scholarly journals An AdaBoost-Based Intelligent Driving Algorithm for Heavy-Haul Trains

Actuators ◽  
2021 ◽  
Vol 10 (8) ◽  
pp. 188
Author(s):  
Siyu Wei ◽  
Li Zhu ◽  
Lijie Chen ◽  
Qingqing Lin
Keyword(s):  
Classification Performance ◽  
Control Mode ◽  
Random Forest Algorithm ◽  
Adaboost Algorithm ◽  
Automatic Driving ◽  
Train Control ◽  
Train Operation ◽  
Heavy Haul ◽  
Heavy Haul Trains ◽  
Cart Algorithm

Heavy-haul trains have the characteristics of large volume, long formation, and complex line conditions, which increase the driving difficulty of drivers and can easily cause safety problems. In order to improve the safety and efficiency of heavy-haul railways, the train control mode urgently needs to be developed towards the direction of automatic driving. In this paper, we take the Shuohuang Railway as the research background and analyze the train operation data of SS4G locomotives. We find that the proportion of operation data under different working conditions is seriously out of balance. Aiming at this unbalanced characteristic, we introduce the classification method in the field of machine learning and design an intelligent driving algorithm for heavy-haul trains. Specifically, we extract the data by random forest algorithm and compare the classification performance of C4.5 and CART algorithms. We then select the CART algorithm as the base classifier of the AdaBoost algorithm to build the model of the automatic air brake. For the purpose of heightening the precision of the model, we optimize the AdaBoost algorithm by improving the generation of training subsets and the weight of voting. The numerical results certify the effectiveness of our proposed approach.

scholarly journals Guidance and evaluation system for smooth operation of heavy-haul trains

2020 ◽  
Vol 2 (3) ◽  
pp. 226-235
Author(s):  
Zhi Zhang ◽  
Xiang Wei ◽  
Tao Zhang ◽  
Songxu Wang
Keyword(s):  
Real Time ◽  
Impact Force ◽  
Guidance System ◽  
Evaluation Standard ◽  
Operation Rules ◽  
Train Operation ◽  
Heavy Haul ◽  
Actual Operation ◽  
Heavy Haul Trains ◽  
The Impact

Abstract The operation rules and methods for heavy-haul trains were studied and summarized according to the characteristics of the Daqin Railway, such as a large traffic volume, a high density and high-speed and difficult-to-operate heavy-haul trains. Combined with traction calculation and operation experience, these can be quantificationally decomposed into an evaluation standard for the smooth modularized operation of heavy-haul trains that can be recognized by computers. A train operation guidance system was designed to collect locomotive drivers’ operation data, display the actual operation and standard curves in real time and give voice prompts and violation-operation alarms for safety-critical operation. In addition, software for operation analysis and evaluation was developed according to the quantified smooth operation standard. The smooth operation of heavy-haul trains was evaluated and statistically analysed through a comparative analysis of the actual operation records. Moreover, a train impact force detection device capable of monitoring the three-dimensional impact force of heavy-haul trains in real time was developed. Meanwhile, the evaluation standard for smooth operation was verified and optimized by real-time monitoring of the impact force of heavy-haul trains. Finally, on the basis of the above studies, a complete closed-loop management scheme for the smooth operation of heavy-haul trains was constructed, and the objectives of optimizing train operation strategy, standardizing drivers’ operations and ensuring the smooth operation of trains were realized through application.

Relative train length and the infrastructure required to mitigate delays from operating combinations of normal and over-length freight trains on single-track railway lines in North America

2018 ◽  
Vol 233 (7) ◽  
pp. 731-742 ◽  
Author(s):  
C Tyler Dick ◽  
Ivan Atanassov ◽  
F Bradford Kippen ◽  
Darkhan Mussanov
Keyword(s):  
North America ◽  
Simulation Software ◽  
Single Track ◽  
Delay Performance ◽  
Expansion Strategy ◽  
Train Operation ◽  
Heavy Haul ◽  
Directional Preference ◽  
Directional Distributions ◽  
Train Length

Distributed power locomotives have facilitated longer heavy-haul freight trains that improve the efficiency of railway operations. In North America, where the majority of mainlines are single track, the potential operational and economic advantages of long trains are limited by the inadequate length of many existing passing sidings (passing loops). To alleviate the challenge of operating trains that exceed the length of passing sidings, railways preserve the mainline capacity by extending passing sidings. However, industry practitioners rarely optimize the extent of infrastructure investment for the volume of over-length train traffic on a particular route. This paper investigates how different combinations of normal and over-length trains, and their relative lengths, relate to the number of siding extensions necessary to mitigate the delay performance of over-length train operation on a single-track rail corridor. The experiments used Rail Traffic Controller simulation software to determine train delay for various combinations of short and long train lengths under different directional distributions of a given daily railcar throughput volume. Simulation results suggest a relationship between the ratio of train lengths and the infrastructure expansion required to eliminate the delay introduced by operating over-length trains on the initial route. Over-length trains exhibit delay benefits from siding extensions while short trains are relatively insensitive to the expanded infrastructure. Assigning directional preference to over-length trains improves the overall average long-train delay at the expense of delay to short trains. These results will allow railway practitioners to make more informed decisions on the optimal incremental capital expansion strategy for the operation of over-length trains.

Non-Stationary Random Vibration Analysis of Railway Bridges Under Moving Heavy-Haul Trains

2018 ◽  
Vol 18 (03) ◽  
pp. 1850035 ◽  
Author(s):  
Zhihui Zhu ◽  
Lidong Wang ◽  
Zhiwu Yu ◽  
Wei Gong ◽  
Yu Bai
Keyword(s):  
Random Vibration ◽  
Vertical Acceleration ◽  
Railway Bridges ◽  
Coupling System ◽  
Ballasted Track ◽  
Heavy Haul ◽  
Train Speed ◽  
Track Irregularity ◽  
Heavy Haul Trains ◽  
Track Bridge

This paper presents a non-stationary random vibration analysis of railway bridges under moving heavy-haul trains by the pseudo-excitation method (PEM) considering the train-track-bridge coupling dynamics. The train and the ballasted track-bridge are modeled by the multibody dynamics and finite element (FE) method, respectively. Based on the linearized wheel-rail interaction model, the equations of motion of the train-ballasted track-bridge coupling system are then derived. Meanwhile, the excitations between the rails and wheels caused by the random track irregularity are transformed into a series of deterministic pseudo-harmonic excitation vectors by the PEM. Then, the random vibration responses of the coupling system are obtained using a step-by-step integration method and the maximum responses are estimated using the 3[Formula: see text] rule for the Gaussian stochastic process. The proposed method is validated by the field measurement data collected from a simply-supported girder bridge (SSB) for heavy-haul trains in China. Finally, the effects of train speed, grade of track irregularity, and train type on the random dynamic behavior of six girder bridges for heavy-haul railways are investigated. The results show that the vertical acceleration and dynamic amplification factor (DAF) of the midspan of the SSB girders are influenced significantly by the train speed and track irregularity. With the increase in the vehicle axle-load, the vertical deflection-to-span ratio ([Formula: see text]) of the girders increases approximately linearly, but the DAF and vertical acceleration fail to show clear trend.

Vibration Energy Harvesting to Power Ultrasonic Sensors in Heavy Haul Railway Cars

2018 ◽  
Author(s):  
Auteliano A. Santos ◽  
Matheus V. Lopes ◽  
Vanessa Gonçalves ◽  
Jony J. Eckert ◽  
Thiago S. Martins
Keyword(s):  
Economic Value ◽  
Low Frequency ◽  
Electrical Energy ◽  
Vibration Energy ◽  
Vibration Energy Harvesting ◽  
Vibration Energy Harvester ◽  
Important Indicator ◽  
Suitable Alternative ◽  
Heavy Haul ◽  
Heavy Haul Trains

Long heavy-haul trains are now a reality, especially for ore transportation. In some railways, compositions of up to 330 wagons are in service, requiring several locomotives. Trains like that travel long distances, sometimes through cities or in uninhabited regions. They are driven by just one driver which must keep the whole train working safely on the track. The wagons don’t have any source of electrical energy to power sensors and to transmit their signals to the locomotive; nor wireless communication. In fact, in some of these railways, there is no internet along with the track out of the cities. One important indicator of the safety of the train is the force between the wagons during the trip, through the shunting. Using strain gauges to measure these forces is a possible solution and ultrasonic stress sensors (UST) is a suitable alternative. UST with Lcr waves requires a low amount of energy and can be employed in rusty and dirty places. However, they also need an energy source. Wind and solar solutions are not always adequate because, unfortunately, there are places where these components have economic value and they can be stolen. A possible source of energy to power the USTs could be the Vibration Energy Harvester (VEH). These simple and not expensive systems can be built in small packs, giving the energy to measure the forces and transmit the data to the locomotive or designated sites along the track. This work aims to evaluate the possibility of using VEH to power USTs to measure the forces between the wagons during the journey. Knowing that the oscillation in the shunting has a very low frequency, the work intent to optimize a multi-beam VEH to be able to capture the highest amount of energy possible, in a very small arrangement, using genetic algorithm. The result shows that VEH is an adequate alternative to power autonomous UST sensors.

scholarly journals Tracking control via sliding mode for heavy-haul trains with input saturation

2020 ◽  
pp. 002029402095245 ◽  
Author(s):  
Jing He ◽  
Xingxing Yang ◽  
Changfan Zhang ◽  
Jianhua Liu ◽  
Qian Zhang ◽  
...  
Keyword(s):  
Tracking Control ◽  
Control Method ◽  
Sliding Mode ◽  
Input Saturation ◽  
Tracking Accuracy ◽  
Uncertain Disturbances ◽  
Heavy Haul ◽  
New Type ◽  
Heavy Haul Trains ◽  
Compensation Signal

To address the tracking control problem of heavy-haul trains (HHTs) with input saturation during operation, an anti-saturation sliding mode (SMES) control method based on dynamic auxiliary compensator (DAC) is presented. Firstly, an HHT model with nonlinear coupling and uncertain disturbances is built. Secondly, a new type of DAC is introduced to overcome the difficulty of traditional dynamic auxiliary compensator (TDAC) with a large upper bound on the compensation signal. Finally, an anti-saturation SMES control algorithm is designed to reduce the influence of input saturation on the tracking accuracy of each carriage. Simulation results verify the effectiveness of the algorithm in terms of tracking accuracy, anti-interference, and anti-saturation.

scholarly journals EBOC: Ensemble-Based Ordinal Classification in Transportation

2019 ◽  
Vol 2019 ◽  
pp. 1-17
Author(s):  
Pelin Yıldırım ◽  
Ulaş K. Birant ◽  
Derya Birant
Keyword(s):  
Historical Data ◽  
Classification Problem ◽  
Classification Performance ◽  
Classification Algorithms ◽  
Ordinal Classification ◽  
Adaboost Algorithm ◽  
Education And Health ◽  
Transportation Sector ◽  
C4.5 Decision Tree ◽  
Target Attribute

Learning the latent patterns of historical data in an efficient way to model the behaviour of a system is a major need for making right decisions. For this purpose, machine learning solution has already begun its promising marks in transportation as well as in many areas such as marketing, finance, education, and health. However, many classification algorithms in the literature assume that the target attribute values in the datasets are unordered, so they lose inherent order between the class values. To overcome the problem, this study proposes a novel ensemble-based ordinal classification (EBOC) approach which suggests bagging and boosting (AdaBoost algorithm) methods as a solution for ordinal classification problem in transportation sector. This article also compares the proposed EBOC approach with ordinal class classifier and traditional tree-based classification algorithms (i.e., C4.5 decision tree, RandomTree, and REPTree) in terms of accuracy. The results indicate that the proposed EBOC approach achieves better classification performance than the conventional solutions.

Comparative Study on Simulation and Experiment of Heavy Haul Train Operation

ICRT 2017 ◽  
2018 ◽  
Author(s):  
Wei Wei ◽  
Yang Hu ◽  
Xubao Zhao ◽  
Jun Zhang ◽  
Yuan Zhang
Keyword(s):  
Comparative Study ◽  
Heavy Haul Train ◽  
Train Operation ◽  
Heavy Haul ◽  
Simulation And Experiment

Stabilizing mechanism and running behavior of couplers on heavy haul trains

2014 ◽  
Vol 27 (6) ◽  
pp. 1211-1218 ◽  
Author(s):  
Ziqiang Xu ◽  
Qing Wu ◽  
Shihui Luo ◽  
Weihua Ma ◽  
Xiaoqing Dong
Keyword(s):  
Heavy Haul ◽  
Heavy Haul Trains
Sign in / Sign up

Export Citation Format

Share Document