Domain Confusion Research Articles

An integrated approach for mechanical fault diagnosis using maximum mean square discrepancy representation and CNN-based mixed information fusion

Bearings are an essential component of modern industry and cross-domain diagnosis of bearings holds significant importance. However, in practical applications, issues such as insufficient training data and differences between equipment present challenges. Transfer learning has become one of the effective methods to address these problems. This article proposes a fault diagnosis method that combines maximum mean square discrepancy (MMSD) measurement with the convolutional neural network (CNN) with mixed information (MIXCNN). MIXCNN enhances spatial position discrimination through deep convolution and achieves cross-channel information interaction using traditional convolution. The introduction of residual connections reduces information loss, while increasing network depth focuses on highly distinguishable features. MMSD constructs a metric that comprehensively reflects the mean and variance information of data samples in the reproducing kernel Hilbert space, thereby enhancing domain confusion. Experimental results show that this method achieves high diagnostic accuracy in various transfer tasks, with a maximum accuracy of 99.29%, providing reliable support for bearing fault diagnosis.

A multi-domain adversarial transfer network for cross domain fault diagnosis under imbalanced data

In the intelligent fault diagnosis of rolling bearings, transfer learning methods extend the applicability of models to diverse working scenarios. However, real-world scenarios often suffer from data imbalance, which reduces diagnostic accuracy. To address this issue, this paper proposes a multi-domain adversarial transfer (MDAT) framework to enhance cross-domain fault diagnosis accuracy for rolling bearings under imbalanced data conditions. First, an enhanced information generation method is introduced to produce realistic and useable synthetic data to mitigate data imbalance. Subsequently, an adversarial multi-domain adaptation module is designed to learn invariant features across multiple domains. Finally, a domain reweighting method is proposed to improve domain alignment and enhance domain confusion. The effectiveness of the proposed method was validated through two case studies on rolling bearing fault diagnosis. The results demonstrated that MDAT achieved cross-domain diagnosis accuracies of 89.2% and 99.0% under imbalanced data conditions, confirming the effectiveness and superiority of the MDAT framework.

A robust domain distribution alignment discriminative network driven by physical samples for rotor-bearing fault diagnosis

The diagnostic performance of most intelligent models depends on having a sufficient number of labeled samples, which are difficult to obtain in real-world scenarios. Physics-guided sample generation emerges as a promising remedy for addressing the scarcity of labeled samples during model training. However, existing studies have tended to overlook the coupling effect between the marginal and conditional distributions of physical and real samples, leading to domain confusion and a subsequent reduction in model generalization and diagnostic accuracy. Therefore, this study introduces a novel approach: the physically driven sample-based domain distribution alignment discriminative network (DDADN), which integrates dynamic modeling and domain adaptation. Specifically, a lumped parameter model is established to generate complete defect samples, subsequently optimized using the Pearson correlation coefficient (PCC). Next, an enhanced joint distribution adaptation (EJDA) mechanism is employed to harmonize distributions across domains, effectively aligning both overall and class-specific distributions within the domains and thus achieving adaptive domain confusion. Meanwhile, to ensure robust feature classification and extraction, an adaptive softmax (A-softmax) loss function is introduced. Finally, in unlabeled real operating conditions, the proposed multitask scheme adeptly transfers knowledge between physical and real signals, yielding impressive classification accuracies of 97.78% and 98.34% for the experimental and Case Western Reserve University (CWRU) datasets, respectively. These results underscore the superiority of the proposed scheme in terms of learning transferable features and maintaining high diagnostic accuracy and generalization capability.

An enhanced transfer learning based on addernet and deep domain confusion for prognostic of proton exchange membrane fuel cells

Proton exchange membrane fuel cells (PEMFCs) offer high energy conversion rate and low pollution, while low durability of PEMFCs hinder the further development. Accurately predicting degradation trends and remaining useful life (RUL) are crucial to timely detecting problem and improving PEMFCs durability. In this paper, an enhanced transfer learning (Add-TL) based on adder network (AdderNet) and deep domain confusion is proposed for the prediction of PEMFCs. To reinforce the ability of extracting key features from extensive data, AdderNet with attention mechanism is applied. Furthermore, the fused deep domain confusion employs existing data to achieve higher prediction accuracy. The experimental results demonstrate that Add-TL outperforms other classical methods in predicting degradation trend, the optimal adjusted R-square (R2) values for the two datasets are 0.99879 and 0.99906, respectively. When Add-TL is applied to RUL prediction, the accuracy scores for two datasets reach 0.995, which further validating the applicability of Add-TL in PEMFCs prediction.

Privacy-Preserving Federated Learning With Domain Adaptation for Multi-Disease Ocular Disease Recognition.

As one of the effective ways of ocular disease recognition, early fundus screening can help patients avoid unrecoverable blindness. Although deep learning is powerful for image-based ocular disease recognition, the performance mainly benefits from a large number of labeled data. For ocular disease, data collection and annotation in a single site usually take a lot of time. If multi-site data are obtained, there are two main issues: 1) the data privacy is easy to be leaked; 2) the domain gap among sites will influence the recognition performance. Inspired by the above, first, a Gaussian randomized mechanism is adopted in local sites, which are then engaged in a global model to preserve the data privacy of local sites and models. Second, to bridge the domain gap among different sites, a two-step domain adaptation method is introduced, which consists of a domain confusion module and a multi-expert learning strategy. Based on the above, a privacy-preserving federated learning framework with domain adaptation is constructed. In the experimental part, a multi-disease early fundus screening dataset, including a detailed ablation study and four experimental settings, is used to show the stepwise performance, which verifies the efficiency of our proposed framework.

Cross-machine deep subdomain adaptation network for wind turbines fault diagnosis

Recently, subdomain adaptation has gained extensive interest in addressing the problem of wind turbine (WT) fault diagnosis. However, current methods mainly focus on the subdomain adaptation of statistical features and scenarios with constant rotation speed. To overcome these limitations, a new cross-machine deep subdomain adaptation network (CMDSAN) is proposed in this paper for fault diagnosis of WT under multiple operating conditions. CMDSAN contains an improved subdomain adaptive (ISA) mechanism. In ISA, a subdomain distribution shift measure of jointed statistical and geometric features is constructed to boost domain confusion. Meanwhile, to further capture fine-grained information and discriminative features, a local correlation alignment (LCA) strategy is proposed. Additionally, a two-stage training trade-off factor is designed for balancing classification and ISA loss during the training process to improve the transferability of features. Subsequently, test rigs are constructed, i.e., a planetary gearbox test rig and a scaled-down test rig for WT gearbox with a reduction ratio of 110.11, to validate the effectiveness and superiority of CMDSAN. The case studies conducted under constant rotation speed, acceleration, and deceleration demonstrate that the proposed CMDSAN exhibits better fault transfer diagnostic ability than other domain adaptation methods.

Adaptive Intermediate Class-Wise Distribution Alignment: A Universal Domain Adaptation and Generalization Method for Machine Fault Diagnosis.

Many transfer learning methods have been proposed to implement fault transfer diagnosis, and their loss functions are usually composed of task-related losses, distribution distance losses, and correlation regularization losses. The intrinsic parameters and trade-off parameters between losses, however, need to be tuned according to the specific diagnosis tasks; thus, the generalization abilities of these methods in multiple tasks are limited. Besides, the alignment goal of most domain adaptation (DA) mechanisms dynamically changes during the training process, which will result in loss oscillation, slow convergence and poor robustness. To overcome the above-mentioned issues, a novel and simple transfer learning diagnosis method named adaptive intermediate class-wise distribution alignment (AICDA) model is proposed, and it is established via the proposed AICDA mechanism, dynamic intermediate alignment (DIA) adaptive layer and AdaSoftmax loss. The AICDA mechanism develops an adaptive intermediate distribution as the alignment goal of multiple source domains and target domains, and it can simultaneously align the global and class-wise distributions of these domains. The DIA layer is designed to adaptively achieve domain confusion without the distribution distance loss and the correlation regularization loss. Meanwhile, to ensure the classification performance of the AICDA mechanism, AdaSoftmax loss is proposed for boosting the separability of Softmax loss. Finally, in order to evaluate the effectiveness and universality of the AICDA diagnosis model to the most degree, various multisource mixed fault transfer diagnosis tasks of wind turbine planetary gearboxes, including DA and domain generalization (DG), are implemented, and the experimental results indicate that our proposed AICDA model has a higher diagnosis accuracy and a stronger generalization ability than other state-of-the-art transfer learning methods.

An End-to-end Domain Generalization Fault Diagnosis Method Based on Adaptive Weighted Domain Adversarial Learning

Domain adaptation (DA) based fault diagnosis methods have attracted great attention for a long time, which leverages domain-invariant knowledge from a source domain (SD) to a special target domain (TD). However, in practise, there not usually exists only single SD and a specific and available TD. Mostly, data is generated from multiple domain distributions due to varied working conditions, and the TD is not always available during model training. Hence, how to use these multiple domain distribution data to build a model to generalize domain knowledge to an “unseen” TD, is an emerging and challengeable issue. In this paper, a novel domain generalization (DG) based fault diagnosis methods is proposed. Multiple domains are considered jointly to extract generalized domain-invariant features. A multiple residual blocks structure is adopted as the main feature extractor, an additional extractor is added to extract prior knowledge from statistic features. Besides, a k-means based adaptive weighted domain adversarial learning is designed to realize multiple domain confusion in a latent space while the wasserstein distance is calculated to assist in narrowing discrepancy between different domain distributions. Experiments of multiple domain distributions tasks from two datasets are conducted to evaluate the proposed method, and the results have verified the effectiveness of proposed method.

DADIN: Domain Adversarial Deep Interest Network for cross domain recommender systems

The cross-domain recommendation (CDR) model addresses challenges such as data sparsity, the long tail distribution of user–item interactions, and the cold start of items or users. However, solely transferring domain-shared knowledge based on the co-occurrence patterns, without considering user preferences, leads to negative transfer in CDR. To overcome these limitations, we propose an advanced deep learning CDR model called the Domain Adversarial Deep Interest Network (DADIN) aims to facilitate smooth knowledge transfer from the source domain to the target domain and effectively alleviate negative transfer. Firstly, the joint distribution alignment of user preference in DADIN is realized by introducing a skip-connection-based domain agnostic layer, and then the domain classifier is artificially designed to distinguish between the information coming from the source domain or the target domain. Additionally, DADIN combines prediction loss, global domain confusion loss, and intra-class domain confusion losses through the Min-Max game and gradient reverse layer to achieve collaborative optimization. Two real-world experiments show the area under curve (AUC) of DADIN is 0.78 on the Huawei dataset, and it outperforms its competitors by 0.71% on the Amazon dataset, showcasing its state-of-the-art performance. Moreover, our ablation studies further demonstrate that domain adversarial technique increases the AUC by 2.34% on the Huawei dataset and 16.67% on the Amazon dataset, respectively.

Cross-Machine Transfer Fault Diagnosis by Ensemble Weighting Subdomain Adaptation Network

Many domain adaptation models have been explored for fault transfer diagnosis. However, most of them only consider global domain adaptation of two domains while neglecting the fine-grained class-wise distribution alignment between the source and target domains. Thus, these models cannot satisfy the diagnostic requirement in some cases. A new ensemble weighting subdomain adaptation network (EWSAN) diagnostic model is established in this paper to improve the degree of domain confusion. In EWSAN, an enhanced joint distribution alignment (EJDA) mechanism is proposed. A multiscale top classifier with multiple diverse branches is designed based on ensemble learning to better achieve EJDA. Ensemble voting with the multiscale top classifier can obtain more reliable pseudo labels in the EJDA mechanism. An ensemble weighting maximum mean discrepancy (EWMMD) with the class weight is constructed to enhance the fine-grained domain confusion. Moreover, the closed and partial transfer diagnostic tasks are made available. Furthermore, the information entropy is introduced to increase the confidence coefficient of the pseudo label. The proposed EWSAN diagnostic model is evaluated via multiple closed, and partial fault transfer diagnosis experiments cross machines. The experimental results validate its effectiveness and superiority.

Applying Feature Transformation-Based Domain Confusion to Neural Network for the Denoising of Dispersion Spectrograms

Abstract Ambient noise tomography has been widely used to estimate the shear-wave velocity structure of the Earth. A key step in this method is to pick dispersions from dispersion spectrograms. Using the frequency–Bessel (F-J) transform, the generated spectrograms can provide more dispersion information by including higher modes in addition to the fundamental mode. With the increasing availability of these spectrograms, manually picking dispersion curves is highly time and energy consuming. Consequently, neural networks have been used for automatically picking dispersions. Dispersion curves are picked based on deep learning mainly for denoising these spectrograms. In several studies, the neural network was solely trained, and its performance was verified for the denoising. However, they all learn single-source data in the training of neural network. It will lead the regionality of trained neural network. Even if we can use domain adaptation to improve its performance and achieve some success, there are still some spectrograms that cannot be solved effectively. Therefore, multisources training is useful and could reduce the regionality in training stage. Normally, dispersion spectrograms from multisources have feature differences of dispersion curves, especially for higher modes in F-J spectrograms. Thus, we propose a training strategy based on domain confusion through which the neural network effectively learns spectrograms from multisources. After domain confusion, the trained neural network can effectively process large number of test data and help us easily obtain more dispersion curves automatically. The proposed study can provide a deep insight into the denoising of dispersion spectrograms by neural network and facilitate ambient noise tomography.

Guided wave-based cross-scene interfacial debonding detection in reinforced concrete structures

The cross-scene problem within the field of guided wave-based interfacial debonding detection in steel-reinforced concrete structures is a significant challenge. This issue arises when the methods initially designed for laboratory-configured structures or numerical models are adapted to real-world scenarios. In response to this challenge, driven by the concept of domain adaptation, a novel method—the discriminative wavelet adversarial adaptation network (DWAAN)—is proposed to assess the health of analogous structures using diagnostic insights from a reference structure. The proposed method utilizes continuous wavelet transform to segregate signal components. A feature extraction network, designed with the convolutional neural network architecture, extracts domain confusion and damage-sensitive features through guided adversarial adaptive training in the wavelet domain. Both the adversarial and statistical alignment are employed during training for comprehensive optimization of data distribution discrepancies. The effectiveness of the proposed method is assessed in both the homogeneous and heterogeneous cross-scene interfacial debonding detection scenarios, revealing an average performance enhancement of 32.5% in distinct homogeneous applications and 26.6% in heterogeneous scenarios, when compared to the traditional supervised learning approach. In addition, the present method demonstrates robust convergence stability, evidenced by the minimized training fluctuations. The proposed method holds promising potential for practical applications in interfacial debonding detection in reinforced concrete structures while addressing the cross-scene challenge.

Category-level selective dual-adversarial network using significance-augmented unsupervised domain adaptation for surface defect detection

Surface defect detection is very important to ensure the quality of industrial products. Traditional machine learning cannot be well extended to a non-identically distributed dataset, making surface defect detection a data-limited task. Unsupervised domain adaptation (UDA) can solve this problem by transferring knowledge from a labeled source domain to an unlabeled target domain. Adversarial learning is one of the latest heuristic methods to deal with domain shift in UDA tasks. Although impressive results have been achieved, the adversarial model still suffers from the equilibrium challenge, which may lead to under-transfer or negative transfer. To this end, we utilize joint distribution adaptation to propose a novel UDA model, named significance-augmented-based category-level selective dual-adversarial (CDASA) network, to learn a generalized model. Specifically, to promote positive transfer, we use the selective dual-adversarial (DA) learning strategy to further minimize the feature distribution difference at equilibrium to achieve better domain confusion. Meanwhile, guided by defect recognition performance, the transferability of confusion domain is measured to enhance the distributions of potential domains. In addition, to avoid under-transfer, we consider the relationship between the target data and the decision boundary, and then the significance-augmented (SA) mechanism is proposed to encourage class-level alignment. Thus, the alignment features with domain-invariant and category discrimination can be captured simultaneously. Extensive experiments on collected real industrial datasets and publicly available steel surface defect datasets confirm the effectiveness of our approach.

Duplex adversarial domain discriminative network for cross-domain partial transfer fault diagnosis

Domain-adaptation technologies have been widely developed for mechanical fault diagnosis. Most related methods assume the same label space between the source and target domains, whereas the partial domain adaptation problem is more widespread and challenging. Moreover, most previous studies focused on data distribution alignment but failed to address fine-grained distributional differences of subdomains. Hence, this study proposes a novel duplex adversarial deep discriminative network (DADDN) for fault diagnosis in cross-domain partial transfer cases. First, a dual-domain adversarial attention mechanism is adopted in the DADDN to discriminate the label space and evaluate the transferability of the data samples. Second, a new metric function of the distribution difference is employed to learn both the fine-grained and discriminative features of the data samples and a weight-joint adaptive distribution mechanism is proposed to improve the domain confusion capability. Third, a center-of-balance weighting strategy is utilized to expand the categories of the target domain and reduce label space asymmetry. In addition, to avoid negative transfer, a weighting mechanism is designed to filter outlier categories, and a dynamic adaptive factor is introduced to weigh the importance of the marginal and conditional distributions. Finally, the effectiveness, robustness, and progressiveness of the proposed method are validated using several partial-transfer diagnostic tasks based on three rotating machinery datasets.

Relationship Transfer Domain Generalization Network for Rotating Machinery Fault Diagnosis Under Different Working Conditions

Many domain adaptation (DA) models have been explored for fault transfer diagnosis. However, their successes completely rely on the availability of target-domain samples during the training process. As target domain is usually unseen, the domain-adaptation-based diagnostic models cannot meet the requirement of real-time diagnosis in actual engineering. To achieve the domain confusion in the actual diagnosis scenario, a novel relationship transfer (RT) diagnosis framework is first proposed, which can indirectly measure and reduce the distribution discrepancy between the source domain and unseen target domain. Based on the proposed RT framework, a new domain generalization transfer method, called relationship transfer domain generalization network (RTDGN) is constructed. RTDGN is divided into two phases including task-irrelevant domain adaptation (TIDA) and task-relevant domain generalization (TRDG). In the TIDA phase, a DA adversarial network with several domain discriminators is built to enhance the domain confusion of RT framework. Furthermore, to bring the adversarial network a more general domain confusion ability, a new inverse entropy loss is designed. In the TRDG phase, a residual fusion classifier is constructed to improve the generalization ability of fault classifier. Finally, the experimental results on the wind turbine planetary gearbox dataset and bearing dataset verify the effectiveness and superiority of the proposed RTDGN.

Real-Time Video Smoke Detection Based on Deep Domain Adaptation for Injection Molding Machines

Leakage with smoke is often accompanied by fire and explosion hazards. Detecting smoke helps gain time for crisis management. This study aims to address this issue by establishing a video smoke detection system, based on a convolutional neural network (CNN), with the help of smoke synthesis, auto-annotation, and an attention mechanism by fusing gray histogram image information. Additionally, the study incorporates the domain adversarial training of neural networks (DANN) to investigate the effect of domain shifts when adapting the smoke detection model from one injection molding machine to another on-site. It achieves the function of domain confusion without requiring labeling, as well as the automatic extraction of domain features and automatic adversarial training, using target domain data. Compared to deep domain confusion (DDC), naïve DANN, and the domain separation network (DSN), the proposed method achieves the highest accuracy rates of 93.17% and 91.35% in both scenarios. Furthermore, the experiment employs t-distributed stochastic neighbor embedding (t-SNE) to facilitate fast training and smoke detection between machines by leveraging domain adaption features.

Unsupervised Domain Deep Transfer Learning Approach for Rolling Bearing Remaining Useful Life Estimation

Abstract Accurate estimation of remaining useful life (RUL) becomes a crucial task when bearing operates under dynamic working conditions. The environmental noise, different operating conditions, and multiple fault modes result in the existence of considerable distribution and feature shifts between different domains. To address these issues, a novel framework TSBiLSTM is proposed that utilizes 1DCNN, SBiLSTM, and attention mechanism (AM) synergically to extract highly abstract feature representation, and domain adaptation is realized using the MK-MMD (multi-kernel maximum mean discrepancy) metric and domain confusion layer. One-dimensional CNN (1DCNN) and stacked bidirectional LSTM (SBiLSTM) are utilized to take advantage of spatiotemporal features with attention mechanism (AM) to selectively process the influential degradation information. MK-MMD provides effective kernel selection along with a domain confusion layer to effectively extract domain-invariant features. Both experimentation and comparison studies are conducted to verify the effectiveness and feasibility of the proposed TSBiLSTM model. The generalized performance is demonstrated using IEEE PHM data sets based on root mean squared error, mean absolute error, absolute percent mean error, and percentage mean error. The promising RUL prediction results validate the superiority and usability of the proposed TSBiLSTM model as a promising prognostic tool for dynamic operating conditions.

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

Discrepancy representation metric completely determines the transfer diagnosis performance of deep domain adaptation methods. Maximum mean discrepancy (MMD) based on the mean statistic, as the commonly used metric, has poor discrepancy representation in some cases. MMD is generally known from the aspect of kernel function, but the inherent relationship between the two is unknown. To deal with these issues, the authors theoretically explore their relationship first. With the revealed relationship, a novel discrepancy representation metric named maximum mean square discrepancy (MMSD), which can comprehensively reflect the mean and variance information of data samples in the reproducing kernel Hilbert space, is constructed for enhancing domain confusion. Additionally, for the real application under limited samples and ensuring the effectiveness of MMSD, biased and unbiased empirical MMSD statistics are developed, and the error bounds between the two empirical statistics and the real distribution discrepancy are derived. The proposed MMSD is successfully applied to the end-to-end fault diagnosis of planetary gearbox of wind turbine without labeled target-domain samples. The experimental results on twelve cross-load transfer tasks validate that MMSD has a better ability of discrepancy representation and a higher diagnosis accuracy compared with other well-known discrepancy representation metrics. The related code can be downloaded from https://qinyi-team.github.io/2023/06/Maximum-mean-square-discrepancy.

Collaborative fault diagnosis of rotating machinery via dual adversarial guided unsupervised multi-domain adaptation network

Most of the existing research on unsupervised cross-domain intelligent fault diagnosis is based on single-source domain adaptation, which fails to simultaneously utilize various source domains with enough and diverse diagnostic information in practical application scenarios. How to better extract common features from multiple domains and integrate multi-source domain knowledge for collaborative diagnosis is a main challenge. To address these problems, a dual adversarial guided unsupervised multi-domain adaptation network (DAG-MDAN) is proposed. Within the proposed framework, the edge adversarial module (EA-Module) in each set of sources-target domain adaptation sub-network is utilized to compute the source-target domain adversarial loss. And an inner adversarial module (IA-Module) is constructed to direct the extraction of common features between multi-source domains, which combined the EA-Module to form the dual adversarial training to enhance domain confusion. Besides, a multi-subnet collaborative decision module (MCD-Module) is designed to compute the confidence scores to assists the multi-subnet classifier to make better fusion decisions. The DAG-MDAN is verified by the several transfer tasks using faulty rotating machinery datasets under the different speed conditions.

Deep Joint Distribution Alignment: A Novel Enhanced-Domain Adaptation Mechanism for Fault Transfer Diagnosis.

Various domain adaptation (DA) methods have been proposed to address distribution discrepancy and knowledge transfer between the source and target domains. However, many DA models focus on matching the marginal distributions of two domains and cannot satisfy fault-diagnosed-task requirements. To enhance the ability of DA, a new DA mechanism, called deep joint distribution alignment (DJDA), is proposed to simultaneously reduce the discrepancy in marginal and conditional distributions between two domains. A new statistical metric that can align the means and covariances of two domains is designed to match the marginal distributions of the source and target domains. To align the class conditional distributions, a Gaussian mixture model is used to obtain the distribution of each category in the target domain. Then, the conditional distributions of the source domain are computed via maximum-likelihood estimation, and information entropy and Wasserstein distance are employed to reduce class conditional distribution discrepancy between the two domains. With joint distribution alignment, DJDA can achieve domain confusion to the highest degree. DJDA is applied to the fault transfer diagnosis of a wind turbine gearbox and cross-bearing with unlabeled target-domain samples. Experimental results verify that DJDA outperforms other typical DA models.