Rail Quality Research Articles

Deep learning-based quality prediction for multi-stage sequential hot rolling processes in heavy rail manufacturing

Traditional quality control practices in heavy rail manufacturing primarily rely on experiential knowledge and numerical simulations. However, these methods come with significant drawbacks, including high costs, safety concerns, and limited accuracy due to the inadequate consideration of various influencing factors. Despite the accumulation of extensive data by some heavy rail manufacturers in recent years, achieving data-driven quality modeling remains a formidable challenge, mainly due to the complexity of the multi-stage sequential production process. This study presents the Temporal-Spatial Mapping approach to transform isochronous sampling data into spatially aligned data. Additionally, it introduces a multi-objective prediction model, Temporal-Fusion-LSTM (TFL), designed for evaluating the quality of heavy rails. The proposed model presents the Double-Layer LSTM with Time-Steps Fusion (DLL) architecture. The first layer of the DLL architecture targets the temporal transfer regularity within a single stage, while the second layer addresses the transition dynamics across multiple rolling stages in the heavy rail rolling process. Following this, the Local Process Correlation Matrix (LPCM) based on the Maximal Information Coefficient (MIC) is employed to empower the model to comprehend the intricate interactions among parameters in each stage of the rolling process. Finally, the Multi-Gate based Shared-Bottom architecture is employed to accentuate manufacturing processes highly correlated with the target quality indicators during multi-objective prediction. Real production data from a heavy rail factory is utilized to validate the effectiveness of the method. The experimental results unequivocally demonstrate that the proposed method accurately predicts heavy rail quality and facilitates cross-stage prediction, thus establishing the groundwork for data-driven quality diagnosis and pre-control in heavy rail production.

Experimental Study of Wheel-to-Rail Interaction Using Acceleration Sensors for Continuous Rail Transport Comfort Evaluation.

Rail transport comfort is ensured by predictive maintenance and continuous supervision of rail quality. Besides the specialized equipment, the authors are proposing a simple system that can be implemented on operational wagons while in service, aiming to detect irregularities in the rail and report them using the train's online communication lines. The sensor itself is an acceleration sensor connected to an electronic microcontroller able to filter the inrush acceleration and send it to the diagnosis system of the wagon. This paper presents a study of real data recorded of the transversal and vertical vibrations of a standard tank wagon, measured on 2 axles and the car body, followed by the interpretation of the recorded data.

The Effectiveness of Distributed Acoustic Sensing (DAS) for Broken Rail Detection

Broken rails remain one of the main causes of railway accidents despite improved rail quality and inspections. Today, signalling system with track circuits are often used to detect broken rails, however new signalling systems such as the European Train Control System (ETCS) with axle counters are replacing track circuits and therefore new methods are needed to detect broken rails. One promising technology is distributed acoustic sensing (DAS). The best DAS analytical techniques to show the position of the rail break are gradient analysis, convolution using the train consist and 2 D sinusoidal convolution. This paper describes field tests carried out on DAS to evaluate its ability to detect broken rails and the moment when rails break. The testing showed that DAS has good potential for detecting broken rails in both scenarios. Especially helpful is the ability of DAS to identify the moment of rail breakage and its potential for determining the break’s location on open lines. Recommendations for further research include testing these qualities in more detail and considering how DAS could be efficiently combined with new signalling systems.

Guidelines for rail quality selection to increase service life based on wear and fatigue behavior of various wheel and rail materials

The Austrian rail network is very diverse: The lines in the alpine areas have very tight radii while the lines in the flat areas (east and north of Austria) are mainly straight high-speed lines. This leads to different levels of wheel and rail wear. Accordingly, the objective of this study was to experimentally model a laboratory-scale cyclic wheel-rail contact to investigate wear behavior and rolling contact fatigue at different radii (RCF).A novel test system was set up at AC2T research GmbH to reproduce unidirectional loading on a real track. Tribotests were performed with rail (grades R260, R350HT & R400HT) and wheel (grades ER7 & ER9) parts from the field. This newly designed principle is an effective method to characterize the wheel-rail contact. Wear characterization was done after defined testing cycles to detect (i) area loss and (ii) change in surface topography.

Airline reactions to high-speed rail entry: Rail quality and market structure

• HSR affects air traffic directly and indirectly via airfare adjustment. • Airfare plays different roles in competition, feeding and long-term effects. • HSR quality and pre-entry airline market structure affect airfare adjustment. • Feeding effect dominates competition effect, causing more airline CO2 emissions. • Airfare adjustment mitigates HSR-induced air traffic and airline CO2 emissions. Airfare reduction is proposed by a theoretical paper to be a possible source of observed air traffic increase in some markets where high-speed rail (HSR) enters and competes with airlines. This paper aims to empirically test whether and to what extent the air traffic impact is channeled by the adjustment in airfares. To understand the varying empirical results found in the literature, we examine heterogeneous airline responses in traffic and airfare in relation to HSR qualities measured by HSR-air travel time difference and pre-entry market structure of airline as well as decompose HSR impacts into competition, feeding and long-term effects. Using a panel dataset of Chinese air routes, we find that airfare adjustment plays crucial roles in channeling HSR’s air traffic impact. Our estimation suggests that HSR introduced over 16.5 million additional passengers to the sampled air routes in our study period, generating 2.17 million tons of extra CO2 emissions from air flights. However, these numbers would increase to 32.2 million additional passengers and 3.4 million tons of extra CO2 emissions after removing the price adjustment.

Understanding the public rail quality of service towards commuters’ loyalty behavior in Greater Kuala Lumpur

Sustainability in urban transport mechanisms is a matter of significance in developing economies. Assessing the commuters’ behavior towards urban transport system facilitates the authorities to devise the policies for the safe and advanced choice of mobility. In the Klang Valley of Malaysia, the personal mobility practices have created the challenges of overcrowding the urban roads with automobile cars which resulted in economic, environmental, and infrastructure losses. The public rail transit system is deemed as the preferable choice of solution. To understand the perception of rail transit service attributes from commuters’ viewpoint, a quantitative study was conducted by accumulating Service Quality (SQ) of rail network towards Behavioural Intention or Loyalty (BI) of commuter to use the public transport. Satisfaction (SAT) was added as mediation between SQ and BI. An online survey was conducted that resulted in 141 commuters’ responses. The data were analyzed through Structural Equation Modelling (SEM) and it was found that SQ has a positive and significant impact on SAT and BI. The partial mediation was developed from the path analysis of the trio. The study strengthened the vitality of service quality features for enhancing the loyalty of denizens towards public transport mechanism. The research provided the attributes of transport services to focus on more for commuter integration.

A spatial coupling model to study dynamic performance of pantograph-catenary with vehicle-track excitation

In the high-speed railway industry, the pantograph-catenary system is responsible to provide continuous electric energy for the high-speed train. The pantograph-catenary system suffers multiple impacts from the complex work environment. The vehicle-track excitation is one of the normal disturbances to the pantograph-catenary interaction. Previous studies only consider the vertical effect of the vehicle-track vibration on the pantograph-catenary interaction. To address this deficiency, both of the pantograph-catenary and vehicle-track models are constructed in this paper. The validations of both models are verified by the experimental test and the world benchmark, respectively. The pantograph base follows the translations and rotations of the car-body caused by random rail irregularities. In combination with a spatial contact model between the contact wire and the pantograph strip, the spatial vibration of the carbody can be fully considered in the pantograph-catenary interaction. The statistical analysis, stochastic analysis and frequency analysis are performed to make sense of the effect of the random track irregularities on the pantograph-catenary interaction. The deviation of the contact point away from the strip centre caused by the carbody vibration is also analysed. The results show that the reliability of the pantograph-catenary system shows a continuous decrease in the degradation of rail quality. The carbody vibration may cause the de-wirement of the pantograph in extreme conditions. Finally, an application example is given to evaluate the dynamic performance of the pantograph-catenary system running on the China high-speed network with realistic rail irregularities.

Nonmetallic Inclusions in Rails Made of Electro-Steel Alloyed with Chromium

Based on metallographic (with an “OLYMPUS GX-51” microscope) and spectral (using spectrometer “ARL iSpark” method “Spark-DAT”) analyses, the relative concentration and size of most non-metallic inclusions for rail elements (head, web) from electro-steel of E79KhF and E90KhАF grades were determined. It was found that the highest relative concentration of manganese sulfides (MnS) is 30.8–43.4 ppm. At the same time, 60–100% of these inclusion types have a small size (less than 4 μm), and cannot be detected using standard metallographic analysis with 100-fold magnification. The revealed high relative-concentration of sulfide inclusions directly correlates with the established positive sulfur liquation in considered rail elements, which reaches up to 40%. Despite the high MnS concentration, their influence on the rail quality can be considered not dangerous, considering their high ductility during hot deformation and the prevalence of these inclusion types with a small size (less than 4 μm). Among silicate-type inclusions, SiO2 inclusions (3.4–14.9 ppm) have a significant concentration. All detected inclusions of this type have a size not exceeding 4 μm. It was found that the concentration of complex inclusions containing alumina (Al2O3–CaO–MgO, Al2O3–CaO–MgO–CaS, Al2O3–CaO, Al2O3–MgO) is insignificant: in total, it does not exceed 3.1 ppm and 1.6 ppm for individual types. The concentration of corundum (Al2O3) is also insignificant and does not exceed 0.3 ppm. In this case, small-sized alumina inclusions (less than 6 μm) prevail. Due to the low contamination (considering the relative concentration and size of inclusions) with non-plastic silicate and alumina non-metallic inclusions, their influence on the rail quality was not significant. It is confirmed by the absence of defects detected during ultrasonic testing.

Rail Quality Standards and Monitoring

Rail quality is essential to railroad safety. Therefore, it is of the utmost importance to establish the characteristics that affect rail life. The goal of the present work is to assess the expediency, necessity, and sufficiency of current quality requirements on rails. Prospective directions for research are suggested, with a view to improving the quality standards.

Influence of Electrosmelting Conditions on Rail Quality and Production Costs

Analysis of literature and production data shows that, despite significant gains in rail quality made possible in the past decade by the reequipment of Russian rail plants, the rejection rate of rails due to surface defects is still high. Research on the composition of rail steel shows that increase in copper content in the range 0.07–0.15% and in sulfur content in the range 0.006–0.011% in Э76XФ electrosteel at AO EVRAZ ZSMK significantly increases the rejection rate of rails due to surface defects. The mechanism by which the copper and sulfur concentration in the steel affects the rail quality is established. The ratio of iron and scrap in the metal batch is found to determine the copper and sulfur content in the rail steel: increase in the hotmetal content from 20 to 50% decreases the copper concentration and increases the sulfur content. To establish the optimal composition of the metal batch in the electrosmelting of rail steel, taking account of the relation between rail quality and the production economics, the influence of the ratio of iron (in liquid and solid forms) and scrap in the metal batch on electrofurnace performance is assessed. It is found that increasing the content of hot metal and pig iron in the metal batch results in linear decrease in power consumption, parabolic increase in oxygen consumption, and linear decrease in manganese content of the steel discharged from the furnace. The dependence of the smelting time on the proportion of batch components includes a minimum when the hot-metal content is 35–40% and the pig-iron content is 30–35%. On the basis of regression equations, we formulate a statistical model describing how the composition of the metal batch affects the overall performance of the electrosmelting shop in rail-steel production. Optimization is based on two factors: the total costs corresponding to the composition of the metal batch; and the productivity of the shop in terms of continuous-cast billet. This model permits recommendations regarding the optimal iron content in the metal batch at current prices of the batch materials and power, taking account of the change in shop productivity.

Rail Profile Measurement Based on Line-structured Light Vision

High-speed railway in China has undergone rapid development in recent years. Technology for structure measurement is recognized as an important aspect of steel rail quality inspection. The shape of the rail welding base is mainly gauged using mechanical contact measurement technology. Matching this technology with the escalating demands for quality inspection of steel rails is a challenging task. In this paper, a structured light measurement approach is proposed and employed which intersects the rail through the structural light plane projected by inner and outer laser sensors. These sensors form a laser light stripe curve containing the profile information of the rail surface. By processing laser light bars using image analysis and contour reduction techniques, 3-D profiles of the rails are generated. The laser plane is fitted using the coordinate points of the laser light bars converted between the image and world coordinate systems. A new calibration method based on the parallel moving target for line-structured light is proposed to improve the calibration and address the issue caused by the limited number of the extracted calibration points during free target calibration. The rail profile, including the geometric dimension, straightness, and twist of the rail, are then measured. By comparing the measured profile with the standard contour of the rails, the rail wear can then be quantitatively assessed. The experimental results show that the proposed measurement system outperforms the traditional single index detection.

Effect of Isothermal Bainitic Quenching on Rail Steel Impact Strength and Wear Resistance

The effect of heat treatment regimes on hardness, impact strength, and wear resistance of rail steel for high-speed tracks (rail quality category R350HT) is studied. Analysis of steel properties with a different structure is compared: pearlitic, and upper and lower bainite. It is shown that the steel with bainitic structure has the best impact strength, but wear resistance is better for steel with a lower bainite structure.

A Profile Measurement System for Rail Quality Assessment During Manufacturing

Steel rails used in the transport sector and in industry are designed and manufactured to support high stress levels generated by high-speed and heavy-loaded modern trains. In the rail manufacturing process, one of the key stages is rolling, where fast, accurate, and repeatable rail profile measurement is a major challenge. In this paper, a rail profile measurement system (PMS) for rail rolling mills based on four conventional, inexpensive laser range finders is proposed. The range finders are calibrated using a common reference to properly express the point clouds generated by each range finder in the world coordinate system (WCS). The alignment of the point clouds to the rail model is performed by means of an efficient and robust registration method. Experiments carried out in a rail rolling mill demonstrate the accuracy and repeatability of the system; the maximum error is below 0.12%. All parallelizable tasks were designed and developed to be executed concurrently, achieving an acquisition rate of up to 210 fps.

Improving the reduction and ladle treatment of Electrosteel for rail production

Research in the electrosmelting shop at OAO EVRAZ ZSMK indicates that, if inert gas is injected into molten rail steel in the ladle for 122 min, rather than 63 min, the quantity of nonmetallic oxide inclusions may be reduced, without impairing overall rail quality. Industrial experiments show that replacing MnS18 silicomanganese with FeMnSi30HP silicomanganese in the reduction of rail steel is economically effective in the electrosmelting shop at OAO EVRAZ ZSMK. The assimilation of carbon and silicon is increased by 4 and 13%, respectively. The mechanical properties and macrostructure of rails obtained by this experimental technology match those of the steel currently produced. According to the calculation results, the use of FeMnSi30HP ferroalloy provides savings of 13.99 and 32.64 rub/t for rails of category T1 and NE, respectively.

The Study of Finite Element Simulation for Cooling after Heating Process of Rail

Because of the non-uniformity of the section shape of rail and complexity of its temperature changing, the degree of thermal expansion and contraction of section must be different which leads to the interior stress is produced inevitable in it. The residual stress in rail is elastic stress and its maximum value is elastic limit stress. They affect the dimension stability, mechanical property, deformation and etc. And it is the important factor of rail quality. This paper builds a finite element model of temperature field through the MSC.Marc software during the process of heating and cooling of 55Q rail, which simulates the rail stress field of air cooling and water cooling. Our paper conducts the experiments on the rails of same material and condition and also selects the temperature and stress of appointed nodes to analyze them. The results of experiments and simulations are very identical. Simulating the residual stress of air cooling and water cooling, the result is that residual stress of water cooling is bigger than that of air cooling. This consequence gives the reference for planning the suitable heat treatment and improving the service life.

Technology and process optimisation of bloom casting of ultrahigh speed rail steel

Since 2008, rail steels have been manufactured at No. 1 Steelmaking works of Wuhan Iron and Steel Corporation (WISCO). Initially a high percentage of defective rails were produced resulting from excessive inclusions, centre porosity and carbon segregation. This paper summaries a research project to improve this performance between the steel plant personnel and Wuhan University of Science and Technology. Measures were implemented including adjusting the composition and performance of mould flux, adopting a four-hole submerged entry nozzle, reducing the specific spray water flow and lengthening the soft reduction position. These measures significantly improved rail quality. Ultrahigh speed rails produced by WISCO are widely applied on the 380 km h−1 Beijing–Shanghai and Wuhan–Guangzhou railways. More improvements should still be developed to obtain more competitive and reliable rails.

The Rail Quality Index as an Indicator of the “Global Comfort” in Optimizing Safety, Quality and Efficiency in Railway Rails

The proposed model uses the stochastic dynamic programming and in particular Markov decision processes applied to the Rail Quality Index (RQI - Italian Indice di Qualità del Binario, IQB).By performing the integrated analysis of the classes of variables which characterize the overall service quality (in terms of comfort and safety), the proposed mathematical approach allows to find the solutions to the decision-making process in function of the probability of deterioration of the state variables of the infrastructure over time and of the flow of available resources.

The Numerical Simulation of Horizontal Straightening for 60 kg/m Heavy Rail with Original Curvature

It has established the FEM model of nine horizontal roller straightening with original curvature for 60㎏/m heavy rail by using explicit dynamics software ANSYS/LS-DYNA in the paper, and it carried out the dynamic simulation process of the nine horizontal roller straightening, analyzed the stress changing rules of heavy rail in the seven deformation zones during the straightening process , even studied the value and distributive condition of residual stress after straightening, disclosed the mechanism of the residual stress in the heavy rail straightening process, and the paper is a guidance to improve heavy rail quality in straightening craft. It has the reference value to the design of heavy rail straightening machine and the formulation of the straightening regulations.

Status and prospects of NDT for rail quality at Kuznetsk Steel Works, Russia

The method and apparatus for automated non-contacting inspection of rails in the process of production are examined. Rails are tested by means of an ultrasonic mirror-shadow method with shear waves excited by electromagnetic acoustic transducers. The status of the eddy current method for rail inspection is also reviewed. The author recommends development of the eddy current method and instruments for detection of surface and below-surface defects in rails.

Contribution of railway dynamics codes to the understanding of the metallurgical behavior of the rail tread

The contact fatigue of rail treads affects railway networks exploiting high-speed straight lines and has been described in many articles (P.E. Bold et al., Wear, 144 (1990) 307–317; R.Y. Deroche et al., Rail Quality and Maintenance for Modern Railway Operation Conf, Delft, June 1992; A.F. Bower and K.L. Johnson, Wear, 144 1–18). The defect may be seen, at an advanced stage of development, as a subsiding of the rail tread due to a slightly inclined cracking. This leads to the formation of a characteristic black patch called a squat that can progress as a crack into the rail until breaking it completely. The origin of the defect is difficult to analyze. It has been believed for a long time that tangential stresses, associated with traction forces of locomotives, were of importance. However, this hypothesis, that should predict a higher probability of these defects on low-speed lines having heavy trains, does not fit with field experience that they develop mainly on high-speed lines and with inclined cracking. After having described the superficial rail tread residual stresses, this paper shows that it is possible to explain them using rail tread loading cases due to the effect of the hunting of high-speed locomotives, with or without traction forces. Loading cases are calculated with the help of the simulation VOCO codes developed by the INRETS.