Mr Jiawei Xie

Geotechnical subsurface stratification based on sparse measurements presents a significant challenge. Learning from prior geological information, such as learning soil layer distribution patterns from stratification results (2D images) of adjacent data-rich projects, is an emerging approach to reducing uncertainties caused by data scarcity. Existing methods rely on pixel-based techniques that require training images to have identical soil types as the testing image. Additionally, pixel-based methods are prone to error accumulation. To address these issues, this study introduces a new framework that focuses solely on learning boundary information from training image rather than soil types. This eliminates the need for matching soil types between training and testing images. Tree-based model is proposed to learn boundary information from training images. Contrary to conventional tree-based models that use coordinates as input, this study employs a set of designed distance fields (boundary dictionary) to represent complex boundary patterns. A selection process is introduced to identify the most important distance fields from the training images. Using these selected distance fields for model input results in soil stratification that aligns well with both borehole data and training image boundaries. The proposed method's efficacy is validated through multiple simulated and real-world cases. The proposed method outperforms pixel-based methods in multiple cases, achieving up to a 25% improvement in accuracy. This method is robust and it yields consistent results for a variety of training images considered. Additionally, the proposed method also provides quantification of interpolation uncertainty through the Gini impurity method.

Numerical simulation is a powerful technique for slope stability assessment and landslide hazard investigation. However, the physicomechanical parameters of the simulation results are susceptible to uncertainty. Displacement back-analysis is considered an effective method for the prediction of the geomechanical parameters of numerical models; therefore, it can be used to deal with the parameter uncertainty problem. In this study, to improve the interpretability of the back-analysis model, an analytical function relationship between slope displacements and physicomechanical parameters was established using geographically weighted regression. By combining the least-squares and linear-algebra algorithms, a displacement back-analysis method based on geographically weighted regression (DBA-GWR) was developed; in particular, the multi-objective displacement back-analysis was represented as an analytical problem. The developed method was subsequently used for a slope of the Guiwu Expressway in Guangxi, China. Simulation experiments and GNSS real-data experiments demonstrated that the GWR could achieve high-precision deformation modelling in the spatial domain with model-fitting precision in the order of mm. Compared with state-of-the-art methods, the precision of the simulated displacement with the proposed method was significantly improved, and equivalent physicomechanical parameters with higher accuracy were obtained. Based on the corrected numerical model, the most severely deformed profiles were forward-analysed, and the simulated deformation and distribution patterns were found to be in good agreement with the field investigation results. This approach is significant for the determination of geomechanical parameters and the accurate assessment of slope safety using monitoring data.

Geotechnical and geophysical testing data are conventionally considered as separated information or combined based on deterministic methods in site investigation programs, which causes loss of information and introduces additional uncertainties. This study aims to reduce the uncertainties and costs in inhomogeneous soil profile characterization and geotechnical analysis by quantitatively integrating these data. The intrinsic collocated co-kriging method (ICCK) is utilized to integrate Multi-channel analysis surface wave (MASW) and CPT data. This research shows the potential of using the MASW data to explore the horizontal scale of fluctuation (SOF) of the cone tip resistance (qc) field which is very difficult to get using the conventional methods due to the limited CPTs. The Markov model is used to avoid the tedious modeling of the cross-covariance relationship in the ICCK method. A series of synthetic case studies show that the combined soil profile is in good agreement with the ¿true¿ qc field with significantly reduced uncertainties. Based on estimating the uncertainties, the optimal distance between CPTs is suggested to be 1¿2 horizontal SOF. This framework is also applied to a real case in the Christchurch area, which involves integration of CPTs and MASW tests. Cross validation and edge detection methods are used to quantitatively compare the integration results, confirming that the proposed framework is fully applicable to field data and can provide realistic and reliable estimations of qc field.

Timely detection and identification of rail breaks are crucial for safety and reliability of railway networks. This article proposes a new deep learning-based approach using the daily monitoring data from in-service trains. A time-series generative adversarial network (TimeGAN) is employed to mitigate the problem of data imbalance and preserve the temporal dynamics for generating synthetic rail breaks. A feature-level attention-based bidirectional recurrent neural network (AM-BRNN) is proposed to enhance feature extraction and capture two-direction dependencies in sequential data for accurate prediction. The proposed approach is implemented on a three-year dataset collected from a section of railroads (up to 350 km) in Australia. A real-life validation is carried out to evaluate the prediction performance of the proposed model, where historical data are used to train the model and future 'unseen' rail breaks along the whole track section are used for testing. The results show that the model can successfully predict nine out of 11 rail breaks three months ahead of time with a false prediction of nonbreak of 8.2%. Predicting rail breaks three months ahead of time will provide railroads enough time for maintenance planning. Given the prediction results, a Shapley additive explanations (SHAP) method is employed to perform a cause analysis for individual rail break. The results of cause analysis can assist railroads to plan appropriate maintenance to prevent rail breaks.

Timely detection and identification of substructure defects in railway track are crucial for the safety and reliability of railway networks. Instrumented in-service trains can provide daily data for assessing the track conditions. This study tries to develop a data-driven model for the prediction of mud pumping defects using daily in-service train data. The data-driven model is based on long short-term memory (LSTM) networks. Bayesian optimization method is used to select the optimal hyper-parameters in LSTM. Genetic algorithm (GA) method is used for feature selection. A four-year real-world dataset from a section of railway network in Australia is used to train and test the data-driven model. The t-distributed Stochastic Neighbor Embedding (t-SNE) method is used to examine the resulting LSTM networks. The results show that the proposed approach can be used to predict the mud pumping defects in advance leaving enough time for maintenance.

Conventional planning of maintenance and renewal work for railway track is based on heuristics and simple scheduling. The railway industry is now collecting a large amount of data with the fast-paced development of sensor technologies. These data sets carry information about the conditions of various components in railway track. Since just before the beginning of the 21st century, data-driven models have been used in the predictive maintenance of railway track. This study presents a systematic literature review of data-driven models applied in the predictive maintenance of railway track. A taxonomy to classify the existing literature based on types of models and types of applications is provided. It is found that applying the deep learning methods, unsupervised methods, and ensemble methods are the new trends for predictive maintenance of railway track. Rail geometry irregularity, rail head defect, and missing rail components detection were the top three most commonly considered issues within the application of data-driven models. Prediction of rail breaks has received increasing attention in the last four years. Among these data-driven model applications, the collected data types are the most critical factors which affect selecting suitable models. Finally, this study discusses upcoming challenges in the predictive maintenance of railway track.