https://mej.aut.ac.ir/ Amirkabir Journal of Mechanical Engineering en daily 1 Wed, 21 Jan 2026 00:00:00 +0330 Wed, 21 Jan 2026 00:00:00 +0330 https://mej.aut.ac.ir/article_6052.html In this article, the active vibration control of isotropic beams and smart composite box beams equipped with piezoelectric layers is investigated using fuzzy controllers. The main objective of the study is to present an efficient framework for vibration control of composite beams with arbitrary cross-sectional geometries and anisotropic materials. To this end, the dynamic behavior of the beams is extracted from the output of a non-classical model based on two-dimensional cross-sectional analysis. This approach preserves the accuracy of analyzing complex composite structures while significantly reducing the computational cost compared to full three-dimensional modeling, and provides a suitable platform for optimization problems. In the first stage, a smart Euler–Bernoulli beam equipped with piezoelectric layers was evaluated for preliminary simulation using three control approaches: fuzzy control, classical proportional–integral–derivative (PID) control, and fuzzy-tuned PID control. Subsequently, the smart composite beam was examined using the proposed non-classical model under both fuzzy and PID controllers. The uncoupled modal equations were derived based on the first mode shape of the beam and discretized in the time domain using the central difference method. Furthermore, the composite box beam model fully incorporates six degrees of freedom, all non-classical material and geometric couplings, and transverse shear effects without requiring complete three-dimensional modeling. The obtained results indicate effective reduction in vibrations, overshoot, and settling time. https://mej.aut.ac.ir/article_6054.html Accurate vehicle speed prediction leads to reduced energy consumption and increased safety of intelligent vehicles. Considering the data available in intelligent transportation systems and the capability of deep neural networks to exploit these data, an intelligent method for speed prediction using deep neural networks is proposed. Speed prediction is performed using the speed history of the target vehicle and its preceding vehicles. In order to increase prediction accuracy, an innovative method for normalizing vehicle speed data is introduced, which results in a reduction in prediction error. Furthermore, to address practical driving challenges, uncertainty in the amount of available speed history and the number of preceding vehicles is considered in the developed method. In this study, speed prediction is carried out with a very short time step, which, although it improves accuracy, increases the dimensionality of the problem and doubles the difficulty of the prediction task; an issue that has not been reported in previous studies. Real-world highway data are used to train the intelligent speed prediction models. The results show that the proposed method achieves higher accuracy, particularly in the initial time steps, and is free of offset. The mean absolute prediction error over a six-second horizon obtained using the proposed method is 0.2410 m/s, which indicates at least a 49.1% reduction compared to analytical models. https://mej.aut.ac.ir/article_6056.html Solar energy, as one of the most promising clean energy sources, plays a pivotal role in advancing sustainable development. Among the various solar thermal technologies, parabolic trough collectors (PTCs) are considered one of the most practical and efficient solutions for medium-temperature heat applications. In this study, the thermal performance of a parabolic trough solar collector was comprehensively analyzed using Computational Fluid Dynamics (CFD). The effects of key operational and geometric parameters including absorber tube rotational speed (10 and 15 rad/s), tube material (copper, brass, and nickel), and wall thickness (1.45–1.85 mm) were systematically examined in relation to the collector’s hydrodynamic and thermal behavior.The findings demonstrated that the rotation of the absorber tube predominantly influences the fluid layers adjacent to the wall. Increasing the rotational speed enhanced flow mixing, thereby improving heat transfer and overall thermal performance. Among the tested materials, the copper tube exhibited the highest thermal efficiency and outlet temperature under all operating conditions, owing to its superior thermal conductivity. Moreover, increasing the wall thickness led to a noticeable decline in heat transfer rate due to higher thermal resistance. This reduction was more significant for the nickel tube (25%) compared with the copper tube (7.7%). Overall, the study provides clear design guidelines and optimization insights for improving the efficiency and reliability of parabolic trough solar collectors. https://mej.aut.ac.ir/article_6060.html Accurate prediction of fatigue life in materials is a fundamental challenge in mechanical design since it strongly affects the safety, reliability, and maintenance cost of engineering structures. Traditional empirical and analytical fatigue models, while widely applied, often fail to capture nonlinear and multiaxial effects arising under variable loading conditions. In this study, a hybrid deep learning architecture is developed that integrates three complementary components: a fully connected (FC) network for static material features, a bidirectional long short term memory (Bi LSTM) network for sequential loading path, and a transformer encoder for multi path feature fusion and high level relational learning. Experimental stress–strain data were normalized and divided into training and testing sets, and the model was optimized using the Adam algorithm with a learning rate of 5×10⁻⁴ for 2000 epochs. Quantitative evaluation demonstrates that the proposed FC–BiLSTM–Transformer model achieves superior accuracy compared with five baseline networks, with MSE = 0.335, MAE = 0.1385, and R² = 0.9470. Physically, the model captures complex fatigue responses without empirical hypotheses, enabling data driven representation of material behavior. The developed framework provides a reliable computational tool for fatigue life estimation and can be extended to complex materials and multiaxial loading conditions in aerospace and automotive applications. https://mej.aut.ac.ir/article_6061.html This study presents a hybrid control framework for the attitude regulation of a three-degree-of-freedom satellite subject to parametric uncertainties, external disturbances, actuator constraints, and implementation imperfections. The core robust controller is formulated using the Super-Twisting Algorithm, which guarantees finite-time convergence and robustness while effectively suppressing the high-frequency chattering typically associated with conventional sliding mode control. To enhance tracking precision and improve adaptability under nonlinear and uncertain conditions, deep reinforcement learning is incorporated as an adaptive compensator within the control loop. Three representative algorithms, namely Deep Deterministic Policy Gradient, Twin Delayed Deep Deterministic Policy Gradient, and Proximal Policy Optimization, are investigated and comparatively evaluated in terms of stability, convergence behavior, and control efficiency. To systematically tune the learning hyperparameters and reduce the computational burden associated with manual trial-and-error procedures, the Taguchi design of experiments method is employed to perform multi-objective optimization considering both tracking performance and control effort. The performance index is defined as a composite measure that combines time-weighted tracking error and control energy. Numerical simulations together with experimental validation on a satellite attitude simulator demonstrate that the proposed hybrid control architecture reduces settling time and control effort while improving disturbance rejection capability, without compromising stability or steady-state tracking accuracy. https://mej.aut.ac.ir/article_6062.html در پژوهش حاضر، عملکرد آیرودینامیکی یک بال با لبه‌ی حمله‌ی سینوسی در جریان غیرقابل‌تراکم به صورت عددی بررسیشده است. هدف اصلی مطالعه تحلیل اثر موج سینوسی بر رفتار جریان و ضرائب آیرودینامیکی در مقایسه با بال ساده است. شبیه‌سازی‌ها با استفاده از نرم‌افزار تجاری فلوئنت مبتنی بر مدل حجممحدود و مدل آشفتگی SSTk-ω انجام شده است. برای ارزیابی اثرات هندسی، شش پیکربندی مختلف دامنه وطول‌موج‌های گوناگون طراحی و تحلیل شدند. نتایج اولیه نشان داد یکی از این پیکربندی‌ها (دارای بزرگ‌ترین دامنه) عملکرد آیرودینامیکی بهتری، به ویژه پس از واماندگی، دارد. بنابراین، این مدل به طور تفصیلی‌تر با مدل بال پایه مقایسه شد. یافته‌ها نشان می‌دهد که لبه حمله موج‌دار موجب تاخیر در جدایش جریان، بهبود پایداری ساختارهای گردابه‌ای سطح بال و انتقال ناحیه واماندگی به زوایای حمله بالاتر می‌شود. از طرف دیگر، ضریب برآی بیشینه حدود ۱۰ درصد نسبت به بال پایه افزایش می‌یابد. علاوه بر این، نتایج نشان می‌دهد که استفاده از لبه موج‌دار می‌تواند موجب کاهش جزئی ضریب پسا و بهبود نسبت برآ به پسا در محدوده‌ای از زوایای حمله شود. تحلیل خطوط همتراز سرعت و توزیع فشار نیز تشکیل جریان‌های عرضی منظم و توزیع یکنواخت‌تر آشفتگی در راستای دهانه بال را تایید می‌کند. نتایج نشان می‌دهد که در مجموع به‌کارگیری موج سینوسی روی لبه حمله، می‌تواند بهبود قابل توجهی در عملکرد آیرودینامیکی بال در رژیم‌های جریان با عدد رینولدز پایین ایجاد کند.