Profile:
At the MEAS division, we leverage artificial intelligence (AI) and computational modeling to enhance real-time decision-making, improve system efficiency, and drive innovation in engineering, energy systems, and autonomous technologies. By integrating AI-driven algorithms, deep learning models, sensor fusion techniques, and computational fluid dynamics (CFD), we develop robust, data-driven solutions that address complex challenges across multiple domains.
Our work bridges the gap between theoretical advancements and practical applications, focusing on the development of intelligent control systems, predictive analytics, and real-time optimization strategies. We specialize in cross-disciplinary AI applications, combining physics-based simulations with data-driven methodologies to improve system performance, enhance safety, and support the next generation of smart technologies.
Our Computational Modeling & AI research is structured around several key areas, including AI-enhanced power grids, sensor fusion, battery state estimation, and CFD-driven system optimization. These areas enable us to push the boundaries of efficiency, automation, and precision in fields such as renewable energy, robotics, automotive engineering, and industrial process optimization.
Key Areas of Expertise:
Computational Fluid Dynamics (CFD) for System Optimization:
At MEAS, we employ Computational Fluid Dynamics (CFD) as a powerful tool for analyzing, predicting, and optimizing fluid flow behavior in a wide range of engineering applications. Our research focuses on improving the efficiency, thermal performance, and reliability of rotating machinery, heat exchangers, cooling systems, and energy storage solutions by leveraging high-fidelity simulations and modeling techniques.
Our expertise in CFD-driven system optimization enables us to:
- Enhance the thermal management of high-performance rotating machinery such as electric motors, turbines, and compressors by optimizing cooling channels, fluid circulation, and heat dissipation mechanisms.
- Develop innovative heat exchanger designs that maximize heat transfer efficiency while minimizing pressure losses, improving energy conservation in industrial applications.
- Optimize airflow and cooling strategies in battery packs, power electronics, and electric vehicle (EV) drivetrains, extending battery life and improving overall thermal stability.
- Improve industrial process cooling solutions by analyzing flow distribution, turbulence effects, and heat dissipation patterns to ensure consistent performance under dynamic operating conditions.
Autonomous Navigation & Sensor Fusion:
Our research team is developing AI-driven solutions for sensor fusion by integrating Real-Time Kinematic (RTK) positioning and Inertial Measurement Unit (IMU) data to enhance navigation accuracy. RTK provides precise geolocation by correcting GPS errors through differential calculations, while IMU sensors capture high-frequency motion data to compensate for temporary GPS signal loss.
By leveraging Kalman filters, deep learning techniques, and advanced cross-domain AI fusion algorithms, we optimize the synchronization and processing of these datasets, significantly reducing positioning errors. This approach is particularly beneficial in GPS-challenged environments such as urban canyons, tunnels, and dense forests, where traditional navigation systems struggle with accuracy.
Our fusion methods improve real-time localization in autonomous vehicles, UAVs, robotic systems, precision agriculture, and surveying applications, ensuring safe, reliable, and efficient autonomous operations. The core objective of our research is to develop robust AI-driven fusion techniques that enhance positioning reliability and adaptability in real-world dynamic scenarios.
AI in Grid Protection:
At MEAS, we are advancing fault detection in distributed low-voltage DC grids using artificial intelligence techniques. With the rapid expansion of renewable energy sources and modern electronic systems, the demand for robust, efficient, and intelligent DC power grids is increasing. However, conventional fault detection methods often struggle to cope with the complex dynamics and variability of these networks, leading to delays in fault identification and increased system vulnerability.
Our research focuses on developing AI-driven adaptive algorithms that enable real-time system monitoring, rapid anomaly detection, and precise fault localization. By analyzing voltage fluctuations, current patterns, and environmental factors, our methodology enhances grid resilience, minimizes operational interruptions, and optimizes the performance of modern energy infrastructures.
Through this work, we contribute to the development of intelligent, self-healing power systems capable of efficiently managing dynamic energy demands while ensuring sustainability, reliability, and adaptability in next-generation electrical grids.
Battery Health Monitoring & AI-driven Estimation:
At MEAS, we employ neural networks and AI-based models to estimate the State-of-Charge (SOC) and State-of-Health (SOH) of lithium-ion batteries, ensuring real-time monitoring and predictive maintenance. Traditional battery monitoring methods often struggle with accuracy and responsiveness, particularly in dynamic operating conditions such as electric vehicles (EVs) and large-scale energy storage systems.
Our AI-driven approach analyzes voltage, current, temperature, and internal resistance data, using machine learning algorithms to detect performance degradation, predict remaining battery life, and optimize energy management strategies. By integrating real-time data processing with predictive analytics, we help prevent overcharging, deep discharging, and capacity loss, ultimately extending battery lifespan and efficiency.
This research is of high significance for improving the reliability and sustainability of next-generation energy storage solutions, supporting the widespread adoption of electric mobility and renewable energy integration. Through AI modeling, we enable smarter battery management systems (BMS) that enhance safety, cost-effectiveness, and overall system performance.