Domain Adaptation for Robot Predictive Maintenance Systems

TL;DR

This paper introduces an unsupervised transfer learning approach for predictive maintenance in industrial robots, enabling models to adapt to different operations without retraining, thereby reducing false alarms and improving fault detection accuracy.

Contribution

The paper presents a novel transfer learning algorithm that transfers knowledge across different robot operations, eliminating the need for retraining and enhancing fault detection reliability.

Findings

The algorithm effectively distinguishes operation changes from mechanical faults.

It yields sharper deviations for mechanical issues, increasing detection confidence.

Deployment on real datasets confirms improved fault detection performance.

Abstract

Industrial robots play an increasingly important role in a growing number of fields. For example, robotics is used to increase productivity while reducing costs in various aspects of manufacturing. Since robots are often set up in production lines, the breakdown of a single robot has a negative impact on the entire process, in the worst case bringing the whole line to a halt until the issue is resolved, leading to substantial financial losses due to the unforeseen downtime. Therefore, predictive maintenance systems based on the internal signals of robots have gained attention as an essential component of robotics service offerings. The main shortcoming of existing predictive maintenance algorithms is that the extracted features typically differ significantly from the learnt model when the operation of the robot changes, incurring false alarms. In order to mitigate this problem, predictive maintenance algorithms require the model to be retrained with normal data of the new operation. In this paper, we propose a novel solution based on transfer learning to pass the knowledge of the trained model from one operation to another in order to prevent the need for retraining and to eliminate such false alarms. The deployment of the proposed unsupervised transfer learning algorithm on real-world datasets demonstrates that the algorithm can not only distinguish between operation and mechanical condition change, it further yields a sharper deviation from the trained model in case of a mechanical condition change and thus detects mechanical issues with higher confidence.