Limited operating data resulting from complex and changeable working conditions significantly undermines the performance of deep learning-based methods for rolling bearing fault diagnosis. Generally, this problem can be solved by using the generative adversarial network (GAN) to augment data. However, most GAN-based methods seldom comprehensively consider the global interactions and local dependencies in raw vibration signals during data generation, leading to a decline in the quality of the generated data and compromising the diagnostic accuracy. To address this problem, a fault diagnosis method based on integrated convolutional transformer GAN (ICoT-GAN) is proposed to improve the diagnostic performance under limited data condition by generating high-quality signals. Firstly, a new data augmentation model ICoT-GAN is developed. In ICoT-GAN, a novel ICoT block is designed to construct the generator and discriminator. The ICoT block achieves the integration of attention-based global information capture and convolution-based local feature extraction through the incorporation of convolution within the transformer encoder. This design allows the ICoT-GAN to comprehensively extract both global and local time-series features of raw signals and generate high-quality signals. Secondly, a novel data evaluation indicator, referred to as the Multiple Time-Domain Features Indicator (MTFI), is designed to quantitatively evaluate generated signals’ quality by calculating the similarity of time-domain features between the real and generated signals. The MTFI can complement probability distribution indicators and provide a comprehensive evaluation of the data augmentation model’s generation ability by considering both time-series feature similarity and probability distribution differences. Finally, the effectiveness of our proposed method has been successfully demonstrated under limited data condition using the CWRU and IMS bearing datasets. With only 16 training samples per class, our proposed method achieves diagnostic accuracy of 99.99% and 99.70%, respectively. Additionally, the data generation time is only 1163.31s, indicating the efficiency of our proposed method.
A radial basis function neural network (RBFNN), with a strong function approximation ability, was proven to be an effective tool for nonlinear process modeling. However, in many instances, the sample set is limited and the model evaluation error is fixed, which makes it very difficult to construct an optimal network structure to ensure the generalization ability of the established nonlinear process model. To solve this problem, a novel RBFNN with a high generation performance (RBFNN-GP), is proposed in this paper. The proposed RBFNN-GP consists of three contributions. First, a local generalization error bound, introducing the sample mean and variance, is developed to acquire a small error bound to reduce the range of error. Second, the self-organizing structure method, based on a generalization error bound and network sensitivity, is established to obtain a suitable number of neurons to improve the generalization ability. Third, the convergence of this proposed RBFNN-GP is proved theoretically in the case of structure fixation and structure adjustment. Finally, the performance of the proposed RBFNN-GP is compared with some popular algorithms, using two numerical simulations and a practical application. The comparison results verified the effectiveness of RBFNN-GP.
1 January 2014 in Advances in Mechanical Engineering
The fault characteristic signals of rolling bearings are coupled with each other, thus increasing the difficulty in identifying the fault characteristics. In this study, a fault diagnosis method of rolling bearing based on least squares support vector machine is proposed. First, least squares support vector machine model is trained with the samples of known classes. Least squares support vector machine algorithm involves the selection of a kernel function. The complexity of samples in high-dimensional space can be adjusted through changing the parameters of kernel function, thus affecting the search for the optimal function as well as final classification results. Particle swarm optimization and 10-fold cross-validation method are adopted to optimize the parameters in the training model. Then, with the optimized parameters, the classification model is updated. Finally, with the feature vector of the test samples as the input of least squares support vector machine, the pattern recognition of the testing samples is performed to achieve the purpose of fault diagnosis. The actual bearing fault data are analyzed with the diagnosis method. This method allows the accurate classification results and fast diagnosis and can be applied in the diagnosis of compound faults of rolling bearing.
14 August 2023 in IEEE Transactions on Instrumentation and Measurement
The extreme unbalance of training samples among different working conditions caused by complex and variable external environment makes the fault diagnosis of chiller based on domain adaptation (DA) poor performance. Although recently emerging fault diagnosis methods based on domain generalization (DG) can learn domain-invariant knowledge from multiple source domains and can generalize to unseen target domains, these methods still rely on multiple similar source domain data and rarely consider how to enhance the ability to distinguish the joint distribution of features extracted from the source domain samples. To address these problems, a generative domain-generalized framework for chillers fault diagnosis, namely, vision transformer generative adversarial domain generalization (VIT-GADG), is proposed. In VIT-GADG, a novel VIT domain generation network (VIT-DGN) is firstly designed to reduce DG’s dependence on multi-source domain data by improving the diversity of the distribution of the source domain samples. Then, a new adversarial domain generalization network called VIT conditional adversarial domain generalization network (VIT-CADGN) is designed to extract domain-invariant knowledge from source domain and latent domains that can be generalized to unseen target domains. Specifically, VIT module can effectively extract the global statistical feature of input samples, which is conducive to the identification of joint distribution. Simultaneously, the collaborative conditional domain discrimination strategy is introduced to improve the distribution discrimination ability of the extracted global statistical features while simultaneously aligning its conditional distribution. In addition, a personalized adaptive weight strategy is proposed to improve the performance of VIT-CADGN. Finally, the comprehensive case study shows that VIT-GADG has a satisfactory ability to extract invariant features, which improves the diagnosis accuracy in the unseen target domain.
In the real chiller fault diagnosis tasks, the training data of target faults is commonly unavailable. This scenario restricts the diagnostic performance of data-driven methods. The existing zero-shot learning-based diagnostic models have conquered this challenge by introducing sparse fault semantic attributes. However, the sparse semantic representation misses the interconnections between attributes, which causes difficulty in representing holistically the latent associations between categories. In this article, an innovative zero-shot fault diagnosis (ZSFD) framework for chillers based on sentence-level text attributes is proposed to overcome this difficulty. The defined fault attributes contain two textual labels for the cause and consequence. Subsequently, all text attributes for each category are combined into a sentence (in text form), which is named sentence-level text attributes. Afterward, a semantic representation model, namely, sentence-level bidirectional encoder representations from transformer (SBERT), is employed to project sentence-level text attributes as the dense semantic attributes. Later, a cross-modal contrastive embedding (CMCE) model is established to embed semantic attributes and collected sensor data into a common latent space, where the distributions of attributes and data are aligned. Meanwhile, a hybrid reconstruction classification strategy is designed in CMCE to fully integrate the intrinsic characteristics of categories from both modalities. Finally, the unseen semantic attributes embedded by the CMCE are employed for training zero-shot learning classifier. Extensive experiments are designed and executed on the chiller dataset. The results demonstrate that the proposed framework can improve the distribution consistency between data and attributes compared with the ZSFD methods based on sparse representation, and achieves satisfactory diagnostic performance.