Ruxu Du

Ruxu Du

Auto-generated profile, based on publicly available information

Ruxu Du

Guangzhou Janus Biotechnology Co., Ltd., Guangzhou 511400, China

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 June 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
GYGuo Yang
Guo Yang
YZYong Zhong
Yong Zhong
Lie YangLie Yang
Lie Yang
HTHui Tao
Hui Tao
JLJianying Li
Jianying Li
RDRuxu Du
Ruxu Du
Harmonic drive is the core component of the industrial robot, and its fault diagnosis is crucial to the reliability and performance of the equipment. Most machine learning methods achieve good results based on the assumption of data balance. However, the scarce fault data of harmonic drive is difficult to collect, resulting in various imbalanced health status samples, which has an adverse effect on fault diagnosis. In this article, we propose a data generation method based on generative adversarial networks (GANs) to solve the problem of data imbalance and utilize the multiscale convolutional neural network (MSCNN) to realize the fault diagnosis of the harmonic drive. First, the data collected from three vibration acceleration sensors are preprocessed by fast Fourier transform (FFT) to obtain the frequency spectrum of the vibration signal. Second, multiple GANs were adopted to generate various fault spectrum data and the data selection module (DSM) is elaborately designed to filter and purify these data. Third, the filtered generated data will be combined with the real data to form a balanced dataset, and then the MSCNN is used to achieve multiclassification of the health status of the harmonic drive. Finally, the experiments have been implemented on an industrial robot vibration test bench to validate the effectiveness of our approach. The results have shown the fault multiclassification accuracy as 98.49% under imbalanced fault data conditions, which outperforms that of the other compared methods.

13 December 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
IMImran Mohsin
Imran Mohsin
KHKai He
Kai He
RTRaymond Kai-yu Tong
Raymond Kai-yu Tong
RDRuxu Du
Ruxu Du
Surface polishing is required in many manufacturing sectors. Currently, it demands a large amount of manual work, which is time-consuming, error-prone, and costly. Additionally, it creates hazards for the workers as it may result in many deadly respiratory diseases. Robotic polishing is the solution to these problems. It can improve productivity, eliminate the defects, and provides consistent product quality. In this paper, an effective approach is presented for the robotic polishing of the complex curved surfaces. The key part of the presented method is the tool path planning with controlled force and polishing parameters optimization evaluated using design of experiments (DOE). The tool path planning is aimed at improving the surface quality and the contact area per path. The constraints of joint limits and productivity are also considered. Moreover, its jerk avoidance strategy allows the robot to move swiftly while ensuring a smooth trajectory. The presented method is verified for the polishing of an eyeglass frame. A considerable improvement of 90% on the average roughness is achieved with the maximum acceptable roughness set at 0.02 µm. The polishing operation takes just 79 secs and the average glossiness of 76 G is achieved on the final product along with the successful elimination of scratches on the surface.

23 January 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
IMImran Mohsin
Imran Mohsin
KHKai He
Kai He
RTRaymond Kai-yu Tong
Raymond Kai-yu Tong
Feifei ZhangFeifei Zhang
Feifei Zhang
RDRuxu Du
Ruxu Du
Surface finishing and polishing are important quality assurance processes in many manufacturing industries. A polished surface (low surface roughness) is linked with many useful properties other than providing an appealing gloss to the product, such as surface friction, electrical and chemical resistance, thermal conductivity, reflection, and product life. All these properties require an efficient polishing system working with the best machining parameters. This study analyzed the effects of the different input polishing parameters on the polishing efficiency and torque in the robotic polishing system for the circular-shaped workpieces (such as ring, cylinder, sphere, cone, etc.) by using the Taguchi method and analysis of variance (ANOVA). A customized rotatory passive gripper is designed to hold the watch bezel during polishing. Under the design of experiments (DOE) technique, Taguchi’s L 18 array is selected to find the optimized process parameters for polishing efficiency (based on surface roughness) and torque. Experimental results with the statistical analysis by signal-to-noise ratio and ANOVA (95% confidence level) confirms that the polishing force and tool speed are the most influencing parameter for polishing efficiency in the system. Linear regression equations are modeled for the polishing efficiency and torque. Finally, a confirmation test is conducted for the validation of the experimentation results against actual results.

16 September 2020 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
GYGuo Yang
Guo Yang
YZYong Zhong
Yong Zhong
Lie YangLie Yang
Lie Yang
RDRuxu Du
Ruxu Du
Harmonic drive is a key component in industry robot. Its complex design is highly sensitive to the manufacturing and assembly errors. Even a small error could cause excessive vibration jeopardizing the performance of the robot. Moreover, the vibration is dependent on the operation conditions. As a result, it is necessary to carry out a comprehensive test to detect possible manufacturing and assembling faults. This paper presents an intelligent approach that can automatically identify the different health conditions of harmonic drives. First, the acquired data from multiple acceleration sensors are cascaded in sequence after several preprocessing steps. Then, the multiscale convolutional neural network (MSCNN) architecture is used for disposing the inherent multiscale characteristics of the harmonic drive vibration signal, which can simultaneously perform multiscale feature extraction and classification. Finally, a large number of experiments were conducted on a real industrial robot vibration test platform to evaluate our approach. Based on the experiment results, the fault detection classification accuracy is 96.79%, which is higher than the other compared methods. This demonstrates that the presented method is effective for shop floor applications.

10 May 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
GYGuo Yang
Guo Yang
HTHui Tao
Hui Tao
KWKai Wu
Kai Wu
RDRuxu Du
Ruxu Du
YZYong Zhong
Yong Zhong
The existing fault diagnosis of harmonic drives is difficult to deploy vibration sensors, and the diagnosis accuracy is insufficient only using current signal. Therefore, we propose an intelligent fault diagnosis method using a multimodal collaborative meta network (MCMN) with severely missing modality. First, multimodal data of the harmonic drive were collected to analyze. Second, a feature reconstruction network is used to achieve a unified model to handle missing modalities in testing. Besides, the uncertainty assessment is used as a feature regularization network to overcome data bias. Third, the inference of the meta-learning is used to obtain the generated weights, and carried out the joint optimization. Finally, MCMN is optimized by using the approximate lower bound of Monte Carlo. Experimental results show that the accuracy of MCMN is 93.75% in the case of full-modalities training data and the severely missing modalities testing data, which is better than the existing method.

12 July 2012 in Journal of Mechanical Science and Technology
Verified
Journal Article
Open access
PDF file
LXLonghan Xie
Longhan Xie
RDRuxu Du
Ruxu Du
It is known that the human body contains rich chemical energy, part of which is converted to mechanical energy of up to 200W when in motion. Therefore, it is ideal to harvest human body kinetic energy to power mobile electronic devices. This paper presents an energy harvester to unintentionally extract human kinetic energy and directly convert it to electricity, which can serve as a power source for portable electronics. The proposed harvester mainly consists of an eccentric rotor made of permanent magnet, electric steel and coils as stator. The eccentric rotor, as a simple pendulum, acts as the kinetic energy harvester, which can absorb the motion from the human body during walking. With the permanent magnets on the rotor, the moving rotor can produce a changing magnetic field, where electric coils can induce electricity. A torsion spring is also added onto the rotor such that the harvester works even when placed on a horizontal plane where the gravitational acceleration fails. The electromagnetic and kinematical model is built to analyze the performance. Numerical analysis and system optimization are also conducted. Simulation shows that the harvester with 40mm diameter and 50g weight, worn on the wrist, can produce dozens of milliwatts of electricity during normal walking.