Short Title: Int. J. Mech. Eng. Robot. Res.
Frequency: Bimonthly
Professor of School of Engineering, Design and Built Environment, Western Sydney University, Australia. His research interests cover Industry 4.0, Additive Manufacturing, Advanced Engineering Materials and Structures (Metals and Composites), Multi-scale Modelling of Materials and Structures, Metal Forming and Metal Surface Treatment.
2024-12-18
2024-10-25
Manuscript received May 31, 2024; revised June 25, 2024; accepted August 1, 2024; published December 6, 2024
Abstract—Linear-motion robots are commonly used for positioning or part-transfer operations in the automation industry. However, such robot systems may suffer mechanical defects, which compromise the performance of the equipment and generate noise and vibration. Human workers are usually placed in charge of anomaly diagnosis for linear robots; however, the results of such diagnoses vary depending on the skill level of the individual in charge. Many attempts have recently been made to utilize artificial intelligence to diagnose anomalies in industrial devices. This study presents a system that can automatically diagnose linear rail misalignment and ball screw misalignment in linear robots using a Long Short-Term Memory (LSTM)-based deep learning model. The time sequence of the statistical feature parameters obtained from acceleration sensor data was used as the input for the LSTM model. Furthermore, the proposed method was validated experimentally. A comparative test with an artificial neural network using signal feature values as input and a 2D- Convolutional Neural Network (CNN) using a spectrogram as input confirmed that the proposed method is effective at anomaly detection. Thus, this method can be used to diagnose anomalies in industrial robots. Keywords—linear motion robot, long short-term memory, misalignment diagnosis, linear rail misalignment, ball screw misalignment Cite: Chanwoo Moon, "Misalignment Diagnostic System for Linear Motion Robots Using Long Short-Term Memory," International Journal of Mechanical Engineering and Robotics Research, Vol. 13, No. 6, pp. 595-600, 2024.Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.