Meng Rao

Dr. Meng Rao

Department of Mechanical Engineering, University of Alberta, Edmonton, AB, Canada
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
24 March 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Yuejian ChenYuejian Chen
Yuejian Chen
Meng RaoMeng Rao
Meng Rao
Ke FengKe Feng
Ke Feng
GNGang Niu
Gang Niu
Planetary gearbox fault detection is important in terms of life-threatening failure prevention and maintenance optimization. This paper focuses on the representation of the planetary gearbox baseline vibration signals via time series models. Faults can be detected by examining any changes in model residuals or parameters. Varying index coefficient autoregression (VICAR) model is a good option for accurately modeling complex nonlinear data-generating-processes. Applying VICAR to represent nonstationary baseline vibrations from a planetary gearbox under variable rotating speed conditions, the covariate vector can be expanded to include the rotating speed. However, we found that lagged predictors dominate the smooth functions in the expanded VICAR. The inclusion of rotating speed becomes in vain. To cope with this problem, we propose a modified VICAR model that effectively makes use of the rotating speed while retaining the highly flexible nonlinearity modeling capacity of the VICAR model. The modification lies in separating the lagged predictor and rotating speed via independent smooth functions. Parameter estimation and variable selection methods were developed accordingly. An experimental study was conducted which reveals the superiority of the modified VICAR model in comparison with autoencoders, expanded VICAR, and linear parameter varying autoregression models.

17 February 2025 in Mechanical Systems and Signal Processing
Verified
Journal Article
Closed access
CLCuiying Lin
Cuiying Lin
Yun KongYun Kong
Yun Kong
QHQinkai Han
Qinkai Han
Xiantao ZhangXiantao Zhang
Xiantao Zhang
JQJunyu Qi
Junyu Qi
FCFulei Chu
Fulei Chu

10 October 2025 in Mechanical Systems and Signal Processing
Verified
Journal Article
Closed access
Meng RaoMeng Rao
Meng Rao
XYXingkai Yang
Xingkai Yang
YCYuejian Chen
Yuejian Chen
MZMingjian Zuo
Mingjian Zuo
ZBZhenfei Bu
Zhenfei Bu
FCFulei Chu
Fulei Chu

27 March 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HZHongsheng Zhang
Hongsheng Zhang
PJPAN Jun
PAN Jun
Meng RaoMeng Rao
Meng Rao
ZLZhengwei Li
Zhengwei Li
Xihui LiangXihui Liang
Xihui Liang
Many researchers have developed analytical methods to evaluate gear meshing stiffness. Some of these methods ignored the effect of the gear body while others used a simplified model to consider its effect. Until now, a detailed investigation of gear body-induced tooth deflections has been rare, especially for the double-tooth-pair meshing period. In this study, we present a detailed investigation of gear body-induced tooth deflections. To be specific, we will discuss how to accurately evaluate gear body-induced tooth deflections using the finite element analysis, and what are the effect of parameters such as loading and gear parameters on gear body-induced tooth deflections. Then, an improved solution is developed for evaluating the body-induced tooth deflection. In the single-tooth-pair meshing period, the improved formula is developed based on a popular formula proposed by Sainsot and Velex. This is achieved by optimizing the coefficients used in their formula to make the formula more accurate to evaluate gear body-induced tooth deflections. Meanwhile, we introduce a new term called affiliated body stiffness to evaluate the body-induced tooth deflections in the double-tooth-pair meshing period. The improved method can give higher accuracy in evaluating gear body-induced tooth deflections of spur gears with a pressure angle of 20°.

9 February 2026 in IEEE Sensors Journal
Verified
Journal Article
Closed access
Meng RaoMeng Rao
Meng Rao
Yuejian ChenYuejian Chen
Yuejian Chen
ZBZhenfei Bu
Zhenfei Bu
YSYiping Sun
Yiping Sun
MZMingjian Zuo
Mingjian Zuo
FCFulei Chu
Fulei Chu
Lifting machines such as elevators and cranes are typically equipped with both a Supervisory Control and Data Acquisition (SCADA) system and a Condition Monitoring System (CMS) to monitor operational and health status, ensuring reliable performance. The SCADA system collects operational data like speed, load, and current, while the CMS collects vibration data. Fusing data from both systems can significantly enhance condition monitoring performances. However, as the two types of data are collected separately with different time clocks, they are asynchronous. This paper proposes a correlation analysis-based method to synchronize SCADA and vibration data. First, vibration data is preprocessed to extract a time-frequency ridge, a feature proportional to the machine’s running speed. Second, the SCADA speed is interpolated and segmented to make sure that the sampling frequencies of the two types of data are matched. Third, the moving correlation coefficient between the time-frequency ridge and the processed SCADA speed is calculated. The time lag between the two datasets is identified when this coefficient is maximized. The subsequent data is synchronized by applying this lag. An experiment on a commissioned elevator validates the method’s effectiveness, showing it can successfully synchronize SCADA and vibration data, thereby ensuring time consistency for robust multi-source data fusion.

13 October 2022
Verified
Conference Paper
Closed access
Meng RaoMeng Rao
Meng Rao
MZMing J Zuo
Ming J Zuo
ZTZhigang Tian
Zhigang Tian
DQDali Qin
Dali Qin
Deep-learning-based rotating machinery fault classification often suffers from the problem of speed induced fault information imbalance when applied to varying speed conditions. The speed adaptive gate (SAG) is an effective auxiliary branch that assists existing deep learning models addressing that problem. This paper presents four types of implementations for SAGs, i.e., the element-wise, channel-wise, time-wise and sample-wise, and compares their fault classification performances with a baseline Convolutional Neural Network (CNN) over two experimental datasets including a planetary gearbox dataset and a fixed-shaft gearbox dataset. Results show that the element-wise achieves the highest fault classification accuracy while the time-wise returns the least. But element-wise consumes about 20% more training CPU time than that of the baseline CNN. A good trade-off is the sample-wise with average speed as the input to the SAG, which obtains fair accuracy improvement, but spends only about 5% more training time than the baseline CNN.