News

Telematics unit

Telematics unit with digital twin

Why?

- Operators do not have a comprehensive overview of the state of their fleet
- In the best case, they have big data, but it is not processed
- We feel that carriers want to know where their money is going, but they do not yet have the tool

What do we offer?

We know immediately how the bus is doing thanks to Digital Twin.
Real-time calculations directly in the device. We work with data! they are not dead. Collection of GPS, CAN and accelerometric data.
Monitoring a new variable? Software change, hardware remains the same.

- An accelerometer located on the axle senses significant impacts from the road
- The unit then counts impacts that exceed a set limit
- Monitoring battery health reveals which scenarios are not good for it
- Why it is important to monitor battery health
Battery health prediction model is based on accurate simulations

Security

- The unit is directly connected to the local network and to the 5G network via IPv6
- Remote access to the device requires a connection to the local network via VPN
- Security is ensured using UFW (Uncomplicated Firewall)
- Only outgoing communication to the 5G network is allowed
- Full communication within the internal network is allowed
- Access via SSH is protected by authentication using a public and private key pair
- Messages sent to Microsoft Azure IoT Hub are secured using: MQTT, TLS, SAS tokens inside the connection string
- This setting ensures secure communication within the local network and towards the cloud
- Communication between Azure and the server takes place via a secure VPN, with data stored in a password-protected database
- A reverse proxy runs on the front-end, which masks the internal architecture and ensures the hiding of backend servers

AI Implementation
= Intelligent Platform for Optimizing Energy Efficiency and Control of Electric Buses

- Project Duration: 3 Years
- Collection of GPS and CAN bus data from serial buses from normal operation
- AI learning with the aim of reducing the energy intensity of electric bus operation through active optimization of driver driving style
- Development of an algorithm with implemented AI

First Phase

- Checking bus drivers and assessing driving economy
- Recommendations for drivers

Second Phase

- Active ECU interventions, control of available power
- Limiting the maximum power of the bus with the idea of saving energy
- The system hands over control to the driver in crisis situations
- The human-machine relationship is the same as, for example, with adaptive cruise control, lane keeping assistant, etc.

Saved energy = longer bus range, improved battery life and thus more economical operation