Ensemble model for rail surface defects detection

Li, Hailang; Wang, Fan; Liu, Junbo; Song, Haoran; Hou, Zhixiong; Dai, Peng

doi:10.1371/journal.pone.0268518

Cited by 15 publications

(11 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nevertheless, it is important to position our contribution. Thus, we take as reference the paper by Li et al [ 56 ], which is also devoted to the detection of defects on the rails. They introduced an ensemble learning model designed to enhance predictive performance through the integration of multiple learning algorithms.…”

Section: Results and Analysismentioning

confidence: 99%

A Hybrid System for Defect Detection on Rail Lines through the Fusion of Object and Context Information

Zhukov,

Rivero,

Benois-Pineau

et al. 2024

Sensors

View full text Add to dashboard Cite

Defect detection on rail lines is essential for ensuring safe and efficient transportation. Current image analysis methods with deep neural networks (DNNs) for defect detection often focus on the defects themselves while ignoring the related context. In this work, we propose a fusion model that combines both a targeted defect search and a context analysis, which is seen as a multimodal fusion task. Our model performs rule-based decision-level fusion, merging the confidence scores of multiple individual models to classify rail-line defects. We call the model “hybrid” in the sense that it is composed of supervised learning components and rule-based fusion. We first propose an improvement to existing vision-based defect detection methods by incorporating a convolutional block attention module (CBAM) in the you only look once (YOLO) versions 5 (YOLOv5) and 8 (YOLOv8) architectures for the detection of defects and contextual image elements. This attention module is applied at different detection scales. The domain-knowledge rules are applied to fuse the detection results. Our method demonstrates improvements over baseline models in vision-based defect detection. The model is open for the integration of modalities other than an image, e.g., sound and accelerometer data.

show abstract

Section: Results and Analysismentioning

confidence: 99%

A Hybrid System for Defect Detection on Rail Lines through the Fusion of Object and Context Information

Zhukov,

Rivero,

Benois-Pineau

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Decision Tree (DT), Random Forest (RF), and K-Nearest Neighbor (K-NN) have outperformed the other classifiers in the classification of six labels of short circuit fault scenarios. Hence, an ensemble model [ 58 ] has been constructed, which combines the prediction performance of the three individual models including Decision Tree (DT), Random Forest (RF) and K-Nearest Neighbor (K-NN) has achieved 99.99% train accuracy and 99.92% test accuracy. In a similar vein, Gradient Boosting (GB), a well-known classifier for multiclass classification, has attained more than 97% train and test accuracy.…”

Section: Experiments and Results Analysismentioning

confidence: 99%

Ensemble learning based transmission line fault classification using phasor measurement unit (PMU) data with explainable AI (XAI)

Bin Akter,

Sarkar Pias,

Rahman Deeba

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

A large volume of data is being captured through the Phasor Measurement Unit (PMU), which opens new opportunities and challenges to the study of transmission line faults. To be specific, the Phasor Measurement Unit (PMU) data represents many different states of the power networks. The states of the PMU device help to identify different types of transmission line faults. For a precise understanding of transmission line faults, only the parameters that contain voltage and current magnitude estimations are not sufficient. This requirement has been addressed by generating data with more parameters such as frequencies and phase angles utilizing the Phasor Measurement Unit (PMU) for data acquisition. The data has been generated through the simulation of a transmission line model on ePMU DSA tools and Matlab Simulink. Different machine learning models have been trained with the generated synthetic data to classify transmission line fault cases. The individual models including Decision Tree (DT), Random Forest (RF), and K-Nearest Neighbor (K-NN) have outperformed other models in fault classification which have acquired a cross-validation accuracy of 99.84%, 99.83%, and 99.76% respectively across 10 folds. Soft voting has been used to combine the performance of these best-performing models. Accordingly, the constructed ensemble model has acquired a cross-validation accuracy of 99.88% across 10 folds. The performance of the combined models in the ensemble learning process has been analyzed through explainable AI (XAI) which increases the interpretability of the input parameters in terms of making predictions. Consequently, the developed model has been evaluated with several performance matrices, such as precision, recall, and f1 score, and also tested on the IEEE 14 bus system. To sum up, this article has demonstrated the classification of six scenarios including no fault and fault cases from transmission lines with a significant number of training parameters and also interpreted the effect of each parameter to make predictions of different fault cases with great success.

show abstract

“…Çalışmada kullanılan veri seti 399 adet görüntüden oluşmaktadır [13]. Kusurlu demiryolu ray görüntüleri görüntü artırım teknikleriyle 939'a arttırılmıştır.…”

Section: Metotunclassified

YOLOv5 ile Topluluk Öğrenmesine Dayalı Olarak Ray Yüzeyindeki Kusurların Tespiti

Sevi

Aydın

Akın

2023

Demiryolu Mühendisliği

View full text Add to dashboard Cite

Railway transportation has increased its capacity with the increase in railway line length in recent years. The development of high-speed trains also contributed to this situation. The increase in passenger and cargo capacity has further increased the importance of security measures. In order to ensure the safety of the railway line, it is necessary to inspect the line at certain intervals. Detection of defects on the rail is extremely important in the maintenance of the railway line. This study focuses on the detection of defects on the rail component, which is an important part of railway maintenance. In the study, it was tried to detect the defects on the rail with YOLO, which is an object detection method. In the study, it has been shown that model ensembling gives better results than YOLO models that validate alone. A method based on ensemble learning is proposed for different YOLO models. Experiment results showed that the detection rate including all classes on the data set containing 8 different defects was over 80%.

show abstract

Ensemble model for rail surface defects detection

Cited by 15 publications

References 44 publications

A Hybrid System for Defect Detection on Rail Lines through the Fusion of Object and Context Information

A Hybrid System for Defect Detection on Rail Lines through the Fusion of Object and Context Information

Ensemble learning based transmission line fault classification using phasor measurement unit (PMU) data with explainable AI (XAI)

YOLOv5 ile Topluluk Öğrenmesine Dayalı Olarak Ray Yüzeyindeki Kusurların Tespiti

Contact Info

Product

Resources

About