Explore the vast range of titles available.

Short-term production planning in industrial mining complexes involves defining daily, weekly or monthly decisions that aim to achieve production targets established by long-term planning. Operational requirements must be considered when defining fleet allocation and production scheduling decisions. Thus, this paper presents an actor-critic reinforcement learning (RL) method to make mining equipment allocation and production scheduling decisions that maximize the profitability of a mining operation. Two RL agents are proposed. The first agent allocates shovels to mining fronts by considering some operational requirements. The second agent defines the processing destination and the number of trucks required for transportation. A simulator of mining complex operations is proposed to forecast the material flow from the mining fronts to the destinations. This simulator provides new states and rewards to the RL agents, so shovel allocation and production scheduling decisions can be improved. Additionally, as the mining complex operates, sensors collect ore quality data, which are used to update the uncertainty associated with the orebody models. The improvement in material supply characterization allows the RL agents to make more informed decisions. A case study applied at a copper mining complex highlights the method’s ability to make informed decisions while collecting new data. The results show a 47% improvement in cash flow by adapting the shovel and truck allocation and material destination compared to a base case with predefined fleet assignments.

Rapid technology advances have made managing charging loads and optimizing routes for electric vehicle (EV) fleets, especially in cities, increasingly important. IoT sensors in EV charging stations and cars enhance prediction and optimization algorithms with real-time data on charging behaviors, traffic, vehicle locations, and environmental factors. These IoT data enable the GNN-ViGNet hybrid deep learning model to anticipate electric vehicle charging needs. Data from 400,000 IoT sensors at charging stations and vehicles in Texas were analyzed to identify EV charging patterns. These IoT sensors capture crucial parameters, including charging habits, traffic conditions, and other environmental elements. Frequency-Aware Dynamic Range Scaling and advanced preparation methods, such as Categorical Encoding, were employed to improve data quality. The GNN-ViGNet model achieved 98.9% accuracy. The Forecast Accuracy Rate (FAR) and Charging Load Variation Index (CLVI) were introduced alongside Root-Mean-Square Error (RMSE) and Mean Square Error (MSE) to assess the model’s predictive power further. This study presents a prediction model and a hybrid Coati–Northern Goshawk Optimization (Coati–NGO) route optimization method. Routes can be real-time adjusted using IoT data, including traffic, vehicle locations, and battery life. The suggested Coati–NGO approach combines the exploratory capabilities of Coati Optimization (COA) with the benefits of Northern Goshawk Optimization (NGO). It was more efficient than Particle Swarm Optimization (919 km) and the Firefly Algorithm (914 km), reducing the journey distance to 511 km. The hybrid strategy converged more quickly and reached optimal results in 100 rounds. This comprehensive EV fleet management solution enhances charging infrastructure efficiency, reduces operational costs, and improves fleet performance using real-time IoT data, offering a scalable and practical solution for urban EV transportation.

We deal with the problem of predictive maintenance (PdM) in a vehicle fleet management setting following an unsupervised streaming anomaly detection approach. We investigate a variety of unsupervised methods for anomaly detection, such as proximity-based, hybrid (statistical and proximity-based) and transformers. The proposed methods can properly model the context in which each member of the fleet operates. In our case, the context is both crucial for effective anomaly detection and volatile, which calls for streaming solutions that take into account only the recent values. We propose two novel techniques, a 2-stage proximity-based one and context-aware transformers along with advanced thresholding. In addition, to allow for testing PdM techniques for vehicle fleets in a fair and reproducible manner, we build a new fleet-like benchmarking dataset based on an existing dataset of turbofan simulations. Our evaluation results show that our proposals reduce the maintenance costs compared to existing solutions.

This paper presents the development of fleet management software for mobile robots, including AGV and AMR technologies, within the scope of a case study from the GreenAuto project. The system was designed to integrate position and status data from different robots, unifying this information into a single map. To achieve this, a web-based platform was developed to allow the simultaneous, real-time visualization of all robots in operation. However, the main challenge of this research lies in the heterogeneity of the fleet, which comprises robots of different makes and models from various manufacturers, each using distinct data formats. The proposed approach addresses this by facilitating fleet monitoring and management, ensuring a greater efficiency and coordination in the robot movement. The results demonstrate that the platform improves the traceability and operational supervision, promoting the optimized management of mobile robots. It is concluded that the proposed solution contributes to industrial automation by providing an intuitive and centralized interface, enabling future expansions for new functionalities and the integration with other emerging technologies. The proposed system demonstrated efficiency in updating and supervising operations, with an average latency of 120 ms for task status updates and an interface refresh rate of less than 1 s, enabling near real-time supervision and facilitating operational decision-making.

Fleet management systems (FMSs), as a pivotal part of any surface mining operation, need to evolve from conventional to intelligent systems because of both Mining 4.0 requirements and some shortcomings inherent in conventional methods. However, this novel transformation needs to be investigated technically and strategically. To this end, previously published research works on intelligent FMSs are explored to track the latest status of these third-generation frameworks within the surface mining context. Their underlying models are then compared in terms of five categories of allocation and dispatching features to pinpoint the technical gaps ignored. Having drawn the future lines of research, the present work then leverages the popular SWOT analysis method to outline the strengths, weaknesses, opportunities, and threats associated with the advent of these intelligent FMSs in mines of future. By and large, the analysis indicates that advantages outweigh disadvantages. Solutions are offered to address the existing weaknesses and threats.

Fleet Management System (FMS) is the latest system that helps manage the fleet of mining units to optimize productivity and avoid various problems, one of which is cycle time. The research uses data from the largest mining area in Berau city, Lati Open-pit Mining (LOM). This study aims to determine the effect model of meteorological parameters (8 parameters) and road conditions (hauling distance and road grade) on the travel time of dump trucks, as well as the effectiveness and validity level of machine learning (ML) in predicting travel time. The integration of dispatch data, meteorological data, and road condition data resulted in a modeling dataset for travel time prediction (TTP) training based on k -Nearest Neighbors (kNN), Support Vector Regression (SVR), and Long-Short Term Memory (LSTM). The Exploratory Data Analysis (EDA) process was carried out before ML prediction modeling; Hauling Distance (m) and Rain Intensity (mm/h) had a strong influence, with values of 0.41 and 0.52, respectively, on dump truck travel time. Model training was conducted in 4 quarters of 2023; Q1, Q2, Q3, and Q4, with the best hyperparameters. The results show that the ML prediction model with meteorological parameters and road conditions is more effective than the conventional prediction method, with an increased accuracy of 9.18%. The ML prediction model based on the LSTM algorithm has a validity rate of 86.31%, better than the SVR and kNN algorithms, which have an accuracy of 85.42% and 85.50%, respectively.

This paper presents a fleet management system (FMS) for multiple robots, utilizing deep reinforcement learning (DRL) for dynamic task allocation and path planning. The proposed approach enables robots to autonomously optimize task execution, selecting the shortest and safest paths to target points. A deep Q-network (DQN)-based algorithm evaluates path efficiency and safety in complex environments, dynamically selecting the optimal robot to complete each task. Simulation results in a Gazebo environment demonstrate that Robot 2 achieved a path 20% shorter than other robots while successfully completing its task. Training results reveal that Robot 1 reduced its cost by 50% within the first 50 steps and stabilized near-optimal performance after 1000 steps, Robot 2 converged after 4000 steps with minor fluctuations, and Robot 3 exhibited steep cost reduction, converging after 10,000 steps. The FMS architecture includes a browser-based interface, Node.js server, rosbridge server, and ROS for robot control, providing intuitive monitoring and task assignment capabilities. This research demonstrates the system’s effectiveness in multi-robot coordination, task allocation, and adaptability to dynamic environments, contributing significantly to the field of robotics.

Offshore oil and gas activities are crucial in the petroleum industry. Offshore oil and gas installations require different cargo to operate. A heterogeneous fleet of platform supply vessels (PSVs) transports cargo supply to installations. The PSV fleet management in Brazil faces challenges such as the non-availability of the spot market, variations and uncertainties in delivery order demands and due dates, inspection and corrective vessel maintenance, and multiple time windows for service at installations. PSV fleet management aims to satisfy cargo delivery requests in time and quantity, avoid delays, and achieve a balance among delivery service levels, vessel costs, and greenhouse gas emissions. We develop several PSV fleet management policies with delivery service level or fuel consumption goals, composed of new fleet management procedures such as vessel control, vessel assignment to voyages including cargo selection, vessel routing, speed selection, and dynamic re-routing. The results of tests on a real Brazilian case demonstrate that the developed policies with the incorporated fleet management procedures improve fleet performance indicators. The comparative analysis of policies shows their different impacts on indicators, allowing managers to select the best fleet management policy by considering the trade-offs between delivery service level, costs, and emissions, depending on their goals.

In this paper we formally introduce a generic real-time multivehicle truckload pickup and delivery problem. The problem includes the consideration of various costs associated with trucks' empty travel distances, jobs' delayed completion times, and job rejections. Although very simple, the problem captures most features of the operational problem of a real-world trucking fleet that dynamically moves truckloads between different sites according to customer requests that arrive continuously. We propose a mixed-integer programming formulation for the offline version of the problem. We then consider and compare five rolling horizon strategies for the real-time version. Two of the policies are based on a repeated reoptimization of various instances of the offline problem, while the others use simpler local (heuristic) rules. One of the reoptimization strategies is new, while the other strategies have recently been tested for similar real-time fleet management problems. The comparison of the policies is done under a general simulation framework. The analysis is systematic and considers varying traffic intensities, varying degrees of advance information, and varying degrees of flexibility for job-rejection decisions. The new reoptimization policy is shown to systematically outperform the others under all these conditions.

Electric vehicle (EV) chargers can be controlled to support the grid frequency by implementing a standard-compliant fast primary frequency control (PFC). This study addresses potential effects on power systems due to control discreteness in aggregated EVs when providing frequency regulation. Possible consequences of a discrete response, as reserve provision error and induced grid frequency oscillations, are first identified by a theoretical analysis both for large power systems and for microgrids. Thus, an EV fleet management solution relying on shifting the droop characteristic for the individual EVs is proposed. The PFC is implemented in a microgrid with a power-hardware-in-the-loop approach to complement the investigation with experimental validation. Both the analytical and the experimental results demonstrate how the controller performance is influenced by the response granularity, and that related oscillations can be prevented either by reducing the response granularity or by applying appropriate shifts on the droop characteristics for individual EVs.