Loading...
3 results
Search Results
Now showing 1 - 3 of 3
- Prediction of mechanical properties of rail pads under in-service conditions through machine learning algorithmsPublication . Ferreño, Diego; Sainz-Aja, Jose Adolfo; Carrascal, Isidro; Cuartas, Miguel; Pombo, João; Casado, José A.; DIEGO, SORAYATrain operations generate high impact and fatigue loads that degrade the rail infrastructure and the vehicle components. Rail pads are installed between the rails and the sleepers in order to damp the transmission of vibrations and noise and to provide flexibility to the track. These components play a crucial role in maximizing the durability of the railway assets and minimizing maintenance costs. Rail pads can be fabricated with different polymeric materials that exhibit non-linear mechanical behaviours, which strongly depend on the service conditions. Therefore, it is extremely difficult to estimate their mechanical properties, in particular the dynamic stiffness. In this work, several machine learning methodologies (multilinear regression, K nearest neighbours, regression tree, random forest, gradient boosting, multi-layer perceptron and support vector machine) were used to determine the dynamic stiffness of rail pads depending on their in-service conditions (temperature, frequency, axle load and toe load). 720 experimental tests, under different realistic operating conditions, were performed to produce a dataset that was then used for the training and testing of the machine learning methods. The optimal algorithm was gradient boosting for EPDM (R2 of 0.995 and mean absolute percentage error of 5.08% in the test dataset), TPE (0.994 and 2.32%) and EVA (0.968 and 4.91%) pads. This model was implemented in an application, available for the readers of this journal, developed on the Microsoft .Net platform that allows the dynamic stiffness of the pads study to be estimated as a function of the temperature, frequency, axle load and toe load.
- Dynamic calibration of slab track models for railway applications using full-scale testingPublication . Sainz-Aja, Jose Adolfo; Pombo, João; Tholken, D.; Carrascal, I.; Polanco, J.; Ferreno, D.; Casado, J.; Diego, S.; Perez, A.; Abdalla Filho, João Elias; Esen, A.; Čebašek, Tina Marolt; Laghrouche, Omar; Woodward, P.Research and development of technology for railways has found new impetus as society continues to search for cost effective and sustainable means of transport. This tasks engineers with using the state-of-the-art science and engineering for rolling stock development and advanced technologies for building high performance, reliable and cost-effective rail infrastructures. The main goal of this work is to develop detailed and validated three-dimensional slab track models using a finite element formulation, which include all components of the infrastructure. For this purpose, the parameters of the computational models are identified by performing full-scale tests of the fastening system and of the slab track, including all its material layers. The computational model proposed here is calibrated using this approach and a good agreement is obtained between experimental and numerical results. This work opens good perspectives to use this reliable track model to study the interaction with railway vehicles in realistic operation scenarios in order to assess the dynamic behaviour of the trains and to predict the long-term performance of the infrastructure and of its components.
- Real-time rail electrification systems monitoring: a review of technologiesPublication . Sainz-Aja, Jose Adolfo; Pombo, João; Brant, Jordan; Antunes, Pedro; Rebelo, José M.; Santos, José; Ferreño, DiegoMost electrified railway networks are powered through a pantograph–overhead contact line (OCL) interface to ensure safe and reliable operation. The OCL is one of the most vulnerable components of the train traction power system as it is subjected to multiple impacts from the pantographs and to unpredictable environmental conditions. Wear, mounting imperfections, contact incidents, weather conditions, and inadequate maintenance lead to increased degradation of the pantograph–OCL current collection performance, causing degradation on contacting elements and assets failure. Incidents involving the pantograph–OCL system are significant sources of traffic disruption and train delays, e.g., Network Rail statistics show that, on average, delays due to OCL failures are 2500 h per year. In recent years, maintenance strategies have evolved significantly with improvements in technology and the increased interest in using real-time and historical data in decision support. This has led to an expansion in sensing systems for structures, vehicles, and machinery. The railway industry is currently investing in condition monitoring (CM) technologies in order to achieve lower failure rates and increase the availability, reliability, and safety of the railway service. This work presents a comprehensive review of the current CM systems for the pantograph–OCL, including their advantages and disadvantages, and outlines future trends in this area.