For a class of uncertain nonlinear sampled-data cyber-physical systems (CPSs) under denial-of-service (DoS) attacks with average frequency and duration constraints, a learning-based rapidly exponentially stabilizing robust adaptive controller (RESRAC) is proposed to improve the control performance in this article. In order to enhance the system robustness against DoS attacks, a rapid exponential stabilization (RES) method is leveraged in controller design to accelerate the convergence rate of the system state. Meanwhile, to take into account the performance boundary of the system state, the learning algorithms are designed to mitigate the peaking phenomenon due to the high-gain feedback in the RES method. In the adaptation law design,$\sigma $-modification combined with G+D estimator is adopted to robustly shape the dynamics of closed-loop system and enhance the steady-state performance. Through Lyapunov stability analysis, it is proved that the CPSs under the proposed control scheme can accommodate the effect of DoS attacks of nearly arbitrary intensity, i.e., the communication is not completely blocked. Finally, a numerical simulation is carried out to illustrate the effectiveness and superiority of the proposed control scheme.

With the rapid development of Artificial Intelligence (AI), deep learning has increasingly become a research hotspot in various fields, such as medical image classification. Traditional deep learning models use Bilinear Interpolation when processing classification tasks of multi-size medical image dataset, which will cause the loss of information of the image, and then affect the classification effect. In response to this problem, this work proposes a solution for an adaptive size deep learning model. First, according to the characteristics of the multi-size medical image dataset, the optimal size set module is proposed in combination with the unpooling process. Next, an adaptive deep learning model module is proposed based on the existing deep learning model. Then, the model is fused with the size fine-tuning module used to process multi-size medical images to obtain a solution of the adaptive size deep learning model. Finally, the proposed solution model is applied to the pneumonia CT medical image dataset. Through experiments, it can be seen that the model has strong robustness, and the classification effect is improved by about 4% compared with traditional algorithms.

In this paper, a novel robust adaptive fault-tolerant coordinated control is proposed for the contour tracking problem of unknown biaxial linear-motor-driven gantry system subject to time-varying actuator faults. Firstly, the dynamic model of the contour error is established by coordinate transformation. The time-varying actuator faults including loss of effectiveness and bias faults with unknown failure time are considered in controller design. The robust adaption law with smooth projection modification is developed to handle for the effect of parametric uncertainties on the system. The proposed control scheme can guarantee that all the signals in the closed-loop system are ultimately bounded even if time-varying actuator faults of the gantry system occur. Finally, two numerical simulations are conducted to show the effectiveness of the proposed control method.

An adaptive iterative learning control method is presented in this paper, for SISO time-varying discrete-time systems. In order to estimate the time-varying unknowns, two iterative learning algorithms, fully-saturated iterative learning projection algorithm and fully-saturated iterative learning least square algorithm, are given, respectively. A one-step ahead controller is developed on the basis of the certainty equivalence principle. The stability and convergence of the closed-loop system are established with the aid of the iteration-domain key technical lemma, which is a variant of the existing one, tailored for the analysis purpose in the iterative domain. The complete tracking is achieved over the pre-specified time interval excluding initial instants, as iteration goes to infinity, while all the signals in the closed-loop remain bounded.