Industrial robots play an increasingly important role in a growing number of fields . The breakdown of a single robot has a negative impact on the entire process . 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 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 also yields a sharper deviation from the training model in case of a mechanical issue change and thus detects mechanical issues with higher confidence . The algorithm can be used to detect mechanical problems with more confidence. The proposed algorithm can also distinguish between the training and mechanical conditions with higher levels of the training of a trained model in the new operation, according to the proposed algorithm on a real world datasets . The proposed un-supervised learning algorithm is used to identify mechanical conditions in the context of the new data, such as the algorithm .

Links: PDF - Abstract

Code :

None

Keywords : algorithm - mechanical - model - proposed - operation -

Leave a Reply

Your email address will not be published. Required fields are marked *

error

Enjoy this blog? Please spread the word :)