Online Process Monitoring Based on Proprioceptive Signals for Robotic Grinding
- 19 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-14
Abstract
Actual robotic grinding depth is difficult to control due to the robot and workpiece’s weak rigidity. The online monitoring of the robotic grinding state is urgently needed for suppressing abnormal conditions and improving surface quality. Previous methods heavily relied on various additional sensors. Multi-sensor proprioceptive signals are not effectively used. Recently, data-driven methods have been used in machining monitoring. However, enormous samples with high costs are required for the training of the deep learning-based monitoring model. This article proposes a proprioceptive signal-based online process monitoring method for robotic grinding. First, a multi-sensor information fusion approach based on velocity synchronous linear chirplet transform (VSLCT) converts the proprioceptive current signals to the fused time-frequency (TF) images. It extracts the intrinsic features of non-stationary signals without user interventions. Second, the Mix-up data augmentation approach derived from the constrained convolutional autoencoder (CCAE) enhances the machining dataset with a better sample generation quality. Third, a residual convolutional neural network (CNN) for classification is designed to complete the grinding monitoring task. Finally, the robotic grinding experiments demonstrate higher classification performance by up to 99.69% under laboratory machining conditions. In addition, the suggested approach performs better under various noises and small training-set proportions than other advanced methods.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB4700302)
- NSFC-Shenzhen Robot Basic Research Center (U2013204)
This publication has 37 references indexed in Scilit:
- Attention mechanism and mixup data augmentation for classification of COVID-19 Computed Tomography imagesJournal of King Saud University Computer and Information Sciences, 2022
- Surface roughness prediction in robotic belt grinding based on the undeformed chip thickness model and GRNN methodThe International Journal of Advanced Manufacturing Technology, 2022
- Intelligent monitoring of multi-axis robots for online diagnostics of unknown arm deviationsJournal of Intelligent Manufacturing, 2022
- Machining quality monitoring (MQM) in laser-assisted micro-milling of glass using cutting force signals: an image-based deep transfer learningJournal of Intelligent Manufacturing, 2021
- RCSMOTE: Range-Controlled synthetic minority over-sampling technique for handling the class imbalance problemInformation Sciences, 2021
- FaultFace: Deep Convolutional Generative Adversarial Network (DCGAN) based Ball-Bearing failure detection methodInformation Sciences, 2021
- Modelling and monitoring of abrasive finishing processes using artificial intelligence techniques: A reviewJournal of Manufacturing Processes, 2020
- An online belt wear monitoring method for abrasive belt grinding under varying grinding parametersJournal of Manufacturing Processes, 2020
- A transfer convolutional neural network for fault diagnosis based on ResNet-50Neural Computing and Applications, 2019
- On-line chatter detection in milling using drive motor current commands extracted from CNCInternational Journal of Machine Tools and Manufacture, 2018