Browsing by Department "Zhejiang University of Science and Technology"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Optimized Design and Thermal Analysis of Printed Magnetorquer for Attitude Control of Reconfigurable Nanosatellites
    (IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2020-02) Mughal, M. R.; Ali, H.; Ali, A.; Praks, J.; Reyneri, L. M.; Jaan Praks Group; Institute of Space Technology, Islamabad; Zhejiang University of Science and Technology; Department of Electronics and Nanoengineering; Politecnico di Torino
    An attitude control system (ACS) is one of the critical subsystems of any spacecraft and typically is in charge of de-tumbling, controlling, and orienting the satellite after initial deployment and during the satellite operations. The magnetorquer is a core magnetic attitude control actuator and, therefore, a good choice for nanosatellite attitude stabilization. There are various methods to achieve control torque using the magnetorquer. An innovative design of a printed magnetorquer has been proposed for the nanosatellites, which is modular, scalable, cost effective, less prone to failure, with reduce harness and power consumption since the traces are printed either on the top layer or inner layers of the printed circuit board. The analysis in terms of generated torque with a range of input applied voltages, trace widths, outer and inner-most trace lengths is presented to achieve the optimized design. The optimum operating voltage is selected to generate the desired torque while optimizing the torque to the power ratio. The results of the analysis in terms of the selection of optimized parameters, including torque to power ratio, generated magnetic dipole moment, and power consumption, have been validated practically on a CubeSat panel. The printed magnetorquer configuration is modular which is useful to achieve mission level stabilization requirements. For spin-stabilized satellites, the rotation time analysis has been performed using the printed magnetorquer.
  • No Thumbnail Available
    Item
    Short-term traffic flow prediction based on whale optimization algorithm optimized BiLSTM_Attention
    (JOHN WILEY & SONS, 2022-05-01) Xu, Xing; Liu, Chengxing; Zhao, Yun; Lv, Xiaoshu; Zhejiang University of Science and Technology; Structures – Structural Engineering, Mechanics and Computation; Department of Civil Engineering
    With the growths in population and vehicles, traffic flow becomes more complex and uncertain disruptions occur more often. Accurate prediction of urban traffic flow is important for intelligent decision-making and warning, however, remains a challenge. Many researchers have applied neural network methods, such as convolutional neural networks and recurrent neural networks, for traffic flow prediction modeling, but training the conventional network that can obtain the best network parameters and structure is difficult, different hyperparameters lead to different network structures. Therefore, this article proposes a traffic flow prediction model based on the whale optimization algorithm (WOA) optimized BiLSTM_Attention structure to solve this problem. The traffic flow is predicted first using the BiLSTM_Attention network which is then optimized by using the WOA to obtain its four best parameters, including the learning rate, the training times, and the numbers of the nodes of two hidden layers. Finally, the four best parameters are used to build a WOA_BiLSTM_Attention model. The proposed model is compared with both conventional neural network model and neural network model optimized by the WOA. Based on the evaluation metrics of MAPE, RMSE, MAE, and R2, the WOA_BiLSTM_Attention model proposed in this article presents the best performance.