Search

In recent years, several time-frequency representation (TFR) and convolutional neural network- (CNN-) based approaches have been proposed to provide reliable remaining useful life (RUL) estimation for bearings. However, existing methods cannot tackle the spatiotemporal continuity between adjacent TFRs since temporal proposals are considered individually and their temporal dependencies are neglected. In allusion to this problem, a novel prognostic approach based on discrete cosine transformation (DCT) and temporal adjacent convolutional neural network (TACNN) is proposed. Wavelet transform (WT) is applied to effectively map the raw signals to the time frequency domain. Considering the high load and complexity of model computation, bilinear interpolation and DCT algorithm are introduced to convert TFRs into low-dimensional DCT spectrum coding matrix with strong sparsity. Furthermore, the TACNN model is proposed which is capable of learning discriminative features for temporal adjacent DCT spectrum coding matrix. Effectiveness of the proposed method is verified on the PRONOSTIA dataset, and experiment results show that the proposed model is able to realize automatic high-precision estimation of bearings RUL with high efficiency. [ABSTRACT FROM AUTHOR]

• A new method based on time-frequency domain combined with phase space reconstruction and singular value decomposition is proposed. • The proposed method integrated with wavelet transform, phase space reconstruction and singular value decomposition can lead to fast and efficient results. • Validity of the proposed method proposed is verified by pratical fault diagnosis application of wind turbine. Operation of wind turbines under fault state will directly affect the power output efficiency of wind farms. This paper proposes a new automatic fault diagnosis method for wind turbines. A fault diagnosis system framework is constructed and data of vibration status of wind turbines collected is processed and used for fault diagnosis. Firstly, wavelet coefficients are obtained using a discrete wavelet transform (DWT) for vibration acceleration signals collected from wind turbines. Then, the wavelet coefficients are sequentially subjected to phase space reconstruction (PSR) and singular value decomposition (SVD) to extract the fault features. Finally, an extreme learning machine (ELM) is used to classify the faults. Experimental results show that the proposed method is more effective and accurate than other fault diagnosis methods for wind turbines, such as support vector machine (SVM) and multiscale convolutional neural network (MSCNN). Image, graphical abstract [ABSTRACT FROM AUTHOR]

Split pins (SPs), as essential fasteners in the pantograph-catenary system, play a critical role in maintaining the structural stability of the catenary support device (CSD) in high-speed railroad. Unfortunately, impact and vibration generated by the interaction between catenary system and high-speed running vehicles will progressively damage SPs, including but not limited to the loose, breakage, and missing of SPs. Current image processing technologies have limited accuracy. Traditional convolutional neural network (CNN)-based systems that directly learn deep features are inefficient in detecting subtle defects (such as fractured and loose SPs). This study presents a novel SP inspection system based on an innovative destruction and reconstruction learning (DRL). In the DRL, a novel cross stage partial network (CSPNet)-based classifier is firstly developed to alleviate the impact of redundant semantic information and optimize gradient regression process. Then, "destruction" in the DRL stream means these partitioned sub-regions in an input image are shuffled by a region shuffling mechanism (RSM); this guides the classifier to pay more attention to the distinguishable regions in the destroyed and original images for a purpose of correct recognition. For "reconstruction", a newly developed position reconstruction network (PRN) is utilized to restore the original spatial distribution of the sub-regions by modeling the semantic correlation among the sub-regions. The proposed DRL can injects more discriminative details to the classifier by jointly training the classification network and PRN. Finally, comprehensive experiments are conducted on CSD datasets captured from real railroad lines, and the results demonstrate that the proposed approach outperforms existing state-of-the-art models yet keeps a reasonable inference speed. [ABSTRACT FROM AUTHOR]

Abstract The railway track fasteners play a critical role in fixing the track on the ballast bed. Achieving full automation of the fastener defect detection is significant in terms of ensuring track safety, and reducing maintains cost. In this paper, innovative and intelligent methods using image processing technologies and deep learning networks are proposed. In the first part, the traditional fastener positioning method based on image processing is reconsidered. In addition, a novel fastener defect detection and identification method using Dense-SIFT features is proposed which can achieve a better performance than the methods available in the literature. In the second part, VGG16 is trained for fastener defect detection and recognition. The result demonstrates that it is possible to carry out the defect detection of fasteners with CNN. Finally, Faster R-CNN is used for fastener defect detection to advance detection rate and efficiency. The fastener positioning and recognition can be carried out simultaneously. The time for the defect detection and classification is only one-tenth of the other methods mentioned above. Highlights • The Dense-SIFT, spatial pyramid decomposition and BOVW techniques are applied to the classification and this method achieves classification accuracy of 99.26%. • The DCNN method uses only one network for fastener defects detection and achieves a sound classification accuracy of 97.14%. • Faster R-CNN based method realizes the positioning and classification of the fasteners simultaneously and the time spent by Faster R-CNN is only about 10% of the time spent by the other methods. [ABSTRACT FROM AUTHOR]

Prediction of passenger flow distribution in urban rail transit stations can provide important data support for passenger flow organization and passenger travel guidance. However, complex station space structure and simulation-based passenger flow data bring challenges to accurate analysis and prediction of the passenger flow inside the station. This paper proposes a temporal graph attention convolutional neural network model (TGACN) to predict the passenger flow volume and density in key areas of the station. Firstly, considering the topological structure of key areas and the characteristics of passenger flow and flow trend in the station, a multi-graph generation method for continuous space in stations is designed, including geographic neighborhood graph and semantic neighborhood graph, to represent the static and dynamic correlation between nodes. Secondly, a new method of spatio-temporal feature fusion is proposed, which takes multi-graph as input to optimize the extraction and expression of spatial and temporal correlation. Finally, the TGACN is verified by passenger flow data set, which is constructed based on real-time video monitoring data of a transit station in Guangzhou. Experiments demonstrate that the TGACN can obtain the spatio-temporal correlation from passenger flow data, and the prediction results are better than the existing baseline models. • A prediction model for multipoint passenger flow in station is proposed. • Geographical graph is constructed to measure the spatial correlation between nodes. • Semantic graph is constructed to measure the correlation of passenger flow state. • Effective spatial information screening is realized by dimensionality reduction. [ABSTRACT FROM AUTHOR]

Nowadays, with the growing scale of high-speed railways and the increasing number of high-speed trains, the research on train equipment fault diagnosis and health management becomes more and more significant. Bearings are parts which are prone to be the failure equipment on high-speed trains. The temperature of a faulty bearing will increase suddenly during the working process, which may lead to potential accidents. So the axle temperature prediction has become a key research direction. This paper proposes a new organization form of axle temperature data, which connects axle temperature measurement points according to their locations so as to form a graph. Then, based on the Graph Convolutional Network (GCN) and Gated Recurrent Units (GRU) models, a new framework named GCG which combines the GCN and GRU is proposed to extract features and predict axle temperature. Finally, the experiments are conducted based on actual data. The results show that the prediction accuracy and tracking sensitivity are better than other advanced methods. [ABSTRACT FROM AUTHOR]

• Combined with CNN and RNN, a RUL method of roller bearing is proposed. • Feature extraction using 1D-CNN instead of manual method. • GMP layer is introduced to optimize the model structure and reduce the parameters. • Reconstruct RNN operation mode and construct SRU network of parallel operation. To overcome the shortcomings of traditional roller bearing remaining useful life prediction methods, which mainly focus on prediction accuracy improvement and ignore labor cost and time, the present work proposed a novel prediction method by combining an improved one-dimensional convolution neural network (1D-CNN) and a simple recurrent unit (SRU) network. For feature extraction, the proposed method uses the ability of the 1D-CNN to extract signal features. Moreover, use the global maximum pooling layer to replace the fully connected layer. In the prediction part, a parallel-input SRU network was established by reconstructing the serial operation mode of a traditional recurring neural network (RNN). Finally, experiments were carried out using the XJTU-SY dataset to verify. Results revealed that on the premise of ensuring prediction accuracy, the 1D-CNN-SRU method could reduce manual intervention and time cost to a certain extent and provide an intelligent method for roller bearing remaining useful life prediction. [ABSTRACT FROM AUTHOR]

Trains shuttle in semiopen environments, and the surrounding environment plays an important role in the safety of train operation. The weather is one of the factors that affect the surrounding environment of railways. Under haze conditions, railway monitoring and staff vision could be blurred, threatening railway safety. This paper tackles image dehazing for railways. The contributions of this paper for railway video image dehazing are as follows: (1) this paper proposes an end-to-end residual block-based haze removal method that consists of two subnetworks, namely fine-grained and coarse-grained network can directly generate the clean image from input hazy image, called RID-Net (Railway Image Dehazing Network). (2) The combined loss function (per-pixel loss and perceptual loss functions) is proposed to achieve both low-level features and high-level features so to generate the high-quality restored images. (3) We take the full-reference criterion (PSNR&SSIM), object detection, running time, and sensory vision to evaluate the proposed dehazing method. Experimental results on railway synthesized dataset, benchmark indoor dataset, and real-world dataset demonstrate our method has superior performance compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]