Sort by
Refine Your Search
-
Category
-
Program
-
Field
-
on Artificial Intelligence (AI), Deep Reinforcement Learning (DRL), and Predictive Maintenance for optimizing wind turbine performance and reliability. This research will develop an AI-powered wind turbine
-
operating filters. Quantify operational performance including headloss recovery, filtrate turbidity, biological stability and lifecycle carbon—using high-resolution sensor data and life-cycle assessment tools
-
required to have high performance, vacuum-based, insulation and integrate equipment capable of surviving this challenging environment. This adds weight and is one of the big challenges for aircraft
-
diagnostic capabilities. The skills and knowledge gained will be transferable to other applications requiring high-performance radiation detection and advanced material interfaces. Through
-
sensors, firmware-controlled automation, wireless connectivity, and maintenance algorithms. Students will design, build, and test smart sanitation solutions that can monitor system performance, optimize
-
profoundly affect their mechanical properties and overall performance. Therefore, understanding the temperature field and developing effective thermal control techniques are vital to ensuring a high-quality WA
-
significantly reduce the amount of vibration data to be stored on edge devices or sent to the clouds. Hence, this project's results will have a high impact on reducing the hardware installation and operation
-
intelligent systems aim to optimize power usage without compromising performance, employing strategies like power-aware computing and thermal-aware optimization. These systems are crucial in extending
-
analytical techniques while contributing to the optimization of toilet system performance through rigorous scientific analysis and data interpretation. Cranfield’s world-class expertise, large-scale facilities
-
the computational inefficiencies of physics-based models and enabling faster, potentially more accurate predictions. However, AI models require substantial volumes of high-quality, labelled training data, which