Fleet Owners Research Articles

Unfolding the state of the adoption of connected autonomous trucks by the commercial fleet owner industry

This paper attempts to address two particular questions about the adoption of connected autonomous trucks (CATs) by trucking companies: (i) what are the factors affecting the decisions to adopt different levels of autonomous trucks? and (ii) how many with what sizes are the groups of CAT adopters? We employ choice modeling and latent-class cluster analysis (LCCA) to address the two questions. US companies working in the freight industry are contacted and 400 full responses are collected. The data is analyzed descriptively and detailed results of modeling efforts are presented and discussed. Focusing on the first question, companies view automation Level 2 not significantly different than Regular trucks. We observe that small-sized companies are more likely to adopt the higher levels of automation, and large companies may be willing to adopt only when the technology become more affordable. Cargo type is found to have some impact on the adoption: for example, companies carrying foodstuff are more likely to adopt higher levels of automation. Having promoters of new technologies in the company increases the likelihood of adoption and the impact is more visible for the higher levels of automation. Turning to the second question, our results indicate that there could be five categories of CAT adopters which is consistent with what the Theory of diffusion of Innovations (DOI) suggests. However, the sizes of the Innovators and Early Majority classes would respectively be four and two times of DOI’s general suggestion. Overall, it is speculated that the CAT adopter distribution may not be a bell-shaped curve but more of a right-skewed figure. This can be contributed to explicit financial benefits of CATs which could incentivize companies to adopt earlier.

Brinell Fault Injection to Enable Development of a Low-Cost Wheel Bearing Fault Monitoring System for Automobiles

Although bearing condition monitoring and fault diagnosis is a widely studied and mature field, applications to automotive wheel bearings have received little attention. This is likely due to the lack of business case, as the vehicle’s four wheel bearings are typically designed to last the vehicle life with low failure rates. Rapid advancements in battery technology are expected to open the door for EVs with million-mile lifespans, exceeding the reliable life of existing low-cost wheel bearing designs. Vehicle designers and fleet owners must choose between paying a higher price for bearings with a longer life or replacing wheel bearings periodically throughout the vehicle life. The latter strategy can be implemented most effectively with the implementation of a low-cost fault detection system on the vehicle.
 
 To develop such a system, data from systems with healthy and faulty wheel bearings is needed. This paper discusses the options for generating this data, such as simulation, bench tests, and vehicle-level tests. The challenges and limitations of each are explored, and the specific challenges of developing an approach for a wheel bearing fault detection system are discussed in detail. A method for injecting Brinell Dent failures is developed, and the results of injecting a total of 40 faulty wheel bearings are presented. Metrics of measuring and summarizing the ground-truth health of a wheel bearing using vibration signals recorded on a test bench are explored. These wheel bearings are used to collect preliminary vehicle data, and some initial analysis is shared highlighting the differences between healthy and faulty wheel bearings, setting the stage for future work to develop a low-cost wheel bearing fault detection system.

Selection of bus chassis for large fleet operators in India: An AHP-TOPSIS approach

Public transport by bus fleet is the most sought-after mode of transportation in India, which is owned and operated by government bodies as well as private players. In general, these operators purchase chassis from different OEMs (Original Equipment Manufacturer) and build bodies according to the statutory norms and conditions prevailing at the place of usage. The fleet operators have their selection criteria for chassis. However, the chassis supplied by distinct OEMs satisfy these selection criteria differently. Hence, the selection of appropriate chassis becomes a complex decision-making problem for fleet organizations. The selection criteria of bus chassis are developed through literature as well as interactions with fleet operators and chassis OEMs. A framework for the selection of the best chassis among alternatives is developed based on a hybrid methodology of AHP (Analytic Hierarchy Process) and TOPSIS (Technique for order preference by similarity to ideal solution). The hybrid methodology will rank various OEM chassis, which will help the bus fleet owners to choose the right chassis that satisfy their requirements in the most optimum manner.

Toward a rational and ethical sociotechnical system of autonomous vehicles: A novel application of multi-criteria decision analysis.

The impacts of autonomous vehicles (AV) are widely anticipated to be socially, economically, and ethically significant. A reliable assessment of the harms and benefits of their large-scale deployment requires a multi-disciplinary approach. To that end, we employed Multi-Criteria Decision Analysis to make such an assessment. We obtained opinions from 19 disciplinary experts to assess the significance of 13 potential harms and eight potential benefits that might arise under four deployments schemes. Specifically, we considered: (1) the status quo, i.e., no AVs are deployed; (2) unfettered assimilation, i.e., no regulatory control would be exercised and commercial entities would “push” the development and deployment; (3) regulated introduction, i.e., regulatory control would be applied and either private individuals or commercial fleet operators could own the AVs; and (4) fleets only, i.e., regulatory control would be applied and only commercial fleet operators could own the AVs. Our results suggest that two of these scenarios, (3) and (4), namely regulated privately-owned introduction or fleet ownership or autonomous vehicles would be less likely to cause harm than either the status quo or the unfettered options.

Transportation-Mission-Based Optimization of Heterogeneous Heavy-Vehicle Fleet Including Electrified Propulsion

Commercial-vehicle manufacturers design vehicles to operate over a wide range of transportation tasks and driving cycles. However, certain possibilities of reducing emissions, manufacturing and operational costs from end vehicles are neglected if the target range of transportation tasks is narrow and known in advance, especially in case of electrified propulsion. Apart from real-time energy optimization, vehicle hardware can be meticulously tailored to best fit a known transportation task. As proposed in this study, a heterogeneous fleet of heavy-vehicles can be designed in a more cost- and energy-efficient manner, if the coupling between vehicle hardware, transportation mission, and infrastructure is considered during initial conceptual-design stages. To this end, a rather large optimization problem was defined and solved to minimize the total cost of fleet ownership in an integrated manner for a real-world case study. In the said case-study, design variables of optimization problem included mission, recharging infrastructure, loading–unloading scheme, number of vehicles of each type, number of trips, vehicle-loading capacity, selection between conventional, fully electric, and hybrid powertrains, size of internal-combustion engines and electric motors, number of axles being powered, and type and size of battery packs. This study demonstrated that by means of integrated fleet customization, battery-electric heavy-vehicles could strongly compete against their conventional combustion-powered counterparts. The primary focus has been put on optimizing vehicle propulsion, transport mission, infrastructure and fleet size rather than routing.

Pollution From Commercial Vessels Machinery Space Bilges

Abstract Over the past decade, the United States Coast Guard Sector Southeastern New England (SENE) along with state and local partner agencies in the New Bedford, Massachusetts area have been attempting to understand commercial vessel's inability to comply with the Code of Federal Regulations (CFR) regarding oily bilge waste and proper disposal options. The regulations have been in effect since 1983 requiring oceangoing vessels of less than 400 gross tons to have the capacity to retain all oily mixtures onboard or install an approved oily water separator (OWS) equipment for processing oily mixtures from bilges. New Bedford, MA is the homeport to over 400 commercial fishing vessels within a 2 square mile port area. The circumstances in New Bedford are considered to be representative of most ports for vessels less than 400 gross tons nationwide. Sector SENE has used various mechanisms to educate the local commercial vessel fleet owners and operators. The education includes the issuance of Marine Safety Information Bulletin 03-18 by Coast Guard Headquarters (United States Coast Guard, 2018). In 2012, the Partner Agency - Massachusetts Department of Environmental Protection created and funded the Bilge-Pump-Out Program. This voluntary program provides commercial vessels with free oily bilge waste disposal services. Previously, there was no established “permanent” solution to the pervasive oily discharge problem and bad practice of illegally disposing of oily waste directly from commercial vessel bilges overboard into U.S. navigable waterways. In conjunction with local authorities having jurisdiction, Sector SENE began a focused pollution prevention and enforcement effort. Several pollution cases were forwarded to the Department of Justice (DOJ) and fines of over 1 million dollars have been issued for the illegal practices. The culmination of educational outreach, surge operations and coordinated interagency efforts have led to the initial levels of compliance.

Examining the determinants of freight transport emissions using a fleet segmentation approach

Concerns over transport energy consumption and greenhouse gas emissions have lately prompted significant attention towards vehicle ownership patterns and the distributional implications of climate mitigation policies. This paper contributes to freight transport literature by examining how establishments can be meaningfully grouped using their fleet ownership pattern (size and composition) and how these segments vary in their freight travel pattern and CO2 emission levels. The analysis performed using an establishment-based freight survey dataset from Kerala, a coastal state in India, revealed five latent classes of fleet ownership. The determinants of freight transport emissions and the gross emitters in fleet segments are presented subsequently by analyzing how the establishment-level characteristics (employment, business age, industry sector, value density, and relative location) explain the variation in CO2 emissions. The study findings offer insights for designing effective carbon policy instruments and incentive schemes to regulate the establishment-level freight travel pattern and control transport emissions.

Feasibility Study of Medium- and Heavy-Duty Compressed Renewable/Natural Gas Vehicles in Canada

Abstract Concerns about environmental degradation and finite natural resources necessitate cleaner sources of energy for use in the transportation sector. In Canada, natural gas (NG) is currently being appraised as a potential alternative fuel for use in vehicles for both medium- and heavy-duty use due to its relatively lower costs compared with that of conventional fuels. The idea of compressed natural gas vehicles (CNGVs) is being mooted as inexpensive for fleet owners and especially because it will potentially significantly reduce harmful emissions into the environment. A short feasibility study was conducted to ascertain the potential for reduced emissions and savings opportunities presented by CNGVs and renewable NGVs (RNGVs) in both medium- and heavy-duty vehicles. The study which is discussed in the present paper was carried out on long-haul trucking and refuse trucks, respectively. Emphasis was laid on individual vehicle operating economics and emissions reduction, and the identification of practical considerations for both the individual application and CNGVs/RNGVs as a whole. A financial analysis of the annual cost savings that is achievable when an individual diesel vehicle is replaced with a CNG vehicle was also presented. This paper drew substantial references from published case studies for relevant data on maintenance costs, fuel economy, range, and annual distance traveled. It relied on a summary report from Argonne National Laboratory’s GREET (Greenhouse Gases, Regulated Emissions, and Energy Use in Transportation) (Argonne National Laboratory, 2018, Argonne GREET Model, US Department of Energy. https://greet.es.anl.gov/. Accessed October 5, 2020) for its discussion on relative fuel efficiency penalties for heavy-duty CNGVs. The fuel cost figures were mostly drawn from motor fuel data of the Ontario Ministry of Transportation since the Ministry is one of the few available sources of compressed natural gas fuel prices. Finally, the GHGenius life-cycle analysis tool ((S&T) Squared Consultants Inc., 2019, GHGenius, (S&T) Squared Consultants Inc. https://www.ghgenius.ca. Accessed October 5, 2020) was employed to determine fuel-cycle emissions in Canada for comparison purposes. The study produced remarkable findings. Results showed that compared with diesel-fuelled vehicles, emissions in CNG heavy-and-medium-duty vehicles reduced by up to 8.7% (for well-to-wheels) and 11.5% (for pump-to-wheels), respectively. Overall, the most beneficial application appeared to be long-haul trucking based on the long distances covered and higher fuel economy achieved (derived from economies of scale), while refuse trucks appeared to have relatively marginal annual savings. However, these annual savings are actually a conservative estimate, which will ultimately be determined by a number of factors that are likely to be predisposed in favor of NG vehicles. Significantly, the prospect of using RNG as fuel was found to be a factor for improving the value proposition of refuse trucks in particular, certainly from an emissions standpoint with a reduction of up to 100%, but speculatively from operational savings as well.

Evolutionary Algorithm for the Electric Vehicle Routing Problem with Battery Degradation and Capacitated Charging Stations

As CO2 emission regulations increase, fleet owners increasingly consider the adoption of Electric Vehicle (EV) fleets in their business. The conventional Vehicle Routing Problem (VRP) aims to find a set of routes to reduce operational costs. However, route planning of EVs poses different challenges than that of Internal Combustion Engine Vehicles (ICEV). The Electric Vehicle Routing Problem (E-VRP) must take into consideration EV limitations such as short driving range, high charging time, poor charging infrastructure, and battery degradation. In this work, the E-VRP is formulated as a Prognostic Decision-Making problem. It considers customer time windows, partial midtour recharging operations, non-linear charging functions, and limited Charge Station (CS) capacities. Besides, battery State of Health (SOH) policies are included in the E-VRP to prevent early degradation of EV batteries. An optimization problem is formulated with the above considerations, when each EV has a set of costumers assigned, which is solved by a Genetic Algorithm (GA) approach. This GA has been suitably designed to decide the order of customers to visit, when and how much to recharge, and when to begin the operation. A simulation study is conducted to test GA performance with fleets and networks of different sizes. Results show that E-VRP effectively enables operation of the fleet, satisfying all operational constraints.

Vehicle Maintenance Contracting in Developing Economies: The Role of Social Enterprise

Problem definition: Difficulties in healthcare delivery in developing economies arise from poor road infrastructure of rural communities, where the bulk of the population resides. Although motorcycles are an effective means for delivering healthcare products, governments in developing economies lack expertise in proper maintenance, resulting in frequent vehicle breakdowns. Riders for Health, a nonprofit social enterprise (SE), has developed specialized capabilities that enable significant enhancements in vehicle maintenance. Riders for Health has engaged with the governments and provided its services using different contracting approaches. However, the effect of such practice on improving vehicle availability—the main social mission of Riders for Health—is not well understood. Academic/practical relevance: This paper presents one of the first rigorous analyses of how SEs achieve their goals through innovations in operations. Our analysis highlights the relationship between a social mission objective and a service contract choice, contrasting it with the choice by a profit-maximizing organization traditionally assumed in the service contracting literature in operations management. Methodology: We construct and analyze a stylized model that combines the elements of reliability theory and contract theory, explicitly accounting for the SE’s social mission in her objective function. Results: We find that the “total solution” approach of providing all aspects of vehicle maintenance, including fleet ownership, is a preferred choice for an SE that prioritizes improving vehicle availability; by contrast, an organization that focuses on profit maximization would find this approach less attractive. Moreover, we show that the total solution approach induces the SE to exert more efforts on failure prevention and repair lead time reduction in equilibrium. Our analysis also suggests that the SE could further improve vehicle availability by the total solution approach if it manages a large fleet that consists of vehicles with high resale values. Managerial implications: Our findings provide theoretical support for Riders for Health’s recent move toward the total solution approach as it expands its service into wider rural areas in many countries. The insights obtained from our analysis offer actionable guidelines to other SEs operating in developing economies.

Potential of Private Autonomous Vehicles for Parcel Delivery

Using the same vehicles for both passenger and freight transport, to increase vehicle occupancy and decrease their number, is an idea that drives transport planners and is also being addressed by manufacturers. This paper proposes a methodology to simulate the behavior of such vehicles within an urban traffic system and evaluate their performance. The aim is to investigate the impacts of resignation from fleet ownership by a transport service company (TSC) operating on a city-wide scale. In the simulation, the service provider hires private autonomous cars for tour performance. Based on assumptions concerning the operation of such vehicles and TSCs, the software Multi-Agent Transport Simulation (MATSim) is extended to model vehicle and operator behavior. The proposed framework is applied to a case study of a parcel delivery service in Berlin serving a synthetic parcel demand. Results suggest that the vehicle miles traveled for freight purposes increase because of additional access and egress trips. Moreover, the number of vehicles en route is higher throughout the day. The lowering of driver costs can reduce the costs of the operator by approximately 74.5%. If the service provider additionally considers the resignation from fleet ownership, it might lower the operation cost by another 10%, not taking into account the costs of system transfer or risks like vehicle non-availability. From an economic perspective, the reduction of the overall number of vehicles in the system seems to be beneficial.

Understanding ride-sourcing drivers' behaviour and preferences: Insights from focus groups analysis

Ride-sourcing has recently been at the centre of attention as the most disruptive mode of transport associated with the so-called shared mobility era. Drivers, riders, the platform, policymakers, and the general public are considered as the main stakeholders of the system. While ride-sourcing platforms have been growing, so did the heightened tension between them and their drivers. That is why understanding drivers' behaviour and preferences is of key importance to ride-sourcing companies in managing their relationship with drivers (also known as driver-partners) and in retaining them in the presence of competence. Ride-sourcing drivers are not only chauffeurs but fleet owners. They can make various operational and tactical decisions that directly influence other stakeholders and the transport system performance as a whole. Conducting a series of focus groups with ride-sourcing drivers in the Netherlands, we have studied their opinions about the system functionalities as well as their possible interactions with the platform and wishes for changes. The focus group results suggest that the main decisions of drivers, which are ride acceptance, relocation strategies, working shift and area in which to work, could be affected by many elements depending on platform strategies, drivers' characteristics, riders' attributes, and exogenous factors. We find that part-time and full-time drivers, as well as experienced and beginning drivers, are characterized by distinctive behaviour. Flexibility and freedom were mentioned as the key reasons for joining the platform while an unfair reputation system, unreliable navigation algorithm, high competition between drivers, passenger-oriented platform, high-commission fee, and misleading guidance were acknowledged as being the main system drawbacks. Based on our findings, we propose a conceptual model that frames the relationship between the tactical and operational decisions of drivers and related factors.

Light duty vehicle choice models examining alternative fuel technology preferences among commercial fleet owners

Agent-based transportation models are valuable tools for evaluating energy use, emissions and mobility impacts of transportation. In this context, vehicle ownership models are critical for linking personal and commercial activities to their impacts on the transportation system. Further, predicting the fuel type that is chosen by an establishment when purchasing a vehicle is important for modeling the impacts of commercial transportation on energy consumption and related outputs. This study develops an econometric model that can be used to predict the fuel technology that is chosen by an establishment when purchasing a Light Duty Vehicle (LDV) for business purposes. Factor analysis was also used to gain insights into the underlying preferences and needs of establishments, which drive the fuel choice decision. The results can be used in agent-based models or other models in simulations of the transportation system and energy consumption. The outcomes are also useful for modeling the adoption of alternative fuels among commercial fleet owners over time, which is important from both a policy perspective as well as an automobile manufacturer perspective.

Expenditure-based segmentation of freight travel markets: Identifying the determinants of freight transport expenditure for developing marketing strategies

There is a substantial body of literature relating to freight transport sector's economic impact at the macro-level, but less is known about how freight demand gets translated to an establishment's expenditures at the micro-level. This paper addresses this research gap by collecting data about expenditure patterns of establishments and applying market segmentation technique based on finite mixture models. Three latent segments - heavy spenders, medium spenders and light spenders – and their associated profiles are identified. The results indicate that significant differences exist between the three expenditure-based segments of establishments in terms of spending patterns, business size indicators, locational characteristics and freight travel patterns. The heavy spenders tend to be strongly influenced by employment, gross-floor area, business age and fleet ownership levels. The length of haul and truck type choice have a strong incremental effect on the volume of expenditures and larger shipment sizes are associated with expenditure reduction due to economies of scale. The diverging characteristics of expenditure segments emphasizes the need of the logistics providers to “identify their markets” and planners to “identify how demand translates to transport expenditures”. The overall conclusion is that segmenting establishments based on unobservable heterogeneity with respect to their freight transport expenditure is preferable and more informative than treating them as one homogeneous group. The study findings provide important information that planners and logistics providers can utilize in developing effective logistics plans and marketing strategies.

FMS Dashboard - Descriptive Analytics and Preventive Maintenance

Fleet tracking or vehicle tracking allows businesses in a variety of industries to keep track of their vehicle fleet in a convenient and cost-effective manner. But with IOT devices connected to each vehicle, it produces huge amount of data, which is an overload to the users of Fleet Management System (FMS). This data itself is not valuable unless it can be analyzed and interpreted correctly. Quality data can help fleet owners to understand the efficiency, driver safety, expenses and profitability of owning and managing their fleet. In this proposed work, we developed a dashboard for the existing Fleet Management System which will provide descriptive analytics and support in preventive maintenance of the fleet. The FMS Dashboard is a key module of the FMS system. This module uses GPS data like vehicle starts, stops, and idling, fuel consumption, engine running hours, vehicle speeds and location from each vehicle to provide real-time useful insights on vehicle activity, driver behavior and tracking of fleet. Based on historic data, descriptive analytics will summarize past performance of the vehicle to enable users to plan for maintenance to perform. Also preventive maintenance reports helps the fleet owners to estimate, when the vehicle service is due and plan for the same. Apart from this, vehicle can be tracked real-time in Google Maps.

The New York City Taxi Rank-and-File Coalition: 1971-1977

ABSTRACT The New York City Taxi Rank and File Coalition was a movement active in the New York City taxi industry from 1971 through 1977. While the group had varying numbers of active members in its six-year history, primarily young white drivers in their twenties and thirties, it also included a number of middle-aged drivers who had previous union experience. Its many accomplishments included a monthly newspaper called The Hot Seat, weekly meetings in lower Manhattan, a statement of purpose called 10 Taxi at the Crossroads, and a vote tally of more than a third of the rank and file in the AFL-CIO Local 3036 union elections of 1971 and at least 20 percent in 1974. This study examines the question of what impact the rank and file coalition had on the overall evolution of the fleet driving industry in New York City as it developed from a commission-based system, in which drivers shared a percentage of their meter bookings with the fleet owners, to a leasing-based system by the early 1980s.

Economic, environmental and congestion impact on the life-cycle cost of ownership: a case study in the Delhi transit bus system

Fast urbanisation and motorisation growth have resulted in degraded air quality and increased burden on most of the cities, globally. Cities utilise two-thirds of the global energy and account for about 70% of GHG emissions. Therefore, it is important to consider electric buses as an eco-friendly alternative to the conventional buses. To study financial and environmental impacts on the life cycle cost of ownership of conventional and electric buses, we have established the total cost of ownership (TCO) model by considering direct cost (acquisition and operation: owned by the fleet owner) and indirect cost (environmental damage and congestion: owned by the society). This study showed that EV's TCO would be economical, giving 30-40% advantage on fuel and maintenance. Further, EVs powered with renewable energy mix could prove to be a positive multiplier for socio-economic and environmental gain.

Electric Vehicle Virtual Power Plant Dilemma: Grid Balancing Versus Customer Mobility

Virtual power plants (VPP) play a crucial role in balancing the electricity smart grid. VPPs aggregate energy from decentralized sources, for example, biogas, solar panels, or hydropower, to generate and consume electricity on demand. We study the management of electric vehicle (EV) fleets organized in VPPs as a way to address the challenges posed by the inflexible energy supply of renewable sources. In particular, we analyze the potential of parked EVs to absorb electricity from the grid, and provide electricity back to the grid when needed. A fleet owner can either charge, discharge for renting, discharge to the grid, or keep an EV idle. A unique property of our mixed rental‐trading strategy is that decisions are made between making an EV available for rental, where the location within the city matters (drivers want a car to be close to their place of departure or arrival) and for discharging it to the grid, where location does not matter (vehicles can discharge to the grid from any capable charging point). We study the feasibility of VPPs for a fleet of 1500 real EVs on the “Nord Pool Spot,” a North European electricity spot market. A Fourier series approach captures the demand patterns of carsharing vehicles accurately, especially when our weighted objective function with asymmetric payoffs is applied. We show that the VPP can be profitable to fleet owners, ecologically advantageous through reductions in wind power curtailment, and beneficial to consumers by reducing energy expenses.

An optimization model for fleet management with economic and environmental considerations, under a cap-and-trade market

The objective of traditional fleet optimization models has been to find the economic life of the assets, neglecting their environmental impacts. However, due to the effect of carbon pricing schemes, in addition to the international concerns about global warming and carbon emissions, it is essential for affected fleet owners to incorporate environmental burdens into their asset management systems. The contribution of this paper is twofold. First, a fleet optimization model is proposed, which factors in the environmental impacts of a fleet of assets over a finite horizon, in addition to its total cost of ownership. As an indicator of environmental impacts, the greenhouse gas (GHG) emissions associated with the fleet ownership is considered. GHG emissions are converted into a monetary value, using the expected price of carbon in the Western Climate Initiative (WCI) market. Thus, the second contribution of this study is to develop a model to predict the price of carbon in this market. The optimization model is then applied to a fleet of excavators located in Ontario, Canada, and the price of carbon in the WCI market is forecasted over the planning horizon of the optimization model.

Data-Driven Battery Lifetime Prediction and Confidence Estimation for Heavy-Duty Trucks

Maintenance planning is important in the automotive industry as it allows fleet owners or regular customers to avoid unexpected failures of the components. One cause of unplanned stops of heavy-duty trucks is failure in the lead-acid starter battery. High availability of the vehicles can be achieved by changing the battery frequently, but such an approach is expensive both due to the frequent visits to a workshop and also due to the component cost. Here, a data-driven method based on random survival forest (RSF) is proposed for predicting the reliability of the batteries. The dataset available for the study, covering more than 50 000 trucks, has two important properties. First, it does not contain measurements related directly to the battery health; second, there are no time series of measurements for every vehicle. In this paper, the RSF method is used to predict the reliability function for a particular vehicle using data from the fleet of vehicles given that only one set of measurements per vehicle is available. A theory for confidence bands for the RSF method is developed, which is an extension of an existing technique for variance estimation in the random forest method. Adding confidence bands to the RSF method gives an opportunity for an engineer to evaluate the confidence of the model prediction. Some aspects of the confidence bands are considered: their asymptotic behavior and usefulness in model selection. A problem of including time-related variables is addressed in this paper with the argument that why it is a good choice not to add them into the model. Metrics for performance evaluation are suggested, which show that the model can be used to schedule and optimize the cost of the battery replacement. The approach is illustrated extensively using the real-life truck data case study.