Selection of an unmanned aerial vehicle for the Brazilian Navy: novel approach for decision support through unsupervised machine learning

Recently, Unmanned Aerial Vehicles (UAV) become a significant research area due to their multiple domains of applications such as: search and rescue operations, aerial surveying of crops, inspecting power lines and pipelines, delivering medical supplies to remote or otherwise inaccessible regions. However the UAV performances (such as autonomy, endurance, maximum flight altitude, maximum takeoff weight, maximum speed etc) depend mainly on its energy storage system (batteries, fuel cells, ultra capacitors). The more the drone’s complexity grows the more energy it consumes. In this paper we will discuss the different electrical architecture used in UAV and we’ll propose a hybrid solution that optimizes the energy consumption for multi-rotor.

The legal regulation, and hence, the training system in the field of unmanned aircraft systems (UAS) in the Russian Federation, the European Union and the United States is based on the unmanned aerial vehicles (UAV) rating with respect to UAS maximum take-off weight (MTOW) and their purpose (method of use). In this regard, small-unmanned aircraft (sUAS) are identified – in our country up to 30 kg, in the EU and the USA up to 55 lbs (25 kg) and UAV with larger weight. In the USA and Europe, the training of remote pilots for sUAS is differentiated based on the degree of risk that UAV can represent for public safety. Thus, the training of remote pilots to use UAVs with MTOW less than 25 kg (55 lbs) in a sparsely populated area during daylight hours under the conditions of visual range is conducted in the online format, the result of which is taking tests. In the United States and Europe, the UAV application with MTOW more than 25 kg (55 lbs) or performing UAV operations, presenting a potential risk for public safety, requires more comprehensive and long-term training of remote pilots. In the Russian Federation, UAS personnel training is conducted in educational organizations according to different programs, which vary significantly depending on a specific type of aviation UAVs refers to: State, Civil or Experimental. UAS personnel training programs for various aviation types are not harmonized, which leads to the failure to credit previously received education in training to perform activities in another aviation type. The article describes the analysis results of the international and national experience, perspectives for the development of the UAS personnel training system, as well as formulates the proposals concerning further development of the national system for UAS specialists training.

One of the most significant disadvantages of electric multirotor unmanned aerial vehicles is their short flight time compared to fuel-powered unmanned aerial vehicles. This is mainly due to the low energy density of electric batteries. Fuel has much more energy density when compared to batteries. Electric-powered motors in multirotor unmanned aerial vehicles cannot be replaced with fuel-based engines because the stability and control of multirotor unmanned aerial vehicles rely on the high response rates of electric motors. One of the possible solutions to overcome this problem of short endurance times is by using hybrid thrusting systems that combine the advantages of both fuel and electrical propulsion systems, where high maneuverability and long endurance flight time could be achieved. In this work, hybrid thrusting and power systems for multirotor unmanned aerial vehicles are studied. Targeted hybrid thrusting systems consist of combustion engines, electric motors, and their power sources. Then a hybrid thrusting system-based quadrotor unmanned aerial vehicle model is developed. The article presents the altitude and attitude control systems of the developed hybrid thrusting system-based unmanned aerial vehicle. The presented hybrid quadcopter model comprises four electric motors and one fuel engine. The fuel engine used in this work is a 4.07 cc internal combustion engine targeting 2–3 kg unmanned aerial vehicles with up to 5 kg maximum takeoff weight. The developed hybrid quadrotor unmanned aerial vehicle achieved a 139% improvement in flight time when compared with traditional electric-based quadrotor unmanned aerial vehicles. The article also reports on other flight time-related issues such as the optimal fuel mass to battery size ratio to maximize the endurance time of the quadrotor unmanned aerial vehicles.

Unmanned aerial vehicles (UAV) have become an important part of aerial carrier for various missions. As for flight safety concerns, UAV has much less reliability and less stability comparing to general categories of transportation passenger aircraft. In order to operate UAVs into National Airspace System (NAS), general criteria to show how the UAVs can be operated at a satisfactory level of safety. Based on the UAV development, it is difficult to establish an equivalent level of safety to the general categories of aircraft. Although the flight risk to the ground is relatively low, once any accidents may cause catastrophic casualties to human life. This study uses a simulator to assess the crashing probability density and presents an adaptive set of the clearance region. The UAV specifications by different classifications, such as wing dimension, power plant, fuel capacity and maximum take-off weight, are selected as parameters in consideration for simulation. The crash scenarios of lose power, lose control, spiral drop and fuselage damage are simulated to find the probability of impact to ground objects and human beings. The results can be used to construct a UAV flight mission by combining with a path planning algorithm to keep off potentially high populated areas. The intended use of the tool is discussed and the adaptive clearance region is assessed by a chosen UAV.

With the increasing complexity of unmanned aerial vehicle (UAV) missions, single-objective optimization for UAV trajectory planning proves inadequate in handling multiple conflicting objectives. There is a notable absence of research on multi-objective optimization for UAV trajectory planning. This study introduces a novel two-stage co-evolutionary multi-objective evolutionary algorithm for UAV trajectory planning (TSCEA). Firstly, two primary optimization objectives were defined: minimizing total UAV flight distance and obstacle threats. Five constraints were defined: safe distances between UAV trajectory and obstacles, maximum flight altitude, speed, flight slope, and flight corner limitations. In order to effectively cope with UAV constraints on object space limitations, the evolution of the TSCEA algorithm is divided into an exploration phase and an exploitation phase. The exploration phase employs a two-population strategy where the main population ignores UAV constraints while an auxiliary population treats them as an additional objective. This approach enhances the algorithm’s ability to explore constrained solutions. In contrast, the exploitation phase aims to converge towards the Pareto frontier by leveraging effective population information, resulting in multiple sets of key UAV trajectory points. Three experimental scenarios were designed to validate the effectiveness of TSCEA. Results demonstrate that the proposed algorithm not only successfully navigates UAVs around obstacles but also generates multiple sets of Pareto-optimal solutions that are well-distributed across objectives. Therefore, compared to single-objective optimization, TSCEA integrates the UAV mathematical model comprehensively and delivers multiple high-quality, non-dominated trajectory planning solutions.

Fixed-wing vertical take-off and landing (VTOL) unmanned aerial vehicle (UAV)s are designed to combine the advantages of multi-rotor UAVs and fixed-wing UAVs in different flight phases in a single UAV. Fixed-wing VTOL UAVs can achieve the mobility of multi-rotor UAVs in hovering, vertical take-off and landing flight phases. Since fixed-wing UAVs are known for their efficiency in power consumption, fixed-wing VTOL UAVs were created to efficiently perform the cruise phase of the flight for a similar reason. In this paper, we made the conceptual design of a fixed-wing VTOL UAV which is called “DOGA”. The mission of DOGA is to carry 0.5 kg. payload. Firstly, maximum take-off weight was calculated, and then the airfoil profile, wings geometry, and the propulsion systems were determined. Also, design and performance parameters of DOGA were calculated. As a result, conceptual design of DOGA was completed and all the needed parameters for the detail design of the fixed-wing VTOL UAV were derived.

Existing mathematical design models for small solar-powered electric unmanned aerial vehicles (UAVs) only focus on mass, performance, and aerodynamic analyses. Presently, UAV designs have low endurance. The current study aims to improve the shortcomings of existing UAV design models. Three new design aspects (i.e., electric propulsion, sensitivity, and trend analysis), three improved design properties (i.e., mass, aerodynamics, and mission profile), and a design feature (i.e., solar irradiance) are incorporated to enhance the existing small solar UAV design model. A design validation experiment established that the use of the proposed mathematical design model may at least improve power consumption-to-take-off mass ratio by 25% than that of previously designed UAVs. UAVs powered by solar (solar and battery) and nonsolar (battery-only) energy were also compared, showing that nonsolar UAVs can generally carry more payloads at a particular time and place than solar UAVs with sufficient endurance requirement. The investigation also identified that the payload results in the highest effect on the maximum take-off weight, followed by the battery, structure, and propulsion weight with the three new design aspects (i.e., electric propulsion, sensitivity, and trend analysis) for sizing consideration to optimize UAV designs.

The climb rate and climb gradient of small fixed-wing Unmanned Aerial Vehicles (UAVs), characterized by extremely compact and lightweight design, are typically limited by the maximum allowable temperature of the engine cylinder head, especially in hot environment conditions. The problem is often overcome by alternating climb and levelled flight phases to let the engine cool down, but the resulting performances are far from satisfactory. This paper aims to evaluate the feasibility of a reconfigurable hybrid propulsion system based on the integration of the UAV internal combustion engine with its electric generator, temporarily (during climb) converted into motor and supplied by the battery pack, to maintain/boost the propeller thrust while reducing the combustion engine temperature. With reference to the lightweight surveillance UAV Rapier X-25 (maximum take-off weight up to 25 kg) by Sky Eye Systems (Italy), a detailed nonlinear model of the reconfigurable hybrid propulsion system is developed and coupled with the models of the propeller and the vehicle flight dynamics. The system dynamic performances during severe climb manoeuvres are thus characterized, by demonstrating that the proposed solution can both improve the UAV climb rate and, by reducing the combustion engine power request, limit the temperature increase of the cylinder head.

This work describes the development of a multipurpose aerial platform using UAV (Unmanned Aerial Vehicle) for tactical surveillance of maritime vessels. By means of a portable control station on the vessel, UAV can be remotely operated. The aircraft is a gas prop medium sized high wing UAV, pusher configuration, wingspan of 4.5 meters, 98 kg MTOW (Maximum Takeoff Weight), flight autonomy of 8 hours (typical) and cruise speed of 100 km/h. The UAV design uses a modular concept, in terms of payload and airframe.

Electrified propulsion offers high efficiency, scalability, and high power discharge capability which can be utilized for increased agility and directed energy applications in unmanned aerial vehicles (UAV). However, the limited energy density of state-of-the-art batteries creates a technological bottle-neck, penalizing the payload and range capabilities compared to conventional propulsion aircraft. This paper is a part of a series of publications that aim to design, assess, and compare various electrified propulsion system architectures on a common UAV testbed. In this paper, a hybrid partial turboelectric distributed propulsion (HPTeDP) system and its thermal management system were designed and analyzed. The battery was managed as a supplementary energy source used only during certain mission segments that require high power. A thermal management system was designed to manage the excess heat generation from the onboard battery, generator, and electric motors. The HPTeDP and thermal management systems were sized under the fixed geometry, maximum takeoff weight and point performance requirements of the conventional testbed. The payload-range capability of the HPTeDP UAV was compared to the conventional, series distributed and turboelectric distributed UAVs designed under the same requirements used in previous studies.

Unmanned aerial vehicle (UAV) swarms must exploit machine learning (ML) in order to execute various tasks ranging from coordinated trajectory planning to cooperative target recognition. However, due to the lack of continuous connections between the UAV swarm and ground base stations (BSs), using centralized ML will be challenging, particularly when dealing with a large volume of data. In this paper, a novel framework is proposed to implement distributed federated learning (FL) algorithms within a UAV swarm that consists of a leading UAV and several following UAVs. Each following UAV trains a local FL model based on its collected data and then sends this trained local model to the leading UAV who will aggregate the received models, generate a global FL model, and transmit it to followers over the intra-swarm network. To identify how wireless factors, like fading, transmission delay, and UAV antenna angle deviations resulting from wind and mechanical vibrations, impact the performance of FL, a rigorous convergence analysis for FL is performed. Then, a joint power allocation and scheduling design is proposed to optimize the convergence rate of FL while taking into account the energy consumption during convergence and the delay requirement imposed by the swarm's control system. Simulation results validate the effectiveness of the FL convergence analysis and show that the joint design strategy can reduce the number of communication rounds needed for convergence by as much as 35% compared with the baseline design.

The engine performance test at altitudes of 0-7000 m was carried out on the high-performance test bench of the Unmanned Aerial Vehicle (UAV) piston engine. The flight performance of UAV was studied, including propeller thrust characteristics, maneuverability, flight envelope, and cruise performance. The results showed that with the increase in altitudes, the UAV climb rate gradually decreased; the maximum climb rate decreased from 2.5 m/s at 2000 m to 0.5 m/s at 7000 m. The maximum flight altitude is 7000 m, and the flight speed range is about 47 m/s-52 m/s at the altitude of 7000 m. Maximum navigation range and endurance of UAV decrease by 5.8% and 8%, respectively, with each increment of 1000 m in altitudes.

The usage of unmanned aerial vehicles (UAVs) is rapidly increasing in the current era as these devices are capable enough in providing unique solutions in applications such as inspection of environment, identification of disaster, rescue operations, and defense systems. For the governance of the flight missions in a complex defense environment, the usage of these systems necessitated a sound command over data mining process. The large volume of data is generated by UAVs and processing of this data is a challenging issue. The existing data tracking and management systems are expensive and complex. For defense systems, smarter solutions are needed to process the large volume of data at low cost and with high accuracy. Therefore, a technique of tracking the data generated by UAV and automatic measurement of trajectory based on micro-electro-mechanical systems sensor in UAV has been proposed in this paper to provide inexpensive solutions to overcome the problems of the existing data tracking and processing systems. An iterative learning control algorithm is utilized in UAV to ascertain the disturbance and modeling errors. The finest characteristics of the Kalman filter technique are used for estimations of UAV trajectory. The quadratic performance function is introduced in discrete equation to solve the model error disturbance. Then on the basis of gyroscope data, the quaternion differential equation is formulated. The gradient descent process is also used to speed up the processing of UAV data. The results depict that the proposed technique has the lowest data tracking error of the UAV trajectory (0.09%) and has good measurement accuracy of 92%. The proposed method also reduces time complexity and searches the solution space in a faster manner.

This paper presents the conceptual design and multidisciplinary analysis of a Medium-Altitude Long-Endurance (MALE) Unmanned Aerial Vehicle (UAV) featuring a hybrid Vertical Take-Off and Landing (VTOL) and fixed-wing configuration. The design is driven by demanding mission requirements, including a 650 kg maximum take-off weight, a 100 kg payload capacity, a 200 km operational range, and an endurance of 10 hours at altitudes up to 7000 meters. The proposed twin-boom aircraft integrates an eight-rotor electric VTOL system for vertical flight and a conventional internal combustion engine (Rotax 914 ULF) for efficient forward cruise. The design process followed a systematic approach, beginning with initial sizing and weight estimation using empirical relations from Raymer's methodology, which established a baseline weight distribution. Constraint analysis identified the VTOL-to-cruise transition phase as the most critical, governing the thrust-to-weight ratio and wing loading. Aerodynamic design focused on the high-lift S1223 airfoil, with performance analyzed using XFLR5 and OpenVSP software to optimize the lift-to-drag ratio. Stability and control analysis were conducted to determine the optimal tail arm length of 3.85 meters, ensuring longitudinal and lateral stability, with the vertical stabilizer airfoil selection (NACA 0020) proving crucial for directional stability. Key results demonstrate a feasible design with an empty weight of 352 kg, a fuel weight of 185 kg, and a calculated cruise power requirement of 26 kW. The VTOL system requires a peak power of approximately 233 kW, met by eight 30 kW electric motors. The study concludes that the proposed VTOL fixed-wing UAV successfully balances the competing demands of vertical flight capability and long-endurance cruise performance. The insights and methodologies presented provide a robust foundation for future detailed design, prototyping, and flight testing of advanced hybrid UAVs.

A review of GNSS-independent UAV navigation techniques