A Railway Fastener Inspection Method Based on Abnormal Sample Generation

Regular fastener detection is necessary to ensure the safety of railways.However,the number of abnormal fasteners is significantly lower than the number of normal fasteners in real railways.Existing supervised inspectionmethods have insufficient detection ability in cases of imbalanced samples.To solve this problem,we propose an approach based on deep convolutional neural networks(DCNNs),which consists of three stages:fastener localization,abnormal fastener sample generation based on saliency detection,and fastener state inspection.First,a lightweight YOLOv5s is designed to achieve fast and precise localization of fastener regions.Then,the foreground clip region of a fastener image is extracted by the designed fastener saliency detection network(F-SDNet),combined with data augmentation to generate a large number of abnormal fastener samples and balance the number of abnormal and normal samples.Finally,a fastener inspection model called Fastener ResNet-8 is constructed by being trained with the augmented fastener dataset.Results show the effectiveness of our proposed method in solving the problem of sample imbalance in fastener detection.Qualitative and quantitative comparisons show that the proposed F-SDNet outperforms other state-of-the-art methods in clip region extraction,reaching MAE and max F-measure of 0.0215 and 0.9635,respectively.In addition,the FPS of the fastener state inspection model reached 86.2,and the average accuracy reached 98.7%on 614 augmented fastener test sets and 99.9%on 7505 real fastener datasets.

A Detection Method of Bolts on Axlebox Cover Based on Cascade Deep Convolutional Neural Network

This paper proposes a cascade deep convolutional neural network to address the loosening detection problem of bolts on axlebox covers.Firstly,an SSD network based on ResNet50 and CBAM module by improving bolt image features is proposed for locating bolts on axlebox covers.And then,theA2-PFN is proposed according to the slender features of the marker lines for extracting more accurate marker lines regions of the bolts.Finally,a rectangular approximationmethod is proposed to regularize themarker line regions asaway tocalculate the angle of themarker line and plot all the angle values into an angle table,according to which the criteria of the angle table can determine whether the bolt with the marker line is in danger of loosening.Meanwhile,our improved algorithm is compared with the pre-improved algorithmin the object localization stage.The results show that our proposed method has a significant improvement in both detection accuracy and detection speed,where ourmAP(IoU=0.75)reaches 0.77 and fps reaches 16.6.And in the saliency detection stage,after qualitative comparison and quantitative comparison,our method significantly outperforms other state-of-the-art methods,where our MAE reaches 0.092,F-measure reaches 0.948 and AUC reaches 0.943.Ultimately,according to the angle table,out of 676 bolt samples,a total of 60 bolts are loose,69 bolts are at risk of loosening,and 547 bolts are tightened.

A De-Noising Method for Track State Detection Signal Based on the Statistical Characteristic of Noise

Based on the statistical characteristics analysis of random noise power and autocorrelation function, this paper proposes a de-noising method for track state detection signal by using Empirical Mode Decomposition (EMD). This method is used to noise reduction refactoring for the first Intrinsic Mode Function (IMF) component in accordance with the “random sort-accumulation-average-refactoring' order. Signal autocorrelation function characteristics are used to determine the cut-off point of the dominant mode. This method was applied to test signals and the actual inertial unit signals;the experimental results show that the method can effectively remove the noise and better meet the precision requirement.

A De-Noising Method for Track State Detection Signal Based on EMD

In the track irregularity detection, the acceleration signals of the inertial measurement unit (IMU) output which with low frequency components and noise, this paper studied a de-noising algorithm. Based on the criterion of consecutive mean square error, a de-noising method for IMU acceleration signals based on empirical mode decomposition (EMD) was proposed. This method can divide the intrinsic mode functions (IMFs) derived from EMD into signal dominant modes and noise dominant modes, then the modes reflecting the important structures of a signal were combined together to form partially reconstructed de-noised signal. Simulations were conducted for simulated signals and a real IMU acceleration signals using this method. Experimental results indicate that this method can efficiently and adaptively remove noise, and this method can better meet the precision requirement.