Train Rolling Research Articles

Lessons learned from implementing a Human Factors programme into an NHS trust*

The interest in employing Human Factors (HF) in healthcare is increasing. There are very few papers that outline an approach to embedding the practical application of HF in healthcare and the lessons that can be learned. The SCReaM HF and Team Resource Management (TRM) programme is not only aimed at raising the awareness and understanding of the science of HF within healthcare, but also to embed its practical application to support staff improve their safety and wellbeing and that of their patients. The programme is divided into three strands: rolling training, HF Projects and HF Engineering. Each strand of the programme supports the use of HF by teaching and applying systems thinking methodology. The programme has been embedded into an NHS Trust and this paper provides a reflection on the approach used to help guide future attempts to integrate HF into an NHS trust.

ЕКСПЕРИМЕНТАЛЬНЕ ДОСЛІДЖЕННЯ ТОЧНОСТІ ПРОКАТКИ НА СТАНІ 800

The purpose of the work is an experimental study of the process of square sections rolling on the rolling mill 800 to determine the influence of rolling parameters on the dimensions and length of the roll. During the study, variations in ingot mass, rolling dimensions, and rolling length were determined, regression equations and correlation coefficients were obtained for the dependence of rolling dimensions and length on the ingot mass, changes in interroll gap and time delay before the finishing stand. It was established that the ingot mass variates within significant limits - 638 kg, which is caused by the melt mass variations. Variations in the mass of the ingot within one ingot mold stool are caused by the dimensions of the ingot molds and are within 154 kg. Variations in the dimensions of the roll are carried out within the following limits: thickness - 1.0 mm, width - 0.5 mm, length - 5.3 m. The change of the interroll gap can be used to correct the length of the finished roll in a small range of lengths, if the mass variations occur within accuracy of ingot casting on one ingot mold stool. It is necessary to take additional measures to stabilize the weight of the ingot. The influence of delays in the rolling train, which occur during rolling and lead to instability of the rolling temperature regime, for this type of profiles does not significantly affect the dimensions of the cross section and the length of the roll.

Freight train derailment severity prediction: a physics-informed one-dimensional model

Purpose Accurately estimating the severity of derailment is a crucial step in quantifying train derailment consequences and, thereby, mitigating its impacts. The purpose of this paper is to propose a simplified approach aimed at addressing this research gap by developing a physics-informed 1-D model. The model is used to simulate train dynamics through a time-stepping algorithm, incorporating derailment data after the point of derailment. Design/methodology/approach In this study, a simplified approach is adopted that applies a 1-D kinematic analysis with data obtained from various derailments. These include the length and weight of the rail cars behind the point of derailment, the train braking effects, derailment blockage forces, the grade of the track and the train rolling and aerodynamic resistance. Since train braking/blockage effects and derailment blockage forces are not always available for historical or potential train derailment, it is also necessary to fit the historical data and find optimal parameters to estimate these two variables. Using these fitted parameters, a detailed comparison can be performed between the physics-informed 1-D model and previous statistical models to predict the derailment severity. Findings The results show that the proposed model outperforms the Truncated Geometric model (the latest statistical model used in prior research) in estimating derailment severity. The proposed model contributes to the understanding and prevention of train derailments and hazmat release consequences, offering improved accuracy for certain scenarios and train types Originality/value This paper presents a simplified physics-informed 1-D model, which could help understand the derailment mechanism and, thus, is expected to estimate train derailment severity more accurately for certain scenarios and train types compared with the latest statistical model. The performance of the braking response and the 1-D model is verified by comparing known ride-down profiles with estimated ones. This validation process ensures that both the braking response and the 1-D model accurately represent the expected behavior.

The non-local effects of 7-week foot sole static stretching and foam rolling training on shoulder extension range of motion.

Static stretching and foam rolling can increase the range of motion (ROM) of a joint acutely as well as chronically. Although studies have reported ROM increases of a non-stretched heterologous muscle (non-local) following an acute static stretching or foam rolling session, these effects have not been studied for long-term training interventions. Therefore, the purpose of this study was to investigate the effects of a comprehensive 7-week static stretching and foam rolling training program of the foot sole on shoulder extension ROM. A total of 33 healthy, physically active participants (20 male) were assigned to either the intervention (n = 19) or control (n = 14) group. The intervention group performed a 7-week combined static stretching and foam rolling intervention comprising three sessions a week, including three exercises of the foot sole for 5 min each. Before and after the intervention period, the shoulder extension ROM was tested with three-dimensional (3D) motion caption. The level of significance for all statistical analyses was set to ρ ≤ 0.05. There was no significant time (p = 0.70, F1, 31 = 0.157; η2 = 0.005) or time×group effect (p = 0.38, F1, 31 = 0.785; η2 = 0.025) in shoulder extension ROM, indicating no ROM changes in the intervention or the control group. Although previous studies on the acute effects of stretching and foam rolling reported non-local increases in ROM in heterologous muscles, this study could show that such effects do not occur after chronic SS and foam rolling training for 7 weeks. Consequently, if the goal is to chronically increase the ROM of a specific joint, it is recommended to directly treat the muscles of interest.

Training effect of repeated rolling motions on boccia players with severe cerebral palsy: comparison with the effect of conventional upper-limb training using a crossover test.

[Purpose] The present study aimed to establish evidence regarding comparisons between training methods for boccia players with severe cerebral palsy. [Participants and Methods] Ten boccia players with severe cerebral palsy were enrolled in this study. This intervention had a cross-over design. Participants were divided into two groups based on the training method applied. The study period was divided into an upper extremity training period and an interval rolling training period, which lasted 4 weeks each. Each was separated by a 4-week training detraining period. Joint range of motion and throwing distance were measured before and after the interventions and the effects were compared and verified. [Results] Compared to upper extremity training, interval rolling training significantly expanded the range of motion and improved throwing distance in bocce players with severe cerebral palsy. [Conclusion] Collectively, interval rolling training is more effective than upper limb training in improving the physical function and throwing distance of boccia players with severe cerebral palsy.

ANN deformation prediction model for deep foundation pit with considering the influence of rainfall

Deep foundation pits involving complex soil–water-structure interactions are often at a high risk of failure under heavy rainfall. Predicted deformation is an important index for early risk warning. In the study, an ANN model is proposed based on the Wave Transform (WT), Copula method, Convolutional Neural Network (CNN) and Long Short-Term Memory Neural Network (LSTM). The total deformation was firstly decomposed into low and high frequency components with WT. The CNN and LSTM were then used for prediction of the two components with rolling training and prediction. The input variables of the CNN and LSTM were determined and optimized based on the correlations analysis of Copula method of the two components with different random variables, especially with the rainfall. And finally, the predicted total deformation was obtained by adding the two prediction components. A deep foundation pit in Chengdu, China was taken as a case study, of which the horizontal deformation curves at different measuring points shows three types of developed trend, as unstable, less stable, and stable types. The predictions of the deformations of different development types by the proposed ANN model show high accuracies with a few input variables and can accurately prompt risk warning in advance.

Sequence-to-sequence digital twin model in chemical plants with internal rolling training algorithm

A data-driven digital twin based on the sequence-to-sequence (StS) model is introduced in this study. The rolling training algorithm is presented as a plug-in in StS training to achieve long-term rolling predictions. The model performs long-term horizontal predictions over 8-days based on initial observed data and manipulation sequence conditions without any new historical inputs. The digital twin model is validated using the dynamic simulation of the vapor-recompression C3 process. When the rolling training algorithm is used, the StS model demonstrates the best predictions than the traditional artificial neural network model and simple StS model for 1- and 8-days tests. Moreover, noise added cannot affect the prediction performance of StS with rolling training, and the step-change test validated the StS with rolling training containing physical meaning. Hence, the proposed StS model is a data-driven digital twin having physical interpretability. The StS model can implement long-term rolling predictions for days.

Study of stress intensity factors in sliding and tearing modes for subsurface elliptical cracks in rolling train wheels

AbstractIn the railway systems, induced contact between wheels and rails creates maximum shear stress around the contact surfaces. These shear stresses vary with the wheel's rolling and can initiate and extend subsurface cracks in the wheel and rail. The most common subsurface cracks in the rail systems have elliptical forms. Sliding and tearing modes of the fracture can be observed due to different components of the shear stresses around the contact area. Compressive normal stress has no considerable effects on in‐plane and out‐of‐plane shear modes for subsurface cracks. In this research, by proper modeling of the wheel and rail, the effects of dimensions, position, and depth of the subsurface cracks on the stress intensity factors of the sliding (KII) and tearing (KIII) modes have been investigated. Also, variations of the KII and KIII values versus wheel rolling angles and frictions have been considered. The validity and accuracy of the cracked model created by sub‐modeling technique have been verified by half‐space modeling and weight function method.

Remote effects of a 7-week combined stretching and foam rolling training intervention of the plantar foot sole on the function and structure of the triceps surae

It is known that a single bout of foam rolling (FR) or stretching can induce changes in range of motion (ROM) and performance in non-directly adjoining areas of the dorsal chain (i.e., remote effects). However, to date, it is not known if such effects exist following long-term interventions. Thus, the purpose of this study was to investigate the remote effects of a 7-week combined stretching and FR training intervention of the plantar foot sole. Thirty-eight recreational athletes were randomly assigned to either an intervention (n = 20) or control (n = 18) group. The intervention group performed stretching and FR exercises of the plantar foot sole for 7 weeks. Before and after the intervention, the dorsiflexion ankle ROM, passive resistive torque at maximum angle (PRTmax) and at a fixed angle, as well as maximum voluntary isometric contraction (MVIC) torque, were measured with a dynamometer. Gastrocnemius medialis and lateralis stiffness was assessed with shear wave elastography. The results showed no interaction effect for any of the parameters. There was a time effect indicating an increase in MVIC and PRTmax, which was more pronounced in the intervention group (+ 7.4 (95% CI 2.5–12.4), + 4.5 (95% CI − 0.2–9.2)) than the control group (+ 3.6 (95% CI − 1.4–8.6), + 4.0 (95% CI − 2.2 to 10.2)). The results indicate no or minor remote effects of combined stretching and FR of the foot sole in the ankle joint. Potential non-significant changes in ROM were accompanied with an increase in stretch tolerance, but not with changes in muscle structure.

Functional forecasting of dissolved oxygen in high‐frequency vertical lake profiles

AbstractPredicting dissolved oxygen (DO) in lakes is important for assessing environmental conditions as well as reducing water treatment costs. High levels of DO often precede toxic algal blooms, and low DO causes carcinogenic metals to precipitate during water treatment. Typically, DO is predicted from limited data sets using hydrodynamic modeling or data‐driven approaches like neural networks. However, functional data analysis (FDA) is also an appropriate modeling paradigm for measurements of DO taken vertically through the water column. In this analysis, we build FDA models for a set of profiles measured every 2 hours and forecast the entire DO percent saturation profile from 2 to 24 hours ahead. Functional smoothing and functional principal component analysis are applied first, followed by a vector autoregressive model to forecast the empirical functional principal component (FPC) scores. Rolling training windows adapt to seasonality, and multiple combinations of window sizes, model variables, and parameter specifications are compared using both functional and direct root mean squared error metrics. The FPC method outperforms a suite of comparison models, and including functional pH, temperature, and conductivity variables improves the longer forecasts. Finally, the FDA approach is useful for identifying unusual observations.

The Effects of Foam Rolling Training on Performance Parameters: A Systematic Review and Meta-Analysis including Controlled and Randomized Controlled Trials.

Foam rolling (FR) is a new and popular technique for increasing range of motion. While there are a few studies that demonstrate increased performance measures after an acute bout of FR, the overall evidence indicates trivial performance benefits. As there have been no meta-analyses on the effects of chronic FR on performance, the objective of this systematic meta-analytical review was to quantify the effects of FR training on performance. We searched PubMed, Scopus, the Cochrane library, and Web of Science for FR training studies with a duration greater than two weeks, and found eight relevant studies. We used a random effect meta-analysis that employed a mixed-effect model to identify subgroup analyses. GRADE analysis was used to gauge the quality of the evidence obtained from this meta-analysis. Egger’s regression intercept test (intercept 1.79; p = 0.62) and an average PEDro score of 6.25 (±0.89) indicated no or low risk of reporting bias, respectively. GRADE analysis indicated that we can be moderately confident in the effect estimates. The meta-analysis found no significant difference between FR and control conditions (ES = −0.294; p = 0.281; I2 = 73.68). Analyses of the moderating variables showed no significant differences between randomized control vs. controlled trials (Q = 0.183; p = 0.67) and no relationship between ages (R2 = 0.10; p = 0.37), weeks of intervention (R2 = 0.17; p = 0.35), and total load of FR (R2 = 0.24; p = 0.11). In conclusion, there were no significant performance changes with FR training and no specific circumstances leading to performance changes following FR training exceeding two weeks.

Improving Probabilistic Quantitative Precipitation Forecasts Using Short Training Data through Artificial Neural Networks

Abstract Conventional statistical postprocessing techniques offer limited ability to improve the skills of probabilistic guidance for heavy precipitation. This paper introduces two artificial neural network (ANN)-based, geographically aware, and computationally efficient postprocessing schemes, namely, the ANN-multiclass (ANN-Mclass) and the ANN–censored, shifted gamma distribution (ANN-CSGD). Both schemes are implemented to postprocess Global Ensemble Forecast System (GEFS) forecasts to produce probabilistic quantitative precipitation forecasts (PQPFs) over the contiguous United States (CONUS) using a short (60 days), rolling training window. The performances of these schemes are assessed through a set of hindcast experiments, wherein postprocessed 24-h PQPFs from the two ANN schemes were compared against those produced using the benchmark quantile mapping algorithm for lead times ranging from 1 to 8 days. Outcomes of the hindcast experiments show that ANN schemes overall outperform the benchmark as well as the raw forecast over the CONUS in predicting probability of precipitation over a range of thresholds. The relative performance varies among geographic regions, with the two ANN schemes broadly improving upon quantile mapping over the central, south, and southeast, and slightly underperforming along the Pacific coast where skills of raw forecasts are the highest. Between the two schemes, the hybrid ANN-CSGD outperforms at higher rainfall thresholds (i.e., >50 mm day−1), though the outperformance comes at a slight expense of sharpness and spatial specificity. Collectively, these results confirm the ability of the ANN algorithms to produce skillful PQPFs with a limited training window and point to the prowess of the hybrid scheme for calibrating PQPFs for rare-to-extreme rainfall events.

Train rolling stock video segmentation and classification for bogie part inspection automation: a deep learning approach

Train rolling stock examination (TRSE) is a physical procedure for inspecting the bogie parts during transit at a little over 30 kmph. Currently, this process is manually performed across many railway networks across the world. This work proposes to automate the process of TRSE using artificial intelligence techniques. The previous works have proposed active contour-based models for the segmentation of bogie parts. Though accurate, the models require manual intervention and are found to be iterative making them unsuitable for real-time operations. In this work, we propose a segmentation model followed by a deep learning classifier that can accurately increase the deployability of such systems in real time. We apply the UNet model for the segmentation of bogie parts which are further classified using an attention-based convolutional neural network (CNN) classifier. In this work, we propose a shape deformable attention model to identify shape variations occurring in the video sequence due to viewpoint changes during the train movement. The TRSNet is trained and tested on the high-speed train bogie videos captured across four different trains. The results of the experimentation have been shown to improve the recognition accuracy of the proposed system by 6% over the state-of-the-art classifiers previously developed for TRSE.

An innovative forecasting model to predict wind energy.

In recent years, the global wind power construction is accelerating. Although wind power is a clean energy without pollution, its volatility and irregularity have a great impact on wind power integration. Therefore, scholars pay more and more attention to the ultra-short-term prediction of wind speed. At present, the popular wind speed prediction model usually combines wind speed decomposition algorithm, machine learning algorithm, and intelligent optimization algorithm. The general wind speed decomposition algorithm cannot use the information contained in the factors affecting wind speed. Besides, the current popular optimization algorithms, such as gray wolf optimization algorithm, have strong convergence and better optimization effect, but their structure is complex and their operation complexity is large. And the PSO algorithm has simple structure and fast operation speed. To solve the above problems, a novel combination prediction model is proposed in this paper. This model uses VMD to decompose the wind speed into high-frequency signal and low-frequency signal and then uses principal component analysis and spectral clustering to extract and classify the influencing factors. In addition, aiming at the problem of slow convergence speed in the later stage of PSO iteration, an adaptive improved PSO is proposed. Finally, this paper also designs a rolling train method to adjust the size of training samples. Through four experiments of wind speed series in two periods, it is proved that the combined prediction model proposed in this paper has the following advantages: the model fully extracts the information of wind speed and influencing factors; the improved PSO algorithm has better optimization effect; rolling training method effectively improves the prediction ability of the model; the combined forecasting model has good adaptability and competitiveness.

Optimization method of urban rail train operational plan based on O-D time-varying demand

PurposeUnder the constraints of given passenger service level and coupling travel demand with train departure time, this study optimizes the train operational plan in an urban rail corridor to minimize the numbers of train trips and rolling stocks considering the time-varying demand of urban rail passenger flow.Design/methodology/approachThe authors optimize the train operational plan in a special network layout, i.e. an urban rail corridor with dead-end terminal yard, by decomposing it into two sub-problems: train timetable optimization and rolling stock circulation optimization. As for train timetable optimization, the authors propose a schedule-based passenger flow assignment method, construct the corresponding timetabling optimization model and design the bi-directional coordinated sequential optimization algorithm. For the optimization of rolling stock circulation, the authors construct the corresponding optimization assignment model and adopt the Hungary algorithm for solving the model.FindingsThe case study shows that the train operational plan developed by the study's approach meets requirements on the passenger service quality and reduces the operational cost to the maximum by minimizing the numbers of train trips and rolling stocks.Originality/valueThe example verifies the efficiency of the model and algorithm.

A Survey on Fault Diagnosis Approaches for Rolling Bearings of Railway Vehicles

This paper reviews the current research status of rolling bearing fault diagnosis technology for railway vehicles. Several domains are covered, including vibration fault diagnosis, acoustic signal fault diagnosis, and temperature prediction diagnosis methods on train rolling bearing test principles and related research. The application scenarios, system diagnosis accuracies, and model structures of various studies in the literature are also compared and analyzed. Furthermore, the main technical points to be improved and the analysis of the possible research directions are proposed, which provide new research ideas for subsequent fault diagnosis methods and system innovation research and development.

Online prediction of total sugar content and optimal control of glucose feed rate during chlortetracycline fermentation based on soft sensor modeling.

In the process of chlortetracycline (CTC) fermentation, no instrument can be used to measure the total sugar content of the fermentation broth online due to its high viscosity and large amount of impurities, so it is difficult to realize the optimal control of glucose feed rate in the fermentation process. In order to solve this intractable problem, the relationship between on-line measurable parameters and total sugar content (One of the parameters that are difficult to measure online) in fermentation tank is deeply analyzed, and a new soft sensor model of total sugar content in fermentation tank and a new optimal control method of glucose feed rate are proposed in this paper. By selecting measurable variables of fermentation tank, determining different fermentation stages, constructing recursive fuzzy neural network (RFNN) and applying network rolling training method, an online soft sensor model of total sugar content is established. Based on the field multi-batch data, the change trend of the amount of glucose feed required at each fermentation stage is divided, and the online prediction of total sugar content and the optimal control strategy of glucose feed rate are realized by using the inference algorithm of expert experience regulation rules and soft sensor model of total sugar content. The experiment results in the real field demonstrate that the proposed scheme can effectively predict the total sugar content of fermentation broth online, optimize the control of glucose feed rate during fermentation process, reduce production cost and meet the requirements of production technology.

Train Rolling Stock Video Segmentation and Classification for Bogie Part Inspection Automation: A Deep Leaning Approach

Train Rolling Stock Video Segmentation and Classification for Bogie Part Inspection Automation: A Deep Leaning Approach

Integrated Train Timetabling and Rolling Stock Circulation Planning for a Metro Line with Multiple Depots

With the expansion of metro networks, it is common that a metro line is equipped with multiple depots. The operation costs of rail operators and the passenger satisfaction are highly dependent on train timetables and rolling stock circulation plans, which are closely related to each other. Therefore, it is important to investigate the integrated train timetabling and rolling stock circulation planning problem for metro lines with multiple depots. A mixed integer linear programming formulation is proposed to generate train timetables and rolling stock circulation plans simultaneously for a metro line with multiple depots, in which the capacity of each depot and the rolling stock balances between depots are considered. Several numerical experiments based on real-world data of Beijing Subway Line 5 and Beijing Subway Line 6 are carried out to demonstrate the effectiveness of the presented model.

Fault Diagnosis for Rolling Bearings of a Freight Train under Limited Fault Data: Few-Shot Learning Method

In recent years, many machine learning-based methods have emerged to detect faulty bearings. However, most of these methods may not be practical due to the need to collect a large number of fault samples for training. This paper developed a novel few-shot learning framework for the fault diagnosis of freight train rolling bearings. The proposed method has the capability to transfer the learning outcome from one bearing fault diagnosis model to another different but related task for which very limited training data are available. The authors established a single-wheelset platform to collect acceleration signals of different types of bearing faults. The authors preprocessed the data through data segmentation and frequency domain transformation, and divided the data into training and test sets according to a certain ratio. A one-dimensional convolutional neural network (1D-CNN) was established to automatically extract the features of the bearing vibration signals and classify the fault types. The authors implemented two few-shot learning methods through parameter fine-tuning and a conditional Wasserstein generative adversarial network (C-WGAN). A case study demonstrated the classification performance of the proposed models. The results showed that the diagnosis capability of the 1D-CNN in the frequency domain is significantly superior to that in the time domain. However, when the amount of data is small, the 1D-CNN model does not work. In contrast, the few-shot learning of bearing faults works well for both the fine-tuned CNN and C-WGAN models. Furthermore, the classification performance of the C-WGAN is better than that of the fine-tuned CNN when the training data are extremely limited.