Search

Railway track maintenance plays an important role in enabling safe, reliable, and seamless train operations and passenger comfort. Due to the increasing rail transportation, rolling stocks tend to run faster and the load tends to increase continuously. As a result, the track deteriorates quicker, and maintenance needs to be performed more frequently. However, more frequent maintenance activities do not guarantee a better overall performance of the railway system. It is crucial for rail infrastructure managers to optimize predictive and preventative maintenance. This study is the world's first to develop deep machine learning models using three-dimensional recurrent neural network-based co-simulation models to predict track geometry parameters in the next year. Different recurrent neural network-based techniques are used to develop predictive models. In addition, a building information modeling (BIM) model is developed to integrate and cross-functionally co-simulate the track geometry measurement with the prediction for predictive and preventative maintenance purposes. From the study, the developed BIM models can be used to exchange information for predictive maintenance. Machine learning models provide the average R 2 of 0.95 and the average mean absolute error of 0.56 mm. The insightful breakthrough demonstrates the potential of machine learning and BIM for predictive maintenance, which can promote the safety and cost effectiveness of railway maintenance.

Railway sleepers are safety-critical components of a railway structure. They support ballasted track superstructure and are a critical factor in track geometry and track components' deterioration. Unsupported sleepers are a common issue incurred after tracks have been utilized. When unsupported sleepers are present, they cause differential settlements of track superstructures, additional dynamic loading, and excessive train-track vibrations which affect passenger comfort, safety, and maintenance cost. This study is the world's first to develop new machine learning models to prognose and better diagnose defect severities of unsupported sleepers aligned with practical track inspection guidelines. Data used to develop machine learning models are based on a verified finite element model with actual field measurements, enabling unbiased full data ranges that govern all defect conditions. Different conditions of unsupported sleepers can be explored by varying locations of unsupported sleepers and the number of unsupported sleepers. Also, other operational parameters can be addressed such as speeds of rolling stock, the roughness of rail surface, and vertical stiffness of wheel-rail contact. In total, 2016 data sets have been obtained. Axle box accelerations are adopted as key indicators for machine learning models. Machine learning techniques used in the study are the convolutional neural network, recurrent neural network, ResNet, and fully convolutional neural network. Data fusion and assimilation have been conducted since the data points are dependent on the train speeds. Our new results reveal a breakthrough essential for real-world applications that the convolutional neural network model provides the best accuracy in both unsupported sleeper prognostics and severity identification. The accuracies of detection and severity identification are 99.34% and 97.02% respectively., (© 2022. The Author(s).)

In recent years, adding fibres into brittle concrete to improve ductility has gained momentum in the construction industry. Despite the significant momentum, limitations do exist in design and industrial applications, contributing to the complexity of shear behaviours in fibre-reinforced concrete and the existing empirical models that can hardly provide a reasonable prediction, especially for high-strength concrete applications. A critical review reveals that current research mostly focuses on single eigenvalue analysis and pay less attention to the different synergetic effect of fibres on high-strength concrete and normal-strength concrete. This study aims to fill the research gap by the unprecedented use of reliable models for the prediction and evaluation of structural and sustainable properties of high-strength fibre-reinforced concrete beams. To this end, this study establishes three novel deep learning (ANN, BNN, and Xgboost) models for designing and optimising the shear capacity of 'high-strength' fibre-reinforced concrete beams towards the circular economy. In addition to introducing a new type of novel machine learning (BNN) model, which is capable of structural design and takes into account complex design features, our study also enhances sustainability by reducing greenhouse gas (GHG) emissions. The novel prediction models unprecedentedly elicit flexural capacity, structural stiffness, carbon emission, and price, together with the shear strength for high-strength fibre-reinforced structures. Firstly, this study focuses on multiple parameters for forecasting high-strength fibre-reinforced concrete beams. In addition, the models provide more comprehensive insights into the design and manufacture of high-strength steel fibre-reinforced concrete structures in a more environmentally friendly manner. With the help of the proposed models, it will be more cost-benefit and time-efficient for the researchers to obtain the optimum design with the consideration of both structural and sustainable performance. The established models exhibit excellent prediction accuracy, and the Bayesian neural network (BNN) is found to have the best performance: R2 is 0.937, MSE is 0.06 and MAE is 0.175 in shear strength prediction; R2 = 0.968, MSE is 0.040, and MAE is 0.110 in flexural capacity prediction; R2 is 0.907, MSE is 0.070, and MAE is 0.204 in shear stiffness prediction; R2 is 0.974, MSE is 0.022, and MAE is 0.063 in carbon emission prediction; and R2 is 0.977, MSE is 0.020, and MAE is 0.082 in price prediction. [ABSTRACT FROM AUTHOR]

Unplanned track inspections can be a direct consequence of any disruption to the operation of on-board track geometry monitoring activities. A novel response strategy to enhance the value of the information for supplementary track measurements is thus established to construct a data generation model. In this model, artificial (synthetic) data is assigned on each measurement point along the affected track segment over a short period of time. To effectively generate artificial track measurement data, this study proposes a NARX (nonlinear autoregressive with exogenous variables) model, which incorporates short-range memory dependencies in the dependent variable and integrates interdependent effects from external factors. Nonlinearities in the proposed model have been determined using an artificial neural network that allowed fast computation of a mapping function in line with the needs of effective disruption management. The risk of over fitting the data generation model, which reflected its generalisation ability, has been effectively managed through risk aversion concept. For the model evaluation, the deviation of track longitudinal level has been taken as a case study, predicted using its degradation rate and track alignment and gauge as exogenous variables. Simulation results on two datasets that are statistically different showed that the data generation model for disrupted track measurements is reliable, accurate, and easy-to-use. This novel model is an essential breakthrough in railway track integrity prediction and resilient operation management. [ABSTRACT FROM AUTHOR]

The increase in demand for railway transportation results in a significant need for higher train axle load and faster speed. Weak and sensitive trackforms such as railway switches and crossings (or called 'turnout') can suffer from such an increase in either axle loads or speeds. Moreover, railway turnout supports can deteriorate from other incidences due to extreme weather such as floods which undermine cohesion between ballast leading to ballast washaway or loss of support under turnout structures. In this study, new intelligent automation based on machine learning pattern recognition has been built to detect and predict the deterioration of railway turnouts exposed to flooding conditions which is the scope of this study. Since the turnout system is very complex by nature, different features and smart filtering are explored to find the potential features for deep learning. Nonlinear finite element models validated by actual field measurements are used to mimic the dynamic behaviors of turnout supports under flooding conditions. The study exhibits that the novel recognition model can achieve more than 98% accuracy, yielding the potential capability to recognize and classify turnout support deteriorations facing extreme weather conditions which will be beneficial for responsible parties to schedule and plan maintenance activities. [ABSTRACT FROM AUTHOR]

Most of the Artificial Intelligence (AI) models currently used in energy forecasting are traditional and deterministic. Recently, a novel deep learning paradigm, called 'transformer', has been developed, which adopts the mechanism of self-attention. Transformers are designed to better process and predict sequential data sets (i.e., historical time records) as well as to track any relationship in the sequential data. So far, a few transformer-based applications have been established, but no industry-scale application exists to build energy forecasts. Accordingly, this study is the world's first to establish a transformer-based model to estimate the energy consumption of a real-scale university library and benchmark with a baseline model (Support Vector Regression) SVR. With a large dataset from 1 September 2017 to 13 November 2021 with 30 min granularity, the results using four historical electricity readings to estimate one future reading demonstrate that the SVR (an R2 of 0.92) presents superior performance than the transformer-based model (an R2 of 0.82). Across the sensitivity analysis, the SVR model is more sensitive to the input close to the output. These findings provide new insights into the research area of energy forecasting in either a specific building or a building cluster in a city. The influences of the number of inputs and outputs related to the transformer-based model will be investigated in the future. [ABSTRACT FROM AUTHOR]

Railway track maintenance plays an important role in enabling safe, reliable, and seamless train operations and passenger comfort. Due to the increasing rail transportation, rolling stocks tend to run faster and the load tends to increase continuously. As a result, the track deteriorates quicker, and maintenance needs to be performed more frequently. However, more frequent maintenance activities do not guarantee a better overall performance of the railway system. It is crucial for rail infrastructure managers to optimize predictive and preventative maintenance. This study is the world's first to develop deep machine learning models using three-dimensional recurrent neural network-based co-simulation models to predict track geometry parameters in the next year. Different recurrent neural network-based techniques are used to develop predictive models. In addition, a building information modeling (BIM) model is developed to integrate and cross-functionally co-simulate the track geometry measurement with the prediction for predictive and preventative maintenance purposes. From the study, the developed BIM models can be used to exchange information for predictive maintenance. Machine learning models provide the average R2 of 0.95 and the average mean absolute error of 0.56 mm. The insightful breakthrough demonstrates the potential of machine learning and BIM for predictive maintenance, which can promote the safety and cost effectiveness of railway maintenance. [ABSTRACT FROM AUTHOR]

The state-of-the-art design methods for railway prestressed concrete sleepers are currently based on the quasi-static stresses resulting from a simplification of dynamic wheel loads, and subsequently the quasi-static responses of concrete sleepers. This method has been widely used in practices to overcome the complexity of dynamic analysis and testing. A single load factor (or called dynamic impact factor) for a partial safety-factored design (or k factors for the test criteria) is commonly used to crudely account for dynamic train–track interactions over different levels of track irregularities. The dynamic impact factors for either design or testing are usually obtained from either (i) railway infrastructure managers (i.e., in EN 13230), or (ii) prescribed standardised factors (i.e., AS 1085.14, AREMA Chapter 30, JSA—JIS E 1201). The existing design concepts for prestressed concrete sleepers using either (i) an allowable stress design or (ii) the limit state design method require many iterations for calculations and optimisations. The design process to achieve optimal products suitable for track, operational, and environmental parameters is, thus, very time-consuming. On this ground, this study investigates the potential capability of machine learning (ML) to learn from large amounts of design data sets and then to facilitate the design and capacity prediction of railway prestressed concrete sleepers. Three ML algorithms are developed, namely deep learning, Bayesian Neural Network, and random forest. Through a combination of hand-calculated design data, industry design data, and experimental investigations in compliance with EN 13230, over 3000 sets of design data have been collected. These data sets are used to assimilate a comprehensive database for machine learning. Four indicators, namely mean squared error (MSE), root-mean-square error (RMSE), mean absolute error (MAE), and R2 are used to benchmark the accuracy and precision of machine learning models. Our results reveal that the random forest algorithm offers the best performance. The values of MSE, RMSE, MAE, and R2 are 0.54, 0.74, 0.25, and 0.99, respectively. Note that the Bayesian neural network also performs very well. In contrast, the deep learning algorithm performs worse than the others. The insight demonstrates machine learning's capability to aid in the design of railway prestressed concrete sleepers, to satisfy both serviceability and ultimate limit states [ABSTRACT FROM AUTHOR]

A primary energy consumption and CO2 emission source stems from buildings and infrastructures due to rapid urbanisation and social development. An accurate method to forecast energy consumption in a building is thus critically needed to enable successful management of adaptive energy consumption and ease the level of CO2 emission. However, energy forecasting for buildings, especially residential buildings, has several challenges, such as significant variations in energy usage patterns due to unpredicted demands of the residences and some intricate factors, which can randomly affect the patterns. Traditional forecasting approaches require a tremendous number of inputs needed for building physic models and variations often exist between as-built and as-designed buildings in reality. Most recent studies have adopted only ambient weather conditions, building components, and the occupant's behaviours. As a result, in order to take into account the complexity of factors that can affect the building energy model development and its computation, we develop advanced machine learning models driven by the inherent electricity consumption pattern associated with the day and time. In this study, we demonstrate benchmarking results derived from three different machine learning algorithms, namely SVR, XGBoost, and LSTM, trained by using 1-year datasets with sub-hourly (30 min) temporal granularity to determine the outperformed predictor. Ultimately, the machine learning model robustness and performance on a basis of the coefficient of variation (CV) obtained by the SVR is benchmarked across XGBoost and LSTM trained by the same datasets containing attributes related to the building type, data size, and temporal granularity. The insight stemming from this study indicates that the suitable choice of the machine learning models for building energy forecasts largely depends on the natural characteristics of building energy data. Hyperparameter tuning or mathematical modification within an algorithm may not be sufficient to attain the most accurate machine learning model for building energy forecast. [ABSTRACT FROM AUTHOR]

Investigating the condition of rail track components is important for track maintenance and developing a greater understanding of track design. Railway inspection can be destructive and non-destructive approaches. In the railway industry, the non-destructive approaches are preferred because they retain the track in operation thus significantly reducing the cost of fault testing. One of the non-destructive approaches is using machine learning which is applied in this study. Field measurements and advanced analysis of results are used to extract track properties. This study creates, tunes and examines the validity of different machine learning techniques. The aim is to extract the dynamic track properties from the in-field measurements without needing the intermediary steps, saving both time and effort. Contributions of this study demonstrate that machine learning techniques have the potential to save cost and time for railway inspection. Moreover, the accuracy is satisfied. The following models are produced: Linear Regression, K-Nearest Neighbors, Gradient Boosting and a Convolutional Neural Network. We observe the limitations of linear regression and tune the remainder, producing three models with low errors. [ABSTRACT FROM AUTHOR]

Railway track health monitoring and maintenance are crucial stages in railway asset management, aiming to enhance the train operation quality and service life. For this aim, various inspection means (using diverse non-destructive testing techniques) have been applied, however, these means are mostly not able to monitor whole railway track network or track underlying layers (e.g., ballast and subgrade). The use of remote sensing techniques, such as Interferometric Synthetic Aperture Radar (InSAR), can expedite the defect diagnosis process for railway tracks, elevating the scope of health monitoring to a network-wide level. The Ground Penetrating Radar (GPR) has emerged as a particularly reliable method, especially for detecting structural deficiencies in underlying layers. As a result, combining the two distinct non-destructive testing techniques – GPR and InSAR – presents a promising strategy for efficient railway asset management. Recognizing the significance of embracing newer and more advanced monitoring strategies, this paper reviews the fusion of GPR and InSAR methodologies, and explores the potential integration of machine learning models to develop a predictive health monitoring and condition-based maintenance approach for railway tracks. • A review of InSAR/GPR with potential fusion for railway monitoring was discussed. • A general framework for fusion of InSAR/GPR data and machine learning integration was proposed. • Predictive strategy based on fusion of characterized techniques for railway health monitoring/maintenance plan was focused. • Future research directions are recommended based on the review of literature and discussion of technology. [ABSTRACT FROM AUTHOR]

Bacterial-based self-healing concrete (BSHC) is a well-known healing technology which has been investigated for a few decades for its excellent crack healing capacity. Nevertheless, considered as costly and time-consuming, the healing performance (HP) of concrete with various types of bacteria can be designed and evaluated only in laboratory environments. Employing machine learning (ML) models for predicting the HP of BSHC is inspired by practical applications using concrete mechanical properties. The HP of BSHC can be predicted to save the time and cost of laboratory tests, bacteria selection and healing mechanisms adoption. In this paper, three types of BSHC, including ureolytic bacterial healing concrete (UBHC), aerobic bacterial healing concrete (ABHC) and nitrifying bacterial healing concrete (NBHC), and ML models with five kinds of algorithms consisting of the support vector regression (SVR), decision tree regression (DTR), deep neural network (DNN), gradient boosting regression (GBR) and random forest (RF) are established. Most importantly, 22 influencing factors are first employed as variables in the ML models to predict the HP of BSHC. A total of 797 sets of BSHC tests available in the open literature between 2000 and 2021 are collected to verify the ML models. The grid search algorithm (GSA) is also utilised for tuning parameters of the algorithms. Moreover, the coefficient of determination (R2) and root mean square error (RMSE) are applied to evaluate the prediction ability, including the prediction performance and accuracy of the ML models. The results exhibit that the GBR model has better prediction ability (R2GBR = 0.956, RMSEGBR = 6.756%) than other ML models. Finally, the influence of the variables on the HP is investigated by employing the sensitivity analysis in the GBR model. [ABSTRACT FROM AUTHOR]

This paper investigates the possibility for implementing machine learning-aided prediction in analyzing the buckling phenomena of ballasted railway tracks induced by extreme temperature. In this study, artificial neural networks (ANNs) have been developed to identify the relationship between various ballasted track conditions and outputs, namely safe temperature and buckling temperature. The variables included in the objective function of the optimization problems are the lateral resistance of ballasted track provided by ballast-sleeper interaction, torsional resistance provided by fastening systems, and misalignment of the track. Due to its complexity in parameter combinations, the objective of this study is to create predictive models with the aim of minimizing the usage of scarce resources. Thus, this paper is the first to develop a novel machine learning-aided prediction of railway track buckling due to extreme temperature. Comprehensively, all 353 datasets of the safe and buckling temperatures derived from previous finite element (FE) simulation results have been collected and trained. Note that the mean squared error (MSE) and the coefficient of determination ( R 2) are considered to quantify the performance of the ANN architectures. The optimal ANN architecture with a very high rate of accuracy has been determined and highlighted. Thus, the suggested neural network model can be applied conveniently to help estimate safe and buckling temperatures of the complex track models in order to improve track conditions and thus prevent track buckling in summer. [ABSTRACT FROM AUTHOR]

To encourage more active activities that have the potential to significantly reduce the risk of people's health, we aim to develop an AI-based mobile app to identify four gym activities accurately: ascending, cycling, elliptical, and running. To save computational cost, the present study deals with the dilemma of the performance provided by only a phone-based accelerometer since a wide range of activity recognition projects used more than one sensor. To attain this goal, we derived 1200 min of on-body data from 10 subjects using their phone-based accelerometers. Subsequently, three subtasks have been performed to optimize the performances of the K-nearest neighbors (KNN), Support Vector Machine (SVM), Shallow Neural Network (SNN), and Deep Neural Network (DNN): (1) During the process of the raw data converted to a 38-handcrafted feature dataset, different window sizes are used, and a comparative analysis is conducted to identify the optimal one; (2) principal component analysis (PCA) is adopted to extract the most dominant information from the 38-feature dataset described to a simpler and smaller size representation providing the benefit of ease of interpreting leading to high accuracy for the models; (3) with the optimal window size and the transformed dataset, the hyper-parameters of each model are tuned to optimal inferring that DNN outperforms the rest three with a testing accuracy of 0.974. This development can be further implemented in Apps Store to enhance public usage so that active physical human activities can be promoted to enhance good health and wellbeing in accordance with United Nation's sustainable development goals. [ABSTRACT FROM AUTHOR]

One of the top long-term threats to airport resilience is extreme climate-induced conditions, which negatively affect the airport and flight operations. Recent examples, including hurricanes, storms, extreme temperatures (cold/hot), and heavy rains, have damaged airport facilities, interrupted air traffic, and caused higher operational costs. With the development of civil aviation and the pre-COVID-19 surging demand for flights, the passengers' complaints of flight delay increased, according to FoxBusiness. This study aims to discover the weather factors affecting flight punctuality and determine a high-dimensional scale of consequences stemming from weather conditions and flight operational aspects. Machine learning has been developed in correlation with the weather and statistical data for operations at Birmingham Airport as a case study. The cross-correlated datasets have been kindly provided by Birmingham Airport and the Meteorological Office. The scope and emphasis of this study is placed on the machine learning application to practical flight punctuality prediction in relation to climate conditions. Random forest, artificial neural network, support vector machine, and linear regression are used to develop predictive models. Grid-search and cross-validation are used to select the best parameters. The model can grasp the trend of flight punctuality rates well where R2 is 0.80 and the root mean square error (RMSE) is less than 15% using the model developed by random forest technique. The insights derived from this study will help Airport Authorities and the Insurance industry in predicting the scale of consequences in order to promptly enact and enable adaptative airport climate resilience plans, including air traffic rescheduling, financial resilience to climate variances and extreme weather conditions. [ABSTRACT FROM AUTHOR]

Cracks typically develop in concrete due to shrinkage, loading actions, and weather conditions; and may occur anytime in its life span. Autogenous healing concrete is a type of self-healing concrete that can automatically heal cracks based on physical or chemical reactions in concrete matrix. It is imperative to investigate the healing performance that autogenous healing concrete possesses, to assess the extent of the cracking and to predict the extent of healing. In the research of self-healing concrete, testing the healing performance of concrete in a laboratory is costly, and a mass of instances may be needed to explore reliable concrete design. This study is thus the world's first to establish six types of machine learning algorithms, which are capable of predicting the healing performance (HP) of self-healing concrete. These algorithms involve an artificial neural network (ANN), a k-nearest neighbours (kNN), a gradient boosting regression (GBR), a decision tree regression (DTR), a support vector regression (SVR) and a random forest (RF). Parameters of these algorithms are tuned utilising grid search algorithm (GSA) and genetic algorithm (GA). The prediction performance indicated by coefficient of determination (R2) and root mean square error (RMSE) measures of these algorithms are evaluated on the basis of 1417 data sets from the open literature. The results show that GSA-GBR performs higher prediction performance (R2GSA-GBR = 0.958) and stronger robustness (RMSEGSA-GBR = 0.202) than the other five types of algorithms employed to predict the healing performance of autogenous healing concrete. Therefore, reliable prediction accuracy of the healing performance and efficient assistance on the design of autogenous healing concrete can be achieved. [ABSTRACT FROM AUTHOR]