A cyber‐secure control‐detector architecture for nonlinear processes

Abstract

This work presents a detector‐integrated two‐tier control architecture capable of identifying the presence of various types of cyber‐attacks, and ensuring closed‐loop system stability upon detection of the cyber‐attacks. Working with a general class of nonlinear systems, an upper‐tier Lyapunov‐based Model Predictive Controller (LMPC), using networked sensor measurements to improve closed‐loop performance, is coupled with lower‐tier cyber‐secure explicit feedback controllers to drive a nonlinear multivariable process to its steady state. Although the networked sensor measurements may be vulnerable to cyber‐attacks, the two‐tier control architecture ensures that the process will stay immune to destabilizing malicious cyber‐attacks. Data‐based attack detectors are developed using sensor measurements via machine‐learning methods, namely artificial neural networks (ANN), under nominal and noisy operating conditions, and applied online to a simulated reactor‐reactor‐separator process. Simulation results demonstrate the effectiveness of these detection algorithms in detecting and distinguishing between multiple classes of intelligent cyber‐attacks. Upon successful detection of cyber‐attacks, the two‐tier control architecture allows convenient reconfiguration of the control system to stabilize the process to its operating steady state.

Integrated cyberattack detection and resilient control strategies using Lyapunov‐based economic model predictive control

“…For linear systems, MPC designs have been explored that can guarantee exponential stability of the origin in the presence of sufficiently short denial of service attacks, 10 guarantee boundedness of the closed‐loop state in an invariant set under random cyberattacks on the sensor measurements, 11 and handle replay attacks 12 . For nonlinear systems, Chen et al 13 combined a neural network‐based attack detection technique developed in 3 with a two‐layer control architecture, where the upper layer is a Lyapunov‐based MPC, to guarantee closed‐loop stability after attacks are detected. Durand 14 explored several MPC techniques with economics‐based objective functions (known as economic MPC's [EMPC's] 15,16 ) in the presence of false sensor measurements to explore cyberattacks in a nonlinear systems context.…”

Application of Artificial Neural Networks to Chemical and Process Engineering

“…It is worth mentioning that ANNs are being used to build detectors to prevent cyber-attacks against process plants [71]. Nowadays, with highly automated systems for controlling chemical plants with real-time operation, breaches in cyber-secure failures can exist, which may cause accidents and economic losses.…”

“…Nowadays, with highly automated systems for controlling chemical plants with real-time operation, breaches in cyber-secure failures can exist, which may cause accidents and economic losses. With this in mind, Chen et al [71] developed a feedback-MPC control architecture with an ANN-detector that can identify the probabilities of cyber-attacks in networked sensors. Therefore, the applicability of ANNs in these safety and control strategies is very significant for the integrability of industrial plants.…”

Detectability‐based controller design screening for processes under multiplicative cyberattacks

“…Cyberattack resilience here is defined as the ability of a PCS to minimize the impact of an attack and recover from it. Research on cyberattack resilience involves approaches that range from designing PCSs that are inherently attack‐resilient to developing cyberattack detection, identification, and mitigation schemes 5–24 …”