González Mendoza, Manuel A.
Preferred name
González Mendoza, Manuel A.
Official Name
González Mendoza, Manuel Alejandro
Alternative Name
manuelgonzalez
Main Affiliation
Scopus Author ID
57226730184
4 results
Now showing 1 - 4 of 4
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Aerodynamic drag reduction strategies for box-shaped payloads in delivery drones: a multimodal experimental study(American Institute of Aeronautics and Astronautics, 2026-01-08)This work presents a multimodal aerodynamic evaluation methodology integrating computational fluid dynamics (CFD), wind-tunnel testing, and full-scale flight experiments to characterize the aerodynamic behavior of standardized box-shaped payloads carried by multirotor unmanned aerial vehicles (UAVs). Three representative configurations—a baseline parcel, a front-fairing modification, and a combined fairing–boat-tail arrangement—were examined to demonstrate the methodology. Across all phases, environment-specific corrective procedures were implemented to address the limitations of each evaluation mode, including turbulence-model verification in CFD, moving-average force filtering in wind-tunnel testing at reduced Reynolds number, and atmospheric-density correction, stabilizer-tail implementation, and force-vector alignment correction with independent measurement of UAV and payload pitch angles during flight. These corrective steps minimized the influence of environmental variability, scale effects, and dynamic flight behavior, allowing the aerodynamic characteristics of each configuration to emerge consistently across the three platforms. Cross-validation across CFD, wind-tunnel, and flight testing showed close agreement in configuration-dependent aerodynamic trends, with all three phases reproducing similar variations in drag coefficient C_D and comparable drag-reduction performance C_(D,RED). The results demonstrate that the proposed multimodal methodology provides a robust and physically consistent framework for assessing UAV payload aerodynamics and establishes a foundation for future studies evaluating additional payload configurations and aerodynamic devices. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Time Management of Modes of Operation for Survival of a Satellite Mission: Power Simulation in MATLAB and STK(2021); ; Scopus© Citations 1 13 1 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Deploying Real-Time Speech Recognition on ESP32 Using TinyML and Edge Impulse(Springer Nature Switzerland, 2025); ; The emergence of Tiny Machine Learning (TinyML) has enabled real-time on-device inference on ultra-low-power microcontrollers, eliminating reliance on cloud computing while significantly reducing latency, power consumption, and bandwidth requirements. This study explores the deployment of a TinyML-based speech recognition system on an ESP32 microcontroller, leveraging Edge Impulse for model development, Mel-Frequency Cepstral Coefficients (MFCCs) for feature extraction, and TensorFlow Lite for Microcontrollers (TFLM) for efficient inference. The model was trained on a curated subset of the Google Speech Commands Dataset, incorporating background noise augmentation to enhance robustness in real-world environments. Using Edge Impulse’s EON Compiler, the model was fully quantized and optimized, achieving a 37% reduction in RAM usage and 27% in ROM. The final model attained 87.14% accuracy on testing data and 97.1% average classification confidence during real-time inference, with excellent noise rejection (99.6%) and latency of 266 ms. Compared to state-of-the-art systems deployed on more powerful platforms, the proposed approach achieves competitive accuracy while maintaining real-time inference and minimal resource consumption on ultra-low-power hardware. This makes it particularly suitable for battery-powered IoT, robotics, and embedded automation applications where connectivity and energy efficiency are critical. By balancing performance and efficiency, this research highlights the viability of deploying speech recognition systems on constrained microcontrollers. Future work will explore advanced architectures and enhanced feature extraction strategies to further improve recognition accuracy, especially for short or phonetically similar commands. ©The authors ©Springer. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Design of an Electric Vehicle Accumulator with LiFePO<sub>4</sub> Batteries for Green Transportation(2021); Scopus© Citations 4 10 1