Maximum mean square discrepancy: A new discrepancy representation metric for mechanical fault transfer diagnosis

Collecting bearing fault signals from several rotating machines or under varied operating conditions often results in data distribution offset. Furthermore, the newly obtained data is typically unlabeled. When intricate confounding aspects of data distribution across several domains are present, achieving desired outcomes through straightforward transfer learning techniques becomes challenging. This research presents a new framework, the Domain-Specific Invariant Adversarial Network, which combines the principles of domain-invariant representation learning and feature de-entanglement to solve the challenge at hand. This framework uses domain-specific information as an auxiliary training tool and employs the data generation process to transfer labelled source domain data to the target domain. The aim of this approach is to uncover potential information components and improve the model's ability to acknowledge patterns. The study showcases the method's strong diagnostic capability by conducting experimental analysis on four fault datasets.

Section: Results Analysismentioning

confidence: 99%

Domain adaptation with domain specific information and feature disentanglement for bearing fault diagnosis

Xie,

Xia,

Zhang

2024

“…In recent years, deep learning has attracted widespread attention in various fields due to its strong feature mining capability, providing a new perspective for fault diagnosis [10][11][12][13][14]. Compared with traditional fault diagnosis methods, deep learning can adaptively extract the fault information from vibration signals, avoiding the information loss caused by manual processing.…”

Section: Introductionmentioning

confidence: 99%

Multi-scale residual neural network with enhanced gated recurrent unit for fault diagnosis of rolling bearing

Liao,

Fu,

Yang

et al. 2024

As the key component of rotating machinery, effective and reliable fault diagnosis of rolling bearing is particularly critical for promoting production safety and economic benefits. The powerful representation learning ability of convolutional neural network (CNN) enables it to effectively extract fault information from vibration signals of rolling bearing. Nevertheless, challenges are faced by CNN in extracting features at multi-scale and capturing temporal features. With regard to this issue, a hybrid deep learning model that incorporates the multi-scale residual neural network (MSRN) with the enhanced gated recurrent unit (EGRU), namely MSRN-EGRU, is proposed in this paper. To begin with, MSRN is designed by introducing multi-scale structure and residual connections into CNN for extracting local features effectively and improving the feature representation of the model. Then, the extracted local features are input into EGRU to further extract temporal features, where EGRU is proposed by improving gated recurrent unit (GRU) structure and embeding scaled exponential liner unit (SELU), which enhances the nonlinear modeling and memory ability. Eventually, the obtained features are processed by α-Dropout and global average pooling (GAP) before being inputted into the softmax layer for fault diagnosis. To validate the effectiveness of the proposed model, three baseline models and two ablation models were employed for comparative experiments with two bearing datasets. The experimental results reveal that the proposed model achieves commendable performance in terms of accuracy, robustness, and convergence for fault diagnosis of rolling bearing.

“…The existing mainstream DA mechanisms are divided into metric-based, adversarial-based, and joint distribution. In the metric-based mechanism, Qian et al [14] improved the maximum mean discrepancy (MMD), explored the mean and variance information of data samples, and proposed the maximum mean square discrepancy to enhance the confusion ability of the model domain. Wang et al [15] improved the correlation alignment (CORAL) and proposed a deep feature correlation matching network, which pays attention to the correlation of the first-order and second-order features of the source domain and the target domain, and reduces the feature discrepancy between different domains.…”

Section: Introductionmentioning

confidence: 99%

Intelligent fault diagnosis of double-aligned domain adaptation based on multi-structure fusion and multi-attention mechanism

Shang,

Wu,

Pan

et al. 2024

Currently, most fault diagnosis methods based on domain adaptation reduce the distribution discrepancy between the source and target domains by aligning their high-dimensional features, but do not consider the impact of the source domain decision boundary on the distribution of the target domain, which leads to slow convergence and poor generalization. Aiming at the above-mentioned issues, this paper proposes a double-aligned domain adaptation deep transfer model (MSADA) based on multi-structure fusion and multi-attention mechanisms. Firstly, a multi-structure fusion network with Inception module is constructed to increase the information capacity in the extracted features and enhance the representation of deep features. Then, the multi-attention mechanism is embedded into different convolutional channels separately to learn globally and locally important information and reduce the influence of the source domain decision boundary on the target domain distribution. Finally, the multi-kernel maximum mean discrepancy (MK-MMD) and KL divergence are combined as a new double-aligned distribution discrepancy metric to align the samples and probability distributions of the source domain and the target domain, respectively. At the same time, a dynamic adaptive factor is designed to adjust the contribution of the two types of distributions, thus effectively improving the training efficiency and the robustness of the model. Through the validation analysis of two rolling bearing dataset cases, the proposed MSADA has better cross-domain diagnostic performance than other domain adaptation methods.