Artificial neural network-based fault detection and isolation in a parabolic-trough solar plant with defocusing strategy

Abstract

Fault detection is crucial for ensuring optimal operation and maintenance of solar plants. This paper proposes a methodology for fault detection and isolation using artificial neural networks (ANNs) in a model of a 50 MW parabolic-trough solar plant that employs a defocusing strategy. The proposed methodology focuses on detecting three different types of faults in the collector area, namely, faults in the optical efficiency, flow rate, and thermal losses. The methodology is divided into three steps. Firstly, a feedforward dynamic neural network that internally models the concentrated parameter model of the system is used to detect faults and output the fault type. Secondly, information on the defocusing mechanism is added to the inputs of the neural network. Finally, the range of faults considered is adjusted based on the neural networks’ ability to detect each fault size and its impact on the plant's outlet temperature. The accuracy of fault detection is evaluated through several simulations, and the proposed methodology shows promising results. The accuracy of fault detection is found to be 71.72%, 83.96%, and 90.62% for the first, second, and third approaches, respectively. The proposed methodology based on ANNs has the potential to improve the operational efficiency and reduce maintenance costs of solar plants.