Industrial control systems (ICSs), as critical national infrastructures, are increasingly susceptible to sophisticated security threats. To address this challenge, our study introduces the CAE-T, a deep convolutional autoencoding transformer network designed for efficient anomaly detection and real-time fault monitoring in ICS. The CAE-T utilizes unsupervised deep learning, employing a convolutional autoencoder for spatial feature extraction from multidimensional time-series data, and combines this with a transformer architecture to capture long-term temporal dependencies. The design of the model facilitates rapid training and inference, while its dual-component approach, utilizing an optimization function based on support vector data description (SVDD), enhances detection accuracy. This integration synergistically combines spatiotemporal feature extraction, significantly improving the robustness and precision of anomaly detection in ICS environments. The CAE-T model demonstrated notable performance enhancements across three industrial control system datasets. Notably, the CAE-T model achieved approximately a 70.8 increase in F1 score and a 9.2 rise in AUC on the WADI dataset. On the SWaT dataset, the model showed improvements of approximately 2.8 in F1 score and 5 in AUC. The power system dataset saw more modest gains, with an approximately 0.1 uptick in F1 score and a 1 increase in AUC. These improvements validate the CAE-T models efficacy and robustness in anomaly detection across various scenarios.

With the increasing deployment of network technologies in industrial control systems (ICSs), cybersecurity has become a challenge in ICSs. Cybersecurity risk assessment (CRA) plays an important role in cybersecurity protection of ICSs. However, the weights of risk indices are constants in traditional CRA methods, and they do not fully consider the requirements of risk identification. In this paper, we define a novel order- $\alpha $ divergence measure for interval-valued intuitionistic fuzzy numbers (IVIFNs) and further develop a novel CRA approach for ICSs based on the proposed divergence measure under an interval-valued intuitionistic fuzzy environment to contribute to the research gap. First, an order- $\alpha $ divergence measure for IVIFNs is defined considering flexibility and robustness of divergence measures with the parameter. Next, a variable weight-based CRA approach for ICSs is developed. In this approach, IVIFNs are adopted to describe evaluation values of risk indices. The weights of risk indices are variable weight vectors and they are determined by the relative divergence closeness. Integration approaches of each node and each attack path in attack-defense trees (ADTs) are proposed based on the operations of IVIFNs, and risk scores of each attack path are calculated by using the score function. Finally, we apply the proposed method to the CRA of a civil aviation fuel supply automatic control system and verify its effectiveness and advantages by comparing it with other methods. This method can dynamically adjust the weights of risk indices considering the relationship between each risk index and the highest risk, and therefore, it can more effectively recognize the highest risk of ICSs than the traditional CRA method. In addition, it can also match the risk attitude of decision-makers by adjusting the parameter $\alpha $ .

Anomaly detection is a unique type of classification challenge. The coupling of imbalance, overlap and other complexity of the data such as noise in industrial internet of things (IIoT) scenarios affect the detection accuracy seriously. To address this issue, this article proposes a novel oversampling approach based on synthetic minority oversampling technology via hypersphere coverage and adaptive differential evolution (HCADE-SMOTE). However, overlap intensification caused by generated samples and over-loss of valid information have always been crucial problems for traditional SMOTE-based approaches. In HCADE-SMOTE, we identify error-prone samples including minority noise and boundary samples based on hypersphere coverage algorithm first. Then, we fine-tune the distribution of these error-prone samples before generation with an adaptive differential evolution algorithm. Instead of deletion mechanism, it avoids transitional information loss. With error-prone samples far away from the boundary, HCADE-SMOTE improves the boundary distribution and simplifies the judge the decision boundary for the detection models. Furthermore, minority samples are oversampled based on local hypersphere density and compactness with a weighted SMOTE mechanism to address imbalance problem. The superiority of this HCADE-SMOTE is verified by experiments from optimization of sample distribution, effect of anomaly detection, and statistical tests, compared with 7 well-known SMOTE-based methods. The experimental results show that HCADE-SMOTE is the most prominent to alleviate overlap with Fishers discriminant ratio metric. After HCADE-SMOTE, the detection results reached the best with classification metrics, for the four detection models Support Vector Machines (SVM), Logistic Regression (LR), Naive Bayes, and Decision Tree (DT). The statistical tests also prove HCADE-SMOTE has significant difference from other SMOTE-based methods, superior to them.

In order to improve the traditional PID control system charged with the parameters perturbed sensitive defects, and use excellent knowledge extraction of neural network and learning ability, people start to put the neural network control strategy into the DC / DC converters, also to design a single neuron PID controller. Furthermore, we just make the Sepic converter as an example to research simulation of its performance. As a result, the simulation indicates that the system has a good dynamic performance and robustness.