitoring IoT solution and work on improving on our maintenance forecasting capabilities. In addition, we plan to add maintenance history records to improve our predictive maintenance modelling.