This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Online monitoring of mechatronic systems and production environments helps operators to steer their processes into regions of optimal performance. Filtering methods, such as the Kalman filter, emerge in this setting thanks to their ability to process sensor data in real-time. Extensive engineering efforts are required to attain a behavioral model on the system dynamics for this filter. What is more, the model needs updating when facing varying conditions that are prevalent in mechatronic and production systems during operation. At the same time, datadriven methods excel in adapting models to match measurements without relying heavily on expert knowledge, but suffer from main drawbacks such as the lack of interpretability and the batchwise approach. This paper proposes a novel methodology relying on two key ideas. First a dual extended Kalman filter allows to jointly estimate and adapt model parameters in an online setting. Secondly, within this filter a hybrid model is embedded that depends on physics-based and data-driven parameters that are being updated, leading up to increased prediction capabilities and hence improved estimations on the state of the system. We evaluate the presented hybrid dual Extended Kalman filter on a cam follower system where it shows the ability to learn the cam shape during operation whilst tracking the state with an increased accuracy of more than 22% compared to other filtering techniques.