Search

This paper focuses on adaptive tracking control for a class of strict-feedback nonlinear systems suffering from the replay attack in the sensor-controller channel. To address the challenges posed by repeating information and complex nonlinearity in nonlinear systems, an adaptive resilient controller based on the multidimensional Taylor network is designed. This controller guarantees that the tracking error converges to zero exponentially in the absence of replay attacks, and it achieves bounded tracking in the presence of replay attacks. Finally, the effectiveness of the proposed control strategy is verified using a chemical reactor with circulating flow simulation.

With the development of urban water supply systems, the leakage detection of water supply pipe networks is of great significance for the safe operation of urban water supply systems. In practice, due to the short of the important data, traditional detection models often fail to achieve good detection results. Therefore, this article proposes a novel pipeline attention integrating the long short-term memory (LSTM) to detect the leakage. The density-based spatial clustering of applications with noise (DBSCAN) method divides the water supply network into several regions according to the leakage characteristics of pipelines. Then, the LSTM extracts dynamic time-varying hydraulic features of pipelines, and the pipeline attention extracts the dynamically changing features between pipelines. Finally, the Attention- LSTM model is used to detect the leak region of urban water supply systems. Compared with multilayer perceptron classifier, $K$ neighbors classifier, decision tree classifier, support vector machine classifier, multiscale fully convolutional network, one-dimensional multichannel convolution neural network, and variational autoencoder, the F1-Score of the Attention- LSTM is greatly improved, which are 116%, 120%, 254%, 180%, 21%, 26%, and 27%, respectively. Therefore, the proposed model can accurately detect the leakage of water supply network and effectively reduce the waste of resources.

A predictive state observer (PSO)-based iterative learning control (ILC) scheme is proposed for industrial batch manufacturing processes with delay response suffering from nonrepetitive uncertainties and disturbances. Combining with a delay-free output predictor, a PSO-based feedback control structure is first presented to improve set-point tracking and disturbance rejection performance against nonrepetitive process uncertainties and disturbances for the initial batch run. Then, an ILC law is introduced to update the closed-loop system set-point in order to improve the tracking performance from batch to batch. A delay-independent sufficient condition is established to ensure the convergence of output tracking error along the batch-direction, based on double-dynamic analysis. Moreover, another delay-dependent sufficient condition is constructed by linear matrix inequality to assess robust stability of the proposed two-dimensional control system along both the time- and batch-directions. Finally, an illustrative example and a real application to the batch temperature regulation of a 4-litre crystallizer are shown to validate the effect and advantage of the proposed ILC scheme.