Railway Track Recognition Based on Radar Cross-Section Statistical Characterization Using mmWave Radar

The track settlement has a great influence on the safe operation of high-speed trains. The existing track settlement measurement approach requires sophisticated or expensive equipments, and the real-time performance is limited. To address the issue, an ultra-high resolution track settlement detection method is proposed by using millimeter wave radar based on frequency modulated continuous wave (FMCW). Firstly, by constructing the RCS statistical feature data set of multiple objects in the track settlement measurement environment, a directed acyclic graph-support vector machine (DAG-SVM) based method is designed to solve the problem of track recognition in multi-object scenes. Then, the adaptive chirp-z-transform (ACZT) algorithm is used to estimate the distance between the radar and the track surface, which realizes automatic real-time track settlement detection. An experimental platform has been constructed to verify the effectiveness of the proposed method. The experimental results show that the accuracy of track classification and identification is at least 95%, and the accuracy of track settlement measurement exceeds 0.5 mm, which completely meets the accuracy requirements of the railway system.

Eksplorasi dan analisis kondisi perkerasan jalan pada jembatan rangka baja Soekarno-Hatta Malang pada bulan Maret 2015 menggunakan metode ground penetrating radar (GPR)

This research that purpose to explore and analyz the structure condition of pavement on the Soekarno-Hatta’s Malang truss bridge by using GPR method. GPR is used to knowing type of material objects based on dielectric constant of every materials, and to showing deformation, cracking, release structure, and water seepage. Data collected by observation techniques and retrieval of data sanples at 101 point of the track. Analysis starts from the stage of processing by using Ms.Excel, notepad, paint, software GeoScan32, and interpreted using software Surfer 9.0. The result is showing that the road pavement structure consists of a flexible pavement asphalt and rigid pavement concrete by identified the type of material is dry asphalt, wet asphalt, dry concrete, wet concrete, and air on surface. Deformation occurred in all of track pavement and there are a few sample points are experienced track surface defect such as cracks and release the structure. The most damage with average value 1.67and 1.69 that occur on the second and third of track, start from track 34-67 and 68-100. The postiton is located in point 33-66 m dan 67-99 m from Surabaya (north of bridge). Mapping result of cracking and release structure showing that 90 percent of pavement on Soekarno-Hatta’s bridge are damage. Water seepage that occur when the water breaking through the subsurface layers (asphalt) until concrete layer in base ground by content wet materal. Data distribution of pavement area that most occur water seepage on track 35-67 it’s on point 33-66 m. Penelitian ini bertujuan untuk mengeksplorasi dan menganalisis kondsi struktur lapisan perkerasan jalan pada jembatan rangka baja Soekarno-Hatta Malang dengan metode Ground Penetratig Radar (GPR). GPR digunakan untuk mengetahui jenis material objek berdasarkan konstanta dielektrik yang dimiliki setiap material, serta untuk melihat adanya defomasi, retak, pelepasan struktur, serta rembesan air. Pengumpulan data dilakukan dengan menggunakan teknik observasi lapangan dan pengambilan data sampel pada 101 titik lintasan di analisis dengan teknik deskriptif kuantitaif menggunakan Ms.Excel, notepad, paint, software GeoScan32, dan di interpretasikan dalam software Surfer 9.0. Hasil penelitian menunjukkan bahwa struktur perkerasan jalan terdiri dari perkerasan lentur aspal dan perkerasan kaku beton yang diketahui berupa lantai kendaraan dengan jenis material pada perkerasan yang dapat teridentifikasi adalah aspal kering, aspal basah, beton kering, beton basah,dan adanya udara dipemukaan. Deformasi terjadi pada semua lintasan dan di beberapa titik lintasan teridentifikasi mengalami retak dan pelepasan struktur. Kerusakan terbanyak dengan nilai rata-rata 1,67 dan 1,69 diketahui terjadi pada bagian yang kedua dan ketiga, yaitu dimulai pada lintasan ke 34-67 dan 68-100. Posisi terletak pada bentang ke 33-66 meter dan 67-99 meter dari arah Surabaya (utara jembatan). Hasil pemetaan retak dan pelepasan lapisan menunjukkan 90 persen dari perkerasan jalan pada Jembatan Soekaro-Hatta telah mengalami kerusakan. Rembesan terjadi ketika air menerobos lapisan permukaan (aspal) bagian bawah hingga menembus lapisan beton di dasar permukaan dengan indikator konten material basah. Data persebaran daerah perkerasan jalan yang banyak mengalami rembesan air terjadi pada lintasan 35-67 yaitu pada posisi bentang ke 33-66 meter.

A Study on Railway Surface Defects Detection Based on Machine Vision

The detection of rail surface defects is an important tool to ensure the safe operation of rail transit. Due to the complex diversity of track surface defect features and the small size of the defect area, it is difficult to obtain satisfying detection results by traditional machine vision methods. The existing deep learning-based methods have the problems of large model sizes, excessive parameters, low accuracy and slow speed. Therefore, this paper proposes a new method based on an improved YOLOv4 (You Only Look Once, YOLO) for railway surface defect detection. In this method, MobileNetv3 is used as the backbone network of YOLOv4 to extract image features, and at the same time, deep separable convolution is applied on the PANet layer in YOLOv4, which realizes the lightweight network and real-time detection of the railway surface. The test results show that, compared with YOLOv4, the study can reduce the amount of the parameters by 78.04%, speed up the detection by 10.36 frames per second and decrease the model volume by 78%. Compared with other methods, the proposed method can achieve a higher detection accuracy, making it suitable for the fast and accurate detection of railway surface defects.

HOT COMPACTION PROCESS OPTIMIZATION FOR IMPROVEMENT TRIBOLOGY BEHAVIOR OF ZIRCONIUM SILICATE STRENGTHENED BMCS

The paper describes the optimization of the hot compaction process to simultaneously increase hardness and decrease the wear coefficient of zirconium silicate reinforced BMCs. L9 orthogonal array is chosen for setup the experiment. Examining the influencing parameters is carried out on factors such as pressure, temperature, particle size, and particle content. Grey relation analysis is used to investigate to produce an optimal combination of parameter levels. The transmission electron scanning is used to study the morphology of zirconium silicate. The wear coefficient of the specimen was investigated by using the weight loss method. A scanning electron microscope was carried out to evaluate the wear track surface of the composite. The test results show that the particle size is the most influential hot compaction parameter. The optimal conditions for the hot compacting process are the temperature level at 350 °C, the pressure level at the 400 MPa level, the particle content level at 12 % weight, and the particle size level at 80 µm. In this optimal condition, the prediction GR-Grade value is 0.695. The validation test results showed that the GR-Grade value increased by 0.15, the hardness increased by 25%, and the wear coefficient decreased by 53%. This optimization method with Gray Relational Analysis has proven to be effective in the hot compaction process for improving the tribology behavior of the composites.

Remote Emergency Braking System for Autonomous Racing Electric Vehicles

Advanced brake assist systems can avoid road accidents since the vehicles impact speed can be significantly reduced. To this end, different autonomous emergency braking systems are designed for recent vehicles on the market. This paper presents a pneumo-hydraulic Emergency Braking System (EBS) for autonomous racing vehicles. The purpose of the system is safely stopping the vehicle in case of any failures during autonomous driving. Failures can be detected both by the autonomous system itself and by human supervisors. The actuation system involves passive energy storage of compressed air to directly activate the hydraulic braking lines through pneumo-hydraulic pressure intensifiers. The coupling component between failures detection and actuation is a normally-open solenoid valve. The system is designed to respect deceleration and actuation time requirements, together with packaging constraints due to integration in an existing racing prototype. Specifically, the system requirements are specified by the racing competition rules: the overall reaction time of the retained EBS must be lower than 0.2 s, and the actuated mean deceleration must be greater than 8 m/s2 on a dry track surface while keeping stable driving conditions. The validation and tuning of the system is performed in a simulated environment. Therefore, an extensive experimental validation of the system is required in the real applications.

Analysis of Dynamic Response of a Railway Locomotive Using ANSYS

Transient dynamic analysis (sometimes called time-history analysis) is a technique used to determine the dynamic response of a structure under the action of any general time-dependent loads. The time scale of the loading is such that the inertia or damping effects are considered to be important. Present work is focused on performing the time history analysis of a typical locomotive coach using finite element analysis in Indian railroad conditions. Track surface irregularity in the form of an ellipsoidal bump is modelled with assumptions that the vehicle passes over the bump in 0.144 seconds, variation in displacement at different key locations of the truck and car body models is plotted against time under standard loading conditions. The response pattern of the front and rear portions of the locomotive truck and car body indicate that these locations are more susceptible to wheel excitations compared to that of the centre portions of it as they are away from the centre of gravity of the vehicle due to unbalanced mass distribution.

A Novel Decomposition Model for Visual Rail Surface Inspection

Rail surface inspection plays a pivotal role in large-scale railway construction and development. However, accurately identifying possible defects involving a large variety of visual appearances and their dynamic illuminations remains challenging. In this paper, we fully explore and use the essential attributes of our defect structure data and the inherent temporal and spatial characteristics of the track to establish a general theoretical framework for practical applications. As such, our framework can overcome the bottleneck associated with machine vision inspection technology in complex rail environments. In particular, we consider a differential regular term for background rather than a traditional low-rank constraint to ensure that the model can tolerate dynamic background changes without losing sensitivity when detecting defects. To better capture the compactness and completeness of a defect, we introduce a tree-shaped hierarchical structure of sparse induction norms to encode the spatial structure of the defect area. The proposed model is evaluated with respect to two newly released Type-I/II rail surfaces discrete defects (RSDD) data sets and a practical rail line. Qualitative and quantitative evaluations show that the decomposition model can handle the dynamics of the track surface well and that the model can be used for structural detection of the defect area.