15 July 2025 in Knowledge-Based Systems
17 September 2025 in IEEE Transactions on Consumer Electronics
Unmanned systems are advancing rapidly, driving widespread attention to multi-agent systems composed of clustered consumer electronic devices. Accurately and timely estimating component states of multi-agent systems during signal transmission is critical for performance. However, existing studies primarily focus on observability in scalar-weighted networks, neglecting matrix-weighted alternatives. These matrix-weighted networks provide greater structural complexity and enhanced modeling capabilities for real-world discrete-time communication models. This paper addresses the observability gap in discrete-time multi-agent systems over matrix-weighted networks, a domain neglected in existing scalar-weighted studies. The observability conditions for systems with fixed weights are first established. The observability criteria are established via spectral decomposition and graph theory, analyzing two eigenvalue distribution cases of the system state matrix. Subsequently, observability criteria for systems with time-varying weights are derived. The criteria are derived using algebraic graph theory, yielding graphical and algebraic conditions based on specific topological configurations. Computational studies validate the effectiveness of the proposed conditions.
6 November 2025 in Signal Processing
3 November 2025 in IEEE Transactions on Instrumentation and Measurement
Deep learning-based fault diagnosis methods have been successfully deployed in a range of engineering applications. However, with the increasing complexity of network structures, it is difficult to perform deep learning training on systems with limited computational resources. To address this challenge, this study proposes a highly precise and lightweight fault diagnosis framework based on sample-related progressive knowledge distillation and multi-scale fusion convolution, called SRPKD-IGhostNet. The SRPKD is proposed to address the limitation that the teacher model is unable to adequately transfer the knowledge in traditional knowledge distillation. The method enables the student model to acquire more accurate and useful knowledge by transferring the attention-based sample-related knowledge in the middle layer of the teacher model and gradually reducing the erroneous output of the distillation process. Additionally, IGhostNet is designed as the student model in the SRPKD, employing a multi-scale fusion convolution block to replace traditional convolution, thereby reducing computational cost while maintaining high diagnostic accuracy. Extensive experiments are conducted on mechanical fault simulation platforms, such as MCDS, with limited computational resources. The results demonstrate that SRPKD-IGhostNet outperforms existing state-of-the-art lightweight fault diagnosis frameworks in accuracy and computational complexity, highlighting its significant potential for industrial applications.