A Method for Health Indicator Evaluation for Condition Monitoring of Industrial Robot Gears

Abstract

Condition monitoring of industrial robots has the potential to decrease downtimes in highly automated production systems. In this context, we propose a new method to evaluate health indicators for this application and suggest a new health indicator (HI) based on vibration data measurements, Short-time Fourier transform and Z-scores. By executing the method, we find that the proposed health indicator can detect varying faults better, has lower temperature sensitivity and works better in instationary velocity regimes compared to several state-of-the-art HIs. A discussion of the validity of the results concludes our contribution.

ROS-Based Condition Monitoring Architecture Enabling Automatic Faults Detection in Industrial Collaborative Robots

“…Raouf et al in [9] proposed prognostic health management for the robotic rotate vector reducer using external sensors mounted on the robot and managed using an embedded system to electrical MCSA for mechanical fault detection. Nentwich et al proposed a new method to evaluate the health indicators for industrial robots and suggest a new health indicator (HI) based on vibration data measurements [10]. In Ref.…”

“…For instance, some papers present results in applications where the system is used in repetitive tasks [5,11,22,23] (e.g., machine tending, pick and placing, etc.) or average values are considered to take into account the speed and load variability on similar applications [14] or in some cases, the isolated movement of a single axis is performed during measurement [10,24]. Furthermore, because most of them are applied to standard industrial robots used in repetitive tasks and not to collaborative robots generally used for flexible manufacturing.…”

“…In particular, we evaluate the dominant frequencies peaks, the wavelet entropy, and the signal kurtosis. These three HIs have been chosen according to [10] where the most effective HIs were derived from several review papers regarding the CM gearbox and bearing CM [28,29]. However, the definition of the best methodology to analyze data is beyond the scope of this work, since in fact, the best methodology to choose depends on which kind of fault we want to identify.…”

A Combined Anomaly and Trend Detection System for Industrial Robot Gear Condition Monitoring

“…The identification of suitable data acquisition systems or the selection of features is not considered in this publication. This is e.g., considered in [3]. Therefore, the presented work builds up on assumptions derived from this publication.…”

“…Such a system must be able to detect anomalies and trends in the health indicator data reliably. Anomalies in the data can be related to faults that occur abruptly (e.g., breaking of a gear tooth) and trends can be an indicator for increasing wear [3]. The occurrence of such events should be presented to the maintenance crew while showing only few false alarms.…”