Self-Supervised Transfer Learning for Remote Wear Evaluation in Machine Tool Elements With Imaging Transmission Attenuation
- 28 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (13) , 23045-23054
Abstract
The Industrial Internet of Things (IIoT) has significantly advanced traditional industrial systems, especially in facilitating remote monitoring and predictive maintenance for computer numerical control (CNC) machines. Ball screw drives (BSDs), crucial in CNC machining, require regular upkeep, often challenged by environmental influences and the limitations of wired sensor-based diagnostic procedures. Wireless sensors offer a cost-effective solution but struggle with data integrity during transmission, impacting remote wear evaluation of BSDs. Current recovery methods are not always adequate, often relying on extensive historical data and suffering from accumulating errors. Addressing these limitations, a novel self-supervised transfer learning (SSTL) model is proposed for remote wear assessment of machine tool components. This model integrates an image capture module into CNC surveillance systems and employs a LocalMIM module, which is pretrained and fine-tuned to adapt to various domains, especially for image quality deterioration during data transmission. The SSTL model is designed to function effectively despite significant pixel data loss, eliminating the need for historical data for image restoration. This innovation is particularly adept at evaluating wear in environments with compromised image transmission, providing a robust predictive maintenance strategy for BSDs that is less affected by data loss, aiding a pressing industrial requirement for consistent and dependable remote monitoring solutions.Keywords
Funding Information
- National Natural Science Foundation of China (52105111)
- Guangdong Basic and Applied Basic Research Foundation (2022A1515010859)
- Guangdong Provincial Science and Technology Special Fund Project (STKJ2021171)
- Shantou University (STU) Scientific Research Initiation (NTF21029)
- Natural Science Foundation of Sichuan Province through (2023NSFSC0861)
- Original Innovation Grant Project of Nuclear Power Institute of China through (YF23051)
This publication has 32 references indexed in Scilit:
- Context Autoencoder for Self-supervised Representation LearningInternational Journal of Computer Vision, 2023
- Deep learning for missing value imputation of continuous data and the effect of data discretizationKnowledge-Based Systems, 2022
- Impact of duration and missing data on the long-term photovoltaic degradation rate estimationRenewable Energy, 2022
- An automatic speed adaption neural network model for planetary gearbox fault diagnosisMeasurement, 2021
- A threshold self-setting condition monitoring scheme for wind turbine generator bearings based on deep convolutional generative adversarial networksMeasurement, 2021
- Prognostic study of ball screws by ensemble data-driven particle filtersJournal of Manufacturing Systems, 2020
- Remaining useful life prediction of machinery under time-varying operating conditions based on a two-factor state-space modelReliability Engineering & System Safety, 2019
- Remaining useful life estimation in aeronautics: Combining data-driven and Kalman filteringReliability Engineering & System Safety, 2019
- Bearing remaining useful life prediction based on deep autoencoder and deep neural networksJournal of Manufacturing Systems, 2018
- Design and realization of an energy autonomous wireless sensor system for ball screw fault diagnosisSensors and Actuators A: Physical, 2017