Spelling suggestions: "subject:"heavy hall"" "subject:"heavy haut""
1 |
Contribuição ao processo de avaliação técnica e seleção dos componentes da grade ferroviária para a implantação em ferrovias de transporte de carga. / Contribution for the process of evaluation and selection of the components of the rail structure on heavy haul railways.Russo, Luis Eduardo Abrantes 14 December 2011 (has links)
Nos últimos anos, tem-se presenciado um contínuo aumento na demanda por transporte de carga ferroviário no Brasil, o que tem se refletido em maior volume de projetos para expansão ou revitalização da malha existente no país. Diante deste quadro atual, torna-se essencial que o profissional envolvido com a elaboração de projetos da via permanente tenha em mãos informações atualizadas a respeito da variedade de componentes da grade ferroviária existente no mercado, a fim de que os projetos atendam plenamente às necessidades do cliente. Assim sendo, o presente trabalho tem como principal objetivo pesquisar e analisar os tipos de componentes existentes no mercado usados na composição da grade ferroviária (trilhos, dormentes e fixações), com foco principal naqueles que podem ser aplicados às ferrovias de transporte de carga. Primeiramente, a partir de pesquisa em material bibliográfico nacional e internacional, serão descritos os principais aspectos técnicos que devem ser considerados no processo de avaliação destes componentes, tendo como base os parâmetros de projeto da via estabelecidos previamente de acordo com as exigências da operação de carga, tais como: carga por eixo, velocidade de operação, rampa máxima, etc. Em seguida, serão apresentados os tipos de trilhos, dormentes (madeira, concreto monobloco e bi-bloco, aço e plástico) e fixações (rígidas e elásticas) existentes atualmente no mercado e suas características de desempenho e condições de uso estabelecidas pelos respectivos fabricantes. Os dados obtidos nas duas etapas descritas anteriormente serão analisados e confrontados, de forma que seja possível explicitar as relações de interdependência que existem entre os diferentes tipos de componentes. Ao final do trabalho, será apresentado um modelo de fluxograma que reúne os dados de entrada para o projeto da ferrovia de transporte de carga, as diretrizes técnicas que devem ser atendidas em seu projeto e, por fim, os tipos de componentes da grade ferroviária que podem ser empregados de acordo com o caso estudado. Com isso, espera-se que o produto final gerado possa ser uma ferramenta útil na etapa de concepção de novos projetos ferroviários, visto que apresentará de maneira clara e objetiva um conjunto de informações bastante abrangente e atualizado a respeito dos critérios técnicos e das opções de componentes disponíveis no mercado, fornecendo uma orientação inicial consistente ao profissional envolvido sobre os materiais que podem ser aplicados à via em estudo. / Over the last years, a continuous increase on demand for railroad heavy haul transport has been witnessed in Brazil, reflecting in bigger volume of projects for expansion or improvement of the existing lines in the country. With this current situation, it becomes essential that the professional involved with the elaboration of projects of the permanent way should have information brought up to date regarding the variety of components of the existing railroad materials in the market, so that the projects take care of fully to the necessities of the customer. Thus being, the present work has as main objective to search and to analyze the types of existing components in the market used in the composition of the railroad superstructure (rails, ties and fastenings), with main focus in that which can be applied to the heavy haul railways. First, from research in national and international bibliographical material, the main aspects related to the performance that must be considered in the process of evaluation of these components will be describes, having as base the design parameters of the way established previously in accordance with the requirements of the load operation, such as: position for axle, speed of operation, maximum slope, and others. After that, the types of rails, ties (wood ties, monoblock and bi-block concrete ties, steel ties and plastic ties) and fastenings (rigid and elastic) currently available in the market and its characteristics of performance and conditions of use will be presented, according to the information provided by the its respective manufacturers. All the reports showed in the two previous described stages will be analyzed and compared, so that is possible to highlight the interdependence relations that exist between the different types of components. At the end of the work, a flowchart model which gathers the input data about the heavy haul railroad, the performance guidelines that should be followed and the types of components of the railroad superstructure that can be used in accordance to the studied case, will be presented. With that, it is expected that the produced flowchart could be a useful tool in the stage of design of a new railroad, once it will present in a clear and objective way an embracing and up-to-date set of information regarding the performance criteria and the options of components available in the market, supplying a consistent initial orientation to the designer about the materials that could be applied to the railway.
|
2 |
Contribuição ao processo de avaliação técnica e seleção dos componentes da grade ferroviária para a implantação em ferrovias de transporte de carga. / Contribution for the process of evaluation and selection of the components of the rail structure on heavy haul railways.Luis Eduardo Abrantes Russo 14 December 2011 (has links)
Nos últimos anos, tem-se presenciado um contínuo aumento na demanda por transporte de carga ferroviário no Brasil, o que tem se refletido em maior volume de projetos para expansão ou revitalização da malha existente no país. Diante deste quadro atual, torna-se essencial que o profissional envolvido com a elaboração de projetos da via permanente tenha em mãos informações atualizadas a respeito da variedade de componentes da grade ferroviária existente no mercado, a fim de que os projetos atendam plenamente às necessidades do cliente. Assim sendo, o presente trabalho tem como principal objetivo pesquisar e analisar os tipos de componentes existentes no mercado usados na composição da grade ferroviária (trilhos, dormentes e fixações), com foco principal naqueles que podem ser aplicados às ferrovias de transporte de carga. Primeiramente, a partir de pesquisa em material bibliográfico nacional e internacional, serão descritos os principais aspectos técnicos que devem ser considerados no processo de avaliação destes componentes, tendo como base os parâmetros de projeto da via estabelecidos previamente de acordo com as exigências da operação de carga, tais como: carga por eixo, velocidade de operação, rampa máxima, etc. Em seguida, serão apresentados os tipos de trilhos, dormentes (madeira, concreto monobloco e bi-bloco, aço e plástico) e fixações (rígidas e elásticas) existentes atualmente no mercado e suas características de desempenho e condições de uso estabelecidas pelos respectivos fabricantes. Os dados obtidos nas duas etapas descritas anteriormente serão analisados e confrontados, de forma que seja possível explicitar as relações de interdependência que existem entre os diferentes tipos de componentes. Ao final do trabalho, será apresentado um modelo de fluxograma que reúne os dados de entrada para o projeto da ferrovia de transporte de carga, as diretrizes técnicas que devem ser atendidas em seu projeto e, por fim, os tipos de componentes da grade ferroviária que podem ser empregados de acordo com o caso estudado. Com isso, espera-se que o produto final gerado possa ser uma ferramenta útil na etapa de concepção de novos projetos ferroviários, visto que apresentará de maneira clara e objetiva um conjunto de informações bastante abrangente e atualizado a respeito dos critérios técnicos e das opções de componentes disponíveis no mercado, fornecendo uma orientação inicial consistente ao profissional envolvido sobre os materiais que podem ser aplicados à via em estudo. / Over the last years, a continuous increase on demand for railroad heavy haul transport has been witnessed in Brazil, reflecting in bigger volume of projects for expansion or improvement of the existing lines in the country. With this current situation, it becomes essential that the professional involved with the elaboration of projects of the permanent way should have information brought up to date regarding the variety of components of the existing railroad materials in the market, so that the projects take care of fully to the necessities of the customer. Thus being, the present work has as main objective to search and to analyze the types of existing components in the market used in the composition of the railroad superstructure (rails, ties and fastenings), with main focus in that which can be applied to the heavy haul railways. First, from research in national and international bibliographical material, the main aspects related to the performance that must be considered in the process of evaluation of these components will be describes, having as base the design parameters of the way established previously in accordance with the requirements of the load operation, such as: position for axle, speed of operation, maximum slope, and others. After that, the types of rails, ties (wood ties, monoblock and bi-block concrete ties, steel ties and plastic ties) and fastenings (rigid and elastic) currently available in the market and its characteristics of performance and conditions of use will be presented, according to the information provided by the its respective manufacturers. All the reports showed in the two previous described stages will be analyzed and compared, so that is possible to highlight the interdependence relations that exist between the different types of components. At the end of the work, a flowchart model which gathers the input data about the heavy haul railroad, the performance guidelines that should be followed and the types of components of the railroad superstructure that can be used in accordance to the studied case, will be presented. With that, it is expected that the produced flowchart could be a useful tool in the stage of design of a new railroad, once it will present in a clear and objective way an embracing and up-to-date set of information regarding the performance criteria and the options of components available in the market, supplying a consistent initial orientation to the designer about the materials that could be applied to the railway.
|
3 |
On Heavy-Haul Wheel Damages using Vehicle Dynamics SimulationHossein Nia, Saeed January 2017 (has links)
Maintenance cost is one of the important issues in railway heavy-haul operations. In most of the cases, these costs are majorly referring to reprofiling and changing the wheels of the locomotives and the wagons. The main reason of the wheel damages is usually severe wear and/or surface initiated rolling contact fatigue (RCF).This work tries to enhance and improve the knowledge of the wheel wear and RCF prediction models using dynamic simulations. While most of the contents of this study can be generalised to other operational networks, this study is focused on the locomotives and wagons of the Swedish iron-ore company LKAB. The trains are operating on the approximately 500 km long IORE line from Luleå to Narvik in the north of Sweden and Norway respectively.Firstly, a literature survey of dynamic modelling of the wagons with various three-piece bogie types is presented. Then, with concentrating on the standard three-piece bogies, parameter studies are carried out to find out what the most important reasons of wheel damages are. Moreover, the long-term stability of wheel profiles of the IORE wagons is analysed. This is done by visualising the wear and RCF evolution on the wheel profiles over 150,000km of simulated running distance.Most of the calculations for the wagons are repeated for the locomotives. However, traction and braking are also considered in the simulation model and their effects on wheel damages are briefly studied. To improve the accuracy of the wheel damage analysis, a newly developed algorithm called FaStrip is used to solve the tangential contact problem instead of FASTSIM. The damage prediction model developed in the thesis is used to study the effects of increasing axle load, correcting the track gauge, limiting the electro-dynamic braking and using a harder wheel material on the wheel life. Furthermore, a new method is developed to predict the running distance between two consecutive reprofilings due to severe surface initiated fatigue. The method is based on shakedown analysis and laboratory tests.Most of the research works in wear calculation are limited to two approaches known as wear number and Archard methods. The correlation between these two methods is studied. The possibility of using the relation between the two methods for the wear calculation process is investigated mainly to reduce the calculation time for wheel profile optimisation models. / <p>QC 20171219</p>
|
4 |
Railway Tunnels Management System in South Africa – Concrete Structural ElementsThako, Luba Jean-Pierre 24 February 2020 (has links)
A reliable transportation network is key to economic development and social well-being of communities. Since 19th century, rail transport has provided the most efficient link between South African’s wealthy mineral heartland and the seaports. In developing this rail network, a considerable number of railway tunnels were built due to the topography of the coastal regions. These tunnels are ageing, their operational and environmental conditions are constantly changing. Thus, their management practice should be optimised to adequately respond to the needs of the organisations managing them and for them to continue providing a safe and sustainable service. Therefore, this study reviewed the current railway tunnels management practice in South Africa and proposed an approach to improve it, considering the existing structures management systems. Further, it focuses on the concrete structural elements and their related defects due to the harsh environments of these tunnels. Therefore, the Procedures to enhance tunnels management applied consisted in outlining the gaps uncovered in the current railway tunnels management practice in South Africa and enhance this practice considering the structures management systems reviewed. This is done by improving the components of each module and integrating them in the proposed railway tunnels management system in South Africa. First, it dealt with the inventory module, designed inventory forms for items and for concrete structural elements and their components to record, inspect and monitor. Second, it designed a Tunnel Inspection Programme that set the inspection intervals, the requirements for the inspection team members, the tools and techniques and procedures to apply. This programme specified also the method of evaluating the defects and the definition of the score and the relative score of the components of elements and the health of the tunnel. Third, it developed a Tunnel Monitoring System that targeted the most critical and vulnerable elements and set the techniques and tools to monitor them. Finally, it integrated all the modules in the system designed. As results, this research has proposed a computerised tunnel management system that enhances the current practice in South Africa. This arises from the scrutinised practice in light of the existing structures management systems reviewed. From the analysis of the existing inventory data on railway tunnels and on the heavy haul lines in South Africa, relevant information was obtained. Thus, an inventory module has been developed comprising tunnel inventory forms that classify the items to be recorded and inspected. This module also described the concrete structural elements and their specific components. A Tunnel Inspection Programme has been designed, specifying the frequency of inspections based on the condition of tunnels, their ages, and the unpredictability and the harshness of their environments. This programme has also promoted the relevant techniques to be applied to inspect concrete structural elements and the appropriate tools to be used. Additionally, the requirements for inspection team concerning the qualifications and experience of each member have been provided. This programme has also recommended the use of the current DER rating system, emphasising that the scope of this study refers to concrete structural elements that should all be rated and recorded. Additionally, it has designed a Tunnel Monitoring System specific to the most critical and vulnerable concrete structural elements of railway tunnels. This system includes a set of tunnel monitoring strategies, the setting up of the system and the sensory system. It finally integrated all these sub-systems into the main Railway Tunnel Management System in South Africa. In conclusion, this research proposes the integrated computerised railway tunnel management system for South Africa. It also set the “big picture” of the overall tunnel structures and the tunnels on the heavy haul lines currently managed by Transnet TFR in South Africa. Additionally, it sustains the current DER rating system and proposes its application to all the defects on the concrete structural elements, instead of the worst defect on the inspected element. As recommendations, the railway tunnels authority should adopt a monitoring system for each tunnel on the heavy haul lines. Also, the authority should make available information on all existing monitoring systems on railway tunnels and the most critical data collected. Moreover, the authority should make available the previous railway tunnels inspection files to be uploaded to the proposed system. Apart from this, we recommend a further comprehensive study to integrate the inspection of non-structural elements to the proposed system. Finally, we recommend to the management authority to organise a comprehensive study of the water leakage issues on railway tunnels to better understand and adequately respond to them.
|
5 |
An Investigation of the Iron-Ore Wheel Damages using Vehicle Dynamics SimulationHossein Nia, Saeed January 2014 (has links)
Maintenance cost is one of the important issues in railway heavy haul operations. For the iron-ore company LKAB, these costs are mainly associated with the reprofiling and changing of the wheels of the locomotives and wagons. The main reason for the wheel damages is usually surface initiated rolling contact fatigue (RCF) on the wheels.The present work tries to enhance and improve the knowledge of the vehicle-track interaction of the Swedish iron-ore freight wagons and locomotives used at Malmbanan. The study is divided into two parts. Firstly, it is tried to get into the roots of RCF using the simulation model of the iron ore wagon (Paper A). Secondly, the study is focused on predicting wear and RCF on the locomotive wheels also via a dynamic simulation model (Paper B).In the first paper, some key issues of the dynamic modelling of the wagons with three piece bogies are first discussed and then parameter studies are carried out to find the most important reasons of wheel damages. These parameter studies include track design geometry, track irregularities, wheel-rail friction level, cant deficiency and track stiffness. The results show a significant effect of the friction level on the amount of RCF risk.As the locomotive wheel life is much shorter than that of the wagons, LKAB has decided to change the locomotive wheel profile. Two final wheel profiles are proposed; however, one had to be approved for the field tests. In the second paper, the long term evolution of the two profiles is compared via wear simulation analysis. Also, the RCF evolution on the wheel profiles as a function of running distance is discussed. The process is first carried out for the current locomotive wheel profiles and the results are compared with the measurements. Good agreement is achieved. Finally, one of the proposed profiles is suggested for the field test because of the mild wear and RCF propagation. / <p>QC 20150210</p>
|
6 |
Truck transport emissions modelCouraud, Amelie 17 September 2007
In the past, transportation related economic analysis has considered agency related costs only. However, transportation managers are moving towards more holistic economic analysis including road user and environmental costs and benefits. In particular, transportation air pollution is causing increasing harm to health and the environment. Transport managers are now considering related emissions in transport economical analyses, and have established strategies to help meet Kyoto Protocol targets, which specified a fifteen percent reduction in Canada's emissions related to 1990 levels within 2008-2012.<p>The objectives of this research are to model heavy vehicle emissions using a emissions computer model which is able to assess various transport applications, and help improve holistic economic transport modeling. Two case studies were evaluated with the model developed.<p>Firstly, the environmental benefits of deploying weigh-in-motion systems at weigh stations to pre-sort heavy vehicles and reduce delays were assessed. The second case study evaluates alternative truck sizes and road upgrades within short heavy oilfield haul in Western Canada. <p>The model developed herein employed a deterministic framework from a sensitivity analysis across independent variables, which identified the most sensitive variables to primary field state conditions. The variables found to be significant included idling time for the weigh-in-motion case study, road stiffness and road grades for the short heavy haul oilfield case study.<p>According to this research, employing WIM at weigh stations would reduce annual Canadian transportation CO<sub>2</sub> emissions by nearly 228 kilo tonnes, or 1.04 percent of the Canadian Kyoto Protocol targets. Regarding direct fuel savings, WIM would save from 90 to 190 million litres of fuel annually, or between $59 and $190 million of direct operating costs.<p>Regarding the short heavy oil haul case study, increasing allowable heavy vehicle sizes while upgrading roads could decrease the annual emissions, the fuel consumption, and their associated costs by an average of 68 percent. Therefore, this could reduce each rural Saskatchewan municipality's annual CO<sub>2</sub> emissions from 13 to 26.7-kilo tonnes, which translates to 0.06 and 0.12 percent of the Canadian Kyoto Protocol targets or between $544,000 and $ 1.1 million annually. <p>Based on these results, the model demonstrates its functionality, and was successfully applied to two typical transportation field state applications. The model generated emissions savings results that appear to be realistic, in terms of potential Kyoto targets, as well as users cost reductions and fuel savings.
|
7 |
Truck transport emissions modelCouraud, Amelie 17 September 2007 (has links)
In the past, transportation related economic analysis has considered agency related costs only. However, transportation managers are moving towards more holistic economic analysis including road user and environmental costs and benefits. In particular, transportation air pollution is causing increasing harm to health and the environment. Transport managers are now considering related emissions in transport economical analyses, and have established strategies to help meet Kyoto Protocol targets, which specified a fifteen percent reduction in Canada's emissions related to 1990 levels within 2008-2012.<p>The objectives of this research are to model heavy vehicle emissions using a emissions computer model which is able to assess various transport applications, and help improve holistic economic transport modeling. Two case studies were evaluated with the model developed.<p>Firstly, the environmental benefits of deploying weigh-in-motion systems at weigh stations to pre-sort heavy vehicles and reduce delays were assessed. The second case study evaluates alternative truck sizes and road upgrades within short heavy oilfield haul in Western Canada. <p>The model developed herein employed a deterministic framework from a sensitivity analysis across independent variables, which identified the most sensitive variables to primary field state conditions. The variables found to be significant included idling time for the weigh-in-motion case study, road stiffness and road grades for the short heavy haul oilfield case study.<p>According to this research, employing WIM at weigh stations would reduce annual Canadian transportation CO<sub>2</sub> emissions by nearly 228 kilo tonnes, or 1.04 percent of the Canadian Kyoto Protocol targets. Regarding direct fuel savings, WIM would save from 90 to 190 million litres of fuel annually, or between $59 and $190 million of direct operating costs.<p>Regarding the short heavy oil haul case study, increasing allowable heavy vehicle sizes while upgrading roads could decrease the annual emissions, the fuel consumption, and their associated costs by an average of 68 percent. Therefore, this could reduce each rural Saskatchewan municipality's annual CO<sub>2</sub> emissions from 13 to 26.7-kilo tonnes, which translates to 0.06 and 0.12 percent of the Canadian Kyoto Protocol targets or between $544,000 and $ 1.1 million annually. <p>Based on these results, the model demonstrates its functionality, and was successfully applied to two typical transportation field state applications. The model generated emissions savings results that appear to be realistic, in terms of potential Kyoto targets, as well as users cost reductions and fuel savings.
|
8 |
Monitoring energy efficiency of heavy haul freight trains with energy meter data / Uppföljning av energieffektiviteten för tunga godståg med hjälp av elmätardataGeiberger, Philipp January 2021 (has links)
In this MSc thesis, it is investigated what parameters are relevant for describing energy consumption of heavy haul freight trains and how these can be used to develop key performance indicators (KPIs) for energy efficiency. The possible set of KPI is bounded by data available from energy meters used in electric IORE class locomotives hauling iron ore trains in northern Sweden. Furthermore, the analysis is only concerned with energy efficiency at the rolling stock level, excluding losses in the electric power supply network. Based on a literature study, parameters of interest describing driver, operations and rolling stock energy efficiency have been identified. By means of simulation, a parametric study is performed, simulating a 30 ton axle load iron ore train with 68 wagons. Train modelling input is obtained from technical documentation or estimated through measurements and statistical analysis. A multi-particle representation of the train is used to calculate gradient resistance for the simulation, which is also applied to determine the curve resistance. Results show that the motion resistance is simulated quite accurately, while the lack of a driver model in the simulation tool leads to overestimation of energy consumption. Taking this into account, the importance of the driver for energy efficiency can still clearly be showcased in the parametric study. Especially on long steep downhill sections, prioritising the electric brakes over mechanical brakes is demonstrated to have a huge influence on net energy consumption, as has the amount of coasting applied. With the same driver behaviour in all simulations, the savings in specific energy from increasing axle load to 32.5 tons is estimated. Moreover, a comparison of increased train length and axle load points towards higher savings for the latter. In the end, parametric study results are used to recommend a structure for a monitoring system of energy efficiency based on a set of KPIs. With a sufficiently high sampling rate of energy meter data, it is adequate for calculating driver related KPIs and some additional KPIs. More KPIs can be tracked with access to additional data, e.g. cargo load. / I detta examensarbete undersöks vilka parametrar som är relevanta för att beskriva energiförbrukning för tunga godståg och hur dessa kan nyttjas för att utveckla nyckeltal för energieffektivitet. Antalet möjliga nyckeltal avgränsas till sådana som kan beräknas med data från elmätare som används i elektriska littera IORE lok som drar tunga malmtåg i norra Sverige. Vidare så tar analysen endast hänsyn till energieffektivitet för rullande materiel, vilket utesluter förluster i elektriska kraftmatningsnätet. Baserad på en litteraturstudie har relevanta parametrar som beskriver förare, drift och rullande materiel identifierats. Med hjälp av simuleringar av ett malmtåg med 30 tons axellast och 68 vagnar så utförs en parameterstudie. Indata för tågmodelleringen erhålls från teknisk dokumentation respektive uppskattas genom mätningar och statistisk analys. En representation av tåget som flertalet partiklar tillämpas i simulering för att beräkna lutningsmotståndet. Dessutom används densamma för att ta fram kurvmotståndet. Resultaten visar att gångmotstånd simuleras ganska exakt, medan avsaknad av en förarmodell i simuleringsvertyget leder till överskattad energiförbrukning. Med hänsyn tagen till detta så kan betydelsen av föraren för energieffektivitet fortfarande påvisas mycket tydligt i parameterstudien. I synnerhet i långa branta nedförsbackar har prioritering av den elektriska bromsen framför den mekaniska bromsen mycket stor påverkan på nettoenergiförbrukningen, likaväl som hur mycket tåget frirullar. Med samma förarbeteende i samtliga simuleringar har besparingar i specifik energiförbrukning kunnat uppskattats för en ökning av axellasten till 32,5 ton. Dessutom pekar en jämförelse av ökad tåglängd och axellast mot att sistnämnda ger större besparingar. Slutligen så har resultaten från parameterstudien nyttjats för att rekommendera en struktur för ett uppföljningssystem av energieffektivitet baserad på en uppsättning av nyckeltal. Med tillräckligt hög samplingsfrekvens på data från elmätare är den adekvat för att beräkna vissa nyckeltal, framförallt relaterad till förare. Fler nyckeltal kan följas upp med mer tillgänglig data så som lastvikter.
|
9 |
[pt] APLICAÇÃO DE ALGORITMOS DE APRENDIZADO DE MÁQUINA PARA PREVER EFICIÊNCIA ENERGÉTICA BASEADO EM PARÂMETROS DE VIAGEM: ESTUDO DE CASO DE UMA FERROVIA DE TRANSPORTE DE CARGA / [en] APPLICATION OF MACHINE LEARNING ALGORITHMS TO PREDICT FUEL EFFICIENCY BASED ON TRIP PARAMETERS: A HEAVY HAUL RAILWAY CASE OF STUDYRODOLFO SPINELLI TEIXEIRA 21 December 2021 (has links)
[pt] O consumo de combustível em empresas do setor de transporte ferroviário
representa um dos maiores gastos operacionais e uma das maiores preocupações
em termos de emissões de poluentes. O alto consumo em combustíveis acarreta
também em uma alta representatividade na matriz de escopo de emissões (mais
de 90 por cento das emissões de ferrovias são provenientes do consumo de combustível
fóssil). Com o viés de se buscar uma constante melhora operacional, estudos
vêm sendo realizados com a finalidade de se propor novas ferramentas na
redução do consumo de combustível na operação de um trem de carga.
Nesse ramo, destaca-se o aperfeiçoamento dos parâmetros de condução de um
trem que são passíveis de calibração com o objetivo de reduzir o consumo
de combustível. Para chegar a esse fim, o presente trabalho implementa
dois modelos de aprendizado de máquina (machine learning) para prever a
eficiência energética de um trem de carga, são eles: floresta randômica e redes
neurais artificiais. A floresta randômica obteve o melhor desempenho entre
os modelos, apresentando uma acurácia de 91 por cento. Visando calcular quanto
cada parâmetro influencia no modelo de previsão, este trabalho também
utiliza técnica de efeitos acumulados locais em cada parâmetro em relação à
eficiência energética. Os resultados finais mostraram que, dentro dos quatro
parâmetros de calibração analisados, o indicador de tração por tonelada
transportada apresentou maior representatividade em termos de impacto
absoluto na eficiência energética de um trem de carga. / [en] Fuel consumption in companies in the rail transport sector represents
one of the largest operating expenses and one of the biggest concerns in terms
of pollutant emissions. The high fuel consumption also entails a high representation
in the emissions scope matrix (more than 90 percent of railroad emissions
come from fossil fuel consumption). Aiming to seek constant operational improvement,
numerous studies have been carried out proposing new tools to
reduce fuel consumption in the operation of a freight train. In this way, it is
important to highlight the improvement of train driving parameters that can
be calibrated to reduce fuel consumption. To accomplish this goal, the present
work implements two machine learning models to predict the energy efficiency
of a freight train: random forest and artificial neural networks. The random
forest achieves the best performance against the models, with an accuracy of
91 percent. To calculate how much each parameter influences the prediction model,
this work also uses the technique of accumulated local effects for each parameter related to energy efficiency. The final results show that, within the four analyzed calibration parameters, the traction per transported ton indicator
presented greater representation in terms of absolute impact on the energy
efficiency of a freight train.
|
Page generated in 0.0619 seconds