Fault diagnosis network design for vehicle on-board equipments of high-speed railway: A deep learning approach

Yin, Jianqin; Zhao, Wentian

doi:10.1016/j.engappai.2016.10.002

Cited by 143 publications

(44 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) ANN-BP The ANN-BP is a typical model that uses an error back-propagation algorithm to train the weights and biases of each neuron, and it contains several layers (i.e., input layer, output layer, and hidden layers) [50]. The ANN-BP has a relatively simple structure, and thus it has been widely used in fitting nonlinear continuous functions and pattern recognition [51].…”

Section: The K-nearest Neighbor and Artificial Neural Network With Bamentioning

confidence: 99%

Health Monitoring for Balancing Tail Ropes of a Hoisting System Using a Convolutional Neural Network

Zhou

Zhu

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

Abstract:With the arrival of the big data era, it has become possible to apply deep learning to the health monitoring of mine production. In this paper, a convolutional neural network (CNN)-based method is proposed to monitor the health condition of the balancing tail ropes (BTRs) of the hoisting system, in which the feature of the BTR image is adaptively extracted using a CNN. This method can automatically detect various BTR faults in real-time, including disproportional spacing, twisted rope, broken strand and broken rope faults. Firstly, a CNN structure is proposed, and regularization technology is adopted to prevent overfitting. Then, a method of image dataset description and establishment that can cover the entire feature space of overhanging BTRs is put forward. Finally, the CNN and two traditional data mining algorithms, namely, k-nearest neighbor (KNN) and an artificial neural network with back propagation (ANN-BP), are adopted to train and test the established dataset, and the influence of hyperparameters on the network diagnostic accuracy is investigated experimentally. The experimental results showed that the CNN could effectively avoid complex steps such as manual feature extraction, that the learning rate and batch-size strongly affected the accuracy and training efficiency, and that the fault diagnosis accuracy of CNN was 100%, which was higher than that of KNN and ANN-BP. Therefore, the proposed CNN with high accuracy, real-time functioning and generalization performance is suitable for application in the health monitoring of hoisting system BTRs.

show abstract

Section: The K-nearest Neighbor and Artificial Neural Network With Bamentioning

confidence: 99%

Health Monitoring for Balancing Tail Ropes of a Hoisting System Using a Convolutional Neural Network

Zhou

Zhu

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…There are also other recent applications of neural networks 13,14 applied in modeling and optimization of systems with complex and multidisciplinary nature. 15,16 Aforementioned studies above apparently revealed the efficiency and accuracy of AI. In this research, an expert system approach based on AI in the modeling of cyclic voltammogram (CV) profiles of green tea extracts was proposed for stability analysis.…”

Section: Introductionmentioning

confidence: 95%

“…For instance, an optimization method of genetic programming was developed by Garg et al to model the power consumption from bone drilling process; Panda et al have proposed AI‐based neural network models to predict the properties of materials for manufacturing processes. There are also other recent applications of neural networks applied in modeling and optimization of systems with complex and multidisciplinary nature . Aforementioned studies above apparently revealed the efficiency and accuracy of AI.…”

Section: Introductionmentioning

confidence: 99%

Experimental and artificial intelligence for determination of stable criteria in cyclic voltammetric process of medicinal herbs for biofuel cells

Chen

Srinivasan

et al. 2019

Int J Energy Res

View full text Add to dashboard Cite

Summary This study proposed an expert system approach on the basis of artificial intelligence (AI) in the modeling of cyclic voltammogram (CV) profiles of green tea extracts. AI approach of artificial neural networks is applied to generate the model phase‐plane portraits of current output versus applied voltage through CV scan cycles. The predicted current values were validated using experiments, and generic ability of approach was examined by testing on the CV scan cycles generated from Syzygium aromaticum and Citrus reticulate. It was concluded that AI approach can be employed to reveal stable point (cycle and voltage) in CV profiles for bioenergy applications.

show abstract

“…After that, a lot of researches about deep learning [40] have been studied in many fields like computer vision [18], speech recognition [19], information retrieval [20] and traffic control [21] over the past 10 years. Many researchers also have applied deep learning in fault diagnosis and condition recognition [22][23][24][25][26][27][28]. Verma et al [24] proposed an intelligent condition monitoring method for rotating machine using sparse auto-encoder.…”

Section: Introductionmentioning

confidence: 99%

A deep learning-based recognition method for degradation monitoring of ball screw with multi-sensor data fusion

Zhang

Gao

Wen

et al. 2017

Microelectronics Reliability

View full text Add to dashboard Cite

Fault diagnosis network design for vehicle on-board equipments of high-speed railway: A deep learning approach

Cited by 143 publications

References 22 publications

Health Monitoring for Balancing Tail Ropes of a Hoisting System Using a Convolutional Neural Network

Health Monitoring for Balancing Tail Ropes of a Hoisting System Using a Convolutional Neural Network

Experimental and artificial intelligence for determination of stable criteria in cyclic voltammetric process of medicinal herbs for biofuel cells

A deep learning-based recognition method for degradation monitoring of ball screw with multi-sensor data fusion

Contact Info

Product

Resources

About