Marine engines confront challenges of varying working conditions and intricate failures. Existing studies have primarily concentrated on fault diagnosis in a single condition, overlooking the adaptability of these methods in diverse working condition. To address the aforementioned issues, we propose a cross working condition fault diagnosis method named the Balanced Adaptation Domain Weighted Adversarial Network (BADWAN). This method combines transfer learning to tackle the challenges of cross working condition diagnosis with limited labels. Specifically tailored for scenarios with incomplete labeling in the target working conditions, we designed an Enhanced Centroid Balance scheme to balance the label space, thereby enhancing the model’s transfer capabilities. Additionally, we designed an Instance Affinity Weighting scheme on the foundation of Class-level Weighting, refining the model to the instance level for effective information interaction. Furthermore, we incorporated the Adaptive Uncertainty Suppression strategy to further boost the model’s classification prowess. Two experimental scenarios were designed to demonstrate the effectiveness of the proposed model using a Wärtsilä9L34DF dual-fuel engine as an experimental subject. The results demonstrate an over 90% diagnostic accuracy in scenarios with complete target working condition labels and 86% accuracy in scenarios with incomplete labels, outperforming other transfer learning models. The BADWAN model excels in cross-condition fault diagnosis tasks for marine engines with incomplete target working condition labels, offering a novel solution to this field.

At present, there are problems such as low fault data, insufficient labeling information, and poor fault diagnosis in the field of ship engine diagnosis. To address the above problems, this paper proposes a fault diagnosis method based on probabilistic similarity and rank-order similarity of multi-head graph attention neural networks (MPGANN) models. Firstly, the ship engine dataset is used to explore the similarity between the data using the probabilistic similarity of T_SNE and the rank order similarity of Spearman’s correlation coefficient to define the neighbor relationship between the samples, and then the appropriate weights are selected for the early fusion of the two graph structures to fuse the feature information of the two scales. Finally, the graph attention neural networks (GANN) incorporating the multi-head attention mechanism are utilized to complete the fault diagnosis. In this paper, comparative experiments such as graph construction and algorithm performance are carried out based on the simulated ship engine dataset, and the experimental results show that the MPGANN outperforms the comparative methods in terms of accuracy, F1 score, and total elapsed time, with an accuracy rate of 97.58%. The experimental results show that the model proposed in this paper can still fulfill the ship engine fault diagnosis task well under unfavorable conditions such as small samples and insufficient label information, which is of practical significance in the field of intelligent ship cabins and fault diagnosis.

In real-world industrial environments, frequent condition changes, mechanical degradation, and incomplete fault labeling often lead to data distribution shifts and label space asymmetry between the source and target domains. Moreover, compounded by the emergence of previously unseen fault types, severely undermine the generalization capability of conventional intelligent diagnostic methods. Although existing open-set domain adaptation methods attempt to address unknown classes, most still rely on the assumption of full label space consistency, limiting their applicability under complex and uncertain industrial conditions. To overcome these limitations, this paper proposes a novel model for generalized open-set cross-working condition fault diagnosis, named Multi-Strategy Progressive Adaptation Network (MSPAN). The model allows for partial class overlap between source and target domains, each containing private classes, thereby reducing reliance on strict label alignment, complete class coverage, and prior knowledge of the target domain. This significantly enhances the model’s adaptability and flexibility under realistic operating conditions. MSPAN integrates three core strategies: Centroid-Guided Expansion (CGE), Progressive Consensus Filtering (PCF), and Localized Knowledge Integration (LKI). CGE expands the label space with pseudo-target domain samples, alleviating interference from private classes in the source domain; PCF combines Dual-Measure Driven Ranking and Consensus-Aware Estimation to adaptively filter unknown classes in the target domain; LKI focuses on learning unknown-class representations while enhancing the transferability of general diagnostic knowledge across domains. Extensive experiments on the PU and NLN-ESP public datasets demonstrate that MSPAN achieves both accurate shared-class diagnosis and effective unknown-class separation under varying degrees of class overlap and openness. These results validate its robustness, generalization ability, and practical potential for deployment in complex industrial fault diagnosis scenarios.