Our objective in this work is to demonstrate how physics-informed neural networks, a type of deep learning technology, can be utilized to examine the mechanical properties of a helicopter blade. The blade is regarded as a one-dimensional prismatic cantilever beam that is exposed to triangular loading, and comprehending its mechanical behavior is of utmost importance in the aerospace field. PINNs utilize the physical information, including differential equations and boundary conditions, within the loss function of the neural network to approximate the solution. Our approach determines the overall loss by aggregating the losses from the differential equation, boundary conditions, and data. We employed a physics-informed neural network (PINN) and an artificial neural network (ANN) with equivalent hyperparameters to solve a fourth-order differential equation. By comparing the performance of the PINN model against the analytical solution of the equation and the results obtained from the ANN model, we have conclusively shown that the PINN model exhibits superior accuracy, robustness, and computational efficiency when addressing high-order differential equations that govern physics-based problems. In conclusion, the study demonstrates that PINN offers a superior alternative for addressing solid mechanics problems with applications in the aerospace industry.

This research addresses the imperative challenge of a lightweight design for an Unmanned Aerial Vehicle (UAV) chassis to enhance the thrust-to-weight and power-to-weight ratios, crucial for optimal flight performance, focused on developing an intriguing lightweight yet robust quadcopter chassis. Advanced generative design techniques, integrated with topology optimization, using Autodesk Fusion 360 software (v. 16.5. 0.2083), 3D-printing methods and lightweight materials like Polylactic Acid (P.L.A.), Acrylonitrile Butadiene Styrene (A.B.S.), and Nylon 6/6 play a significant role in achieving the desired balance between structural integrity and weight reduction. The study showcases successful outcomes, presenting quadcopter chassis designs that significantly improve structural efficiency and overall performance metrics. The findings contribute to aerial robotics and hold promise for precision agriculture applications with relevant performed simulations, emphasizing the importance of tailored design methodologies for other engineering domains. In conclusion, this research provides a foundational step toward advancing drone technology, with weight reductions of almost 50%, P/W and T/W ratios increment of 6.08% and 6.75%, respectively, at least an 11.8% increment in Factor of Safety, at least a 70% reduction in stress values and reduced manufacturing time from its comparative DJI F450 drone, demonstrating the critical role of innovative design approaches in optimizing operational efficiency for targeted applications.

An aeroelastic analysis is used to investigate the rate dependent hysteresis in piezoceramic actuators and its effect on helicopter vibration control with trailing edge flaps. Hysteresis in piezoceramic materials can cause considerable complications in the use of smart actuators as prime movers in applications such as helicopter active vibration control. Dynamic hysteresis of the piezoelectric stack actuator is investigated for a range of frequencies (5 Hz (1/rev) to 30 Hz (6/rev)) which are of practical importance for helicopter vibration analysis. Bench top tests are conducted on a commercially available piezoelectric stack actuator. Frequency dependent hysteretic behavior is studied experimentally for helicopter operational frequencies. Material hysteresis in the smart actuator is mathematically modeled using the theory of conic sections. Numerical simulations are also performed at an advance ratio of 0.3 for vibration control analysis using a trailing edge flap with an idealized linear and a hysteretic actuator. The results indicate that dynamic hysteresis has a notable effect on the hub vibration levels. It is found that the theory of conic sections offers a straight forward approach for including hysteresis into aeroelastic analysis.

Bird wings demonstrate phenomenal adaptation and aerodynamic performance across varied flight conditions. In contrast, conventional aircraft wings are designed for specific scenarios, limiting their adaptability. Therefore, the integration of smart cellular structures into morphing airfoils is crucial for furthering aircraft development. This entails integrating actuators, sensors, and innovative control systems to modernize aircraft engineering. One intriguing approach is adopting a re-entrant arrangement which exhibits a negative Poisson’s ratio, popularly known as auxetic behaviour. This particular trait can bring substantial advantages to the morphing process. Morphing airfoils containing an auxetic core offer various benefits, including greater deformability, ease of control, variable stiffness, and improved stress tolerance. This research provides a novel approach by discovering the optimal re-entrant unit cell and extending its key advantage within the aerospace sector, focusing on achieving maximal wing trailing edge deflection. The paper explores the in-plane characteristics of a 2D re-entrant auxetic structure and evaluates the consequences of parameter changes on the structure’s negative Poisson ratio. Through multi-objective optimisation employing a genetic algorithm, the study achieves a remarkable 99.53 % enhancement in Poisson’s ratio and a substantial 158.70 % rise in the relative elastic modulus, as evaluated analytically. Further, Finite element analysis (FEA) of the Eppler 420 airfoil reveals that integrating the improved re-entrant core within the airfoil leads to a significant augmentation of 63.56 % in trailing edge deflection compared to past research. This research emphasizes the potential of adopting optimised re-entrant structures to boost the performance and adaptability of aircraft wings.

Our objective in this work is to demonstrate how Physics-Informed Neural Networks, a type of deep learning technology, can be utilized to examine the mechanical properties of a helicopter blade. The blade is regarded as a prismatic cantilever beam that is exposed to triangular loading, and comprehending its mechanical behavior is of utmost importance in the aerospace field. PINNs utilize the physical information, including differential equations and boundary conditions, within the loss function of the neural network to approximate the solution. Our approach determines the overall loss by aggregating the losses from the differential equation, boundary conditions, and data. We employed a Physics-Informed Neural Network (PINN) and an Artificial Neural Network (ANN) with equivalent hyperparameters to solve a fourth-order differential equation. By comparing the performance of the PINN model against the analytical solution of the equation and the results obtained from the ANN model, we have conclusively shown that the PINN model exhibits superior accuracy, robustness, and computational efficiency when addressing high-order differential equations that govern physics-based problems. In conclusion, the study demonstrates that PINN offers a superior alternative for addressing solid mechanics problems with applications in the aerospace industry.