Condition monitoring of self-driving vehicles

autonomous driving, sensor network, digital twin, condition diagnosis, kingpin

Drivers of conventional vehicles steer them safely from their starting point to their destination, while keeping an eye on the vehicle’s condition. But who monitors the condition of autonomous vehicles when the driver is no longer there? The IdenT research project is developing a concept for determining the condition of trailer components relating to driving-dynamics, as well as of trailer dynamics and the surrounding environment. The automated driving functions of the tractor can use this information to optimize driving tasks and make autonomous driving safe. 

MBS model of the axles in the offline twin IdenT trailer
KingPin with measurement platform for recording the connection forces between trailer and tractor unit

Digital offline twin

The IdenT system is built on a cloud-based data platform that regularly exchanges data between the trailer data network, digital online twin and digital offline twin.

The digital offline twin serves to numerically simulate driving sequences relevant to structural durability and check the plausibility of measurement data, as well as data from an online twin. The central element of the offline twin is a detailed MBS model of a truck trailer in which specific model parameters are subjected to a regular update process using a variety of identification procedures. On the one hand, the aim is to identify time-variant behavior, for example, in the load, as well as wear or defects in chassis components, and to project this onto the simulation model. On the other hand, the numerical simulation of individual driving sequences determines the dynamic behavior of the trailer and thus the component internal loads, from which a prognosis of the condition regarding structural durability can be deduced.

Sensor network

In an autonomous vehicle, what the human truck driver perceives through their eyes, ears and the sensation of driving has to be taken over by sensors. A sensor network is therefore installed in the IdenT trailer, which records the relevant physical quantities and makes them available to the digital twins for interpretation. The focus here is on energy-saving sensor concepts that can be used economically and are highly-reliable when actually in operation. To achieve this, the measurement data is already preprocessed in the sensor node to reduce the volume of data transmitted and minimize the energy required for radio transmission. Furthermore, the minimum requirements that need to be in place for sensor data quality are being investigated to allow such a system to be built in a cost effective but reliable way.

Sensory KingPin

The KingPin is the trailer coupling that links the tractor and trailer. All forces that occur during braking, acceleration or cornering are transmitted through this element. Although the aim is to equip each KingPin with sensors to record important internal forces via the sensor network, an exact force measurement poses a challenge. The IdenT project therefore involves setting up a unique high-precision force measuring device. This will be used to collect measurement data during the road test. The digital twins will be aligned with these data so that these internal forces can be determined by models in the future. The measuring elements used for measuring force on the KingPin involve a measuring platform that records all forces and moments the pin is subject to.

Sponsors and partners 

Funded by the German Federal Ministry for Economic Affairs and Energy

»Today, we’re seeing that the focus of autonomous driving is on the tractor unit. Until now, trailers haven’t been given much consideration. We’re changing that with our IdenT project: We’re convinced that autonomous driving of semitrailer trucks can only be safe and economical if the trailer is included and we’re grateful for the valuable contribution of Fraunhofer LBF to this challenging project.«

Dr.-Ing. Jan-Philipp Kobler, BPW Bergische Achsen

More current projects

Area Of Expertise Future Mobility