Staff publications (AIRS)

Browse

Browsing Staff publications (AIRS) by Subject "4008 Electrical engineering"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    A comparative analysis of hybrid sensor fusion schemes for visual–inertial navigation
    (Institute of Electrical and Electronics Engineers (IEEE), 2025-12-31) Tabassum, Tarafder Elmi; Petrunin, Ivan; Rana, Zeeshan A.
    Visual Inertial Odometry (VIO) has been extensively studied for navigation in GNSS-denied environments, but its performance can be heavily impacted by the complexity of the navigation environments such as weather conditions, illumination variation, flight dynamics, and environmental structure. Hybrid fusion approaches integrating Neural Networks (NN), especially Gated Recurrent units (GRU) with the Kalman filters (KF), such as Error-State Kalman Filter (ESKF) have shown promising results mitigating system nonlinearities due to challenging environmental conditions data issues, there is a lack of systematic studies quantitively analysing and comparing performance differences unhand. To address this gap and enable robust navigation in complex conditions, this study proposes and systematically analyses the performance of three hybrid fusion schemes for VIO-based navigation of Unmanned Aerial Vehicles (UAV). These three hybrid VIO schemes include Visual Odometry (VO) error compensation using NN, KF error compensation using NN, and prediction of Kalman gain using NN. The comparative analysis is performed using data generated in MATLAB incorporating the Unreal Engine involving diverse challenging environmental conditions: fog, rain, illumination level variability and variability in the number of features available for extraction during the UAV flight in the urban environment. The results demonstrate the performance improvement achieved by hybrid VIO fusion schemes compared to ESKF-based traditional fusion methods in the presence of multiple visual failure modes. Comparative analysis reveals notable improvement achieved by method 1 with enhancements of 93% in sunny, 91% in foggy and 90% in rainy conditions than the other two hybrid VIO architectures.
  • Thumbnail Image
    ItemOpen Access
    An advanced performance-based method for soft and abrupt fault diagnosis of industrial gas turbines
    (Elsevier, 2025-04-15) Chen, Yu-Zhi; Zhang, Wei-Gang; Tsoutsanis, Elias; Zhao, Junjie; Tam, Ivan C. K.; Gou, Lin-Feng
    Integrating gas turbines with intermittent renewable energy must operate for prolonged periods under transient conditions. Existing research on fault diagnosis in such systems has concentrated on the primary rotating components in steady-state conditions. There is a gap in investigating the interplay between shaft bearing failure and performance metrics, as well as fault identification under transient conditions. This study aims to identify faults not only in the main rotating components but also in the shaft bearings under transient conditions. Firstly, the performance model and fault propagation model of gas turbines are established, and the influence of bearing fault on the whole engine performance is analysed. Then, the fault diagnosis method is determined and the dynamic effects are compensated in fault identification at each time interval. Finally, the steady-state and transient fault diagnosis are carried out considering the constant and sudden faults for the main rotating components and bearings. The average run time and maximum error during the engine life cycle are 0.1064 s and 0.0086 %. For the proposed dynamic effects compensation method, the average computation time and peak error at every moment are 0.1152 s and 0.0143 %, clearly superior to the benchmark method. These results provide evidence that the proposed method can correctly diagnose the fault of the main rotating components and shaft bearings under transient conditions. Therefore, the findings mark an advancement in real-time fault diagnostic techniques, ultimately enhancing engine availability while upholding secure and affordable energy production.
  • Thumbnail Image
    ItemOpen Access
    Personalizing driver agent using large language models for driving safety and smarter human–machine interactions
    (IEEE, 2025-12-31) Xu, Zixuan; Chen, Tiantian; Huang, Zilin; Xing, Yang; Chen, Sikai
    Driver assistance systems have been shown to reduce crashes by providing real-time warnings or assistance, with their effectiveness depending on communication with driver. Due to their unique characteristics, human drivers possess varying hazard perception skills and interaction preferences, making personalized assistance crucial to improving the user experience and system acceptance. However, how to leverage multimodal interfaces that dynamically adapt to warning contents and driver characteristics remains an open question. At the same time, large language models (LLMs) have demonstrated advanced capabilities in knowledge acquisition, planning, and human–machine collaboration, offering potential solutions for existing warning systems. Thus, we develop an LLM-based personalized driver agent (PDA), which provides personalized warnings through multimodal interactions (visual, voice, and tactile). The agent’s architecture mimics human cognitive processes via four core modules: memory, perception, control, and action. Results from our experiments indicate that the LLM-PDA effectively customizes warning contents for different drivers in various situations, providing enhanced safety and driver support. This article pioneers the integration of LLMs into automotive human–vehicle interaction and offers novel insights into personalized human–machine interaction in intelligent vehicles.