A practical and synchronized data acquisition network architecture for industrial robot predictive maintenance in manufacturing assembly lines

Abstract

This manuscript presents a methodology and a practical implementation of a network architecture for industrialrobot data acquisition and predictive maintenance. We propose a non-intrusive and scalable robot signalextraction architecture, easily applicable in real manufacturing assembly lines. The novelty of the paper liesin the fact that it is the first proposal of a network architecture which is specially designed to address thepredictive maintenance of industrial robots in real production environments. All the infrastructure needed forthe implementation of the architecture is comprised of traditional well-known industrial assets. We synchronizethe data acquisition with the execution of robot routines using common Programmable Logic Controllers(PLC) to obtain comparable data batches. A network architecture that acquires comparable and structureddata over time, is a crucial step to advance towards an effective predictive maintenance of these complexsystems, in terms of effectively detecting time dependent degradation. We implement the architecture in areal automotive manufacturing assembly line and show the potential of the solution to detect robot jointfailures in real world scenarios. The architecture is therefore specially interesting for industrial practitionersand maintenance personnel. Finally, we test the feasibility of using one-class novelty detection models forrobot health status degradation assessment using data of a real robot failure. To the best of our knowledge,this is the first contribution that uses robot torque signals of a real production line failure to train one-classmodels.