Browse Topic: Fleet management
The rapid evolution of intelligent transportation systems has made drivers’ attentiveness and adherence to safety protocols more critical than ever. Traditional monitoring solutions often lack the adaptability to detect subtle behavioral changes in real time. This paper presents an advanced AI-powered Driver Monitoring System designed to continuously assess driver behavior, fatigue, distractions, and emotional state across various driving conditions. By providing real-time alerts and insights to vehicle owners, fleet operators, and safety personnel, the system significantly enhances road safety. The system integrates lightweight AI/ML algorithms, image processing techniques, perception models, and rule-based engines to deliver a comprehensive monitoring solution for multiple transportation modes, including automotive, rail, aerospace, and off-highway vehicles. Optimized for edge devices, the models ensure real-time processing with minimal computational overhead. Alerts are communicated through web and mobile platforms, supplemented by audio-visual cues for prompt user responses. Data from multi-camera setups, auditory sensors, and vehicle CAN bus inputs are processed by a real-time analytics engine that detects abnormal behaviors and safety violations, improving situational awareness and enabling timely interventions. For both individual drivers and fleet managers, the platform serves as an intelligence hub that boosts situational awareness, operational efficiency, and safety compliance. Drivers receive real-time feedback on their behavior, allowing them to make proactive adjustments and reduce risks. Fleet managers can leverage cloud-based connectivity to access predictive analytics, real-time monitoring, and detailed historical behavior data. This enables the identification of unsafe driving patterns, enforcement of safety protocols, and optimization of fleet performance. The system also simplifies regulatory reporting and auditing processes, ensuring compliance with safety standards. By continuously monitoring driver behavior, managers can foster a culture of safety and performance while improving overall fleet operations.
Tillage, a fundamental agricultural practice involving soil preparation for planting, has traditionally relied on mechanical implements with limited real-time data collection or adjustment capabilities. The lack of real-time data and implement statistics results in fleet managers struggling to track performance, driver behavior, and operational efficiency of the implements. Lack of data on vehicle performance can result in unexpected breakdowns and higher maintenance costs, ensuring compliance with regulations is challenging without proper data tracking, potentially leading to fines and legal issues. Bluetooth-enabled mechanical implements for tillage operations represent an emerging frontier in precision agriculture, combining traditional soil preparation techniques with modern wireless technology. Implement mounted battery powered BLE (Bluetooth Low Energy) modules operated by solar panel based rechargeable batteries to power microcontroller. When Implement is operational turns module active and establishes communication with BLE capable wireless controller to share implement statistics and parameters. Sensors like magnetic pickup rotary shaft speed and accelerometer sensors interfaced with module to acquire implement working shaft speed, depth of implement operation in field. Based on dynamic data collected by module such as hours of usage, Trip hours, Oil change alert, maintenance alerts made available to the fleet managers. BLE module transmits acquired data to the tractor mounted wireless controller which makes data available on cloud, to fleet managers using dedicated applications to track all tillage implement statistics. Also, this solution helps implement manufacturers to track implement usage and avoid false warranty claim issues.
Warehouse logistics increasingly rely on automation in the form of autonomous mobile robots (AMRs), scanners, complex conveyors, and fleet management systems for seamless operation, but it’s the ubiquitous, century-old pallet that remains the critical support system. Make no mistake, if even one of those thousands of pallets is defective, it can create havoc in the warehouse.
Traditional safe-life methodologies for rotorcraft structural components often result in overly conservative life estimates, increasing maintenance costs and reducing aircraft availability. This study explores the integration of digital twin concepts with probabilistic modeling and machine learning to enhance structural life assessment, demonstrated through a practical case involving the Royal Canadian Air Force CH-146 Griffon helicopter. A probabilistic fatigue model determines a fatigue life distribution by incorporating material variability and uncertain operational loads inferred directly from flight data. Unlike conventional approaches, this method dynamically estimates load spectra, including uncertainty instead of relying on conservative assumptions. Monte Carlo simulations are used to quantify structural risk and assess the impact of load and material uncertainties. Sensitivity analyses highlight these uncertainties’ contributions to failure probability. The proposed approach provides probabilistic life predictions, supporting risk-based maintenance strategies to potentially optimize operational efficiency. The long-term goal is to develop an adaptive digital twin model that continuously updates with new operational flight data, enhancing predictive accuracy for helicopter fleet management.
Commercial transportation is the key pillar of any growing economy. Light and Small commercial vehicles are increasing every day to cater the logistics demand, but there is always a gap between customer’s actual and desired operational efficiency. This is because of lack of organized fleet and efficient fleet operation. The major requirement of fleet owners is timely delivery, high productivity, downtime reduction, real time tracking, etc., Automakers are now providing fleet management application in modern LCV & SCV to satisfy the fleet operator requirement. However, any feature malfunction, consignment mismatch, wrong notification, missed alerts, etc., can incur huge loss to fleet operator and disrupt the entire supply chain. Hence it is very critical to extensively validate the telematics features in fleet management application. This paper explains the approach for exhaustive validation strategy of fleet management applications (B2B) from end user perspective. An effective test methodology was established to validate every feature against the real-world possibilities and actual data (CAN/sensor values). Key feature such as Consignment Assignment can be verified by recreating all real-world circumstances such as different delivery scenario, consignment pickup scenario, breakdown scenario, true testing, mock testing, consignment transfer in case of breakdown, partial consignment delivery scenario, etc. The driver and vehicle efficiency mapping feature such as Mileage monitoring, driver monitoring, scheduled maintenance, fuel logs, trip logs can be verified by recreating all customer and field use cases. All the location and real time tracking based features are verified against the instrumented Geo position sensors. Vehicle-based alerts such as idle alert, start stop alert, overspeed, door alert, etc., can be verified against the vehicle logger data values. Lastly, the User interface and user experience of the application is also validated up to icon level in every screen, to ensure ease of use and adaptability for the customer. Thus, an innovative and customer centric approach is established to validate Telematics feature for fleet customers, which is robust and time efficient.
This paper proposes a practical optimal-time window-based path-planning approach for a fleet of autonomous vehicles. Specifically, autonomous vehicles in this work refers to fleet of tractors that performs spraying operations in a vineyard field. The approach involves two main steps. In the first step based on a behavior and actions of the tractors that mimic manual spraying operations, a linear integer programming (ILP) optimization model is constructed. The second step then seeks a solution for this MIP model to obtain paths for autonomous navigation of the tractors in a vineyard field. The simulation results on a real-world data collected using Google Maps application for Sula vineyards located in the Nashik region [1] is reported. The obtained results show effectiveness of the proposal with respect to manual operator driven fleet management.
Vehicle miles traveled (VMT) statistics is a key parameter which has many applications, such as the assessment of vehicle quality, evaluation of driving behavior and oil consumption, and other applications in vehicle monitoring system. In the earlier studies, the calculation of VMT usually focused on improving the accuracy and frequency of vehicle GPS data, but the VMT estimation error due to them were getting smaller with the development of positioning technology. Nowadays in the practical application of internet of vehicles, errors due to the out-of-order location data which caused by communication mechanism have become increasingly obvious. In this paper, we propose a VMT estimate method based on improved ant colony algorithm and local search method which is suitable for dealing with timestamp chaotic location data sequence. To evaluate our method, we use real-world vehicle data gathered by China mobile’s vehicle fleet management products, the analysis result shows the MRE of proposed ant colony algorithm is usually less than 8%, at least 3 percentage points lower than that of uniform motion distance accumulation statistics, at least 7 percentage points lower than that of Euclid distance accumulation statistics.
Military rotorcraft engines operating in harsh environments routinely ingest large quantities of mineral dust, which can degrade components and ultimately reduce operability. Time off-wing for unscheduled maintenance is a costly burden, both financially and operationally. Rapidly predicting engine deterioration rates as a function of the mission presents an opportunity to optimise flow of supplies, better manage fleets, and perform safety risk assessments when dust loading is expected to be particularly high. In the current contribution, we present our ongoing efforts in this field with a new methodology for assessing the effectiveness of inertial particle separators and quantifying the changes they impart to the inbound dust. We demonstrate that both the concentration reduction and the modification to the particle size distribution can be made on the basis of a single independent variable- a generalised Stokes number for inertial particle separators- and a single performance parameter- the corrected separation efficiency. To develop these parameters we conduct numerical simulations of the flow through a generic axi-symmetric inertial particle separator, over a range of five mass flow rates, three scavenge mass flow rates, and 16 particle diameters. In addition to this, a framework is presented to enable an estimation of the dust concentration at the engine intake. This is achieved by correlating the total wake strength to an existing dust landing trial dataset. A coupled rotorcraft-engine model is then used to combined the two methodologies to investigate the influence of engine mass flow rate on dust ingestion rate. A weak non-linear relationship is observed, which arises due to the simultaneous increase in wake strength with engine mass flow rate as rotor power requirements increase. The additional dust stirred up by the stronger wake leads causes this non-linearity. Finally, we show that an improvement in separation efficiency caused by higher engine mass flow rate is far outweighed by the associated increase in dust loading in this condition.
Plug-in hybrid (PHEV) technology offers the ability to achieve zero tailpipe emissions coupled with convenient refueling. Fleet adoption of PHEVs, often motivated by organizational and regulatory sustainability targets, may not always align with optimal use cases. In a car rental application, barriers to improving fuel economy over a conventional hybrid include: diminished benefits of additional battery capacity on long-distance trips, sparse electric charging infrastructure at the fleet location, lack of renter understanding of electric charging options, and a principle-agent problem where the driver accrues fewer benefits than costs for actions that improve fuel economy, like charging and eco-driving. This study uses high-resolution driving data collected from twelve Ford Fusion Energi sedans owned by University of California, Davis (UC Davis), where the vehicles are rented out for university-related activities. The data is analyzed to understand the degree to which the electric battery is taken advantage of by fleet management and end users to reduce fuel costs and emissions. Specifically, characteristics of trips assigned to those vehicles, driver behavior, locations of charging events and missed charging opportunities, state of charge (SOC) at the start of rentals, and segments of trips typically covered by electric driving range are examined. Finally, machine learning techniques, including a decision tree analysis, are used to understand predictors of fuel economy for this fleet. Conversations with fleet management, including presentation of analysis results, are used to generate policy recommendations. We find that due to the typical length of trips, a conventional hybrid would achieve roughly equivalent fuel economy in the UC Davis motor pool, although the plug-in option offers an opportunity to expand exposure of drivers to electrification. Steps for improvement include expanding on-site fleet charging infrastructure, educating users on charging options prior to rental, and consideration of trip destination in vehicle selection for rental.
ABSTRACT Defense fleet managers require maintenance strategies that deliver high readiness, reliable and sustainable combat equipment in the face of operational uncertainty and chaotic tactical environments. Shaping depot maintenance strategy is complex: aircraft, vehicles, and weapons systems operate in unpredictable and dynamic environments while component aging, convoluted maintenance practices, and overlapping sustainment programs all influence requirements. Yet, most predictive analytics efforts are focused on short-term tactics and historical data. As a result, these models cannot deliver the needed long-run precision suitable for depot strategies. Despite new big-data feeds, cloud applications, and innovative visualizations, most underlying predictive models are not suited for the challenge due to a simple reason: The past does not represent the future. Without the appropriate predictive tools, fleet managers lean heavily and cautiously towards doing more maintenance. The underlying assumption is that more maintenance yields more readiness. Four case studies, show successful predictive modeling of depot maintenance complexities. An advanced, approach towards predictive analysis across the lifecycle of defense programs can accurately shape strategies and identify cases where too much maintenance is scheduled.
Airframes in the future will include a significant amount of composite material components that need to be designed for both optimal structural efficiency and damage tolerance. Current composite design methodology relies on the establishment of worst-case scenarios for each of the factors that influence the structural capacity and life of airframe components. The layered application of these factors can result in excessive levels of conservatism and maintenance requirements that reduce aircraft availability. The combat aircraft of the future can be designed and maintained based on specific knowledge derived from data driven methodologies to define risk, threat impact, and measured structural response in order to maximize aircraft availability, while ensuring safety and reliability. This work describes an Advanced Structural Integrity Framework (ASIF) that probabilistically models composite residual strength. Full-scale damage tolerance tests of a UH-60M stabilator provided input data for various threat types and severities. Threat probabilities were derived from prior studies and recent fleet repair data. The model estimated the risk of failure in various structural zones to identify areas for reducing conservatism. Trend studies confirmed that the model appropriately responded to changes in composite material properties and threat exposures, thus showing its potential as a powerful structural risk assessment tool for design and fleet management.
Health and Usage Monitoring Systems (HUMS) generate a significant amount of data used for on-board and off-board monitoring of the health of the aircraft and its components. When this data is aggregated over the life of an aircraft, it becomes an invaluable resource that enables decision making for diagnostics, prognostics, and fleet management. At the fleet level, the amount of data being ingested, stored, and processed becomes a challenge in itself. The capability to easily handle data of this size is critical to be responsive to time-critical inquiries, iterate on data modeling, and enable efficient diagnostics and prognostics algorithm development. This paper discusses how massively scalable data analytics technologies have been used to enable rapid decision support using HUMS and other data sources. Several use cases are highlighted to show the novel opportunities enabled by these technologies along with associated challenges.
According to the recent study, Thailand has the 2nd most dangerous road in the world. Based on many researches, the driver is the main influencers of the traffic fatalities. Since the more dangerous the driver drive, the more chance of accident become. Therefore, driver’s monitoring system become one of the solutions that acceptable and reliable, especially for fleet management and public transportation. This paper’s goal is to find an algorithm that can distinguish driving behaviour based on cars’ acceleration and velocity, calling it as Risk Driving Score (RDS). The algorithm was tested by driving test by volunteers on highways with observers, who were told to rank the drivers in terms of driving risk from the 1-5 point. Meanwhile, the drivers were asked to drive in 3 different styles, normal, safety, and hurry. All drives were recorded by satellite and video data then filtered and used for the algorithm calculation. After that, the linear regression shows that there is a trend of driving score evaluated by algorithm and observers in term of linear equation with high correlation. In conclusion, the algorithm can replace the observers in driver monitoring method and can be used with satellite data.
Items per page:
50
1 – 50 of 111