Digital Twin-Driven Rear Axle Assembly Torque Prediction and Online Control

Abstract

During the assembly process of the rear axle, the assembly quality and assembly efficiency decrease due to the accumulation errors of rear axle assembly torque. To deal with the problem, we proposed a rear axle assembly torque online control method based on digital twin. First, the gray wolf-based optimization variational modal decomposition and long short-term memory network (GWO-VMD-LSTM) algorithm was raised to predict the assembly torque of the rear axle, which solves the shortcomings of unpredictable non-stationarity and nonlinear assembly torque, and the prediction accuracy reaches 99.49% according to the experimental results. Next, the evaluation indexes of support vector machine (SVM), recurrent neural network (RNN), LSTM, and SVM, RNN, and LSTM based on gray wolf optimized variational modal decomposition (GWO-VMD) were compared, and the performance of the GWO-VMD-LSTM is the best. For the purpose of solving the insufficient information interaction capability problem of the assembly line, we developed a digital twin system for the rear axle assembly line to realize the visualization and monitoring of the assembly process. Finally, the assembly torque prediction model is coupled with the digital twin system to realize real-time prediction and online control of assembly torque, and the experimental testing manifests that the response time of the system is about 1 s. Consequently, the digital twin-based rear axle assembly torque prediction and online control method can significantly improve the assembly quality and assembly efficiency, which is of great significance to promote the construction of intelligent production line.

Towards Integrated Learning and Assistance Systems: A Framework for Technology Selection and Design

“…In 2022, research on digital twin-driven rear axle assembly torque prediction and online control showed significant improvements in assembly quality and efficiency. This study is particularly relevant for the advancement of intelligent production lines, showcasing how digital twin technology can be effectively utilized for precision and control in assembly processes (Liu et al, 2022). According to Assad et al(2021) demonstrated the application of a Web-based Digital Twin (WDT) architecture to improve sustainability in assembly lines.…”

Structure‐Crack Detection and Digital Twin Demonstration Based on Triboelectric Nanogenerator for Intelligent Maintenance

“…Digital twin is regarded as the best technology to achieve the integration of the physical world and digital space, which possesses the characteristics of virtual-real mapping, data-driven, and so on. [17] By digital twin, maintenance personnel can quickly pinpoint the location of device failures without the necessity of on-site physical inspections, thereby improving maintenance efficiency. Combining TENG and digital twin, Jin et al built a soft-robotic gripper system, which displays virtual robotic manipulation.…”

Multi-step prediction of automobile rear axle assembly torque based on adaptive time series data decomposition hybrid deep learning model

“…In the process of rear axle assembly, assembly torque is a crucial parameter to control and test the connection quality of threaded fasteners, which is the key to realize the quality control of rear axle assembly [2]. There are many factors affecting the assembly torque, such as the matching state between the screw pairs, the difference in material and hardness of the parts, the smoothness and flatness of the surface of the clamped parts, the accuracy and speed of the tightening tool and the tightening process sequence [3]. In the rear axle assembly production line, due to the vibration of the tightening gun, the wear of the fixture and the plastic deformation of the workpiece material, the output torque of the tightening gun reaches the assembly threshold, which affects the assembly quality of the rear axle.…”