The paper proposed a filtering for vibration signals using artificial hydrocarbon networks (AHNs). AHNs are a supervised learning method inspired in organic chemistry in order to simulate the chemical rules involved within organic molecules, representing the structure and behavior of data. The main characteristic is packaging information in modules called molecules. These packages are then organized and optimized using heuristic mechanisms based on chemical energy. In that sense, a AHNs-based filtering is established to cancel noise from vibration signals. The presented method has been applied to perform the extraction of fault signals, and the efficiency of the method has been verified using practical examples.