11 June 2021 in IEEE Transactions on Instrumentation and Measurement
The data-driven methods in machinery fault diagnosis have become increasingly popular in the past two decades. However, the wide applications of this scheme are generally compromised in real-world conditions because of the discrepancy between the training data and testing data. Although the recently emerging transfer fault diagnosis can learn transferable features from relevant source data and adapt the diagnostic model to the target data, these methods still only work on the target domain with a priori data distribution. The generalization capability of the transferred model cannot be guaranteed for unseen domains. Since the working conditions of machinery are varying during operation, the generalization capability of the diagnosis methods is crucial in this case. To tackle this challenge, this article proposes a domain generalization-based hybrid diagnosis network for deploying to unseen working conditions. The main idea is to regularize the discriminant structure of the deep network with both intrinsic and extrinsic generalization objectives such that the diagnostic model can learn robust features and generalize to unseen domains. The triplet loss minimization of intrinsic multisource data is implemented to facilitate the intraclass compactness and the interclass separability at the class level, leading to a more generalized decision boundary. The extrinsic domain-level regularization is achieved by using adversarial training to further reduce the risk of overfitting. Extensive cross-domain diagnostic experiments on planetary gearbox demonstrate the effectiveness of the proposed method.
11 January 2022 in IEEE Transactions on Reliability
With the lack of failure data, class imbalance has become a common challenge in the fault diagnosis of industrial systems. The oversampling methods can tackle the class-imbalanced problem by generating the minority samples to balance the training set. However, one of the main challenges of the existing oversampling methods is how to generate high-quality minority samples. Traditional oversampling methods regard all synthetic samples as minority ones to be added to the training set without filtering. The low-quality synthetic samples would distort the distribution of the dataset and worsen the classification performance. In this article, we propose a weakly supervised oversampling method that treats all synthetic samples as unlabeled samples and develops a graph semisupervised learning algorithm to select high-quality synthetic samples, adding into the final training set as minority samples. To improve the quality of synthetic samples, we propose a cost-sensitive neighborhood component analysis dimensionality reduction method to enhance domain information validity in high-dimensional datasets. Finally, combining a boosting-based ensemble framework, we propose a new imbalanced learning framework suitable for high dimensionality and highly imbalanced fault diagnosis in industrial systems. The experimental validation is performed on five real-world wind turbine blade cracking failure datasets and compared to 15 benchmark methods. The experimental results show that average performances and robustness of the proposed framework are significantly better than those of the benchmark methods.
21 October 2021 in IEEE Transactions on Industrial Informatics
Intelligent fault detection methods based on deep learning have been developed rapidly in recent years. However, most of these methods are based on supervised learning which requires a fully labeled training set. It is difficult to obtain massive labeled samples in real applications incredibly accurately labeled fault samples from an operating system. The lack of labels and label noise becomes a great challenge for fault detection. To tackle this problem, in this article, we propose a positive-unlabeled learning based hybrid network (PUHN). It only needs part of the normal operating samples to be labeled. All other samples (including the rest of the normal samples and all fault samples) are unlabeled, which greatly reduces the labeling cost. PUHN consists of three modules: a nonnegative risk positive-unlabeled (PU) network for training the classifier, a feature extraction module, and a clustering layer for improving data separability and estimating the class priors of PU learning. The three are optimized as a whole and the corresponding optimization strategy is designed. The monitoring data of 24 wind turbines are used to verify the effectiveness and robustness of the proposed method. The experimental results indicate that the proposed method is superior to the benchmark methods, and the performance is significantly better than the supervised learning method when there exists label noise.
26 March 2020 in PLOS ONE
To investigate the effect and mechanism of SB525334 on self-renewal, migration and invasion of ovarian cancer stem cells. ALDHhigh-expressing cancer stem cells (CSCs) were isolated from human ovarian cancer cell line SKOV-3 by flow cytometry and treated with 2μg/mL SB525334 for 6h. The sphere forming assay was used to detect the ability of self-renewal of CSCs and the colony formation assay was used to detect the tumorigenicity in vitro. Transwell migration and invasion assay were used to detect the migration and invasion ability of CSCs. To further explore the mechanism, real-time quantitative PCR and flow cytometry were used to detect the mRNA and protein expression of TGF-β, Smad2, Smad3, phosphorylated Smad2, phosphorylated Smad3 and Smad4, respectively. Expressions of epithelial-mesenchymal transition (EMT)-related genes E-cadherin, Snail, Vimentin were also assessed. The self-renewal ability, tumorigenicity in vitro, migration and invasion ability of CSCs were significantly attenuated after SB525334 treatment. The expressions of TGF-β, phosphorylated Smad2, phosphorylated Smad3, Snail, and Vimentin were decreased, while Smad4 and E-cadherin expressions were increased. SB525334 may inhibit the self-renewal, invasion and migration of ovarian CSCs by blocking the TGF-β/Smad/EMT pathway.
25 October 2022 in IEEE Transactions on Reliability
Class-imbalance is a prevalent and challenging problem in the field of fault detection. The undersampling ensemble framework is an effective method to deal with imbalance problems. However, designing a suitable sampling strategy to generate effective and divergent subsets is a major difficulty of this type of method. Hence, we propose a novel adaptive undersampling framework. It models the entire training process as a Markov decision process (MDP), thus, enabling dynamic decision-making for subsequent sampling strategies based on the current training performance of the ensemble framework. The sampler is optimized by the soft actor-critic reinforcement learning method. Considering the imbalance dataset's nature and the need for state definition, the clustering method is applied to the original training dataset. The state (training performance) and the action (sampling strategy) are determined according to the clustering results. The unique state definition and sampling decision mechanism are designed to ensure the convergence speed of MDP and improve the divergence of the subsets. We validate the effectiveness of the proposed framework on the real-world wind turbine blade cracking datasets and the high-speed train braking system dataset. The experimental results show that the classification performance and robustness of the proposed framework are significantly better than the 16 benchmark methods.
25 October 2022 in IEEE Transactions on Industrial Informatics
In practical industrial applications, the need for a large number of accurately labeled training samples is a significant challenge for fault detection tasks. However, labeling all training samples is expensive and prone to labeling errors, especially for early fault detection of wind turbine blades. This article proposes a labeling bias hypothesis. Assuming the labeler only needs to label parts of normal samples that are easy to judge, we design a probability ratio least-squares importance fitting (PRL-SIF) method based on variable homogeneity. Unlike other state-of-the-art positive unlabeled learning methods, PRL-SIF does not require knowledge of the class priors to achieve training. Furthermore, to better handle the multidimensional time-series data of wind turbines, we provide a data preprocessing method based on functional analysis to achieve time series feature extraction and dimensionality reduction. The effectiveness and robustness of the proposed method are verified on 23 real-world wind turbine datasets. Experimental results show that the proposed method can achieve nearly 90% accuracy while only labeling 20% of normal samples.