Mechanism model-based and data-driven approach for the diagnosis of solid oxide fuel cell stack leakage

Safety and reliability are key objectives for the efficient operation of solid oxide fuel cell (SOFC) power generation systems. Out of many possible faults, the gas leakage of SOFC stack remains a critical issue that leading to efficiency reduction or even degradation. Therefore, the real-time monitoring and diagnosis of gas leakage in the power generation systems are not only an important premise to improve the efficiency, but also can develop the corresponding fault-tolerant strategy for ensuring the system performance. Motivated by this fact, an on-line fault diagnosis scheme based on mechanism model and data-driven method is proposed to monitor and diagnose the gas leakage of the stack. Firstly, the two-state mechanism model of the SOFC stack is established, which can effectively describe the temperature of the fuel layer and air layer. Then, easily-measured stack inputs and outputs are selected, and a novel gas leakage state estimator combined with unscented Kalman filter (UFK) is developed to reconstruct the leakage state. Furthermore, an adaptive thresholds generator is designed to enhance the robustness of the diagnostic scheme. The performance of the fault diagnosis scheme under different leakage scenarios is evaluated, and the simulation results demonstrate the effectiveness of the proposed scheme. The sudden stack fuel leakage failure that occurred in the stable power generation experiment further illustrates the practicability of the scheme. The proposed fault diagnosis scheme has good practicability and can guide the next step compensates for leakage.