DPGCN Model: A Novel Fault Diagnosis Method for Marine Diesel Engines Based on Imbalanced Datasets
Ruihan Wang, Hui Chen, Cong Guan
Abstract
The class imbalance problem is prevalent in the condition monitoring (CM) data of marine diesel engines. That significantly deteriorates the diagnostic performance of a data-driven fault diagnosis. In this article, a novel fault diagnosis method named graph convolutional network (GCN) based on the distance and probability topological graphs (DPGCN) model is proposed for solving the problem of imbalanced classification. First, the collected CM dataset is transformed into two topological graphs—the distance topological graph and the probability topological graph—by exploring the similarity between samples from the linear and nonlinear relationships. Graph learning is then introduced to learn and extract the correlation between adjacent samples in addition to the samples’ own features, which provides more topological information for this imbalanced classification task. After multilayer graph learning, two feature embeddings based on samples’ features and topological graphs are learned, and a self-attention mechanism substantially fuses these two embeddings into one combination embedding to derive deeper correlation information for the fault diagnosis. The collected dataset of a marine diesel engine shows that the proposed DPGCN model can improve the classification accuracy and stability under the imbalanced datasets.