Made available in DSpace on 2014-08-20T14:23:47Z (GMT). No. of bitstreams: 1 Maira_Eveline_Schmitz_Dissertacao.pdf: 4232550 bytes, checksum: 6537dd56360d322df71ec4f4f3c80aa2 (MD5) Previous issue date: 2013-03-15 / This work has a theme the railroad in the city of Pelotas, in the specific period of 1884, time of inauguration of the Rio Grande Bagé Railroad and railway station of Pelotas until the first decades of the 20th century, between the years 1910 and 1920. The central object of the research is the relationships and social conflicts that came with trains and exceeded the space station, building what can be called "urban railway area". The focus, therefore, is directed to visual development and to the formation of specific sociability at these spacialities. For the preparation of this work was to analyze, mainly, through newspapers and photographs that represent the area of the railroad in the period, added to reports and technical regulations, correspondence and memoirs. In relation to the methodology with the images, starting work as Ana Maria Mauad and Zita Possamai, the fonts was divided into thematic categories; after, following the contributions of Canabarro, we opted for a scheme of analysis that focuses on the different planes of an image, whether in relation to what is shown, or the way that evokes the representation; lastly, the line interpretive theoretical and methodological started the three main spots suggested by Ulpiano Bezerra de Menezes, to think about the relationship of the History with pictures: visual, the visible and the vision. In relation to the journals, followed the line of interpretive by Tania Regina de Luca. In a sense, the treatment of journals did not differ much from that given to images, being also classified by themes, to continue after an analysis centered on how the narratives were exposed and its content / O presente trabalho possui por tema a ferrovia na cidade de Pelotas, no período específico de 1884, momento da inauguração da Estrada de Ferro Rio Grande Bagé e da estação ferroviária pelotense, até as primeiras décadas do século XX entre os anos de 1910 e 1920. O objeto central da pesquisa são as relações e os conflitos sociais que vieram com os trens e ultrapassaram o espaço da estação, construindo o que pode ser chamado de espaço ferroviário urbano . O foco, assim, direciona-se para a elaboração visual e para a constituição de sociabilidades específicas nestas espacialidades. Para a elaboração deste trabalho, a análise ocorreu, principalmente, por meio de jornais e fotografias que representassem o espaço da ferrovia no período, somados a relatórios e regulamentos técnicos, correspondências e memórias escritas. Em relação à metodologia com as imagens, partindo de trabalhos como de Ana Maria Mauad e Zita Possamai, dividiu-se as fontes em categorias temáticas; após, seguindo as contribuições de Canabarro, optou-se por um esquema de análise que focaliza os diversos planos de uma imagem, seja em relação ao que está representado, ou aos sentidos que a representação evoca; por fim, a linha interpretativa teórico-metodológica principal partiu dos três focos sugeridos por Ulpiano Bezerra de Meneses, ao pensar a relação da história com as imagens: o visual, o visível e a visão. Em relação aos periódicos, seguiu-se na linha interpretativa de Tânia Regina de Luca. De certo modo, o tratamento dos periódicos não diferiu muito daquele dado às imagens, sendo também classificados por categorias temáticas, para após prosseguir com uma análise centrada na forma como as narrativas eram expostas e no seu conteúdo

När nya betongbroar över järnväg ska upprättas finns det många aspekter som försvårar byggandet, som t.ex. att trafiken inte kan stoppas helt förutom under kortare perioder under byggtiden. Tågstoppen planeras in många år i förväg vilket gör att produktionen måste planeras och utföras utefter de planerade stoppen. Det är svårt att få till en industrialiserad brobyggnadsprocess med högre effektivitet och mer upprepning. Den traditionella platsgjutna metoden är den metod som är vanligast i Sverige trots att det finns metoder som skulle kunna ersätta den. Det huvudsakliga syftet med rapporten är att ta reda på om prefabricerade betongelement på plats är en möjlig metod för att underlätta byggandet av nya betongbroar över järnväg. Denna rapport baseras på en fallstudie av ett befintligt broprojekt för att se vilka fördelar och förbättringar metoden med prefab på plats kan ge i olika aspekter. Utöver detta har intervjuer och en enkätundersökning genomförts för att samla in material och åsikter om prefab och industrialiserade brobyggnadsprocesser. Resultatet i denna rapport visar att metoden med prefab på plats är mer fördelaktig än den traditionella platsgjutna metoden i flera hänseenden. Det är en metod som gör det möjligt att nå upprepning och serietillverkning av broar. Vid intervjuerna framkom att entreprenörerna är intresserade av prefablösningar men bland annat krav på utformning och konservativ syn på prefab från beställarna hindrar möjligheterna för att tillämpa metoden / When new concrete bridges over railway is to be established there are many aspects that complicates the construction, such as that traffic not can be stopped completely except for short periods during the construction process. The train stop is planned many years in advance, which means that construction must be planned and performed along the planned stops. It is difficult to get to an industrial bridge construction process with higher efficiency and more repetition. The traditional cast on site method is the most common in Sweden although there are methods that could replace it. The main purpose of the report is to find out if precast concrete elements on site is a possible method to facilitate the construction of new concrete bridges over the railway. This report is based on a case study of an existing bridge project to see the benefits and improvements the method with precast on site can provide in various aspects. Also interviews and surveys was conducted to collect opinions about prefabrication and industrial bridge construction. The results in this report show that the method of prefab on site is more advantageous than the traditional cast on site method in several respects. It is a method that makes it possible to reach repetition and serial production of bridges. The interviews revealed that contractors are interested in prefabricated solutions, but among other requirements for the design and conservative view of prefabrication from clients prevents the possibility of applying the method.

The form of the energy function (i.e. Total, Hellinger-Reissner, Hu-Washizu or Complementary energy functions) has a significant influence on FEM performance. Motivated by the ability of the force-based method to satisfy the equilibrium equation and ability of the displacement-based method to satisfy compatibility equation, this thesis proposes a mathematical framework, namely the ‘Hybrid Force-Based Method’ which employs two physical concepts; the Total and Complementary Potential Energy functions. Satisfaction of both the Total and Complementary Potential Energy function is critical to the success of the Hybrid Force-Based Method. The Hybrid Force-Based Method is constructed using these two independent energy functions in order to perform inelastic structural analyses. The method has been proposed, implemented and evaluated across the entire structure, element, section and material domains first considering each domain separately and then in combination. The equilibrium and compatibility equations are satisfied simultaneously by discretisation of these two equations, and accuracy is controlled by specifying the upper and lower bounds of the results. Outcomes following evaluation of the proposed method can be classified into the following three categories: (i) structure-level performance (see Chapter 2), (ii) material-level performance (see Chapter 3), and (iii) element level performance (see Chapter 4). The proposed Hybrid Force-Based Method is constructed by deriving the governing equations directly from the Total and Complementary Potential Energy functions, leading to two distinct variants of the hybrid approach (i) the so-called ‘augmented Hybrid Force-Based Method’, and (ii) the so-called ‘unaugmented Hybrid Force-Based Method’. A number of numerical posterior process tests were devised and used to demonstrate the performance of these two variations of the hybrid method (see Sections 2.9.4.1 and 2.9.5.1) to demonstrate those methods ability in convergence in contrast to the Large Increment Method. Due to the occurrence of numerical instabilities experienced when using various established solution algorithms in solving the fundamental equations at the material level, within implicit approach (such as the Standard Implicit Method, the Cutting Plane Method, and the Closest Point Projection Method). A new form of the constitutive equation solver is proposed in Sections 3.9, referred to as the General Implicit Method (GIM). It is shown that the GIM can be implemented both in the strain and stress domains, and is therefore appropriate for use in both the displacement- and the force-based solution family of methods. The GIM is then evaluated by comparing its predictions to those of other common solution algorithms for inelastic analysis. Performance evaluation involves the use of a new error indicator that guarantees the uniqueness and accuracy of a solution in both the stress and the strain domains. Three iso-error maps serve to emphasis the accuracy, reliability, and computational performance of the General Implicit Method as a solution method compared to those are evaluated for the defined Stress Increment Ratio. The fundamental equations at the element level are followed, based on structured fibre discretisation. The decomposition of the various degrees of freedom into deformational and rigid-body motion serve as a mechanism by which independent equilibrium equations can be determined for each element. The subsequent equation is able to involve axial force, torsion, and both in and out of plane moments while a general form of shear strain distribution is also involved. The original form of the solution at the cross section of the elements leads to novel governing equations that are based on the characteristics of the hybrid force-based approach. The numerical evaluation in Section 4.11.7.1 demonstrates the performance of the proposed method. The newly defined error indicators demonstrate the accuracy and computational performance of the method and the uniqueness of the solution in satisfying both the equilibrium and compatibility equations for Euler-Bernoulli, Timoshenko, and Reddy strain distributions across the element section. Further to the structured fibre, distributed, semi-distributed and concentrated inelastic approach elements, as a simplified form of the element are implemented and evaluated. Although performance of those original formulations is evaluated independently in in comparison with the conventional approaches, compatibility of those as an important issue is followed as well. The numerical evaluation demonstrates higher accuracy and reliability by following the proposed method, further to the higher computational performance respect to the conjugate approaches.

Les voies ferrées, construites pour la plupart depuis plus d'une centaine d'années, sont des ouvrages vieillissants. Elles nécessitent une maintenance et un entretien accrus, ce qui constitue un enjeu technique et économique majeur pour les années à venir. Jusqu'à l'ouverture des marchés à la concurrence, la mise en œuvre des voies nouvelles était vérifiée empiriquement par la SNCF. Du fait de la mise en œuvre de la directive européenne 91/440/10, l'exploitant historique se tourne d'un objectif de moyen vers un objectif de résultat. Cela nécessite donc de disposer de méthodes d'auscultation non destructives, permettant de vérifier que le compactage du ballast est correctement réalisé, avant de faire circuler le trafic voyageurs, en vue de garantir un niveau de sécurité élevé. Cette première approche pourrait être poursuivie pour assurer une auscultation à grand rendement. Cependant, les méthodes existantes permettant d'obtenir l'état de compactage du ballast à la mise en œuvre sont ponctuelles et difficiles à mettre en place; elles ne répondent pas à la problématique de doublement de la maintenance des voies des prochaines années. L'étude de la propagation d'ondes vibratoires dans le ballast est une alternative à ces méthodes qui peut permettre de répondre à ces contraintes. Le ballast est un milieu discontinu complexe pour la compréhension des ondes car elles se propagent dans un chaînon de force. Il présente une grande difficulté dans la modélisation du fait de la taille élevée des éléments et doit être traité comme un milieu discret ne répondant pas à une mécanique élastique de milieu continu. Étant donné la difficulté de modéliser cette couche discrète, il convient de traiter le problème par l'expérimentation. L'objectif de cette thèse est donc d'orienter la recherche vers l'utilisation de la propagation des ondes vibratoires dans la structure de la voie. Ce mémoire est organisé comme suit :- un premier chapitre détaille la structure de la voie ferrée et le matériau granulaire qu'est le ballast, ainsi que les méthodes de diagnostic des voies ferrées existantes.- le deuxième chapitre décrit les différents types d'ondes vibratoires se propageant dans un milieu élastique homogène, puis dans le ballast, et étudie la réponse du ballast à travers celle de la traverse ferroviaire.- Ces deux chapitres, issus de l'état de l'art, permettent de définir dans le chapitre trois les expérimentations réalisées dans le cadre de ce travail sur une structure ferroviaire en vraie grandeur : mise en œuvre, instrumentation, résultats. Ce chapitre s'attache particulièrement à décrire la vitesse des ondes et leur amortissement dans le ballast, les courbes de dispersion mesurées.- Enfin, la propagation d'une onde vibratoire dans le ballast est étudiée dans le chapitre quatre par le biais d'une simulation numérique, avec la comparaison de deux modélisations discrète et continue avec l'expérimentation / Railways, most of them built for over one hundred years, are old structures. They require increasing maintenance, a major technical and economic challenge for the coming years. Until the opening of markets to competition, the implementation of new railroads was empirically controlled by SNCF. Because of the application of the European directive 91/440/10, the historical operator turns from a goal of means to a goal of results. This calls for non-destructive highly efficient auscultation methods to check the right compaction of the ballast. However, existing methods for obtain ballast compaction assessment during implementation stage are surface-limited and difficult to apply; they do not respond to the issue of the doubling of track maintenance. Thus the study of the propagation waves in the ballast is an alternative to these methods and may allow to answer these requirements. The ballast is a discontinuous medium, complex for the understanding of waves, as they propagate in a force link. Modelling ballast is especially difficult because of the large size of its components and because it should be treated as a discrete environment, not following the elastic mechanics of continuous media. Given the difficulty to model this discrete layer, it is necessary to undertake the problem with experimentation. The aim of this thesis is to focus on the use of the propagation of vibration waves in the railroad structure. This work is organized as follows : the first chapter details the structure of the railroad and the ballast as a granular material, and the existing assessment methods for railroad. The second chapter describes the different types of vibration waves that propagate, first, in an elastic homogeneous medium, second in the ballast, and presents the answer of ballast through the answer of the sleeper. The two previous chapters, derived from the state of the art, allow to define in chapter three the experiments implemented as part of this work on a full scale railroad structure : realization, instrumentation, results. This chapter especially endeavours to describe the waves celerity, their damping in ballast and the measured dispersion curves. Finally, the propagation of a vibration wave in the ballast is studied in chapter four and a numerical simulation, compares with a disctete model and a continuous model with experimental results

Anläßlich des Festkolloquiums 60 Jahre Elektrische Bahnen stellt sich die Professur vor. Es wird ein Überblick zur Geschichte der Professur gegeben.

L’histoire de la noblesse au cours du XIXeme siècle est un champ historiographique peu exploité par les historiens français. La première grande étude étant celle de David Higgs. Auparavant, l’histoire de la noblesse post-révolutionnaire a toujours été envisagée comme partie de l’histoire des élites telles qu’établie par Louis Bergeron et Guy Chaussinand-Nogaret. Pour envisager la noblesse du XIXeme sujet spécifique, il faut dépasser le bilan dressé par Karl Marx et Jean Jaures qui ont voulu voir dans la noblesse l’expression d’une société sclérosée disparue au cours des événements révolutionnaires.Le premier point à résoudre est de trouver une définition de la noblesse qui permette d’établir une base de travail non équivoque. Ainsi, la noblesse du XIXeme siècle n’est plus celle de l’Ancien Régime. Elle n’est plus protégée par des statuts et des privilèges qu’elle a souhaité elle-même supprimer. Par conséquent la noblesse est composée d’hommes et de femmes qui ont une conscience ethnologique d’appartenir à un groupe ayant des valeurs et des comportements similaires.Le cadre géographique de la recherche est élargi à l’ensemble des cinq départements normands afin de mieux repérer et suivre les particularismes de la noblesse ainsi que l’influence de Paris limitrophe avec la région.La période s’étend de 1789 à 1910 afin de saisir l’ensemble des variations de l’influence politique de la noblesse normande. L’impact de chacune des révolutions ainsi que le rôle de la noblesse dans l’émergence des mouvements révolutionnaires entrent ainsi dans le champ de l’étude.De manière connexes seront envisagés les influences économiques et intellectuelles de la noblesse, notamment son rôle sur les tracés de chemins de fer ou sur la Société des Antiquaires de Normandie. / The history of the nobility during the 19th century is a historiographical field less strudied by historians. The first of them were the one of David Higgs. Previously, the history of the post-revolutionary nobility was always envisaged as part of elites hystory, such as established by Louis Bergeron and Guy Chaussinand-Nogaret. To envisage the nobility of the specific subject 19th, it is necessary to exceed the balance assessment raisedby Karl Marx and Jean Jaures who wanted to see in the nobility the expression of a calcified society, which has disappeared during the revolutionary events.The first point to be solved is to find a definition of the nobility which allows to establish basis of not ambiguous work. So, the nobility of the 19th century is not any more the one of the Ancien Régime.It is not any more protected by statutes and privileges which she wished herself to rease. Consequently the nobility consists of men and women who have an ethnological consciousness to belong to a group having values and similar behavior.The geographical frame of the search is widened to the set of five Norman departments in order to find and follow the senses of identity of the nobility as well as the influence of bordering Paris.The period extends from 1789 till 1910 to seize all the variations of the political influence of the Norman nobility. The impact of each of the revolutions as well as the role of the nobility in the emergence of the revolutionary movements so enter the field of the study.In a related way will be envisaged the economic and intellectual influences of the nobility, in particular its role on the plans of railroads or on the Société des Antiquaires de Normandie.

This report aims to determine the economical benefits of improved public transport in some of Stockholms northern suburbs that are strategic locations for further urbanization. The correlation between public transport (PT) and property values will be explored. How will the PT scenarios that are suggested here increase the value of real estate in the regional focal points? How can the financial winners by this improvement be prepared to take part in financing the PT solutions? Denna uppsats syftar till att fastställa de ekonomiska fördelarna av förbättrad kollektivtrafik i norra Stockholmsregionen. Det kommer att undersökas i vilken utsträckning det föreligger ett samband mellan tillgänglighet till kollektivtrafik och fastighetsvärden. Hur kan de olika kollektivtrafiklösningarna komma att påverka fastighetsvärdena i de regionala kärnorna? Hur skulle nyttotagarna av en sådan investering kunna vara med att finansiera den?

This thesis is an investigation into the feasibility of one-dimensional Light Detection and Ranging (LIDAR) sensors for tracking the position and motion of trains on railroad classification yards. Carefully monitoring railway traffic in these areas is important, in order to avoid accidents, optimise logistical operations and hence reduce delays. However, existing technologies for tracking trains on regular stretches of train-line, including Radio Frequency Identification (RFID) and Global Positioning System (GPS), have various drawbacks when applied to classification yards. As such, it is pertinent to investigate the extent to which simple LIDAR sensors could be used for this purpose, as part of a basic Internet of Things (IoT) system. To tackle this problem, we considered different ways of positioning the sensors around railway tracks. We then proposed a floating average algorithm for calculating a target object’s velocity using continuous LIDAR distance readings. To know when to apply the algorithm as a train is passing the sensor, we observed how the distance readings varied as a model train passed the sensor. The data was used to construct a Finite-state machine (FSM) that can fully describe the status of trains as they pass the sensor. In order to test our solution, we constructed a prototype sensor node implementing the FSM and evaluated its performance first with a model train and then on actual commuter trains on an outdoors train platform. We found that one-dimensional LIDAR sensors could feasibly be deployed to monitor the position and motion of trains with a high degree of consistency and accuracy. However, LIDAR may need to be corroborated with other types of technology such as RFID so that trains can be distinguished from other moving objects. / Detta projekt undersöker möjligheten att använda endimensionella Light Detection and Ranging (LIDAR) sensorer för att spåra läge och rörelse av tåg på rangerbangårdar. Att övervaka tågtrafik i dessa områden är viktigt för att undvika trafikolyckor, optimera logistiska operationer och därmed minska förseningar. Dagens teknik för att spåra tåg på vanliga tågspår, till exempel Radio Frequency Identification (RFID) och Global Positioning System (GPS), har flera begränsningar när de ska användas till rangerbangårdar. Följaktligen så är det relevant att undersöka till vilken grad enkla LIDAR sensorer kan tillämpas för detta ändamål som en del av ett Internet of Things (IoT) system. För att lösa detta problem, övervägde vi olika sätt att placera sensorerna kring tågspår. Därefter implementerade vi en glidande medelvärdealgoritm för att beräkna målobjektets hastighet genom att använda kontinuerliga LIDAR avståndsmätningar. För att kunna veta när algoritmen skulle tillämpas när riktiga tåg passerade sensorn, noterade vi först hur avståndsmätningarna varierade när ett modelltåg passerade sensorn. Mätningarna användes sedan för att konstruera en ändlig tillståndsmaskin (FSM) som kan fullständigt beskriva statusen av tåget när det åker förbi sensorn. För att testa vår lösning, tillverkade vi en sensornodprototyp med vår FSM implementerad och utvärderade först dess prestationsförmåga med ett modelltåg och sedan med riktiga pendeltåg.Vi observerade att endimensionella LIDAR sensorer kan användas för att övervaka läge och hastighet av tåg med hög precision och konsekventa resultat. Däremot visade sig att LIDAR ska med fördel kombineras med andra typer av teknologi, som till exempel RFID, för att urskilja tåg från andra objekt i rörelse.

Syftet med arbetet är att undersöka vad det är som hindrar företag i dagsläget från att använda intermodala godstransporter med järnvägen, där frågeställningar som arbetet kommer att besvara är: Överväger fördelarna de nackdelar som finns med användningen av intermodala godstransporter på järnvägen? Samt hur ser framtiden ut för intermodala godstransporter på järnväg? För att besvara syftet har vi använt oss av kvalitativa metoder i form av intervjuer, där intervjufrågorna utformades utifrån semistrukturerade intervjuer. Det teoretiska ramverket är uppbyggt med hjälp av vetenskapliga artiklar och indelat i fyra aspekter som anses vara viktiga för kunder och deras val av transportslag vid transport av gods. Det empiriska materialet är utformat efter intervjuer med intervjupersoner som arbetar med intermodala godstransporter och där dessa arbetar på olika företag. Det empiriska materialet har sedan ställts mot det teoretiska ramverket för att ta fram en analys, där materialet analyserades genom en tematisk analysmetod. Arbetet kom fram till resultatet att hållbarhet alltid varit en av järnvägens starkaste fördelar, men järnvägens nackdelar är de som påverkar kundernas val mest. Nackdelarna är tid och leveranssäkerhet, för att motverka dessa nackdelar krävs det att man gör investeringar i järnvägsinfrastrukturen. Dessa investeringar kan vara att bygga ut eller förbättra den nuvarande järnvägsinfrastrukturen i hopp om att få fler spår och ett starkare nätverk kommer att minimera nackdelarna så att transporterna kan utföras snabbare och effektivare. Framtiden för järnvägen är lovande om investeringar och projekt planeras rätt. Förbättringar kommer leda till att godstransporter på järnväg ökar, dock överväger fördelarna i dagsläget inte nackdelarna om man är ett företag som har tidskänsliga transporter. / The purpose of this work is to investigate what prevents companies from currently using intermodal rail transportation, where the research questions to be answered are: Do the benefits outweigh the disadvantages of using intermodal rail transportation? What does the future hold for intermodal freight transportation by rail? To address the purpose, we have utilized qualitative methods in the form of interviews, where the interview questions were designed based on semi-structured interviews. The theoretical framework is built using scientific articles and divided into four aspects considered important for customers and their choice of transport mode for the transportation of goods. The empirical material is based on interviews with interviewees working with intermodal rail freight, representing different companies. The empirical material was then compared to the theoretical framework to conduct an analysis, where the material was analyzed using thematic analysis method. The study concluded that sustainability has always been one of the strongest advantages of rail transportation, but it is the disadvantages of rail transportation that have the greatest impact on customers' choices. The disadvantages include time and delivery reliability, and to counteract these disadvantages, investments in rail infrastructure are required. These investments can involve expanding or improving the current rail infrastructure, with the hope that more tracks and a stronger network will minimize the disadvantages, allowing for faster and more efficient transportation. The future of rail transportation is promising if investments and projects are planned correctly. Improvements will lead to an increase in rail freight, but currently, if a company has time-sensitive shipments, the disadvantages outweigh the benefits.

Malfunction in the overhead contact line system is a common cause of disturbances in the train traffic in Sweden. Due to the preventive methods being inefficient, the Swedish Transport Administration has stated the need to develop the railroad maintenance services and has identified Artificial Intelligence (AI) as an important tool for this undertaking.  Light Detection and Ranging (LiDAR) is a remote sensing technology that has been gaining popularity in recent years due to its high ranging accuracy and decreasing data acquisition cost. LiDAR is commonly used within the railroad industry and companies such as WSP collects large amount of data through LiDAR measurements every year. There is currently no reliable fully automatic method to process the point cloud data structure. Several studies propose innovative methods based on traditional machine learning to extract railroad system components from point clouds and have been able to do so with good results. However, these methods have limited applicability in real world problems, as they build upon hand-crafted features based on previous knowledge of the data on which they are applied. Deep learning technology may be a better alternative for the task as it does not require the same amount of human interaction for feature engineering and knowledge about the data in advance.  This thesis investigates if contact line poles can be recognized from LiDAR data with the use of the neural network architecture DGCNN. Data from two Swedish railroad lines, Saltsjöbanan and Roslagsbanan, provided by WSP was used. Point labels were predicted through semantic segmentation from which objects were distinguished using the clustering algorithm DBSCAN. The network was trained and validated on Saltsjöbanan using k-fold cross-validation and was later tested on Roslagsbanan to simulate the application of trained models on an unknown dataset. On point level the network achieved an estimated precision of 0.87 and a recall of 0.89 on the data from Saltsjöbanan and an estimated precision of 0.92 and recall of 0.83 on the data from Roslagsbanan. In the object recognition task, the approach achieved an average precision of 0.93 and recall of 0.998 on the data from Saltsjöbanan and on the data from Roslagsbanan, an average precision of 0.96 and a recall of 1 was achieved, indicating that it is possible to apply this method on railroad segments other than the one the network was trained on. Despite not being accurate or reliable enough on point level to be used for thorough inspection of the contact line system, this approach has various applications in terms of object recognition along Swedish railroads. Future research should investigate how adding additional classes beyond contact line poles would affect the results and what changes can be done to the parameters to optimize the performance. A side-by-side comparison with the current methods and traditional machine learning-based methods would be valuable as well. / Fel i kontaktledningssystemet är en vanlig orsak till störningar i tågtrafiken i Sverige. Då dagens metoder för att förebygga dessa fel är ineffektiva har Trafikverket uttryckt behovet av att utveckla underhållsarbetet av den svenska järnvägen och har identifierat artificiell intelligens (AI) som ett viktigt verktyg i det syftet. Light Detection and Ranging (LiDAR) är en fjärranalysteknologi som har blivit allt mer populär med åren tack vare sin höga mätnoggrannheten och allt billigare datainsamling. LiDAR används regelbundet inom järnvägsindustrin och företag som WSP samlar årligen in stora mängder data med denna teknologi. I dagsläget finns det däremot ingen tillräckligt pålitlig automatisk metod för att segmentera och klassificera punktmoln. Ett flertal studier föreslår lösningar baserade på traditionell maskininlärning för att ta ut järnvägskomponenter ur punktmolnsdata. Eftersom dessa metoder bygger på förkunskap och noga utvecklade funktioner för att hitta mönster i datan är de svåra att tillämpa i verkliga problem. Istället kan djupinlärning som inte kräver samma förkunskap eller noggranna matematiska modellering tillämpas. I det här arbetet identifierades kontaktledningsstolpar ur LiDAR data med hjälp av det neurala nätverket DGCNN. Datan som användes var punktmolnsdata från Saltsjöbanan och Roslagsbanan försedd av WSP. Först klassificerades punkter genom semantisk segmentering och från klassificeringen kunde objekt identifierades genom att tillämpa klusteringsalgoritmen DBSCAN. Nätverket tränades med hjälp av korsvalidering på data över Saltsjöbanan och testades därefter på data över Roslagsbanan för att undersöka om tränade modeller kan tillämpas på andra järnvägslinjer. På datan över Saltsjöbanan uppnådde nätverket en estimerad specificitet på 0.87 och sensitivitet på 0.89 på punktnivå. Motsvarande värden på datan över Roslagsbanan låg på 0.92 och 0.83. Metoden för objektigenkänning uppnådde en genomsnittlig specificitet på 0.93 och sensitivitet på 0.998 på datan över Saltsjöbanan och motsvarande värden på datan över Roslagsbanan låg på 0.96 och 1. Resultatet indikerar att metoden går att tillämpa på andra järnvägslinjer utan specifik träning för dessa.  Trots att metoden inte är träffsäker nog på punktnivå för att användas för grundlig besiktning av kontaktledningssystemet kan den användas för objektigenkänning längs svensk järnväg. Framtida forskning bör undersöka hur resultatet påverkas om ytterligare klasser utöver kontaktledningsstolpar används och vilka förändringar bör göras bland parametrarna för att optimera det undersökta tillvägagångssättet. En utförlig jämförelse mot nuvarande metoder och metoder baserade på traditionell maskininlärning skulle dessutom vara av värde.