Prediction Models for Railway Track Geometry Degradation Using Machine Learning Methods: A Review

Abstract

Keeping railway tracks in good operational condition is one of the most important tasks for railway owners. As a result, railway companies have to conduct track inspections periodically, which is costly and time-consuming. Due to the rapid development in computer science, many prediction models using machine learning methods have been developed. It is possible to discover the degradation pattern and develop accurate prediction models. The paper reviews the existing prediction methods for railway track degradation, including traditional methods and prediction methods based on machine learning methods, including probabilistic methods, Artificial Neural Network (ANN), Support Vector Machine (SVM), and Grey Model (GM). The advantages, shortage, and applicability of methods are discussed, and recommendations for further research are provided.

Analysis and prediction of railway track longitudinal level using multiple machine learning methods

“…The GM (1, 1) model has been mainly used for data with a smooth trend and is not ideal for predicting data with positive and negative alternation and many peak values [3]. Because the SDD1L, SDD1R, SDD2L, and SDD2R are positive and generally monotonically increasing over time in degradation cycles, the GM (1, 1) model can be used to predict the datasets in January 2020.…”

“…It becomes more challenging to the maintenance the track quality. Commonly, track recording cars (TRCs) or comprehensive inspection trains (CITs) are used to collect the track geometry data, including gauge, cross level (cant), alignment, longitudinal level, and twist as shown in figure 1 [3]. They are recorded at the fixed measuring points (usually 25 cm), and the standard deviation of them (usually calculated over 200 m) and mean value are used to evaluate track geometry quality [4].…”

“…With the fast development of computer science, prediction models based on machine learning methods have been proposed in the railway industry, which can better predict the random characteristics in track degradation, find unknown factors through data mining, and deliver accurate prediction results even when track geometry data is insufficient [3]. The most popular machine learning methods used for track degradation are the support vector machine (SVM), grey model (GM), and artificial neural network (ANN).…”

Estimation of Daily Actual Evapotranspiration of Tea Plantations Using Ensemble Machine Learning Algorithms and Six Available Scenarios of Meteorological Data

“…The SVM algorithm is normally introduced as a supervised learning model, and it has been widely used to deal with classification and regression problems [48,49]. It has also been utilized for prediction [50]. In general, the SVM model aims to generate the best separation hyperplane that can linearly divide classes (Figure S2a) [51].…”

Big Data aplicado à tarefa de categorização de níveis de severidade de vias férreas a partir de dados de veículos sensoriais.

“…Nos últimos dez anos, o número de publicações sobre o assunto aumentou drasticamente (CARVALHO et al, 2019). Além da significativa importância do assunto, a maior difusão de meios de coleta massiva de dados, possibilitada em parte pela disseminação da Internet das Coisas, aliada à capacidade de transmissão desses dados (KONDAKA et al, 2022), também contribui para a maior viabilidade dessa estratégia de identificar a necessidade de realizar manutenção (XU et al, 2019) (LIAO et al, 2022).…”