11 February 2025 in IEEE Sensors Journal
In complex industrial environments, mechanical devices predominantly operate under normal conditions, resulting in a shortage of available fault samples. This imbalance significantly impedes the effectiveness of intelligent fault diagnosis approaches. To overcome the challenge, an innovative generative adversarial network (GAN) model is proposed in this study, termed the bidirectional local-global interaction guided GAN with discriminator gradient gap regularization (Bi-Interaction GAN). Firstly, the generator is designed to incorporate a bidirectional interaction mechanism that accounts for the interaction between local and global features of vibration signals, effectively capturing the deep relationships between local and global information within the bearing vibration signals with limited datasets. Subsequently, the stability of the model is enhanced by introducing a novel loss function that integrates discriminator gradient gap regularization with the Wasserstein distance. This approach aims to minimize the gradient discrepancy between real and generated samples within the discriminator, thereby facilitating a more stable training process. Extensive comparative experiments are carried out to validate the proposed approach using a widely utilized dataset and realistic experimental configuration. The results indicate that the Bi-Interaction GAN outperforms existing state-of-the-art GAN models in generating superior-quality samples while achieving high classification accuracy.
2 September 2024 in IEEE Transactions on Instrumentation and Measurement
Fault diagnosis is of great significance for ensuring the reliability and safety of electromechanical equipment. However, in practical applications, the cost of labeling samples is high, which poses difficulties for most supervised fault diagnosis models that rely on a large number of labeled samples for training. Therefore, this paper proposes a novel semi-supervised fault diagnosis method for bearings under low labeled rates, which has the following characteristics: firstly, the first convolutional layer of the feature extraction network is reconstructed using the idea of wavelet transform, addresses the challenges of ineffective learning of the layer caused by long gradient propagation distance, consequently enhancing the feature extraction capability. Secondly, a semi-supervised loss is defined through pseudo-labeling, which makes the boundaries between different classes more explicit on the feature space. Thirdly, A new learning strategy is also designed for this process to overcome the confirmation bias problem. The experimental results based on a widely used public dataset and two real testbeds show that the proposed method achieve satisfactory diagnosis performance at labeled rates as low as 1.25% to 5%, and is superior to other classic and latest models.
12 May 2025 in IEEE Transactions on Instrumentation and Measurement
Wheeled robots are widely deployed across diverse scenarios, necessitating robust fault diagnosis to ensure operational reliability. However, their sophisticated structures, complex tasks, and dynamic working conditions lead to the emergence of new faults, constituting an open-set diagnosis problem. This challenge is further compounded by the multi-modal nature of data from heterogeneous sensors, making it difficult for existing open-set methods to efficiently address this issue due to their inability to capture the intricate interdependencies among different sensors. To solve this problem, this paper proposes a novel multi-modal open-set generative adversarial network (MMOGAN), which has the following characteristics: First, this network employs feature-level adversarial learning to simplify the generation process, and uses the discriminator for direct open-set recognition, which avoids the difficulties of synthesize complex data and limited utility of generated samples. This approach realizes adaptable and modular network architectures, enhancing its flexibility and ease of integration into various diagnostic systems. Second, an improved spatial-temporal extraction module is developed, alternating between temporal and spatial feature extraction to effectively process multi-modal data. This enhancement facilitates the adversarial learning process by providing representative and distinctive features, thereby further ensuring robust open-set fault diagnosis. Experiments are conducted on a Mecanum-wheeled robot equipped with 18 channels of heterogeneous sensors developed by our research group, and the results show that the proposed model exhibits a notable advantage over other classic and state-of-the-art comparison methods.