Academic literature on the topic 'Fleet-level evaluation'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Contents
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Fleet-level evaluation.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Fleet-level evaluation"
1
Schneider, Kellie, and C. Richard Cassady. "Evaluation and comparison of alternative fleet-level selective maintenance models." Reliability Engineering & System Safety 134 (February 2015): 178–87. http://dx.doi.org/10.1016/j.ress.2014.10.017.
Full text
2
Bitetto, Isabella, Loretta Malvarosa, Jörg Berkenhagen, Maria Teresa Spedicato, Evelina Sabatella, and Ralf Döring. "Reconciling the economic and biological fishery data gathered through the European Data Collection Framework: A new R-tool." PLOS ONE 17, no. 3 (March 31, 2022): e0264334. http://dx.doi.org/10.1371/journal.pone.0264334.
Full textAbstract:
Fishing fleets and targeted stocks are the basis for the design of multiannual management plans at European or Mediterranean levels. Management Strategy Evaluation and bioeconomic modeling need data at a specific level of resolution in terms of time, area and type of fishing activity for analyzing measures for management procedures using simulations. Within the Data Collection Framework, data are to be aggregated at different levels, e.g.: fleet segment and métier, the former linked to the predominant gear and the size of the vessel and the latter to the activity itself. Fishing costs are collected by fleet segment, effort and landings by fleet segment and métier. Bioeconomic modeling for management purposes requires data at the same resolution. The aim of this paper is to describe a methodology, implemented in SECFISH R package, to disaggregate variable cost data from the fleet segment to the métier level. The presented tool allows to determine the correlation between the variable costs of a vessel and its activities to estimate costs at the activity level (e.g. métiers). The tool is applied to selected Italian fleet segments characterized by a variety of métiers and high dynamicity.
3
Bauby, C. E., B. Charbonnier, P. Haik, S. Lacombe, J. Lonchampt, and E. Remy. "Asset Management Evaluation: A Pilot Case Study." Journal of Pressure Vessel Technology 129, no. 1 (April 24, 2006): 148–54. http://dx.doi.org/10.1115/1.2389032.
Full textAbstract:
The long term management of a production asset raises several major issues, among which rank the technical management of the plant, its economics, and the fleet level perspective one has to adopt. Decision makers are therefore faced with the need to define long term policies (up to the end of asset operation) that take into account multiple criteria including safety (which is paramount) and performance. In this paper we first remind the reader of the EDF three-level methodology for asset management. As introduced in PVP 2003 and PVP 2004, this methodology addresses the component/technical level (how to safely operate daily and invest for the future), the plant level (how to translate technical decisions into plant-wide consequences including economic performance), and the fleet level (how to manage a large number of similar assets). We then focus on the software tool that implements this methodology in order to allow decision makers to define, evaluate, and analyze long term plant operation and maintenance policies. Lastly we show how the methodology and the software tool were used on a pilot case study. The technical and economic results obtained at the plant level are described as well as the conclusions one can draw from them in order to help decision makers evaluate and analyze long term asset management strategies.
4
Barjoveanu, George, Florenta Dinita, and Carmen Teodosiu. "Aging Passenger Car Fleet Structure, Dynamics, and Environmental Performance Evaluation at the Regional Level by Life Cycle Assessment." Sustainability 14, no. 14 (July 11, 2022): 8443. http://dx.doi.org/10.3390/su14148443.
Full textAbstract:
The need to limit climate change and to improve air quality clearly is a driver for technology and policy changes in the transport sector. This study investigates how this technology shift at the European level ages personal car fleets at the regional level in Romania through second-hand imports. It also asks what how the situation will evolve in terms of environmental impacts. The study presents an in-depth assessment of the environmental performance and evolution of the passenger car fleet in Iasi County (Romania). The analysis is based on the car fleet structure and dynamic statistics, and uses the Copert 5.5 model to estimate the specific use-phase emissions, which subsequently are used as input data into an LCA analysis. The study considers three scenarios regarding fleet evolution and environmental performance, and focuses solely on the use phase of passenger cars. It models exhaust emissions in various driving situations (rural, urban, hot-cold operation, and peak-offpeak traffic values) and considers the current environmental performance classes and age of vehicles in the fleet. The results show that by considering these vehicle performance aspects, impacts are better represented. The no-change scenario would lead to a 2.5 times increase of global warming impacts by 2035 as compared to 2020, while by limiting the import of used cars and increasing the share of electric and hybrid vehicles would lead to mitigating these impacts.
5
Ildarkhanov, Radik. "Quality and Competitive Ability Evaluation Method Development Mobile Fleet." Periodica Polytechnica Transportation Engineering 47, no. 1 (February 16, 2018): 44–50. http://dx.doi.org/10.3311/pptr.10547.
Full textAbstract:
The purpose of the article was to develop the evaluation method of mobile fleet. It is found that to evaluate production quality criterion of "integrated quality coefficient" is needed. Quality coefficient can be defined analytically. The author proposes the special formula to do this. Usage of analytical formula enables to conclude where one model excels the other, and where it is inferior. The formula validity check was performed. The research activities pursued by author enable to conclude that designed formula gives opportunity to evaluate product quality level objectively. Thus, competitive ability evaluation method resolves itself into choosing estimated product analogues and defining product quality coefficient using analytical method. Subsequently, prices and analogous product quality coordinates are put on two-coordinate field and dependency diagram of product price on its quality is built via least square method. Such method enables to evaluate quality and competitive ability of mobile fleet and make right choice.
6
Schroer, Karsten, Wolfgang Ketter, Thomas Y. Lee, Alok Gupta, and Micha Kahlen. "Data-Driven Competitor-Aware Positioning in On-Demand Vehicle Rental Networks." Transportation Science 56, no. 1 (January 2022): 182–200. http://dx.doi.org/10.1287/trsc.2021.1097.
Full textAbstract:
We study a novel operational problem that considers vehicle positioning in on-demand rental networks, such as car sharing in the wider context of a competitive market in which users select vehicles based on access. Existing approaches consider networks in isolation; our competitor-aware model takes supply situations of competing networks into account. We combine online machine learning to predict market-level demand and supply with dynamic mixed integer nonlinear programming. For evaluation, we use discrete event simulation based on real-world data from Car2Go and DriveNow. Our model outperforms conventional models that consider the fleet in isolation by a factor of two in terms of profit improvements. In the case we study, the highest theoretical profit improvements of 7.5% are achieved with a dynamic model. Operators of on-demand rental networks can use our model under existing market conditions to build a profitable competitive advantage by optimizing access for consumers without the need for fleet expansion. Model effectiveness increases further in realistic scenarios of fleet expansion and demand growth. Our model accommodates rising demand, defends against competitors’ fleet expansion, and enhances the profitability of own fleet expansions.
7
Silva, Carlos A., and Carlos Guedes Soares. "Sizing a fleet of containerships for a given market." PROMET - Traffic&Transportation 26, no. 4 (August 20, 2014): 333–44. http://dx.doi.org/10.7307/ptt.v26i4.1387.
Full textAbstract:
The potential growth found inthe short sea shipping sector motivated the development of a methodology usedas a decision support tool in which both the parameters regarding the demand ofmarkets and the characteristics of the fleet may be tested for its evaluation.It is also possible to determine the fleet deployment, establishing its routesand scales in the ports for a particular scenario. The considered methodologymay be divided in two parts, being the first one related with the generation ofall feasible routes, alongside all the parameters specific to each route foreach vessel class. The second part is the introduction of a linear programmingmodel that maximizes the shipping operation’s total profit, according a givenset of restrictions. The models were structured according to three main criteria:the evaluation of the fleet for each vessel’s class; the optimal route for eachvessel and the frequency in each port. To provide the methodology’s validation,the developed models shall be submitted to a fictitious operational scenario,considering three different situations: the fleet’s normal operation; aparametric variation of required demand for the same fleet composition; anevaluation of several fleet compositions for the same demand level.
8
Silberhorn, Daniel, Katrin Dahlmann, Alexander Görtz, Florian Linke, Jan Zanger, Bastian Rauch, Torsten Methling, Corina Janzer, and Johannes Hartmann. "Climate Impact Reduction Potentials of Synthetic Kerosene and Green Hydrogen Powered Mid-Range Aircraft Concepts." Applied Sciences 12, no. 12 (June 11, 2022): 5950. http://dx.doi.org/10.3390/app12125950.
Full textAbstract:
One of aviation’s major challenges for the upcoming decades is the reduction in its climate impact. As synthetic kerosene and green hydrogen are two promising candidates, their potentials in decreasing the climate impact is investigated for the mid-range segment. Evolutionary advancements for 2040 are applied, first with an conventional and second with an advanced low-NOx and low-soot combustion chamber. Experts and methods from all relevant disciplines are involved, starting from combustion, turbofan engine, overall aircraft design, fleet level, and climate impact assessment, allowing a sophisticated and holistic evaluation. The main takeaway is that both energy carriers have the potential to strongly reduce the fleet level climate impact by more than 75% compared with the reference. Applying a flight-level constraint of 290 and a cruise Mach number of 0.75, causing 5% higher average Direct Operating Costs (DOC), the reduction is even more than 85%. The main levers to achieve this are the advanced combustion chamber, an efficient contrail avoidance strategy, in this case a pure flight-level constraint, and the use of CO2 neutral energy carrier, in a descending priority order. Although vehicle efficiency gains only lead to rather low impact reduction, they are very important to compensate the increased costs of synthetic fuels or green hydrogen.
9
Quintili, Alessio, and Beatrice Castellani. "The Energy and Carbon Footprint of an Urban Waste Collection Fleet: A Case Study in Central Italy." Recycling 5, no. 4 (October 7, 2020): 25. http://dx.doi.org/10.3390/recycling5040025.
Full textAbstract:
Municipal solid waste collection and transport are functional activities in waste management, with a significant energy and carbon footprint and a significant effect on the urban environment. An issue related to municipal solid waste collection and transport is their regional and municipal implementation, affected by sorting and recycling strategies at local level. An efficient collection is necessary to optimize the whole recycling process. The present paper shows the results of an energy, environmental, and economic evaluation of a case study, analyzing the fleet used for municipal solid waste collection and transport in 10 municipalities in Central Italy. The current scenario was compared with alternative scenarios on the basis of some parameters for performance evaluation: vehicles’ energy consumption, carbon footprint, routes, and costs. Results show that for passenger cars, the alternative scenario based on an entire fleet of dual compressed natural gas (CNG) vehicles led to a reduction of the CO2 emissions (−2675 kgCO2eq) in the analyzed period (January–August 2019) and a reduction of the energy consumption (−1.96 MJ km−1). An entire fleet of CNG vehicles led to an increase of CO2 emissions: +0.02 kgCO2eqkgwaste−1 (+110%) for compactors (35–75 q) and +0.09 kgCO2eqkgwaste−1 (+377%) for compactors (80–180 q). Moreover, both categories report a higher fuel consumption and specific energy consumption. For waste transport high-capacity vehicles, we propose the installation of a Stop-Start System, which leads to environmental and energy benefits (a saving of 38,332 kgCO2eq and 8.8 × 10−7 MJ km−1kgwaste−1). On three-wheeler vehicles, the installation of the Stop-Start System is completely disadvantageous.
10
Parsa, Mahdi, Timothy J. Emery, Ashley J. Williams, and Simon Nicol. "An empirical Bayesian approach for estimating fleet- and vessel-level bycatch rates in fisheries with effort heterogeneity and limited data: a prospective tool for measuring bycatch mitigation performance." ICES Journal of Marine Science 77, no. 3 (February 27, 2020): 921–29. http://dx.doi.org/10.1093/icesjms/fsaa020.
Full textAbstract:
Abstract Minimizing fishing-induced mortality on bycatch and endangered, threatened or protected species is a necessity for fisheries managers. Estimating individual vessel bycatch rates by dividing the amount of bycatch by effort (nominal rate) can be biased, as it does not consider effort heterogeneity within the fleet and ignores prior knowledge of fleet bycatch rates. We develop an empirical Bayesian approach for estimating individual vessel and fleet bycatch rates that: (i) considers effort heterogeneity among vessels and; (ii) pools data from similar vessels for more accurate estimation. The proposed standardized bycatch rate of a vessel is, therefore, the weighted average of the pool rate and nominal rate of the vessel; where the weights are functions of the vessel’s fishing effort and a constant estimated from the model. We apply this inference method to the estimation of seabird bycatch rates in the component of the Australian Eastern Tuna and Billfish Fishery targeting yellowfin tuna. We illustrate the capability of the method for providing fishery managers with insights on fleet-wide bycatch mitigation performance and the identification of outperforming and underperforming vessels. This method can also be used by fishery managers to develop fleet-wide performance measures or quantitative evaluation standards.
Conference papers on the topic "Fleet-level evaluation"
1
Doering, Robert, and Frank Thielecke. "An Evaluation of the Potential of Local Electric Power Packages on Aircraft Fleet Level." In AIAA Aviation 2019 Forum. Reston, Virginia: American Institute of Aeronautics and Astronautics, 2019. http://dx.doi.org/10.2514/6.2019-2804.
Full text
2
Bauby, Catherine E., Vale´ry E. Just, and Caroline Garreau. "Asset Management Evaluation Methods: The EDF Perspective." In ASME 2003 Pressure Vessels and Piping Conference. ASMEDC, 2003. http://dx.doi.org/10.1115/pvp2003-2155.
Full textAbstract:
The long term management of a production asset raises several major issues, among which rank the technical management of the plant, its economics and the fleet level perspective one has to adopt. Decision makers are therefore faced with the need to define long term policies (until the end of the life of the asset) which take into account multiple criteria including safety (which is paramount) and performance. In this paper we describe the French context where EDF (Electricite´ de France) is both Plant Owner and Operator of a fleet of 58 PWRs. We introduce a three-level methodology for asset management: the component / technical level (how to safely operate daily and invest for the future), the plant level (how to translate technical decisions into plant-wide consequences including economic performance) and the fleet level (how to manage a large number of similar assets). We then focus on the theoretical and practical links one can draw between the component level and the plant level. We describe several plant-wide indicators that are used to assess the value of the asset and we show how they can be inferred from the component-level technical and economic assessment (long-term equipment reliability, maintenance strategies, ...) by « rolling up » component level plans into a plant-wide decision process while taking into account the various sources of uncertainty associated with this assessment. We finally exemplify how this process could be applied to the life management of nuclear assets. To conclude, it appears asset management can be a major means for assessing and enhancing the long term value of a production unit while meeting everyday constraints.
3
Bauby, C. E., B. Charbonnier, P. Haik, S. Lacombe, J. Lonchampt, and E. Remy. "Asset Management Evaluation: A Pilot Case Study." In ASME 2005 Pressure Vessels and Piping Conference. ASMEDC, 2005. http://dx.doi.org/10.1115/pvp2005-71598.
Full textAbstract:
The long term management of a production asset raises several major issues among which rank the technical management of the plant, its economics and the fleet level perspective one has to adopt. Decision makers are therefore faced with the need to define long term policies (up to the end of asset operation) which take into account multiple criteria including safety (which is paramount) and performance. In this paper we first remind the reader of the EDF three-level methodology for asset management. As introduced in PVP 2003 and PVP 2004, this methodology addresses the component/technical level (how to safely operate daily and invest for the future), the plant level (how to translate technical decisions into plant-wide consequences including economic performance) and the fleet level (how to manage a large number of similar assets). We then focus on the software tool that implements this methodology in order to allow decision makers to define, evaluate and analyze long term plant operation and maintenance policies. Lastly we show how the methodology and the software tool were used on a pilot case study. The technical and economic results obtained at the plant level are described as well as the conclusions one can draw from them in order to help decision makers evaluate and analyze long term asset management strategies.
4
Bauby, Catherine E., Philippe Hai¨k, Emmanuel Remy, and Benoiˆt Ricard. "Knowledge Modeling for Asset Management Evaluation." In ASME/JSME 2004 Pressure Vessels and Piping Conference. ASMEDC, 2004. http://dx.doi.org/10.1115/pvp2004-2981.
Full textAbstract:
The long-term management of a production asset raises several major issues among which rank the technical management of the plant, its economics and the fleet level perspective one has to adopt. Decision-makers are therefore faced with the need to define long term policies (up to the end of asset operation), which take into account multiple criteria including safety (which is paramount) and performance. In this paper we remind the reader of the EDF three-level methodology for asset management. As introduced in PVP 2003, this methodology provides decision-makers with indicators to evaluate the status of a plant. The methodology addresses the component/technical level (how to safely operate daily and invest for the future), the plant level (how to translate technical decisions into plant-wide consequences including economic performance) and the fleet level (how to manage a large number of similar assets). Identifying what might occur to ageing plant components, how operations or maintenance decisions might influence these occurrences and what the consequences of these decisions and events might have on plant operation, is definitely an expert task. In order to gather, preserve, share, maintain and exploit this expert knowledge, we therefore relied on a “knowledge modeling” activity. This activity is used to support the asset management evaluation methodology. We detail the knowledge model — an entity/relation expert description of the plant life-management domain — on which our three-level methodology relies. Lastly, we focus on the software tool that implements this model in order to allow decision-makers to define, analyze and evaluate long-term plant operation and maintenance policies.
5
Hai¨k, P., C. Bauby, J. Lonchampt, and E. Remy. "Asset Management Evaluation: Extended Pilot Case Studies." In ASME 2007 Pressure Vessels and Piping Conference. ASMEDC, 2007. http://dx.doi.org/10.1115/pvp2007-26354.
Full textAbstract:
The long term management of a production asset raises several major issues among which rank the technical management of the plant, its economics and the fleet level perspective one has to adopt. Decision makers are therefore faced with the need to define long term policies (up to the end of asset operation) which take into account multiple criteria including safety (which is paramount) and performance. In this paper we first remind the reader of the EDF three-level methodology for asset management. As introduced in PVP 03 [1] and PVP 04 [2], this methodology addresses the component/technical level (how to safely operate daily and invest for the future), the plant level (how to translate technical decisions into plant-wide consequences including economic performance) and the fleet level (how to manage a large number of similar assets). We then focus on the software tools — introduced in PVP 04 [2] and PVP 05 [4] — that implement this methodology in order to allow decision makers to define, evaluate and analyze long term plant operation and maintenance policies. Lastly we show how the methodology and the software tool were used, in 2006, on two pilot case studies. Examples of technical and economic results obtained at the plant level are described as well as the conclusions one can draw from them in order to help decision makers evaluate and analyze long term asset management strategies or compare different plants. We also analyze the added value of probabilistic evaluations and of our “rolling-up” process that allows to take into account interactions existing between the components of the plant. Finally, we introduce some of the possible uses of our methodology and tools.
6
Bernardo, Jose Enrique, Emmanuel Lacouture, Michelle Kirby, and Dimitri N. Mavris. "Application of Mixture Design of Experiments for Dynamic Fleet-Level Evaluation of Multi-Objective Environmental Technology Trade-offs." In AIAA/3AF Aircraft Noise and Emissions Reduction Symposium. Reston, Virginia: American Institute of Aeronautics and Astronautics, 2014. http://dx.doi.org/10.2514/6.2014-2734.
Full text
7
Hai¨k, P., S. Parfouru, K. Fessart, J. Lonchampt, and E. Remy. "“Adaptative” User Interface as a Support for Evaluation Analysis in the Context of Asset Management." In ASME 2008 Pressure Vessels and Piping Conference. ASMEDC, 2008. http://dx.doi.org/10.1115/pvp2008-61505.
Full textAbstract:
The long term management of a production asset raises several major issues among which rank the technical management of the plant, its economics and the fleet level perspective one has to adopt. Decision makers are therefore faced with the need to define long term policies (up to the end of asset operation) which take into account multiple criteria including safety (which is paramount) and performance. In this context, EDF “PWR Durability I & II” research projects have consecutively been launched, since 2001, at EDF – Research & Development in order to develop methods and tools for EDF fleet. The aim of this paper is: • to summarize and analyze the research work that has been performed by EDF – R&D in the field of decision making for nuclear power plant maintenance and operation during the past seven year; • to highlight the strong and weak points of the developed methodology and tools and to identify the research work needed in order to ensure their use by EDF decision makers; • to introduce and illustrate our last development based on the use of an “adaptative” man/machine user interface in order to allows technical/strategic experts and decision makers to consult the useful pieces of knowledge in a context dependent way and, thus, facilitate the validation of the knowledge-base content and the analysis of the processed results. As a result, in this paper, we first remind the reader of the EDF overall methodology for asset management and its adaptations to plant-level life cycle management and to fleet-level component major replacement or capital investment management. We then focus on the three software tools that implement this methodology in order to allow decision makers, in several different contexts to define, evaluate and analyze long term plant operation and maintenance policies, major component replacement policies and capital investment strategies. We also show how the methodology and the software tools were used, from 2003 to 2007, on several pilot case studies. Examples of technical and economic results obtained for plant level pilot case study is quickly described as well as the kinds of conclusions one can draw from them in order to help decision makers evaluate and analyze long term asset management strategies or compare different plants. We then present the opinion of EDF’s decision makers about the developedmethodology and tools — and their use — and our understanding of their feedback. Lastly, we illustrate, using examples of technical and economic knowledge, data and results obtained from our previous pilot case studies, how the concept of an “adaptative” man/machine user interface could be used in order to facilitate the mastering of the methodology and tools’ complexity and to support decision makers’ evaluation and analysis of long term asset management strategies.
8
Thompson, Bruce D., and Ben Wainscott. "Systematic Evaluation of US Navy LM2500 Gas Turbine Condition." In ASME Turbo Expo 2000: Power for Land, Sea, and Air. American Society of Mechanical Engineers, 2000. http://dx.doi.org/10.1115/2000-gt-0667.
Full textAbstract:
From an operational availability stand point, the US Navy is interested in the short term reliability of its ship based LM2500 gas turbine engines. That is the likelihood that an engine will operate successfully through a six-month deployment (usually 1500 to 2000 operational hours). From a maintenance and cost of ownership standpoint both the short term and long term reliability are of concern. Long term reliability is a measure in time (in operating hours) between engine removals. To address these requirements US Navy Fleet support maintenance activities employ a system of tests and evaluations to determine the likelihood that an LM2500 will meet its short and long-term goals. The lowest level inspection is the pre deployment inspection, which attempts to identify primarily mechanical faults with the engine. Gas Turbine Bulletin inspections are used to determine if predefined wear out modes exists. Performance evaluations can be performed which determine the ability of the LM2500 and its control system to meet expected power requirements. Lube oil system data can be analyzed to determine if excessive leakage or excessive scavenge temperatures exist. Engine vibration characteristics can be reviewed to identify the source of both synchronous and non-synchronous vibration and determine if corrective measures need to be taken. This paper will discuss how the lowest level inspections feed the more sophisticated analysis and how these inspections and evaluations work to provide a systematic method of insuring both short and long term LM2500 reliability.
9
Isnadi, Biramarta, Luong Ann Lee, Sok Mooi Ng, Ave Suhendra Suhaili, Quailid Rezza M Nasir, Hanisah Sham, Kathy Ping Puloh, et al. "A Hybrid Topside Structural Approach to the Management of Aging Fleet." In International Petroleum Technology Conference. IPTC, 2021. http://dx.doi.org/10.2523/iptc-21174-ms.
Full textAbstract:
Abstract The objective of this paper is to demonstrate the best practices of Topside Structural Integrity Management for an aging fleet of more than 200 platforms with about 60% of which has exceeded the design life. PETRONAS as the operator, has established a Topside Structural Integrity Management (SIM) strategy to demonstrate fitness of the offshore topside structures through a hybrid philosophy of time-based inspection with risk-based maintenance, which is in compliance to API RP2SIM (2014) inspection requirements. This paper shares the data management, methodology, challenges and value creation of this strategy. The SIM process adopted in this work is in compliance with industry standards API RP2SIM, focusing on Data-Evaluation-Strategy-Program processes. The operator HSE Risk Matrix is adopted in risk ranking of the topside structures. The main elements considered in developing the risk ranking of the topside structures are the design and assessment compliance, inspection compliance and maintenance compliance. Effective methodology to register asset and inspection data capture was developed to expedite the readiness of Topside SIM for a large aging fleet. The Topside SIM is being codified in the operator web-based tool, Structural Integrity Compliance System (SICS). Identifying major hazards for topside structures were primarily achieved via data trending post implementation of Topside SIM. It was then concluded that metal loss as the major threat. Further study on effect of metal loss provides a strong basis to move from time-based maintenance towards risk-based maintenance. Risk ranking of the assets allow the operator to prioritize resources while managing the risk within ALARP level. Current technologies such as drone and mobile inspection tools are deployed to expedite inspection findings and reporting processes. The data from the mobile inspection tool is directly fed into the web based SICS to allow reclassification of asset risk and anomalies management.
10
Wang, Jiawei, and Lijun Sun. "Reducing Bus Bunching with Asynchronous Multi-Agent Reinforcement Learning." In Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}. California: International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/ijcai.2021/60.
Full textAbstract:
The bus system is a critical component of sustainable urban transportation. However, due to the significant uncertainties in passenger demand and traffic conditions, bus operation is unstable in nature and bus bunching has become a common phenomenon that undermines the reliability and efficiency of bus services. Despite recent advances in multi-agent reinforcement learning (MARL) on traffic control, little research has focused on bus fleet control due to the tricky asynchronous characteristic---control actions only happen when a bus arrives at a bus stop and thus agents do not act simultaneously. In this study, we formulate route-level bus fleet control as an asynchronous multi-agent reinforcement learning (ASMR) problem and extend the classical actor-critic architecture to handle the asynchronous issue. Specifically, we design a novel critic network to effectively approximate the marginal contribution for other agents, in which graph attention neural network is used to conduct inductive learning for policy evaluation. The critic structure also helps the ego agent optimize its policy more efficiently. We evaluate the proposed framework on real-world bus services and actual passenger demand derived from smart card data. Our results show that the proposed model outperforms both traditional headway-based control methods and existing MARL methods.
Reports on the topic "Fleet-level evaluation"
1
LaClair, Tim J., and Amy Marie Moore. Development of Fleet Energy Savings Evaluation Tools for Smart Mobility: Smart Vehicle Energy Technology (SVET) Model for Passenger Fleets and Freight Fleet Level Energy Estimation Tool (FFLEET) for Freight Fleets. Office of Scientific and Technical Information (OSTI), March 2018. http://dx.doi.org/10.2172/1471856.
Full text