Research on deep learning method for rail surface defect detection

Feng, Jiang; Hao, Yuan; Hu, Yun; Lin, Jun; Liu, Shi Wang; Luo, Xiangfeng

doi:10.1049/iet-est.2020.0041

Cited by 47 publications

(20 citation statements)

References 20 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And overcomes the shortcomings of traditional detection methods. Feng J H et al [22] discussed a new object detection technique for detecting rail problems. The proposed network design of algorithm incorporates a MobileNet backbone network and numerous novel detection layers with multi-scale feature mappings.…”

Section: A Defect Detection Based On Cnnmentioning

confidence: 99%

Intelligent Detection Method of Forgings Defects Detection Based on Improved EfficientNet and Memetic Algorithm

et al. 2022

View full text Add to dashboard Cite

In the process of production, automobile steel forgings are prone to various cracks, which affect the product quality. At present, forgings defects are mainly detected by fluorescent magnetic particle inspection and manual inspection. Aiming at the problems of low detection accuracy and efficiency in this method, an improved convolutional neural network model is proposed. The fluorescent magnetic particle inspection images of two typical forgings were intelligently inspected. Firstly, a deep learning model with EfficientNet as the backbone and Feature Pyramid Network (FPN) as the fusion layer is constructed. Secondly, In order to improve the convergence speed and detection accuracy, the calculation method of intersection over union is improved, and the network is improved by using the Attention Mechanism. Finally, Particle Swarm Optimization algorithm (PSO) with adaptive parameters is introduced to optimize the hyperparameters of neural network, and a fluorescent magnetic particle inspection image acquisition platform is built for verification. The mean Average Precision (mAP) of the best model of EfficientNet-PSO on the validation set is 95.69%. F1 score is 0.94 and FLOPs is 1.86B. Compared with other five deep learning neural network models, this method effectively improves the defect detection efficiency and accuracy of flange plate and cylinder head, which can meet the defect detection requirements.

show abstract

Section: A Defect Detection Based On Cnnmentioning

confidence: 99%

Intelligent Detection Method of Forgings Defects Detection Based on Improved EfficientNet and Memetic Algorithm

et al. 2022

View full text Add to dashboard Cite

show abstract

“…During this process, we choose a loss function named transformation-aware loss 𝓁 t (t , t ) to quantify the difference between a transformation t and its estimate t . The objective functions can be formulated as Equation (3):…”

Section: Dual Transformation Predictionsmentioning

confidence: 99%

“…A nomaly detection is a practical machine learning task which has attracted ever-increasing attention in a variety of fields, including medical image diagnoses [1], video surveillance [2] and industrial defect detection [3]. For example, to ensure product accuracy, modern manufacturing processes are becoming more and more complex and meeting unmanned operation expectation [4].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised anomaly detection via dual transformation‐aware embeddings

Wang

Hou

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Unsupervised anomaly detection refers to the discovery of unconventional images that are globally or locally different from the training set. Recently, reconstruction-based anomaly detection methods have made great progress. However, most of the existing methods take reconstructing the original image as the goal of latent feature learning. Due to lack of effective semantic guidance, latent features have intrinsic characteristics which retain redundant details of spatial structure. Such information is too general and cause over-expression problem. To solve this problem, in this paper, dual transformation-aware embeddings are coined which aims to achieve a stable model to learn high-level latent features in a self-supervised manner. To be more specific, the authors try to extract transformation-detectable feature embeddings for both structure and content views which explore the regular pattern under different transformations in normal situations. In addition, the relationship between the original feature and the transformed feature is established. Based on such relationship, the latent feature of generated image to predict transformation parameter is extracted. Then, a transformation-consistency regularization is proposed to constrain decoder to generate high-quality image with high-level consistency and achieve a more stable model. Experiments on MVTec-AD and CIFAR10 datasets prove the effectiveness and robustness of the proposed method.

show abstract

“…Thus, the same reference may appear under different columns. [38], [39], [40], [35] Rails' Heads [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57], [58], [59], [60], [61], [62] [63] † , [64] Fasteners/ Fastening Systems [48], [65], [66], [67], [68], [69], [70], [71] [72], [55] Welded Joints [21] † Sleepers [36] The † mark indicates data obtained from specimens only (laboratory tests)…”

Section: Rail Trackmentioning

confidence: 99%

A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance

et al. 2022

View full text Add to dashboard Cite

Within Artificial Intelligence, Deep Learning (DL) represents a paradigm that has been showing unprecedented performance in image and audio processing by supporting or even replacing humans in defect and anomaly detection. The Railway sector is expected to benefit from DL applications, especially in predictive maintenance applications, where smart audio and video sensors can be leveraged yet kept distinct from safety-critical functions. Such separation is crucial, as it allows for improving system dependability with no impact on its safety certification. This is further supported by the development of DL in other transportation domains, such as automotive and avionics, opening for knowledge transfer opportunities and highlighting the potential of such a paradigm in railways. In order to summarize the recent state-of-the-art while inquiring about future opportunities, this paper reviews DL approaches for the analysis of data generated by acoustic and visual sensors in railway maintenance applications that have been published until August 31st, 2021. In this paper, the current state of the research is investigated and evaluated using a structured and systematic method, in order to highlight promising approaches and successful applications, as well as to identify available datasets, current limitations, open issues, challenges, and recommendations about future research directions.

show abstract

Research on deep learning method for rail surface defect detection

Cited by 47 publications

References 20 publications

Intelligent Detection Method of Forgings Defects Detection Based on Improved EfficientNet and Memetic Algorithm

Intelligent Detection Method of Forgings Defects Detection Based on Improved EfficientNet and Memetic Algorithm

Unsupervised anomaly detection via dual transformation‐aware embeddings

A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance

Contact Info

Product

Resources

About