International Journal of Systems, Control and Communications (4 papers in press)

Regular Issues

• Non-fragile H control for 2D Markov jump systems with partially unknown probabilities and its application in metal rolling process  
  by Peng Cui, Zhenghao Ni, Feng Li 
  Abstract: This article studies the asynchronous H non-fragile control problem of two-dimensional Markov jump systems with imperfect probability information based on the Roesser systems. First, to make the system better simulate actual engineering applications, its transition probability and observation probability are considered to be completely known, partially unknown and completely unknown. Second, the hidden Markov model addresses the asynchronous phenomenon between the controller and the system, given that the system mode might not be precisely achieved in the actual environment. Simultaneously, non-fragile control is used to overcome the influence of controller gain fluctuation during the action process. Furthermore, a suitable Lyapunov function is constructed, and the associated theorem is used to deduce adequate requirements for the closed-loop systems stability. Lastly, the industrial steel rolling process and the Darboux equation example are used to confirm the feasibility of the suggested asynchronous non-fragile controller.
  Keywords: Roesser systems; hidden Markov model; HMM; non-fragile control; partially information; 2D systems.
  
  
• Multimodal comparative learning chip defect detection algorithm based on GLIP guidance  
  by Ziyi He, Bingqi Wang, Li Ma, Jingjing Fang 
  Abstract: In the production of semiconductor chips, the existing process technology and the working environment have an impact on the quality of the chip, so defect detection on the chip surface is crucial. However, in real-world environments, it is challenging to collect a sufficiently large and highly representative sample of defects. In this paper, we propose a multimodal comparative learning approach with GLIP for location guidance and Multi scale fusion modules for different multiscale fusions to localise defect locations of different shapes and sizes. In the testing phase, samples from different chip types in the training set were used to demonstrate the good generalisation ability and accuracy of our model and tested on the MVTEC dataset to demonstrate the superiority of our method, where the image-level and pixel level accuracies on our privately owned chip dataset can reach 91.3 and 92.6, and the pixel-level accuracy on the MVTEC is 92.3.
  Keywords: defect detection; visual language model; zero-sample inference; comparative learning; transfer learning.
  
  
• A Q-learning-based approach in clock synchronisation in wireless sensor networks  
  by M. Muthumalathi, P.B. Pankajavalli, A. Priya Dharshini 
  Abstract: In this paper, clock synchronisation in wireless sensor networks through Q-learning-based approach is investigated. This paper proposes a distributed approach that leverages distributed Q-learning-based synchronisation (DQS) to optimise packet transmission decisions for enhancing clock synchronisation. The proposed DQS method dynamically adjusts transmission behaviours based on historical experiences, aiming to minimise packet loss and energy consumption while synchronising clocks among sensor nodes. In particular, DQS approach presents a more efficient communication path with only fewer updates and transmission which result in less energy consumption for enhancing clock variance. The experimental result reveals that the proposed DQS approach has 3% to 7% reduction in energy consumption when compared to traditional distributed synchronisation (TDS) and gradient time synchronisation (GTS). Further, the packet loss and logical clock variance are reduced to 31% and 33% comparing with TDS and GTS with 500 rounds of synchronisation.
  Keywords: wireless sensor networks; WSNs; clock synchronisation; Q-learning; reinforcement learning; packet transmission and energy consumption.
  
  
• Event-triggered adaptive PID control for nonlinear dynamic process  
  by Cong Xu, Wuyu Zhou 
  Abstract: Proportional-integral-derivative (PID) control has been extensively employed for nonlinear dynamic process due to its simple control mechanism, high reliability, and easy implementation. However, difficult to determine the control parameters of the conventional PID controllers, which makes it difficult to adapt to the changes in nonlinear dynamic process. To address the challenges of low precision and excessive updates in nonlinear dynamic process control, an innovative event-triggered adaptive PID (EAPID) control method is proposed in this paper. Firstly, an adaptive PID controller based on the long short-term memory neural network is designed to enhance control precision. The network parameters are updated online using the back-propagation through time (BPTT) algorithm and the momentum term is introduced to update the controller parameters to improve the control accuracy. Secondly, an event triggered mechanism is exploited to ensure the stability of the system, so that the controller is updated only when the triggering mechanism is violated, reducing computational resource consumption. Finally, the effectiveness of the proposed control method is validated by two numerical examples. The comparison results with other methodologies demonstrate the effectiveness and superiority of the proposed EAPID control method.
  Keywords: PID control; long short-term memory network; LSTM; event-triggered control; nonlinear dynamic process.
  DOI: 10.1504/IJSCC.2025.10070804