Distributed data-based fault identification and accommodation in networked process systems

• A methodology for the design and analysis of networked plant-wide fault–tolerant control systems for large-scale process systems is presented.
• Resource-aware quasi-decentralized networked control balances the tradeoff between the stability and communication requirements.
• Distributed optimization-based fault identification using sampled data allows timely on-line estimation of the fault magnitude and its location.
• A fault accommodation algorithm that determines the appropriate fault compensation measure based on the plant׳s stability region is presented.
• The results are applied via simulations to a reactor–separator process network.

This paper presents a data-based framework for distributed actuator fault identification and accommodation in networked process systems controlled over a resource-constrained communication medium. Initially, a quasi-decentralized networked control structure is designed to stabilize the plant in the absence of faults. The structure consists of a set of local model-based control systems that communicate with one another at discrete times. An explicit characterization of the networked closed-loop stability region is obtained in terms of the update period, the accuracy of the models, and the choice of controller design parameters. To address the actuator fault identification problem, a set of local fault diagnosis agents are designed and embedded within the various subsystems. Each agent uses a moving-horizon parameter estimation scheme to estimate on-line the size and location of the local faults using the locally sampled states and the model state estimates for the interconnected units. Potential discrepancies or ambiguities in the local fault diagnosis results, which may be caused by the strong dynamic coupling between the individual subsystems and the presence of plant-model mismatch, are reconciled by means of a fault estimation confidence interval which is obtained by analyzing the networked closed-loop dynamics at update times. Once the locations and magnitudes of the actuator faults are identified, the resulting estimates are transmitted to a higher-level supervisor to select and implement a suitable fault accommodation strategy. A number of stability-preserving fault accommodation strategies are devised, including updating the post-fault models, adjusting the controllers’ parameters, or a combination of both. The selection of the appropriate fault accommodation strategy is made on the basis of the estimated fault magnitude and the characterization of the networked closed-loop stability region. Finally, the developed methodology is illustrated using a reactor–separator process example subject to both sudden and incipient control actuator faults.