A novel deep learning-based model for fault diagnosis of complex systems with high uncertainty

The deterministic convolutional neural network (CNN), gated recurrent unit (GRU), and softmax classifier (SC) combination (CNN-GRU-SC) is a well-established deep learning model for fault diagnosis of complex systems. However, the model cannot accurately diagnose the faults for complex systems with high uncertainty. This research aims to propose a novel model integrating interval type-2 fuzzy set (IT2FS) to address this challenge. Specifically, IT2FS is used to define the IT2FS operations of convolution and pooling in CNN, reset and update gates and candidate hidden and hidden states in GRU, and full-connection and softmax in SC, yielding the IT2FS-CNN, IT2FS-GRU, and IT2FS-SC models, respectively. These are coupled to propose a novel IT2FS-based deep learning model for fault diagnosis of complex systems with high uncertainty. Using the dataset (2096 samples: 1404 training, 692 testing across 8 conditions) on the reactor coolant system (RCS) for AP1000 from personal computer transient analyzer (PCTRAN), the proposed model achieved accuracy of 99.71%, recall of 99.75%, precision of 99.71%, F1-score of 99.73%, and area under the curve (AUC) of 1.00 at a lower noise level (standard deviation (SD) = 0.1), and accuracy of 87.14%, recall of 86.76%, precision of 87.49%, F1-score of 86.28%, and AUC of 0.98 at a higher noise level (SD = 0.5), outperforming traditional models in identifying fault modes, locations, and severity under high uncertainty. This model enhances diagnostic reliability in engineering applications and holds promise for broader use in safety-critical systems with inherent uncertainties. • Design an IT2FS-CNN model. • Design an IT2FS-GRU model. • Design an IT2FS-SC model. • Propose a novel IT2FS-based deep learning model for fault diagnosis of complex systems with high uncertainty. • Diagnose faults of a reactor coolant system in NPP applying IT2FS-based deep learning model.