ABSTRACT
As cyber-physical systems (CPSs) become more prevalent, they also become more vulnerable to security threats that differ from those encountered by internet-based systems. To address these challenges, the chapter proposes a new approach to intrusion detection in cyber-physical manufacturing systems (CPMS) that uses Kernel Principal Component Analysis (KPCA) and Self-Organizing Maps (SOM) to detect anomalous system behavior. This approach involves converting high-dimensional data into a lower-dimensional feature space, which improves the accuracy of pattern classification and intrusion detection. The proposed method was evaluated through simulations on a continuous stirred tank reactor (CSTR) model, and the results showed that it achieved significantly higher accuracy (95.05%) than commonly used intrusion detection techniques.
