Sharpness-aware multidomain imbalance generalization with external adversarial learning and intrinsic balanced entropy regularization for intelligent fault diagnosis

In practical industrial scenarios, due to the diversity of operating conditions and the complexity of equipment operations, target condition data are often difficult to obtain. Moreover, mechanical faults occur sporadically and unpredictably, leading to complex class imbalance and domain imbalance phenomena in data across different conditions. The coupling of source domain data imbalance and target condition unknowability forms an imbalance domain generalization (IDG) problem, severely limiting the accuracy and industrial application of intelligent fault diagnosis models. To address this, this paper proposes a sharpness-aware multidomain imbalance generalization method, incorporating external adversarial learning and intrinsic balanced entropy regularization, to construct a class-unbiased and domain-invariant intelligent fault diagnosis model. Specifically, a novel spatiotemporal feature extraction module is designed to achieve an efficient fusion of multi-order spatial and multi-channel features, significantly enhancing the model's feature extraction capability. Subsequently, through the joint domain generalization with the balanced regularization approach, the model aligns the marginal and conditional probabilities across domains under data imbalance conditions, effectively mitigating the negative impact of data imbalance. Finally, the sharpness-aware minimization training strategy is employed to optimize the loss landscape during IDG, further improving the model's generalization performance. Experimental results on four typical IDG engineering scenarios and various imbalance degrees demonstrate that the proposed method achieves state-of-the-art performance, highlighting its significant advantages and application potential in addressing IDG engineering problems.