This master thesis investigates the use of machine learning for predicting and assessing the risk of railway vehicle component failures. Data used for failure prediction often comes with limitations due to the complex nature of maintenance or sometimes requires investments for the extraction of information. Instead of real-time data, historical data and failure timestamps, easily accessed by organisations, are examined to see if they have the potential to contribute to a more effective maintenance strategy. Datasets used in maintenance often contain censored data and to overcome this problem survival machine learning models were also examined. Therefore both traditional machine learning models and survival machine learning models were evaluated and compared based on their C-index value. The results demonstrate that the survival machine learning models, which incorporate the risk and time-to-event aspects of the data, performed better than the traditional ones regarding the risk ranking of components. Random survival forest had the best result, and a ranking of important features. These findings indicate that there is a potential for survival machine learning, applied to existing historical data used for risk assessment for components failure.

Thesis (Ph. D. in Civil Engineering)--University of California, Berkeley, 2006. / Cover title. "Fall 2006." Includes bibliographical references (leaves 292-300). Also available online.

An important aspect during the planning of commuter trains is how long they will be waiting at the platform. All travelers must be able to board and get off the train in time while the process cannot take too long. The train’s waiting time is called its dwell time, and this is a study of how the dwell time of the commuter trains in Stockholm behaves with a focus on the larger station Stockholm Odenplan and the smaller station Årstaberg. The duration of the dwell time compared to the stations planned dwell time was analyzed with manual measurements on the stations. The dwell time was analyzed both during and after rush hours. Possible reasons for the dwell time’s length were also analyzed and a potential factor that was in focus was the impact of the removal of train conductors. Train conductors in Stockholm’s rail system are responsible for monitoring the boarding and closing the train’s doors after it is finished. They began to dismantle from the trains Mars 2023 due to efficiency reasons. Half of the trains will run with a train conductor until autumn 2023, where they will disappear entirely. The train drivers will afterwards monitor the travelers with cameras instead. The commuter trains in Stockholm have three routes between Bålsta and Nynäshamn, Uppsala/Märsta and Södertälje and Södertälje and Gnesta. Factors considered when planning their timetables are the system’s capacity, how long the train should wait at a station and how long it takes to drive between stations. 94 % of the trains run on time in the system according to the operator MTR. The analyzed stations Stockholm Odenplan and Årstaberg are in Stockholm and have their separate conditions. Stockholm Odenplan is the second to largest station in the system and is in a central part of the city. The station is underground, and the rails are separated from the platform with platform doors. The doors are shown to cause delays for the dwell time as they are slow. Årstaberg has considerably fewer travelers than Stockholm Odenplan and is in the south parts of the city. The station is over the ground and has no platform doors. There are many theories about the causes behind a train’s dwell time based on the behavior of the passengers. They vary from where they are waiting on the platform, how they are queueing during boarding and the behavior during the boarding. The study shows that the dwell time in Årstaberg stays under its planned 42 seconds, but it is six seconds too long from its planned 60 seconds in Stockholm Odenplan. The dwell time increases during rush hour in Årstaberg and decreases outside of it, while Stockholm Odenplan seems to be largely unaffected by rush hours. Trains with train conductors seem to have a lower dwell time than those without them. The boarding has a shorter duration with train conductors, which shows that they are more efficient than the train drivers using cameras to monitor the boarding. However, it does take a little longer for the train to depart after the boarding is finished when they have a train conductor. Factors causing the dwell time are believed to be related to the flow of passengers and the design of the stations. The platform doors are believed to increase the dwell time in Stockholm Odenplan. Meanwhile, the protection from the weather and the location of the entrance in Årstaberg might impact its dwell time. When the number of passengers increases will the boarding take longer. The boarding will also be concentrated on a few doors in Årstaberg depending on the weather or if the trains are short. The dwell time should be analyzed further for a longer period and during more hours of the day. More stations in Stockholm’s rail system should be analyzed too.

Typescript (photocopy). / Digitized by Kansas Correctional Industries

The drive train components and the machine control system significantly influence the fuel consumption of mobile machinery. The demonstrator vehicle “Green Wheel Loader” developed within the joint research project “TEAM” combines the most promising drive concepts currently available for mobile machines with an innovative operating strategy. The developed drive and control system proved its functionality and performance under realistic operation conditions in a gravel pit. Reference test showed 10 – 15 % fuel savings of the prototype vehicle compared to a state-of-the-art series machine.

The activities of pairs of mammalian motor neurons (MNs) receiving varying degrees of common excitatory synaptic input were simulated to study the relationship between nearly-coincident spiking and common excitatory drive. The somatic membrane potential of each MN was modeled using a single compartment model. Each MN was modeled toreceive synaptic contacts from hundreds of pre-synaptic fibers. The percentage of pre-synaptic fibers that diverged to supply both MNs of a pair with common synaptic input could be varied from 0 (no common inputs) to 100% (all common inputs). Spikes trains on separate re-synaptic fibers were independent of one another and were modeled as realizations of renewal processes with mean firing rates (10 - 50Hz) resembling that associated with supra-spinal input. Maximum synaptic conductances and time constants were varied across synapsesto match experimentally observed somatic EPSPs. The number of active pre-synaptic fibers to each MN was adjusted in order that the firingrates of MNs were between 8 and 15 Hz. For each common input condition, 100 s of concurrent spiking activity of the MNs was usedto construct cross-correlation histograms. The sizes of the central peaks in the histograms were quantified using both the k' (Ellaway and Murthy 1985) and CIS (Nordstrom et al. 1992) indices ofsynchrony. Monotonically increasing linear relationships between the proportion of common synaptic input and the magnitude of synchronywere observed for both indices. For example, the model predicted that 10% common input would yield a CIS value of 0.27 whereas 100% commoninput would yield a CIS value of 1.5. These values are within the range of values observed experimentally. These results, therefore,provide a means to translate measures of nearly-coincident spiking into plausible renditions of synaptic connectivity.

We are interested in the onset of instability of the axisymmetric flow between two concentric spherical shells that differentially rotate about a common axis in the narrow-gap limit. The expected mode of instability takes the form of roughly square axisymmetric Taylor vortices which arise in the vicinity of the equator and are modulated on a latitudinal length scale large compared to the gap width but small compared to the shell radii. At the heart of the difficulties faced is the presence of phase mixing in the system, characterised by a non-zero frequency gradient at the equator and the tendency for vortices located off the equator to oscillate. This mechanism serves to enhance viscous dissipation in the fluid with the effect that the amplitude of any initial disturbance generated at onset is ultimately driven to zero. In this thesis we study a complex Ginzburg-Landau equation derived from the weakly nonlinear analysis of Harris, Bassom and Soward [D. Harris, A. P. Bassom, A. M. Soward, Global bifurcation to travelling waves with application to narrow gap spherical Couette flow, Physica D 177 (2003) p. 122-174] (referred to as HBS) to govern the amplitude modulation of Taylor vortex disturbances in the vicinity of the equator. This equation was developed in a regime that requires the angular velocities of the bounding spheres to be very close. When the spherical shells do not co-rotate, it has the remarkable property that the linearised form of the equation has no non-trivial neutral modes. Furthermore no steady solutions to the nonlinear equation have been found. Despite these challenges Bassom and Soward [A. P. Bassom, A. M. Soward, On finite amplitude subcritical instability in narrow-gap spherical Couette flow, J. Fluid Mech. 499 (2004) p. 277-314] (referred to as BS) identified solutions to the equation in the form of pulse-trains. These pulse-trains consist of oscillatory finite amplitude solutions expressed in terms of a single complex amplitude localised as a pulse about the origin. Each pulse oscillates at a frequency proportional to its distance from the equatorial plane and the whole pulse-train is modulated under an envelope and drifts away from the equator at a relatively slow speed. The survival of the pulse-train depends upon the nonlinear mutual-interaction of close neighbours; as the absence of steady solutions suggests, self-interaction is inadequate. Though we report new solutions to the HBS co-rotation model the primary focus in this work is the physically more interesting case when the shell velocities are far from close. More specifically we concentrate on the investigation of BS-style pulse-train solutions and, in the first part of this thesis, develop a generic framework for the identification and classification of pulse-train solutions. Motivated by relaxation oscillations identified by Cole [S. J. Cole, Nonlinear rapidly rotating spherical convection, Ph.D. thesis, University of Exeter (2004)] whilst studying the related problem of thermal convection in a rapidly rotating self-gravitating sphere, we extend the HBS equation in the second part of this work. A model system is developed which captures many of the essential features exhibited by Cole's, much more complicated, system of equations. We successfully reproduce relaxation oscillations in this extended HBS model and document the solution as it undergoes a series of interesting bifurcations.

No description available.

Este trabalho utiliza uma metodologia simplificada de análise dinâmica para o estudo das vibrações em pontes ferroviárias, produzidas pela passagem de um trem de alta velocidade, associadas à presença de irregularidades nos trilhos. Iniciou-se o estudo a partir de um modelo do veículo composto por quinze graus de liberdade, referentes aos deslocamentos verticais e horizontais transversais, e rotações em torno dos eixos longitudinal, transversal e vertical. Os modelos dinâmicos do trem e da ponte foram tratados de forma desacoplada, sendo conectados pelas forças de interação trem-ponte. Desta forma, foram calculados os carregamentos provenientes da modelação dinâmica do trem, adotando-se inicialmente a hipótese de tabuleiro rígido e indeslocável e, ainda, considerando-se a presença de irregularidades geométricas nos trilhos no plano vertical. Neste trabalho, foi considerado um estudo de caso utilizando-se o modelo veicular Alfa Pendular, avaliando-se a resposta dinâmica do trem e da estrutura, considerando o efeito das irregularidades geométricas nos trilhos, bem como a presença do lastro. As forças de interação obtidas da modelagem do veículo foram aplicadas em um modelo estrutural de alta hierarquia da ponte, dividido em elementos finitos de casca, sendo que em cada nó do modelo da ponte foram especificados os esforços obtidos da análise dinâmica do veículo. Para representar a passagem do comboio sobre a ponte, foram utilizadas funções que descrevem as forças de interação trem-ponte em cada nó do modelo da ponte, em cada intervalo de tempo, até que todo o trem tenha percorrido o comprimento da ponte. A consideração de tabuleiro rígido indeslocável foi corrigida por meio de um processo iterativo, de forma que os deslocamentos do tabuleiro obtidos para a primeira determinação dos esforços de interação foram somados às irregularidades do trilho (excitação de suporte aplicada nas rodas do trem). Com isso, foi possível identificar a resposta dinâmica proveniente da carga em movimento e das irregularidades geométricas nos trilhos, avaliando o conforto dos passageiros no interior do vagão. Por fim, realizou-se uma análise de distribuição estatística para avaliar a probabilidade de se ultrapassar os limites estabelecidos pelo Eurocode. / This thesis resorts to a simplified methodology of dynamic analysis for the study of vibrations in railway bridges, produced by the passage of a high speed train, associated to the presence of irregularities in the rails. The study started from a vehicle model composed of fifteen degrees of freedom, namely, vertical and lateral displacements, and rotations about the longitudinal, lateral and vertical axes. The dynamic models of the train and the bridge were treated as uncoupled, yet being bound by the interaction train-bridge forces. Thus, the loads from the dynamic model of the train were calculated, adopting initially the hypothesis of rigid and fixed deck and also, considering the presence of geometric irregularities in the vertical track plane. In this work, we considered a case study using the Alfa Pendular vehicle model, evaluating the dynamic response of the train and the structure, considering the effect of the geometric irregularities at the tracks, as well as the presence of the ballast. The interaction forces obtained from the model of the vehicle were applied in a high hierarchy structural model of the bridge, divided into shell finite elements, specifying the forces obtained from the dynamic analysis of the vehicle at each node of the bridge model. To represent the train passage on the bridge, functions were used to describe the bridge-train interaction forces at each node of the bridge model at each time interval, until the entire train had travelled the bridge length. The consideration of rigid and fixed deck was corrected by means of an iterative process, so that the deck displacements obtained for a first determination of the interaction forces were added to the rail irregularities (excitation applied to the train wheels). Thus, it was possible to identify the dynamic response caused both by the moving loading and the geometrical irregularities of the tracks, evaluating the comfort of the passengers inside the wagon. Finally, a reliability study was carried out to evaluate the probability of exceeding the limits established by Eurocode.

Thesis (Master of Engineering in Electrical Engineering)--Cape Peninsula University of Technology, 2018. / The purpose of this paper was to design and develop an electrical power train for an Urban Concept electric vehicle geared to complete the Shell Eco-Marathon Africa in 2019. Various technologies which make up the electrical drive train of an electrical vehicle were also reviewed which include the battery pack, the battery management system, the motors, the motor management system and the human interface. Upon completion of this, the various topologies best suited for this project were selected, designed, constructed and developed. Two motors were re-designed and constructed for this vehicle and the motor drive was also constructed to control these motors. A Lithium-Ion battery pack was constructed and developed to drive the motors and an off-the-shelf battery management system was purchased and developed to suit the requirements for the Shell Eco- Marathon competition rules. A human interface was also developed in order for the driver to see various parameters of the electric vehicle defined by the Shell Eco-Marathon competition rules. After each component of the drive train was constructed, they underwent various testing procedures to determine the efficiency of each individual component and the overall efficiency for the complete drive train of this electric vehicle was ascertained. The Product Lifecycle Management Competency Centre group developed the chassis for this vehicle. For this reason, only the electric subsystems were evaluated and a simulation was completed of the complete drive train. After the complete drive train was constructed and all the individual subsystems evaluated and simulated, a vehicle with an overall efficiency of about sixty percent was expected and the completed drive train should be adequate enough to complete the entire Shell Eco-Marathon Africa circuit.