Search

According to diagnostic criteria, skin tumors can be divided into three categories: benign, low degree and high degree malignancy. For high degree malignant skin tumors, if not detected in time, they can do serious harm to patients' health. However, in clinical practice, identifying malignant degree requires biopsy and pathological examination which is time costly. Furthermore, in many areas, due to the severe shortage of dermatologists, it's inconvenient for patients to go to hospital for examination. Therefore, an easy to access screening method of malignant skin tumors is needed urgently. Firstly, we spend 5 years to build a dataset which includes 4,500 images of 10 kinds of skin tumors. All instances are verified pathologically thus trustworthy; Secondly, we label each instance to be either low-risk, high-risk or dangerous in which Junctional nevus, Intradermal nevus, Dermatofibroma, Lipoma and Seborrheic keratosis are low-risk, Basal cell carcinoma, Bowen's disease and Actinic keratosis are high-risk, Squamous cell carcinoma and Malignant melanoma are dangerous; Thirdly, we apply the Xception architecture to build the risk degree classifier. The area under the curve (AUC) for three risk degrees reach 0.959, 0.919 and 0.947 respectively. To further evaluate the validity of the proposed risk degree classifier, we conduct a competition with 20 professional dermatologists. The results showed the proposed classifier outperforms dermatologists. Our system is helpful to patients in preliminary screening. It can identify the patients who are at risk and alert them to go to hospital for further examination.

In the past years, the practical cross-domain machinery fault diagnosis problems have been attracting growing attention, where the training and testing data are collected from different operating conditions. The recent advances in closed-set domain adaptation have well addressed the basic problem where the fault mode sets are identical in the source and target domains. While some attempts have also been made on the partial and open-set domain adaptations, no prior information of the target-domain fault modes can be usually available in the real industries, that forms a challenging problem in transfer learning. This article proposes a universal domain adaptation method for fault diagnosis, where no explicit assumption is made on the target label set. A hybrid approach with source class-wise and target instance-wise weighting mechanism is proposed for selective adaptation. By using additional outlier identifier, the proposed method can automatically recognize the unknown fault modes while achieving class-level alignments for the shared health states, without knowing the target label set. Experiments on two rotating machine datasets validate the proposed method, which is promising for practical applications under strong data uncertainties. [ABSTRACT FROM AUTHOR]

Data-driven machinery fault diagnosis methods have been successfully developed in the past decades. However, the cross-domain diagnostic problems have not been well addressed, where the training and testing data are collected under different operating conditions. Recently, domain adaptation approaches have been popularly used to bridge this gap, which extract domain-invariant features for diagnostics. Despite the effectiveness, most existing methods assume the label spaces of training and testing data are identical that indicates the fault mode sets are the same in different scenarios. In practice, new fault modes usually occur in testing, which makes the conventional methods focusing on marginal distribution alignment less effective. In order to address this problem, a deep learning-based open-set domain adaptation method is proposed in this study. Adversarial learning is introduced to extract generalized features, and an instance-level weighted mechanism is proposed to reflect the similarities of testing samples with known health states. The unknown fault mode can be effectively identified, and the known states can be also recognized. Entropy minimization scheme is further adopted to improve generalization. Experiments on two practical rotating machinery datasets validate the proposed method. The results suggest the proposed method is promising for open-set domain adaptation problems, which largely enhances the applicability of data-driven approaches in the real industries. [ABSTRACT FROM AUTHOR]

Recently, transfer learning has been receiving growing interests in machinery fault diagnosis due to its strong generalization across different industrial scenarios. The existing methods generally assume identical label spaces, and propose minimizing marginal distribution discrepancy between source and target domains. However, this assumption usually does not hold in real industries, where testing data mostly contain a subspace of the source label space. Therefore, transferring diagnosis knowledge from a comprehensive source domain to a target domain with limited machine conditions is motivated. This challenging partial transfer learning problem is addressed in this study using deep learning-based domain adaptation method. A class weighted adversarial neural network is proposed to encourage positive transfer of the shared classes and ignore the source outliers. Experimental results on two rotating machinery datasets suggest the proposed method is promising for partial transfer learning. • The partial transfer learning problem in machinery fault diagnostics is addressed. • Class weighted adversarial neural network is proposed for feature extraction and condition alignments. • Instead of minimizing marginal distribution gap, the conditional data alignments are focused on. • Practical experiments validate the effectiveness of the proposed method on partial transfer learning tasks. [ABSTRACT FROM AUTHOR]

• A deep learning-based domain generalization method is proposed on intelligent fault diagnostics. • Promising domain adaptation effects can be achieved without availability of target-domain data. • Generalized knowledge can be learned from multiple source domains, which holds in new target domain. • Experiments validate the proposed method, which is promising for on-line cross-domain fault diagnosis. The past years have witnessed the successful development of intelligent machinery fault diagnostic methods. Besides the basic data-driven fault diagnosis tasks where the training and testing data are collected from the same distribution, the more practical cross-domain problems have also attracted much attention considering variations of machine operating conditions. In the literature, most existing studies generally assume the availability of testing data during model training, thus facilitating explicit domain adaptations. However, this assumption poses obstacles in the application on real-time cross-domain fault diagnosis, where the testing data can not be obtained in advance. This paper proposes a deep learning-based domain generalization method for machinery fault diagnosis. A domain augmentation method is adopted to expand the available dataset. Domain adversarial training is implemented, and generalized features can be learned from different domains, which hold in new working scenarios without assuming the availability of testing data. Distance metric learning is also used to further enhance model robustness in fault classifications. Through experiments on two rotating machinery datasets, the effectiveness of the proposed method is validated, which is promising in on-line cross-domain fault diagnosis tasks. [ABSTRACT FROM AUTHOR]

• The challenging cross-machine transfer learning problem in fault diagnosis is investigated. • The machine-invariant features are extracted using deep auto-encoder, and domain adaptation is used for feature alignment. • The practical scenarios in fault diagnosis are considered where only the target-machine data in healthy state are available. • Different fault locations and severities are both considered in the cross-machine fault diagnosis. • Experiments on three rotating machinery datasets validate the effectiveness of the proposed method. Recently, due to the rising industrial demands for intelligent machinery fault diagnosis with strong generalization, transfer learning techniques have been used to enhance adaptability of data-driven approaches. Particularly, the domain shift problem where training and testing data are sampled from different operating conditions of the same machine is well addressed. However, it is still difficult to prepare sufficient labeled data on the tested machine. Therefore, the idea of transferring fault diagnosis knowledge learned from one machine to different but related machines is motivated, and that is realized through a deep learning-based method in this paper. Features of different equipments are first projected into the same subspace using an auto-encoder structure, and cross-machine adaptation algorithm is adopted for knowledge generalization, where the distribution discrepancy between data from different machines is minimized. Experiments on three rolling bearing datasets are implemented to validate the proposed method. The results suggest it is feasible to transfer fault diagnosis knowledge across different machines, and the proposed method offers a novel and promising approach for knowledge generalization. [ABSTRACT FROM AUTHOR]

Intelligent data-driven system prognostic methods have been popularly developed in the recent years. Despite the promising results, most approaches assume the training and testing data are from the same operating condition. In the real industries, it is quite common that different machine entities work under different scenarios, that results in performance deteriorations of the data-driven prognostic methods. This paper proposes a transfer learning method for remaining useful life predictions using deep representation regularization. The practical and challenging scenario is investigated, where the training and testing data are from different machinery operating conditions, and no target-domain run-to-failure data is available for training. In the deep learning framework, data alignment schemes are proposed in the representation sub-space, including healthy state alignment, degradation direction alignment, degradation level regularization and degradation fusion. In this way, the life-cycle data of different machine entities across domains can follow the same degradation trace, thus achieving prognostic knowledge transfer. Extensive experiments on the aero-engine dataset validate the effectiveness of the proposed method, which offers a promising solution for industrial prognostics. • The cross-domain remaining useful life prediction problem is investigated. • A deep learning-based transfer learning method is proposed for prognostics. • The target domains only include unlabeled data at early degradation periods. • Deep representation regularization schemes are proposed for data alignments. • Experiments validate the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Intelligent data-driven machinery fault diagnosis methods have been successfully and popularly developed in the past years. While promising diagnostic performance has been achieved, the existing methods generally require large amounts of high-quality supervised data for training, which are mostly difficult and expensive to collect in real industries. Therefore, it is motivated that the distributed data of multiple clients can be integrated and exploited to build a powerful data-driven model. However, that basically requires data sharing among different users, and is not preferred in most industrial cases due to potential conflict of interests. In order to address the data island problem, a federated learning method for machinery fault diagnosis is proposed in this paper. Model training is locally implemented within each participated client, and a self-supervised learning scheme is proposed to enhance the learning performance. The server aggregates the locally updated models in each training round under the dynamic validation scheme, and a global fault diagnosis model can be established. Only the models are mutually communicated rather than the data, which ensures data privacy among different clients. The experiments on two datasets suggest the proposed method offers a promising approach on confidential decentralized learning. • A specially designed federated learning method is proposed for machinery fault diagnosis problems. • A self-supervised learning algorithm is proposed for better explorations of time-series machinery data. • A dynamic validation scheme is proposed to adaptively implement model averaging operation. • The challenging scenarios with non-independent and identically distributed user data are addressed. • The proposed data privacy-preserving learning scheme is validated through experiments on two rotating machinery datasets. [ABSTRACT FROM AUTHOR]

Recently, intelligent data-driven machinery prognostics and health management have been attracting increasing attention due to the great merits of high accuracy, fast response and easy implementation. While promising prognostic performance has been achieved, the first predicting time for remaining useful life is generally difficult to be determined, and the data distribution discrepancy between different machines is mostly ignored, which leads to deterioration in prognostics. In this paper, a deep learning-based prognostic method is proposed to address the problems. Generative adversarial networks are used to learn the distributions of data in machine healthy states, and a health indicator is proposed to determine the first predicting time. Afterwards, adversarial training is further introduced to achieve data alignments of different machine entities in order to extract generalized prognostic knowledge. Experiments of remaining useful life prediction on two rotating machinery datasets are implemented, and the promising prognostic results validate the effectiveness of the proposed method. • A deep learning-based prognostic method is proposed for rotating machines. • Generative adversarial networks formulate a health indicator for degradation. • Data distribution discrepancy is minimized through adversarial training. • The proposed scheme is validated through experiments on two datasets. [ABSTRACT FROM AUTHOR]

• A deep learning method is proposed to address the data imbalance problem. • Deep generative adversarial networks are designed to generate fake samples. • Fake samples are similar with real machinery vibration data. • Experiments validate the proposed method on data augmentation in diagnosis. Despite the recent advances of intelligent data-driven fault diagnosis methods on rotating machines, balanced training data for different machine health conditions are assumed in most studies. However, the signals in machine faulty states are usually difficult and expensive to collect, resulting in imbalanced training dataset in most cases. That significantly deteriorates the effectiveness of the existing data-driven approaches. This paper proposes a deep learning-based fault diagnosis method to address the imbalanced data problem by explicitly creating additional training data. Generative adversarial networks are firstly used to learn the mapping between the distributions of noise and real machinery temporal vibration data, and additional realistic fake samples can be generated to balance and further expand the available dataset afterwards. Through experiments on two rotating machinery datasets, it is validated that the data-driven methods can significantly benefit from the data augmentation, and the proposed method offers a promising tool on fault diagnosis with imbalanced training data. [ABSTRACT FROM AUTHOR]