Fault detection of a wheelset bearing in a high-speed train using the shock-response convolutional sparse-coding technique

Ding, Jianming

doi:10.1016/j.measurement.2017.12.010

Cited by 64 publications

(26 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6 The sum square error diagram based on training, test, validation data in NNPCA method [14] Fig. 7 The neural classifier training situation diagram in NNPCA method [14] shown that system operation in normal and fault condition is appropriate, while idv(1) has existed but in three faults idv(4), idv (8), idv (12) , simultaneously, with idv (15) have not properly operated. In this way, the results are illustrated in Figs.…”

Section: The Neural Network With Raw Datamentioning

confidence: 99%

“…The TE process is unstable in open-loop mode and the first limitation that causes this instability is exceeding from reactor allowed pressure range. Realized control structure should be able to save process in operational conditions and can put process variables in its proposed constraints range [4][5][6][7][8][9][10][11][12][13][14][15][16][17]. Regarding the proposed research novelty and its innovation, it can be expressed in three lines.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

High efficiency fault-detection and fault-tolerant control approach in Tennessee Eastman process via fuzzy-based neural network representation

Adeli

Mazinan

2019

Complex Intell. Syst.

View full text Add to dashboard Cite

We looked at the background of fault-detection and fault-tolerant control algorithms to propose a new high efficiency one with a focus on Tennessee Eastman process through fuzzy-based neural network representation. Due to the fact that the openloop system may not be stabilized, an advanced control strategy to generate proper control signals needs to be designed. At first, to detect and identify the fault, data preprocessing theories have been considered. Based upon the matter disclosed, to provide a reliable decision-maker block, fusion classifier idea has been realized. For this one, raw data, time, and frequency characteristics are divided into various classification tools and finally the obtained knowledge combination regarding each one of them is adopted. It should be noted that the proposed implementation tools are taken into real consideration as the fuzzy-based neural network representation. Subsequently, the fault-tolerant control approach based on local controller regulation in case of each fault occurrence has been researched, which the investigated outcomes emphasize the effectiveness of the approach proposed here.

show abstract

Section: The Neural Network With Raw Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

High efficiency fault-detection and fault-tolerant control approach in Tennessee Eastman process via fuzzy-based neural network representation

Adeli

Mazinan

2019

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…e axle box bearing, which supports the weight of the vehicle and suffers various loads from the wheel set or other components of the bogie, is one of the key rolling components to guarantee the safety operation of the railway vehicle [2]. erefore, the fault diagnosis of axle box bearing is crucial for the operation safety of the railway vehicle [3]. Vibration signal is commonly applied for rotational machinery fault diagnosis because of its convenience and efficiency.…”

Section: Introductionmentioning

confidence: 99%

A Morphological Filtering Method Based on Particle Swarm Optimization for Railway Vehicle Bearing Fault Diagnosis

Huang

Lin

Liu

et al. 2019

Shock and Vibration

View full text Add to dashboard Cite

With the rapid development of high-speed railway, the fault diagnosis of railway vehicles has become more and more important for ensuring the operating safety. The MF is a nonlinear signal processing method which can extract the modulated faulty information via reshaping the analyzed signal. However, the choices of operators and structure elements (SE) are numerous and complicated to determine the best MF solution for different bearing faulty signals. In this paper, the particle swarm optimization (PSO) was introduced to optimize the effect of MF among several classical MF operators and different SE parameters. The proposed method applied PSO to select the best MF result with respect to the fitness function adopting kurtosis. A set of bearing signals with additional interference of wheel-track excitement are analyzed to verify the effectiveness of the proposed method. The results demonstrated that the proposed method is capable of obtaining the optimized solution and accurately extracting the fault information. Furthermore, the shaft rotation frequency and wheel-track interference were reduced by the proposed method.

show abstract

“…Compared with traditional time-domain statistical indicators and transform-based methods, dictionary learning is a data-driven method and can adaptively match the fault feature information from the measured vibration signals [19,20]. Dictionary learning methods mainly include regular dictionary learning and shift-invariant dictionary learning [21]. A wheelset bearing is rotating machinery, and its vibration signal has shift-invariant features when there are some defects on the surfaces of their components.…”

Section: Introductionmentioning

confidence: 99%

Train Wheelset Bearing Multifault Impulsive Component Separation Using Hierarchical Shift‐Invariant Dictionary Learning

Zhang

Ding

Lin

2019

Shock and Vibration

View full text Add to dashboard Cite

A wheelset bearing is a crucial energy transmission element in high-speed trains. Any parts of the wheelset bearing that have faults may endanger the safety of the railway service. Therefore, it is important to monitor the running condition of a wheelset bearing. The multifault on a wheelset bearing is very common, and these impulsive components generated by different types of faults may interact with each other, which increases the difficulty of entirely identifying those faults. To solve the multifault problem, this paper proposed a hierarchical shift-invariant K-means singular value decomposition (H-SI-K-SVD) to hierarchically separate those multifault impulsive components based on their fault power levels. Each of the separated impulse signals contains only one fault impulse, and the fault information could be highlighted both in time domain and frequency domain. In addition, the sparsity of envelope spectrum (SES) is introduced as an indicator to adaptively tune a key parameter in this method. The effectiveness of the proposed method is verified by both simulation and experimental signals. Compared with ensemble empirical model decomposition (EEMD), the proposed method exhibits better performance in separating the multifault impulsive components and detecting the faults of a wheelset bearing.

show abstract

Fault detection of a wheelset bearing in a high-speed train using the shock-response convolutional sparse-coding technique

Cited by 64 publications

References 66 publications

High efficiency fault-detection and fault-tolerant control approach in Tennessee Eastman process via fuzzy-based neural network representation

High efficiency fault-detection and fault-tolerant control approach in Tennessee Eastman process via fuzzy-based neural network representation

A Morphological Filtering Method Based on Particle Swarm Optimization for Railway Vehicle Bearing Fault Diagnosis

Train Wheelset Bearing Multifault Impulsive Component Separation Using Hierarchical Shift‐Invariant Dictionary Learning

Contact Info

Product

Resources

About