Fault Data Detection of Traffic Detector Based on Wavelet Packet in the Residual Subspace Associated with PCA

Li, Xiaolu; Zhang, Xi; Zhang, Peng; Zhu, Guangyu

doi:10.3390/app9173491

Cited by 13 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also performed principal component analysis (PCA) which is a statistical method of dimension reduction. Several studies use PCA to identify key factors afecting trafc fow [30,31], and the main calculation formula is as follows:…”

Section: Calibration Of the Car-following Model According Tomentioning

confidence: 99%

See 1 more Smart Citation

Exploring the Stability and Capacity Characteristics of Mixed Traffic Flow with Autonomous and Human-Driven Vehicles considering Aggressive Driving

Zhang

Pan

et al. 2023

Journal of Advanced Transportation

View full text Add to dashboard Cite

With the popularization of autonomous vehicle (AV) technology, mixed traffic flows that consist of AVs and human-driven vehicles (HDVs) will appear in the real world. Although many studies of the features of mixed traffic flow have been carefully evaluated, few studies have focused on the effect of aggressive driving performance on mixed traffic flow. This study aims to develop an approach to evaluate the effects of aggressive driving on the stability and capacity performance under the conditions of AV and HDV mixed traffic flow. First, since a car-following model can describe the relationship between vehicles, we calibrate a car-following model for aggressive driving and nonaggressive driving behaviors based on real traffic data and previous research results. Then, in a mixed traffic flow environment, a basic linear stability formula and capacity calculation expression are developed that consider the effects of vehicle order on the capacity. Finally, because the proportion of aggressive driving and aggressive driving parameters may change, nine combinations of three aggressive driving proportions and three driving parameter cases are used for the sensitivity analysis. The results indicate that the effect of aggressive driving on mixed traffic flow is complex. When the proportion of aggressive driving is less than 35%, the increase in the proportion of aggressive driving increases the traffic capacity and reduces the unstable part. However, when the proportion of aggressive driving is greater than 35%, the increase in the proportion of aggressive driving increases the unstable part. When the penetration rate of AVs exceeds 0.490, mixed traffic flow remains stable at all aggressive driving proportions. In addition, the capacity of a mixed traffic flow may be improved as the penetration rate of AVs increases. To a certain extent, these conclusions provide a theoretical basis for formulating different management modes of AVs and HDVs.

show abstract

Section: Calibration Of the Car-following Model According Tomentioning

confidence: 99%

“…Subsequently, the FDM of the mixed trafc fow can be obtained by substituting equations ( 23) and ( 24) into equation (25) and combining the volume-density-speed relationship of the basic trafc fow, as presented in equation (31).…”

Section: Fdmmentioning

confidence: 99%

Exploring the Stability and Capacity Characteristics of Mixed Traffic Flow with Autonomous and Human-Driven Vehicles considering Aggressive Driving

Zhang

Pan

et al. 2023

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…Wavelet packet is another important development of wavelet theory in signal processing. It has the characteristics of multidimensional and multiresolution analysis and can provide more complex signal analysis methods [15]. The signal can be decomposed into a series of frequency bands layer by layer.…”

Section: Fusion Of Time-frequency Featuresmentioning

confidence: 99%

Motor Fault Diagnosis Algorithm Based on Wavelet and Attention Mechanism

Yan

Chen

Gao³

2021

Journal of Sensors

View full text Add to dashboard Cite

In order to improve the maintenance efficiency of the motor and realize the real-time fault diagnosis function of the motor, a motor fault diagnosis algorithm based on wavelet and attention mechanism is proposed. Firstly, the motor vibration signal is decomposed by wavelet transform, and the high-frequency signal is denoised to improve the signal-to-noise ratio. Secondly, the frequency band and time dimension after wavelet decomposition are taken as input data, the convolution neural network is used to fuse the frequency band features of data, and the bidirectional gated loop unit is used to fuse the time series features. Then, the attention mechanism is used to adaptively integrate the features of different time points. Finally, motor fault diagnosis and prediction are realized by classifier recognition. Experimental results show that, compared with the existing deep learning fault diagnosis model, this method has higher diagnosis accuracy and can accurately diagnose the running state of the motor.

show abstract

“…Such features should be conveniently extracted in such a way to emphasize the differences between normal and one or various abnormalities operating conditions. The MSPCA model was developed by Bakshi [32] with the aim of combining the ability of PCA to extract cross-correlation between variables with the ability of orthonormal wavelets to separate feature from noise and approximately decorrelate autocorrelation between available measurements [32,33]. Some of the advantages of multiscale representation in process modeling and monitoring are presented in [32,34].…”

Section: Feature Extraction and Selection Using Multiscale Pcamentioning

confidence: 99%

Multivariate Features Extraction and Effective Decision Making Using Machine Learning Approaches

et al. 2020

View full text Add to dashboard Cite

Fault Detection and Isolation (FDI) in Heating, Ventilation, and Air Conditioning (HVAC) systems is an important approach to guarantee the human safety of these systems. Therefore, the implementation of a FDI framework is required to reduce the energy needs for buildings and improving indoor environment quality. The main goal of this paper is to merge the benefits of multiscale representation, Principal Component Analysis (PCA), and Machine Learning (ML) classifiers to improve the efficiency of the detection and isolation of Air Conditioning (AC) systems. First, the multivariate statistical features extraction and selection is achieved using the PCA method. Then, the multiscale representation is applied to separate feature from noise and approximately decorrelate autocorrelation between available measurements. Third, the extracted and selected features are introduced to several machine learning classifiers for fault classification purposes. The effectiveness and higher classification accuracy of the developed Multiscale PCA (MSPCA)-based ML technique is demonstrated using two examples: synthetic data and simulated data extracted from Air Conditioning systems.

show abstract

Fault Data Detection of Traffic Detector Based on Wavelet Packet in the Residual Subspace Associated with PCA

Cited by 13 publications

References 23 publications

Exploring the Stability and Capacity Characteristics of Mixed Traffic Flow with Autonomous and Human-Driven Vehicles considering Aggressive Driving

Exploring the Stability and Capacity Characteristics of Mixed Traffic Flow with Autonomous and Human-Driven Vehicles considering Aggressive Driving

Motor Fault Diagnosis Algorithm Based on Wavelet and Attention Mechanism

Multivariate Features Extraction and Effective Decision Making Using Machine Learning Approaches

Contact Info

Product

Resources

About