Pub Date : 2025-12-01DOI: 10.1016/j.hspr.2025.09.005
Gunawan Gunawan , Basil David Daniel , Slamet Budi Utomo , Jenny Caroline
Indonesia is facing severe congestion and high accident rates as motor vehicle growth continues to outpace road capacity, underscoring the urgent need for alternative mass transportation. A promising solution is the reactivation of the Surabaya–Madura railway, an abandoned infrastructure with significant potential to enhance regional connectivity and urban mobility. However, academic studies on railway reactivation remain limited, particularly in the Madura context where dependence on road-based transport persists. This research gap highlights the importance of examining reactivation not only as a transportation alternative but also as a catalyst for regional development. This study adopts a qualitative approach through descriptive surveys to evaluate infrastructure conditions, identify feasible routes, and analyze broader spatial implications. Findings reveal that railway reactivation could strengthen multimodal integration, reduce congestion, and support sustainable growth. This study provides the first empirical evidence of the strategic value of the Surabaya–Madura railway within Indonesia’s transport and regional development discourse.
{"title":"Reactivation of the railway line from Surabaya to Madura: Enhancing regional connectivity and transportation infrastructure","authors":"Gunawan Gunawan , Basil David Daniel , Slamet Budi Utomo , Jenny Caroline","doi":"10.1016/j.hspr.2025.09.005","DOIUrl":"10.1016/j.hspr.2025.09.005","url":null,"abstract":"<div><div>Indonesia is facing severe congestion and high accident rates as motor vehicle growth continues to outpace road capacity, underscoring the urgent need for alternative mass transportation. A promising solution is the reactivation of the Surabaya–Madura railway, an abandoned infrastructure with significant potential to enhance regional connectivity and urban mobility. However, academic studies on railway reactivation remain limited, particularly in the Madura context where dependence on road-based transport persists. This research gap highlights the importance of examining reactivation not only as a transportation alternative but also as a catalyst for regional development. This study adopts a qualitative approach through descriptive surveys to evaluate infrastructure conditions, identify feasible routes, and analyze broader spatial implications. Findings reveal that railway reactivation could strengthen multimodal integration, reduce congestion, and support sustainable growth. This study provides the first empirical evidence of the strategic value of the Surabaya–Madura railway within Indonesia’s transport and regional development discourse.</div></div>","PeriodicalId":100607,"journal":{"name":"High-speed Railway","volume":"3 4","pages":"Pages 330-336"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01DOI: 10.1016/j.hspr.2025.08.006
Jianfeng Mao , Yun Zhang , Li Zheng , Mansoor Khan , Zhiwu Yu
To enhance the efficiency of stochastic vibration analysis for the Train-Track-Bridge (TTB) coupled system, this paper proposes a prediction method based on a Genetic Algorithm-optimized Backpropagation (GA-BP) neural network. First, initial track irregularity samples and random parameter sets of the Vehicle–Bridge System (VBS) are generated using the stochastic harmonic function method. Then, the stochastic dynamic responses corresponding to the sample sets are calculated using a developed stochastic vibration analysis model of the TTB system. The track irregularity data and vehicle–bridge random parameters are used as input variables, while the corresponding stochastic responses serve as output variables for training the BP neural network to construct the prediction model. Subsequently, the Genetic Algorithm (GA) is applied to optimize the BP neural network by considering the randomness in excitation and parameters of the TTB system, improving model accuracy. After optimization, the trained GA-BP model enables rapid and accurate prediction of vehicle–bridge responses. To validate the proposed method, predictions of vehicle–bridge responses under varying train speeds are compared with numerical simulation results. The findings demonstrate that the proposed method offers notable advantages in predicting the stochastic vibration response of high-speed railway TTB coupled systems.
{"title":"A method for predicting random vibration response of train-track-bridge system based on GA-BP neural network","authors":"Jianfeng Mao , Yun Zhang , Li Zheng , Mansoor Khan , Zhiwu Yu","doi":"10.1016/j.hspr.2025.08.006","DOIUrl":"10.1016/j.hspr.2025.08.006","url":null,"abstract":"<div><div>To enhance the efficiency of stochastic vibration analysis for the Train-Track-Bridge (TTB) coupled system, this paper proposes a prediction method based on a Genetic Algorithm-optimized Backpropagation (GA-BP) neural network. First, initial track irregularity samples and random parameter sets of the Vehicle–Bridge System (VBS) are generated using the stochastic harmonic function method. Then, the stochastic dynamic responses corresponding to the sample sets are calculated using a developed stochastic vibration analysis model of the TTB system. The track irregularity data and vehicle–bridge random parameters are used as input variables, while the corresponding stochastic responses serve as output variables for training the BP neural network to construct the prediction model. Subsequently, the Genetic Algorithm (GA) is applied to optimize the BP neural network by considering the randomness in excitation and parameters of the TTB system, improving model accuracy. After optimization, the trained GA-BP model enables rapid and accurate prediction of vehicle–bridge responses. To validate the proposed method, predictions of vehicle–bridge responses under varying train speeds are compared with numerical simulation results. The findings demonstrate that the proposed method offers notable advantages in predicting the stochastic vibration response of high-speed railway TTB coupled systems.</div></div>","PeriodicalId":100607,"journal":{"name":"High-speed Railway","volume":"3 4","pages":"Pages 305-317"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01DOI: 10.1016/j.hspr.2025.08.001
Bin Chen , Jinlu Yang , Hanwei Zhao , Mancheng Lu
There are multiple types of risks involved in the service of long-span railway bridges. Classical methods are difficult to provide targeted alarm information according to different situations of load anomalies and structural anomalies. To accurately alarm different risks of long-span railway bridges by structural health monitoring systems, this paper proposes a cross-cooperative alarm method using principal and secondary indicators during high-wind periods. It provides the prior criterion for monitoring systems under special conditions, defining the principal and secondary indicators, alarm levels, and thresholds based on the relationship between dynamic equilibrium equations and multiple linear regression analysis. Analysis of one-year monitoring data from a long-span railway cable-stayed bridge shows that the 10-min average cross-bridge wind speed (excitation indicator) can be selected as the principal indicator, while lateral displacement (response indicator) can serve as the secondary indicator. The threshold levels of the secondary indicator prioritize the safety of bridge operation (mainly aiming at the safety of trains traversing bridges), with values significantly lower than structural safety thresholds. This approach enhances alarm timeliness and effectively distinguishes between load anomalies, structural anomalies, and equipment failures. Consequently, it improves alarm accuracy and provides timely decision support for bridge maintenance, train traversing, and emergency treatment.
{"title":"Multi-task multi-level alarm of long-span railway bridge monitoring systems via excitation-response indicators cross-cooperation","authors":"Bin Chen , Jinlu Yang , Hanwei Zhao , Mancheng Lu","doi":"10.1016/j.hspr.2025.08.001","DOIUrl":"10.1016/j.hspr.2025.08.001","url":null,"abstract":"<div><div>There are multiple types of risks involved in the service of long-span railway bridges. Classical methods are difficult to provide targeted alarm information according to different situations of load anomalies and structural anomalies. To accurately alarm different risks of long-span railway bridges by structural health monitoring systems, this paper proposes a cross-cooperative alarm method using principal and secondary indicators during high-wind periods. It provides the prior criterion for monitoring systems under special conditions, defining the principal and secondary indicators, alarm levels, and thresholds based on the relationship between dynamic equilibrium equations and multiple linear regression analysis. Analysis of one-year monitoring data from a long-span railway cable-stayed bridge shows that the 10-min average cross-bridge wind speed (excitation indicator) can be selected as the principal indicator, while lateral displacement (response indicator) can serve as the secondary indicator. The threshold levels of the secondary indicator prioritize the safety of bridge operation (mainly aiming at the safety of trains traversing bridges), with values significantly lower than structural safety thresholds. This approach enhances alarm timeliness and effectively distinguishes between load anomalies, structural anomalies, and equipment failures. Consequently, it improves alarm accuracy and provides timely decision support for bridge maintenance, train traversing, and emergency treatment.</div></div>","PeriodicalId":100607,"journal":{"name":"High-speed Railway","volume":"3 4","pages":"Pages 261-266"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01DOI: 10.1016/j.hspr.2025.08.002
Zhenqian Li , Maoru Chi , Wubin Cai , Yabo Zhou
Axle box bearings serve as crucial components within the transmission system of high-speed trains. Their failure can directly impact the operational safety of these trains. Accurately determining the dynamic load experienced by bearings during the operation of high-speed trains can provide valuable boundary inputs for the study of bearing fatigue life and service performance, thereby holding significant engineering implications. In this study, we propose a high-speed train axle box bearing load estimation method (FMCC-DKF). This method is founded on the Kalman filtering technique of the Maximum Correntropy Criterion (MCC) and employs dummy measurement technology to enhance the stability of estimated loads. We develop a kernel size update algorithm to address the challenges associated with obtaining the key parameter, kernel size of MCC. Comparative analysis of the vertical and lateral loads of the axle box bearing obtained using FMCC-DKF, DKF, and AMCC-DKF, under both measurement noise-free and non-Gaussian noise conditions, is conducted to demonstrate the superiority of the proposed estimation method. The results indicate that the proposed FMCC-DKF method exhibits high estimation accuracy under both measurement noise-free and non-Gaussian noise interference, and maintains its high estimation accuracy despite changes in train speed. The proposed load estimation method demonstrates reliable performance within the low-frequency domain below 70 Hz.
{"title":"An estimating methodology for the load of train axle box bearings","authors":"Zhenqian Li , Maoru Chi , Wubin Cai , Yabo Zhou","doi":"10.1016/j.hspr.2025.08.002","DOIUrl":"10.1016/j.hspr.2025.08.002","url":null,"abstract":"<div><div>Axle box bearings serve as crucial components within the transmission system of high-speed trains. Their failure can directly impact the operational safety of these trains. Accurately determining the dynamic load experienced by bearings during the operation of high-speed trains can provide valuable boundary inputs for the study of bearing fatigue life and service performance, thereby holding significant engineering implications. In this study, we propose a high-speed train axle box bearing load estimation method (FMCC-DKF). This method is founded on the Kalman filtering technique of the Maximum Correntropy Criterion (MCC) and employs dummy measurement technology to enhance the stability of estimated loads. We develop a kernel size update algorithm to address the challenges associated with obtaining the key parameter, kernel size of MCC. Comparative analysis of the vertical and lateral loads of the axle box bearing obtained using FMCC-DKF, DKF, and AMCC-DKF, under both measurement noise-free and non-Gaussian noise conditions, is conducted to demonstrate the superiority of the proposed estimation method. The results indicate that the proposed FMCC-DKF method exhibits high estimation accuracy under both measurement noise-free and non-Gaussian noise interference, and maintains its high estimation accuracy despite changes in train speed. The proposed load estimation method demonstrates reliable performance within the low-frequency domain below 70 Hz.</div></div>","PeriodicalId":100607,"journal":{"name":"High-speed Railway","volume":"3 4","pages":"Pages 267-280"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01DOI: 10.1016/j.hspr.2025.09.003
Haichuan Tang, Yifan Sun, Xiaoyu Shen, Qi Liu
In the field of railway traction drive systems, voltage sensor intermittent faults can significantly impact the reliability and safety of the entire system. This paper proposes an online diagnosis method for detecting such faults using an Artificial Intelligence (AI) predictor based on a Nonlinear Autoregressive with eXogenous inputs (NARX) data structure. The model is trained efficiently using the Extreme Learning Machine (ELM) algorithm. The NARX model captures the dynamic characteristics of the voltage sensor data, enabling the AI predictor to learn complex nonlinear relationships. The ELM training method ensures rapid convergence and high accuracy. Through extensive experimental validation, the proposed method demonstrates high sensitivity to voltage sensor intermittent faults and robust performance under varying operating conditions. This approach offers a promising solution for enhancing the diagnostic capabilities of railway traction systems, ensuring timely fault detection and improving overall system reliability.
{"title":"An online diagnosis method for voltage sensor intermittent fault in railway traction drive systems based on NARX-ELM predictor","authors":"Haichuan Tang, Yifan Sun, Xiaoyu Shen, Qi Liu","doi":"10.1016/j.hspr.2025.09.003","DOIUrl":"10.1016/j.hspr.2025.09.003","url":null,"abstract":"<div><div>In the field of railway traction drive systems, voltage sensor intermittent faults can significantly impact the reliability and safety of the entire system. This paper proposes an online diagnosis method for detecting such faults using an Artificial Intelligence (AI) predictor based on a Nonlinear Autoregressive with eXogenous inputs (NARX) data structure. The model is trained efficiently using the Extreme Learning Machine (ELM) algorithm. The NARX model captures the dynamic characteristics of the voltage sensor data, enabling the AI predictor to learn complex nonlinear relationships. The ELM training method ensures rapid convergence and high accuracy. Through extensive experimental validation, the proposed method demonstrates high sensitivity to voltage sensor intermittent faults and robust performance under varying operating conditions. This approach offers a promising solution for enhancing the diagnostic capabilities of railway traction systems, ensuring timely fault detection and improving overall system reliability.</div></div>","PeriodicalId":100607,"journal":{"name":"High-speed Railway","volume":"3 4","pages":"Pages 325-329"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01DOI: 10.1016/j.hspr.2025.08.004
Dunya Zeki Mohammed , Ahmed J.A. Al-Gburi
This research presents a compact, high-gain millimeter-wave antenna tailored for reliable 5 G communication in high-speed railway environments. The proposed antenna supports dual-band operation at 28 GHz (n257/n258) and 38 GHz (n260), enabling robust Vehicle-to-Infrastructure (V2I) links required for next-generation railway systems. The radiator occupies only 12 mm × 8 mm on a Rogers 6010LM substrate (εᵣ = 10.2, h = 0.64 mm). A Metallic Ground-Backing (MGB) reflector, positioned 9 mm behind the patch—λ/4 at 28 GHz—enhances forward radiation, suppresses back-lobes, and ensures highly directional coverage along railway tracks. The antenna achieves measured peak gains of 7.96 dBi at 28 GHz and 8.20 dBi at 38 GHz, with excellent impedance matching and stable radiation patterns under mobility scenarios. Its unique combination of compact footprint, reflector-aided gain enhancement, and stable dual-band performance under dynamic conditions distinguishes it from conventional millimeter-wave solutions, making it a strong candidate for 5G-based high-speed railway communication modules and arrays.
{"title":"Compact, gain-enhanced 5G mmWave antenna with metallic ground-backed reflector for high-speed railway communication systems","authors":"Dunya Zeki Mohammed , Ahmed J.A. Al-Gburi","doi":"10.1016/j.hspr.2025.08.004","DOIUrl":"10.1016/j.hspr.2025.08.004","url":null,"abstract":"<div><div>This research presents a compact, high-gain millimeter-wave antenna tailored for reliable 5 G communication in high-speed railway environments. The proposed antenna supports dual-band operation at 28 GHz (n257/n258) and 38 GHz (n260), enabling robust Vehicle-to-Infrastructure (V2I) links required for next-generation railway systems. The radiator occupies only 12 mm × 8 mm on a Rogers 6010LM substrate (<em>ε</em>ᵣ = 10.2, <em>h</em> = 0.64 mm). A Metallic Ground-Backing (MGB) reflector, positioned 9 mm behind the patch—<em>λ</em>/4 at 28 GHz—enhances forward radiation, suppresses back-lobes, and ensures highly directional coverage along railway tracks. The antenna achieves measured peak gains of 7.96 dBi at 28 GHz and 8.20 dBi at 38 GHz, with excellent impedance matching and stable radiation patterns under mobility scenarios. Its unique combination of compact footprint, reflector-aided gain enhancement, and stable dual-band performance under dynamic conditions distinguishes it from conventional millimeter-wave solutions, making it a strong candidate for 5G-based high-speed railway communication modules and arrays.</div></div>","PeriodicalId":100607,"journal":{"name":"High-speed Railway","volume":"3 4","pages":"Pages 281-292"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
During the trial operation of a certain electric multiple unit, it was found that although the noise amplitude in the passenger compartment above the traction motor met the limit standard requirements when operating at speeds between 100 and 160 km/h. However, during the traction and braking processes, there were distinct frequency peaks in the traction motor noise, affecting passenger comfort. To improve the ride comfort during this speed range, without affecting the performance of the traction system, rectifications were made to address the motor noise issue. Measures such as adjusting the switching frequency and modifying the direct current voltage were proposed to optimize the traction control software. Through comparative testing of different control measures, the most effective control measure was selected, which effectively eliminated the single-frequency noise of the motor in this speed range. Additionally, a safety assessment was conducted to demonstrate that the new motor traction measures met the requirements for traction and operational reliability.
{"title":"Study on noise control and safety assessment of an EMU motor","authors":"Leiwei Zhu, Wenlong Ma, Yanju Zhao, Dawei Chen, Jianqiang Guo","doi":"10.1016/j.hspr.2025.09.001","DOIUrl":"10.1016/j.hspr.2025.09.001","url":null,"abstract":"<div><div>During the trial operation of a certain electric multiple unit, it was found that although the noise amplitude in the passenger compartment above the traction motor met the limit standard requirements when operating at speeds between 100 and 160 km/h. However, during the traction and braking processes, there were distinct frequency peaks in the traction motor noise, affecting passenger comfort. To improve the ride comfort during this speed range, without affecting the performance of the traction system, rectifications were made to address the motor noise issue. Measures such as adjusting the switching frequency and modifying the direct current voltage were proposed to optimize the traction control software. Through comparative testing of different control measures, the most effective control measure was selected, which effectively eliminated the single-frequency noise of the motor in this speed range. Additionally, a safety assessment was conducted to demonstrate that the new motor traction measures met the requirements for traction and operational reliability.</div></div>","PeriodicalId":100607,"journal":{"name":"High-speed Railway","volume":"3 4","pages":"Pages 318-324"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01DOI: 10.1016/j.hspr.2025.08.005
Ruiling Feng , Ou Wang , Zhenhao Zhang , Jing Huang , Yanping Wang
Peat soil is a loose, moisture-rich organic matter accumulation formed by the deposition of plants in swamps and lakes after their death. It is characterized by high moisture content, large void ratio, high compressibility, and strong rheological properties. These characteristics result in a complex consolidation process. A systematic understanding of the consolidation mechanism of peat soil is essential for elucidating its consolidation behavior. Previous studies have failed to provide consistent information on the microscopic morphology of peat soil. Moreover, quantitative studies on pore structure changes during peat soil consolidation remain lacking. To resolve these research gaps, the microscopic morphology and pore types of peat, highly organic peaty soil, and medium organic peaty soil from certain regions of Yunnan province, China, were observed and analyzed using scanning electron microscopy. Additionally, quantitative research on pore structure changes during peat soil consolidation was conducted. The results show that the humic acid in peat soil of Yunnan province has no pores, and there is no pore between humic acid and clay minerals. There are three typical pore structures, and the three typical pores were quantitatively analyzed. During consolidation, the consolidation deformation of peat soil is primarily caused by the internal pore compression of plant residues and pores between plant residues. At the same time, the revelation of the differentiated influence mechanism of load levels on the compression of inter/intra-plant residue pores. The decrease in the proportion of pores between plant residues first increased and then decreased with an increase in load, reaching a peak between 100–200 kPa. The decrease in pores inside the plant residues increased with an increasing load. Additionally, pore compression between the plant residues under different load levels primarily caused the compression deformation of Dali peat during the primary consolidation stage. By contrast, the pore compression inside the plant residues primarily caused the compression deformation during the secondary consolidation stage.
{"title":"Microstructure change rule during the consolidation process of peat soil from Yunnan province","authors":"Ruiling Feng , Ou Wang , Zhenhao Zhang , Jing Huang , Yanping Wang","doi":"10.1016/j.hspr.2025.08.005","DOIUrl":"10.1016/j.hspr.2025.08.005","url":null,"abstract":"<div><div>Peat soil is a loose, moisture-rich organic matter accumulation formed by the deposition of plants in swamps and lakes after their death. It is characterized by high moisture content, large void ratio, high compressibility, and strong rheological properties. These characteristics result in a complex consolidation process. A systematic understanding of the consolidation mechanism of peat soil is essential for elucidating its consolidation behavior. Previous studies have failed to provide consistent information on the microscopic morphology of peat soil. Moreover, quantitative studies on pore structure changes during peat soil consolidation remain lacking. To resolve these research gaps, the microscopic morphology and pore types of peat, highly organic peaty soil, and medium organic peaty soil from certain regions of Yunnan province, China, were observed and analyzed using scanning electron microscopy. Additionally, quantitative research on pore structure changes during peat soil consolidation was conducted. The results show that the humic acid in peat soil of Yunnan province has no pores, and there is no pore between humic acid and clay minerals. There are three typical pore structures, and the three typical pores were quantitatively analyzed. During consolidation, the consolidation deformation of peat soil is primarily caused by the internal pore compression of plant residues and pores between plant residues. At the same time, the revelation of the differentiated influence mechanism of load levels on the compression of inter/intra-plant residue pores. The decrease in the proportion of pores between plant residues first increased and then decreased with an increase in load, reaching a peak between 100–200 kPa. The decrease in pores inside the plant residues increased with an increasing load. Additionally, pore compression between the plant residues under different load levels primarily caused the compression deformation of Dali peat during the primary consolidation stage. By contrast, the pore compression inside the plant residues primarily caused the compression deformation during the secondary consolidation stage.</div></div>","PeriodicalId":100607,"journal":{"name":"High-speed Railway","volume":"3 4","pages":"Pages 293-304"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Automated detection of suspended anomalous objects on high-speed railway catenary systems using computer vision-based technology is a critical task for ensuring railway transportation safety. Despite the critical importance of this task, conventional vision-based foreign object detection methodologies have predominantly concentrated on image data, neglecting the exploration and integration of textual information. The currently popular multimodal model Contrastive Language-Image Pre-training (CLIP) employs contrastive learning to enable simultaneous understanding of both visual and textual modalities. Drawing inspiration from CLIP’s capabilities, this paper introduces a novel CLIP-based multimodal foreign object detection model tailored for railway applications, referred to as Railway-CLIP. This model leverages CLIP’s robust generalization capabilities to enhance performance in the context of catenary foreign object detection. The Railway-CLIP model is primarily composed of an image encoder and a text encoder. Initially, the Segment Anything Model (SAM) is employed to preprocess raw images, identifying candidate bounding boxes that may contain foreign objects. Both the original images and the detected candidate bounding boxes are subsequently fed into the image encoder to extract their respective visual features. In parallel, distinct prompt templates are crafted for both the original images and the candidate bounding boxes to serve as textual inputs. These prompts are then processed by the text encoder to derive textual features. The image and text encoders collaboratively project the multimodal features into a shared semantic space, facilitating the computation of similarity scores between visual and textual representations. The final detection results are determined based on these similarity scores, ensuring a robust and accurate identification of anomalous objects. Extensive experiments on our collected Railway Anomaly Dataset (RAD) demonstrate that the proposed Railway-CLIP outperforms previous state-of-the-art methods, achieving 97.25 % AUROC and 92.66 % F1-score, thereby validating the effectiveness and superiority of the proposed approach in real-world high-speed railway anomaly detection scenarios.
{"title":"Railway-CLIP: A multimodal model for abnormal object detection in high-speed railway","authors":"Jiayu Zhang , Qingji Guan , Junbo Liu , Yaping Huang , Jianyong Guo","doi":"10.1016/j.hspr.2025.06.001","DOIUrl":"10.1016/j.hspr.2025.06.001","url":null,"abstract":"<div><div>Automated detection of suspended anomalous objects on high-speed railway catenary systems using computer vision-based technology is a critical task for ensuring railway transportation safety. Despite the critical importance of this task, conventional vision-based foreign object detection methodologies have predominantly concentrated on image data, neglecting the exploration and integration of textual information. The currently popular multimodal model Contrastive Language-Image Pre-training (CLIP) employs contrastive learning to enable simultaneous understanding of both visual and textual modalities. Drawing inspiration from CLIP’s capabilities, this paper introduces a novel CLIP-based multimodal foreign object detection model tailored for railway applications, referred to as Railway-CLIP. This model leverages CLIP’s robust generalization capabilities to enhance performance in the context of catenary foreign object detection. The Railway-CLIP model is primarily composed of an image encoder and a text encoder. Initially, the Segment Anything Model (SAM) is employed to preprocess raw images, identifying candidate bounding boxes that may contain foreign objects. Both the original images and the detected candidate bounding boxes are subsequently fed into the image encoder to extract their respective visual features. In parallel, distinct prompt templates are crafted for both the original images and the candidate bounding boxes to serve as textual inputs. These prompts are then processed by the text encoder to derive textual features. The image and text encoders collaboratively project the multimodal features into a shared semantic space, facilitating the computation of similarity scores between visual and textual representations. The final detection results are determined based on these similarity scores, ensuring a robust and accurate identification of anomalous objects. Extensive experiments on our collected Railway Anomaly Dataset (RAD) demonstrate that the proposed Railway-CLIP outperforms previous state-of-the-art methods, achieving 97.25 % AUROC and 92.66 % <em>F</em><sub>1</sub>-score, thereby validating the effectiveness and superiority of the proposed approach in real-world high-speed railway anomaly detection scenarios.</div></div>","PeriodicalId":100607,"journal":{"name":"High-speed Railway","volume":"3 3","pages":"Pages 194-204"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145128396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01DOI: 10.1016/j.hspr.2025.08.003
Huimin Li , Lingfeng Li , Bin Liu , Ge Xin
High-Speed Trains (HSTs) have emerged as a mainstream mode of transportation in China, owing to their exceptional safety and efficiency. Ensuring the reliable operation of HSTs is of paramount economic and societal importance. As critical rotating mechanical components of the transmission system, bearings make their fault diagnosis a topic of extensive attention. This paper provides a systematic review of image encoding-based bearing fault diagnosis methods tailored to the condition monitoring of HSTs. First, it categorizes the image encoding techniques applied in the field of bearing fault diagnosis. Then, a review of state-of-the-art studies has been presented, encompassing both monomodal image conversion and multimodal image fusion approaches. Finally, it highlights current challenges and proposes future research directions to advance intelligent fault diagnosis in HSTs, aiming to provide a valuable reference for researchers and engineers in the field of intelligent operation and maintenance.
{"title":"Image encoding-based bearing fault diagnosis: Review and challenges for high-speed trains","authors":"Huimin Li , Lingfeng Li , Bin Liu , Ge Xin","doi":"10.1016/j.hspr.2025.08.003","DOIUrl":"10.1016/j.hspr.2025.08.003","url":null,"abstract":"<div><div>High-Speed Trains (HSTs) have emerged as a mainstream mode of transportation in China, owing to their exceptional safety and efficiency. Ensuring the reliable operation of HSTs is of paramount economic and societal importance. As critical rotating mechanical components of the transmission system, bearings make their fault diagnosis a topic of extensive attention. This paper provides a systematic review of image encoding-based bearing fault diagnosis methods tailored to the condition monitoring of HSTs. First, it categorizes the image encoding techniques applied in the field of bearing fault diagnosis. Then, a review of state-of-the-art studies has been presented, encompassing both monomodal image conversion and multimodal image fusion approaches. Finally, it highlights current challenges and proposes future research directions to advance intelligent fault diagnosis in HSTs, aiming to provide a valuable reference for researchers and engineers in the field of intelligent operation and maintenance.</div></div>","PeriodicalId":100607,"journal":{"name":"High-speed Railway","volume":"3 3","pages":"Pages 251-259"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145128401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号