article · Technologies
Modern manufacturing relies increasingly on predictive maintenance to avoid costly equipment breakdowns. Traditional monitoring techniques frequently struggle to detect impending faults early enough to prevent disruptions. To tackle this, a predictive maintenance framework was created using an enhanced long short-term memory deep learning model to forecast machine failures. The system combines real-time measurements of current, voltage, and temperature calibrated using ultra-sensitive whispering gallery optical mode sensors, which reliably detect minute environmental changes. When tested on data gathered from two humanoid robots, GUCnoid 1.0 and ARAtronica, the model achieved high accuracy with a coefficient of determination of 0.99. It successfully predicted machinery faults up to ten minutes in advance, offering a practical approach to reduce downtime and improve operational productivity in automated precision robotics manufacturing.
Unplanned equipment breakdowns in automated manufacturing lead to expensive delays and halted production lines. By predicting failures ten minutes before they occur, this framework provides operators with a crucial window to intervene. Using ultra-sensitive optical sensing alongside deep learning helps ensure robotic systems remain reliable, making industrial automation safer and more cost-effective.
This framework could enable predictive maintenance tools for automated manufacturing plants and developers of precision robotics components. Potential users include robotics manufacturers seeking to avoid unexpected downtime during production. The research appears to be applied and tested, having been validated on two physical humanoid robots, but further engineering would be required to package it for wider industrial use.
AI-generated from the published abstract. Always read the original work before citing.
Industry 4.0 is transforming predictive failure management by utilizing deep learning to enhance maintenance strategies and automate production processes. Traditional methods often fail to predict failures in time. This research addresses this issue by developing a time-to-fault prediction framework that utilizes an enhanced long short-term memory (LSTM) model to predict machine faults. The proposed method integrates real-time sensor data, including current, voltage, and temperature calibrated via ultra-sensitive optical sensing technologies based on the typical whispering gallery optical mode (WGM) to create a robust dataset. Due to the high-quality factor that these sensors exhibit, any minute change on the surrounding medium will makes a significant change on its transmission spectrum. The LSTM model trained on these data demonstrated rapid and stable convergence, outperforming other deep learning techniques with a mean absolute error (MAE) of 0.83, a root mean squared error (RMSE) of 1.62, and a coefficient of determination (R2) of 0.99. The results show the superior performance of LSTM in predicting machine failures early in real-world environments within 10 min lead time, improving productivity and reducing downtime. This framework advances smart industries by improving fault prediction in manufacturing precision robotics components, demonstrated through two humanoid robots, GUCnoid 1.0 and ARAtronica.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/technologies13020042
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
