Fault Diagnosis Strategies for SOFC-Based Power Generation Plants

Abstract

The success of distributed power generation by plants based on solid oxide fuel cells (SOFCs) is hindered by reliability problems that can be mitigated through an effective fault detection and isolation (FDI) system. However, the numerous operating conditions under which such plants can operate and the random size of the possible faults make identifying damaged plant components starting from the physical variables measured in the plant very difficult. In this context, we assess two classical FDI strategies (model-based with fault signature matrix and data-driven with statistical classification) and the combination of them. For this assessment, a quantitative model of the SOFC-based plant, which is able to simulate regular and faulty conditions, is used. Moreover, a hybrid approach based on the random forest (RF) classification method is introduced to address the discrimination of regular and faulty situations due to its practical advantages. Working with a common dataset, the FDI performances obtained using the aforementioned strategies, with different sets of monitored variables, are observed and compared. We conclude that the hybrid FDI strategy, realized by combining a model-based scheme with a statistical classifier, outperforms the other strategies. In addition, the inclusion of two physical variables that should be measured inside the SOFCs can significantly improve the FDI performance, despite the actual difficulty in performing such measurements.

WITHDRAWN: Performance Modelling of the Regenerative Blower for Air Supply of SOFC System with Random Forest and Bayesian Optimization

“…On the other hand, it is di cult to obtain the speci c geometry parameters of a blower for operators. Nowadays, machine learning based methods driven by a great amount of experimental data have been widely used in industry, such as wake modelling of wind turbine (Ti et al 2020), characteristic analysis of axial compressor (Wu et al 2019;Wu and Li 2012), fault diagnosis and modelling of SOFC system (Costamagna et al 2016;Razbani and Assadi 2014). Thus, the performance model driven by experimental data is a better and necessary method to predict and control the air ow rate supplied to fuel cell stacks more accurately.…”

Multiscale Modelling of Fuel Cells and Related Energy Conversion Systems

“…The random forest classification was used to select regular and faulty modes. A hybrid approach coupling a model-based scheme with a statistical classifier showed the most effective [27][28][29][30].…”

An Overview of Digital Twin Concept for Key Components of Renewable Energy Systems

“…The agent model realizes the multi-physical resolution digital twinning of PEMFC, which can be used to know the healthy operating range of the battery in advance and be embedded into the digital twinning module of PEMFC control system. Jia-lin Kang et al proposed a fault diagnosis method based on DT technology for PEMFC quality waste heat to recover in cogeneration and bottoming cycles [54]. The size and scale of solid oxide fuel cell systems are often large, which presents operational challenges.…”