Fleet Management Research Articles

Fleet Management and Vehicle Routing Plan using Dijkstra's Shortest Path Algorithm

Fleet Management and Vehicle Routing Plan using Dijkstra's Shortest Path Algorithm

Fleet management system, perceived service quality and the public health sector performance in Zimbabwe

PurposeThe purpose of the study is to establish the relationship between public health sector performance (PHSP), fleet management system, perceived service quality (PSQ) and management style (MS).Design/methodology/approachA total of 260 managerial employees were randomly selected from 5 major public hospitals in Zimbabwe to participate in this cross-sectional survey.FindingsFleet management system was found to positively influence both PSQ and PHSP. The results indicated that PSQ has a positive effect on PHSP. MS was found to moderate the effect of fleet management system on both PSQ and PHSP.Originality/valueThe current study provides fresh insights and validates extant knowledge on PHSP, fleet management and PSQ within the public health sector departments. It extends further knowledge on the public health performance in the Sub-Saharan region, as it shows that dimensions on fleet management have a direct influence on PHSP.

Proposed Improvement of Pertalite Fuel Outbound Logistics Performance to Achieve Pertamina Patra Niaga MS2 Compliance (A Case Study of Bandung City)

PT. Pertamina Patra Niaga was founded in 2004, is a sub-holding of PT. Pertamina which handles Pertamina’s downstream oil and gas processes, especially fuel trading and handling, as well as fleet and depot management. This study took Fuel Terminal Bandung Group – Ujung Berung as a research location which encounter issue related to the not achieved of the MS2 Compliance target in delivery time delay related to the external logistics performance. This research focuses on the delivery of Pertalite fuel in the city of Bandung in the third quarter of 2022. This study aims to identify the factor that affect the value of MS2 Compliance in Fuel Terminal Bandung Group-Ujung Berung and initiate the improvement initiatives to improve outbound logistic performance for Fuel Terminal Bandung Group – Ujung Berung. The conceptual framework used in this research describes the supply chain design and focuses on outbound logistics in terms of moving the final product to the retailers to achieve responsive supply chain strategy is improving the outbound logistic performance. The equipment that used to carry the delivery are tank trucks. The method used in this study uses a quantitative approach with heuristic methods using a sweep algorithm. Quantitative data were obtained from company data, observations at the company and interviews with departments that related to the company’s logistics. Secondary data analysis using literature and company data. The analysis was carried out by finding the root of the problem with a fishbone diagram and analysing quantitative data with a sweep algorithm. The analysis is carried out by taking days that have low MS2 Compliance in Quarter III 2022 in one week, where one day has three delivery batch. From the results of the analysis, it was found that there were four main causes, namely method, environment, human, and equipment factors. Then examine by the sweep algorithm analysis which results in more effective route selection and maximizing the use of tank trucks by calculating the travel time for each shipment by considering the allowance time for each shipment.

Two-Sided Deep Reinforcement Learning for Dynamic Mobility-on-Demand Management with Mixed Autonomy

Autonomous vehicles (AVs) are expected to operate on mobility-on-demand (MoD) platforms because AV technology enables flexible self-relocation and system-optimal coordination. Unlike the existing studies, which focus on MoD with pure AV fleet or conventional vehicles (CVs) fleet, we aim to optimize the real-time fleet management of an MoD system with a mixed autonomy of CVs and AVs. We consider a realistic case that heterogeneous boundedly rational drivers may determine and learn their relocation strategies to improve their own compensation. In contrast, AVs are fully compliant with the platform’s operational decisions. To achieve a high level of service provided by a mixed fleet, we propose that the platform prioritizes human drivers in the matching decisions when on-demand requests arrive and dynamically determines the AV relocation tasks and the optimal commission fee to influence drivers’ behavior. However, it is challenging to make efficient real-time fleet management decisions when spatiotemporal uncertainty in demand and complex interactions among human drivers and operators are anticipated and considered in the operator’s decision making. To tackle the challenges, we develop a two-sided multiagent deep reinforcement learning (DRL) approach in which the operator acts as a supervisor agent on one side and makes centralized decisions on the mixed fleet, and each CV driver acts as an individual agent on the other side and learns to make decentralized decisions noncooperatively. We establish a two-sided multiagent advantage actor-critic algorithm to simultaneously train different agents on the two sides. For the first time, a scalable algorithm is developed here for mixed fleet management. Furthermore, we formulate a two-head policy network to enable the supervisor agent to efficiently make multitask decisions based on one policy network, which greatly reduces the computational time. The two-sided multiagent DRL approach is demonstrated using a case study in New York City using real taxi trip data. Results show that our algorithm can make high-quality decisions quickly and outperform benchmark policies. The efficiency of the two-head policy network is demonstrated by comparing it with the case using two separate policy networks. Our fleet management strategy makes both the platform and the drivers better off, especially in scenarios with high demand volume. History: This paper has been accepted for the Transportation Science Special Issue on Emerging Topics in Transportation Science and Logistics. Funding: This work was supported by the Singapore Ministry of Education Academic Research [Grant MOE2019-T2-2-165] and the Singapore Ministry of Education [Grant R-266-000-135-114].

Using Transport to Quantify the Impact of Vertical Integration on the Construction Supply Chain: A New Zealand Assessment

New Zealand (NZ) construction is highly fragmented, comprises primarily micro small and medium enterprises (MSMEs); 32.5% of approximately 67,000 operating businesses are ‘small’ (up to 19 employees), while 65% are sole traders. The construction supply chain (CSC) is extensive, prone to inefficiencies at segmental boundaries accentuated by project-centric delivery. Conversely, it presents significant opportunity for consolidation and improved efficiency. Vertical integration and CSC management from the supplier-end rather than the project-end enable component elements to be individually independent in terms of ownership, while integrating their management above the tactical CSC level. This leads to improved operational philosophy and employment. Quantifying impacts, however, is a challenge due to lack of tangibility. This can be effectively overcome using quantifiable parameters associated with the CSC’s transport component. The paper investigates transport operations in a narrow NZ CSC segment over a three-month period to quantify improved performance using operational data and further potential for resource optimisation using operations research-based planning. Research outcomes point towards: (i) Fleet management strategy; (ii) Integrated planning and operational delivery; (iii) Non-price attributes in tendering/contracting; (iv) Change in the delivery model of manufactured construction products; (v) Information and communication technology-based solutions; and (vi) Integration of reverse logistics.

Hitting two birds with one emissions-based maintenance stone – a literature review on improving overall productivity of underground diesel fleets

Many industries regard occupational health and safety as a core value and an integral component to maintaining high productivity, and, thus, shareholder value. Diesel fleets’ engine maintenance is instrumental in ensuring affected workplaces meet production requirements while controlling health and safety hazards that these fleets introduce to the workplace. This systematic literature review focuses on production and occupational health and safety advantages associated with the implementation and adherence to an emissions-based maintenance (EBM) program. The literature review was conducted across eight databases relevant to workplace health and engineering. To be eligible for inclusion, the publication had to contain maintenance interventions that were informed by diesel engine emissions (DEE) data. Eight publications met the inclusion criteria. The quality of evidence was evaluated by applying the Authority, Accuracy, Coverage, Objectivity, Date, and Significance (AACODS) checklist [1]. There is a paucity in peer-reviewed EBM literature. Available research show evidence for productivity gains such as reduced DEE at the source, reduced fuel consumption, reduced worker exposure, and anecdotal evidence for extended exhaust aftertreatment (EAT) service life. There was no evidence that EBM improved fleet management (measured as fleet availability and reliability) or resulted in reduced underground dilution ventilation delivery.

Fleet management enterprise systems and traffic control synergies: a literature review and research agenda

Synergies between fleet management enterprise systems and traffic control systems for information sharing and collaborative planning can contribute to significant improvements to operational efficiency, safety and environmental impact. This paper provides a synthesis of the extant body of research on synergies between fleet management and traffic control systems identifying five key topics in prior research and suggesting research directions. The findings are based on a systematic literature review and topic modelling with the use of natural language processing (Latent Dirichlet Allocation). The five topics identified are related to: hazardous goods transportation, environment and emissions, position tracking and navigation technologies, traffic management and fleet operations´ optimization. The two most frequent topics link to social responsibility (minimizing accidents during hazardous goods transportation and minimizing environmental impact) indicating the relevance of this area of research to sustainability. Despite the strong potential for synergies between intelligent transportation systems and enterprise fleet management systems, the review identified a paucity of research on the coordination between real-time fleet management and traffic control measures (e.g. ramp metering, route guidance, variable speed limits and signal control).

A Data-Intelligent Scheme Toward Smart Rescue and Micro-Services

A considerable portion of the world frequently experiences flooding during the monsoon season. As a result of this catastrophic event, hundreds of individuals have become homeless. In addition, rescuers are not usually effective enough to rescue the majority of victims. This is due to inadequate rescue operations infrastructure, a severe flaw in today’s technologically advanced society. This manuscript proposes a microservice-dependent secure rescue framework that uses geographic information system mapping with a K-Means clustering algorithm to identify flood-prone regions. Numerous microservices, such as fleet management, cloud computing, and data security, integrate and execute the framework in pre- and post-flood situations. Labeling data from the proposed framework generates a support vector machine-based classifier for predicting flood risk. Furthermore, a hybrid A* algorithm is developed to find an optimal route for the rescue operation. Based on the K-means clustering results, which reduced the variance by 89.2 percent overall, dividing the data into six clusters was the best option for this study. The smoothness of the suggested hybrid algorithm is also used to verify its superiority.

The effect of road characteristics on timber truck driving speed and fuel consumption based on visual interpretation of road database and data from fleet management system

Road transport produces 90% of greenhouse gas emissions in timber transport in Finland. It is therefore necessary to understand the factors that affect driving speed, fuel consumption, and ultimately, emissions. The objective of this study was to assess the effect of road characteristics on timber truck driving speed and fuel consumption. Data from the fleet management and transport management systems of two timber trucks were collected over a year. A sample of 104 trips was drawn, and the tracking points were overlaid on the road data in a geographical information system. Thereafter, work phases were determined for the points, and they were visually classified into road and pavement classes. Subsequently, the data of 80 trips were utilised in regression analysis to further study the effects of the visually interpreted variables on driving speed and fuel consumption. Fuel consumption was explained by the proportion of forest roads and distance travelled with a loader, and the number of crossings and season when driving without a load. When driving with a load, both asphalt and gravel pavements decreased consumption, in contrast to an unpaved road. Crossings increased fuel consumption, as did the winter and spring months, and the total laden mass of the truck. In conclusion, the study showed that the functional Finnish road and pavement classes can be used to predict driving speed and fuel consumption.

An IIoT-Based Approach to the Integrated Management of Machinery in the Construction Industry

In recent years, considerable advances in connecting industrial equipment to the Internet allowed a higher level of operational efficiency, productivity, and automation. Nevertheless, the construction industry still presents challenging requirements, like long-distance wireless communication, interconnection of out-of- coverage areas, constant mobility of machinery, and support for legacy and proprietary systems. All these requirements pose different challenges when compared with traditional smart factory Industry 4.0 solutions. This paper discusses some of the current key questions regarding fleet management in the construction industry, identifies requirements for heavy-duty machinery, and proposes an Industrial Internet of Things (IIoT)-based solution for the integrated monitoring of such machinery. Also, it proposes and presents an open, innovative solution for the integrated management of non-standardized civil construction vehicle technologies. The developed prototype uses the J1939 protous and protocol to collect machinery status and Long-Range Wide Area Network (LoRaWAN) to communicate the monitored data. The solution was assessed at the construction site of the new port of Sines in Portugal. A detailed description of the proposed system is provided, along with information on trials and evaluation results regarding its performance. Additionally, the paper provides insights into open issues and challenges in this field and how our solution can contribute to overcoming them.

Fleet management systems in Logistics 4.0 era: a real time distributed and scalable architectural proposal

In an era marked by the big data paradigm and ubiquitous computing systems, it is increasingly common to see devices embedded in any type of object with the aim of collecting and sharing owned or read data from its environment. This type of interconnection between devices is known as the Internet of Things (IoT). In particular in the logistics sector, vehicles are equipped with control units that are capable of monitoring a large number of parameters to ensure the correct operation of the vehicle. In addition, they are now able to share this data in near real time so that this information can be accessed and analysed at any time. However, due to the large amount of shared data, the frequency of data generation and delivery, and the high potential for growth in the number of devices, traditional technologies and architectures are not able to meet the performance demands of these real time decision making systems. In this article we describe and evaluate the benefits and potential trade-offs of implementing services based on a distributed and scalable architecture, called RAI4.0, in a truck fleet management company, which currently has 20,000 on-board devices and expects to grow to 80,000 devices in the next 2 years. With the change of architecture, the company expects to be able to implement near real-time services to monitor and notify its drivers of driving tips and diagnose possible vehicle failures in advance, among others.

Vehicular Applications of Koopman Operator Theory—A Survey

Koopman operator theory has proven to be a promising approach to nonlinear system identification and global linearization. For nearly a century, there had been no efficient means of calculating the Koopman operator for applied engineering purposes. The introduction of a recent computationally efficient method in the context of fluid dynamics, which is based on the system dynamics decomposition to a set of normal modes in descending order, has overcome this long-lasting computational obstacle. The purely data-driven nature of Koopman operators holds the promise of capturing unknown and complex dynamics for reduced-order model generation and system identification, through which the rich machinery of linear control techniques can be utilized. Given the ongoing development of this research area and the many existing open problems in the fields of smart mobility and vehicle engineering, a survey of techniques and open challenges of applying Koopman operator theory to this vibrant area is warranted. This review focuses on the various solutions of the Koopman operator which have emerged in recent years, particularly those focusing on mobility applications, ranging from characterization and component-level control operations to vehicle performance and fleet management. Moreover, this comprehensive review of over 100 research papers highlights the breadth of ways Koopman operator theory has been applied to various vehicular applications with a detailed categorization of the applied Koopman operator-based algorithm type. Furthermore, this review paper discusses theoretical aspects of Koopman operator theory that have been largely neglected by the smart mobility and vehicle engineering community and yet have large potential for contributing to solving open problems in these areas.

Strategic asset management of a heterogeneous locomotive fleet

Strategic asset management of a heterogeneous locomotive fleet

Strategic asset management of a heterogeneous locomotive fleet

Strategic asset management of a heterogeneous locomotive fleet

Blockchain-Enabled VANET for Smart Solid Waste Management

Internet of things (IoT) is being applied in every aspect of daily living to improve the quality of life. Waste management is a critical issue, especially for developing countries. The purpose of this study is to propose an IoT-driven state-of-the-art system for solid waste management for developing countries and urban areas. The lack of planning and availability of resources in urban areas have made a living in densely populated surroundings even more difficult. This research work provides a framework based on blockchain-enabled vehicular ad-hoc networks (VANETs) in the realm of IoT. The step-by-step methods are proposed for the decentralized solution for solid waste management using blockchain-enabled VANET. Advanced ultra-high frequency (UHF) technology is used along with IoT devices for the real-time location of waste vehicles and the detection of waste bins. Geo-fencing techniques are also applied for the monitoring and timely collection of waste from the dump spots. Lastly, blockchain technology is applied in the proposed solution to make machine-to-machine (M2M) communication more secure, reliable and trustworthy across IoT devices. The experimental results are also obtained by deploying a pilot project in Karachi, Pakistan. The real-time dashboard is also obtained to demonstrate the daily statistics of the waste collection and performance of the waste vehicles. The results indicate the successful implementation of SSWMS to achieve real-time tracking, intelligent identification of waste bins, trash weighing, and keeping tabs on waste collection from dump spots using geofencing. In future, the blockchain-enabled VANETs can be applied for route management, intelligent transportation and fleet management systems (FMS) due to the inherent characteristics of blockchain and IoT.

The ongoing electrification in light vehicle public fleets: Lessons learned from an experience at Brazilian public safety sector

This paper reports a pioneering experience in Brazil of implementing an electrified fleet for the Civil Municipal Guard of the city of São José dos Campos - SP. The main objective is to bring contributions to the expansion of light vehicle public fleet electrification through lessons learned and recommendations established from this case study linked to the public security sector. Semi-structured questionnaires were applied to fleet managers and users, in addition a survey of data on vehicles, fuel and electricity prices, to then present implementation barriers, financial savings estimations and lessons learned with recommendations. The bureaucracy present in public hiring processes and convincing users to change to an unknown technology were the main barriers raised. The implantation presented economic viability, considering the characteristics of the fleet, and demands some adjustments related to the technical specification of the vehicles and chargers to avoid influences on the core activities. Based on these results, the main recommendations are the early and detailed construction of the basic project for contracting, establishing a maintenance plan that includes preventive actions and stock of imported spare parts and a training plan that involves all users, prior experimentation and emphasis on vehicle efficiency and autonomy.

Development of a Customer Churn Model for Banking Industry Based on Hard and Soft Data Fusion

There has been an increase in customer churn over the past few years—customers decide not to continue purchasing products or services from an organization. Customers’ data lie in two categories: soft and hard. The term “hard data” refers to the records generated by various devices and programs, including but not limited to smartphones, computers, sensors, smart meters, fleet management systems, call detail records (CDRs), and consumer bank transaction data. On the other hand, information that is subject to interpretation and viewpoint is known as “soft data.” Fusing these two types of data leads to better customer behaviour analysis. This paper uses a supervised machine learning algorithm, namely a decision tree (DT), and the change mining method to model hard data. K-means clustering, an unsupervised machine learning algorithm, is also used along with the data preprocessing techniques. This paper also considers the Dempster-Shafer theory and other steps for soft data modelling. By fusing soft and hard data, the churn rate of customers compared with each other can be calculated. Besides, the customers’ banking data are leveraged for data modelling. The results show that the banking industry will gain a more dynamic and efficient customer relationship management system by using this model.

Lightweight and Effective Convolutional Neural Networks for Vehicle Viewpoint Estimation From Monocular Images

Vehicle viewpoint estimation from monocular images is a crucial component for autonomous driving vehicles and for fleet management applications. In this paper, we make several contributions to advance the state-of-the-art on this problem. We show the effectiveness of applying a smoothing filter to the output neurons of a Convolutional Neural Network (CNN) when estimating vehicle viewpoint. We point out the overlooked fact that, under the same viewpoint, the appearance of a vehicle is strongly influenced by its position in the image plane, which renders viewpoint estimation from appearance an ill-posed problem. We show how, by inserting in the model a CoordConv layer to provide the coordinates of the vehicle, we are able to solve such ambiguity and greatly increase performance. Finally, we introduce a new data augmentation technique that improves viewpoint estimation on vehicles that are closer to the camera or partially occluded. All these improvements let a lightweight CNN reach optimal results while keeping inference time low. An extensive evaluation on a viewpoint estimation benchmark (Pascal3D+) and on actual vehicle camera data (nuScenes) shows that our method significantly outperforms the state-of-the-art in vehicle viewpoint estimation, both in terms of accuracy and memory footprint.

Principles for improving the quality of fuel level monitoring based on IoT

Recently, the Internet of Things (IoT) has spread to all areas of life and industry. More and more companies around the world are actively investing in technologies related to the Internet of Things to optimize their own business processes. Analysts even see that the industry will become one of the drivers of the growth of this market in the next six months. One of the industry’s most vulnerable to the IoT revolution is retail. Functional capabilities of sensors and the information provided by them allow solving the largest range of tasks inherent in industry. The combination of IoT technology objects with the help of sensors, sensors and the network are similar to digital intelligence, capable of transmitting various necessary data in real time independently, without constant human control. This is facilitated by the spread of wireless Internet networks and the development of microprocessor technologies. One of the industries where IoT is being implemented is the fuel industry, in particular, gas stations. A gas station in the modern world is a provider of complex services built on fuel. In addition, the need to fill the capacity often becomes a reason to obtain a wider set of services, and in this light, every aspect of the station takes on additional importance, and IoT helps to optimize them all. Fuel level monitoring solutions provide accurate real-time fuel usage readings, alerting fleet managers if readings exceed normal limits to prevent fuel shortages.

Maintenance Forecasting Model for Geographically Distributed Home Appliances Using Spatial-Temporal Networks

The application of machine learning in predicting regular and ad-hoc maintenance demand has been widely discussed recently. Reliable forecasting of uncontrollable, ad-hoc maintenance can improve resource allocation and spare part supply planning. However, the scope of its application is still limited to manufacturing and fleet management areas. Developing predictive analytics techniques for geographically distributed household appliances has been less discussed in literature. In this research, we propose a Spatial–Temporal Network (STN) model for forecasting ad-hoc maintenance needs of private home heating appliances considering external factors such as regional situation and weather. To evaluate the results of the model, we use five years of historical maintenance order data of a heating service company as training and test data. We compare the results of our model with traditional forecasting approaches like historical average, time series analysis and multi-factor linear regression. The evaluation results show a clear improvement of forecasting accuracy and outperformed the MAPE of the best traditional model by over 6%. The developed STN model provides the basis for implementing advanced prediction of maintenance requirements for uncontrollable, ad-hoc demand and offers a reliable demand planning base.