1 |
On validation of a wheel-rail wear prediction codeSánchez Arandojo, Adrián January 2013 (has links)
During the past years, several tools have been developed to try predicting wheel and rail wear of railway vehicles in an e-cient way. In this MSc thesis a new wear prediction tool developed by I.Persson is studied and compared with another wear prediction tool, developed by T.Jendel, which has been already validated and is in use since several years ago. The advantages that the new model gives are simpler structure, the consideration of wear as a continuous variable and that all the code is integrated in the same software. The two models have the same methodology until the part of the wear calculations and the post-processing. Wheel-rail geometry functions and time domain simulations are performed with the software GENSYS. In the simulation model the track and the vehicle are dened as well as other important properties such as vehicle speed and coe-cient of friction. Three simple tracks are used: tangent track, R=500 m curve with a cant of ht=0.15 m on the outer rail and R=1000 m curve with a cant of ht=0.1 m on the outer rail. The model is assumed to be symmetric so just outer (first and fourth axle) and inner (second and third axles) wheels are considered. During the vehicle-track interaction, the normal and tangential problems are solved. The wheel-rail contact is modelled according to Hertz's theory and Kalker's simplied theory with the help of the algorithm FASTSIM. Then wear calculations are performed according to Archard's wear law. It is applied in dierent ways, obtaining wear depth directly in Jendel's and wear volume rate in Persson's model. Jendel's model is rstly analyzed. Its specifc methodology is briefly explained and modications are performed on the code to make it work as similar as possible to Persson's model. Also parameters regarding the distance in which wear calculations are taken, the discretization of the width of the wheel and the discretization of the contact patch are analyzed. The methodology of Persson's model is also studied, most of all the performance of the post-processing which is one of the keys to the code. The parameters analyzed in this code are the ones regarding a statistical analysis performed during the post-processing and the discretization of the contact patch. Finally the comparisons between the wear depth obtained for both models are carried out. The discrepancies between the models are explained with the parameters analyzed and the dynamic behaviour of both models. Also a theoretical case is used as reference for comparison.
|
2 |
Estimating the load weight of freight trains using machine learningKongpachith, Erik January 2023 (has links)
Accurate estimation of the load weight of freight trains is crucial for ensuring safe, efficient and sustainable rail freight transports. Traditional methods for estimating load weight often suffer from limitations in accuracy and efficiency. In recent years, machine learning algorithms have gained significant attention and use cases within the railway industry due to their strong predictive capabilities for classification and regression tasks. This study aims to present a proof of concept in the form of a comparative analysis of five machine learning regression algorithms: Polynomial Regression, K-Nearest Neighbors, Regression Trees, Random Forest Regression, and Support Vector Regression for estimating the load weight of freight trains using simulation data. The study utilizes two comprehensive datasets derived from train simulations in GENSYS, a simulation software for modeling rail vehicles. The datasets encompasses various driving condition factors such as train speed, track conditions and running gear configurations. The algorithms are trained and evaluated on these datasets and their performance is evaluated based on the root mean squared error and R2 metrics. Results from the experiments demonstrate that all five machine learning algorithms show promising performance for estimating the load weight. Polynomial regression achieves the best result for both of the datasets when using many features of the datasets are considered. Random forest regression achieves the best result for both of the data sets when a small number features of the datasets are considered. Furthermore, it is suggested that the methodical approach of this study is examined on real world data from operating freight trains to assert the proof of concept in a real world setting. / Noggrann uppskattning av godstågens lastvikt är avgörande för att säkerställa säkra, effektiva och hållbara godstransporter via järnväg. Traditionella metoder för att uppskatta lastvikt lider ofta av begränsningar i noggrannhet och effektivitet. Under de senaste åren har maskininlärningsalgoritmer fått betydande uppmärksamhet och användningsfall inom järnvägsindustrin på grund av deras starka prediktiva förmåga för klassificerings- och regressionsproblem. Denna studie syftar till att presentera en proof of concept i form av en jämförande analys av fem maskininlärningalgoritmer för regression: Polynom regression, K-Nearest Neighbors, Regression träd, Random Forest Regression och Support Vector Regression för att uppskatta lastvikten för godståg med hjälp av simuleringsdata. Studien använder två omfattande dataset konstruerade från tågsimuleringar i GENSYS, en simuleringsprogramvara för modellering av järnvägsfordon. Dataseten omfattar olika körfaktorer såsom tåghastighet, spårförhållanden och vagns konfigurationer. Algoritmerna tränas och utvärderas på dessa dataset och deras prestanda utvärderas baserat på root mean squared error och R2 måtten. Resultat från experimenten visar att alla fem maskininlärningsalgoritmerna visar lovande prestanda för att uppskatta lastvikten. Polynom regression uppnår det bästa resultatet för båda dataset när många variabler i datan beaktas. Random Forest Regression ger det bästa resultatet för båda dataset när ett mindre antal variabler i datan beaktas. Det föreslås det att det metodiska tillvägagångssättet för denna studie undersöks på verklig data från aktiva godståg för att fastställa en proof of concept på en verklig världsbild.
|
Page generated in 0.017 seconds