Enhancing Situational Awareness in Industrial Automation and Cybersecurity Through an Integrated Framework That Leverages Both Machine Learning and Deep Learning Technologies
Xingcheng Lu, Kechen Wu, Yixuan Chen · 2024
With the rapid development of artificial intelligence technology, machine learning and deep learning are widely applied in various fields, showing great potential and value. This article is aimed to explore the integrated application of machine learning with deep learning technologies in industrial automation and cybersecurity situational awareness. Utilizing deep learning technology to facilitate real-time monitoring and early detection of network security threats. This study first reviews the application status of machine learning in industrial safety, including feature selection, model construction, and performance evaluation. Then, the key technologies of deep learning in cybersecurity situational awareness, such as anomaly detection and intrusion identification, are discussed in depth. Furthermore, this paper proposes a framework that integrates machine learning and deep learning to improve their liability and network security protection capabilities of industrial control systems. By conducting experiments, the proposed framework demonstrates its ability to accurately forecast potential equipment failures in industrial settings and promptly detect security threats within the network, offering a novel approach to enhancing industrial automation and safeguarding network security. After the experiment, the accuracy of the improved algorithm is more than 85%, the prediction is more than 75, the regression line is more than 55%, and the modified algorithm is better than XGBost and other algorithms. The concentration of the improved CNN in identifying attack information can reach 95%.