Virtual Sensors based on CAN bus signals

thumbnail_can-bus

Abstract

Sensors in general are physical hardware devices that make use of physical or chemical effects in order to measure a physical quantity like temperature, pressure, weight, distance, force, torque, speed and many others. In some cases, such sensors are too complex to implement and operate, or too costly in larger series.

Virtual sensors are software-based. Via machine learning algorithms, they calculate a precise estimation of the targetted physical quantity out of other already available signals. In other words, virtual sensors are the result of data extraction and sensor fusion.

This article explains how virtual sensors can use the data from a vehicle’s CAN-bus to yield deep insights into the behavior of the vehicle’s subsystems like steering, drivetrain, tires, brakes, battery, electronics and more. We provide stunning results for a physical quantity that is tricky to physically measure otherwise: the dynamic drive shaft torque.

Read the full article on Medium.com

Get in touch with us to discuss about your application !

Contact

+49 (0)6151 3844614

contact@compredict.ai

COMPREDICT GmbH

Rheinstraße 40-42

64283 Darmstadt, Germany