Search

Recently, deep learning techniques have been widely applied to fault diagnosis due to their outstanding feature extraction abilities. The success of deep-learning-based fault diagnosis methods is highly dependent on the quantity and quality of the training data. In practical scenarios, it is challenging to obtain sufficient high-quality training data for fault diagnosis tasks due to complex environments, which would affect the effectiveness of the deep learning methods. In this paper, a new fault diagnosis method is proposed for motor bearing fault diagnosis under small samples. The Siamese neural networks (SNNs) are employed to extract the fault features. A multi-stage training strategy is proposed to train the SNNs with the aim to prevent the training stagnation problem and handle the small sample problem. A multi-source feature fusion network is developed to make full use of the multi-source sensor data by fusing the extracted fault features for further fault diagnosis. The proposed method is applied to motor bearing fault diagnosis on two real-world datasets. Experimental results demonstrate the effectiveness and feasibility of the introduced method for motor bearing fault diagnosis under small samples. [ABSTRACT FROM AUTHOR]

Zero-shot learning is a promising technique for diagnosing mechanical faults in complex and uncertain environments. However, when diagnosing mechanical faults across different severities using zero-shot learning, the impact of insensitive features should be minimized due to the susceptibility of zero-shot prototypes and the vulnerability of vibration signals. To accomplish this, an Insensitive Feature Removal Network (IFRN) with an entire attention mechanism (EAM) module and a denoise autoencoder module is proposed to remove insensitive features hierarchically by dividing them into two categories: common insensitive features (CIF) and private insensitive features (PIF), each with different properties depending on their corresponding sub-labels presence in mechanical faults. Concretely, EAM removes insensitive features that the classifier cannot differentiate with the help of the entire attention weight comparison by attention generation, attention comparison, and attention limitation parts. Then, the denoise autoencoder module with long short memory term (LSTM) is utilized to remove the insensitive features that are not completely removed, especially for the insensitive features that independently arise. The IFRN's effectiveness is demonstrated through comparative experiments and ablation studies using the Case Western Reserve University (CWRU) dataset, where the experimental result shows that IFRN outperforms conventional zero-shot learning methods. Furthermore, an analysis with prototype distance and sample aggregation is presented to further justify the effectiveness of the proposed method in reducing the prototype shift and improving classification accuracy by removing insensitive features. • IFRN with EAM is proposed to hierarchically alleviate the effect of insensitive features. • EAM can effectively eliminate insensitive features that the classifier cannot differentiate. • IFRN performance is verified on the CWRU rolling bearing dataset. [ABSTRACT FROM AUTHOR]

Aiming at limitations in fully exploiting the temporal correlation features of the original signals, expensive cost in parameter tuning, and difficulties in obtaining sufficient training data under multiple working conditions, this paper proposes an optimized Convolutional Neural Network (CNN) with Bi-directional Long Short-Term Memory (BiLSTM) scheme for bearing fault diagnosis under multiple working conditions with limited training samples. A CNN-BiLSTM network is developed to obtain precise fault features and high detection accuracy by extracting high-dimensional and temporal correlation features of raw vibration signals. An improved particle swarm optimization (PSO) algorithm is leveraged to optimize the training hyperparameters of the CNN-BiLSTM network for further advances in fault diagnosis performance. The optimized CNN-BiLSTM network is regarded as a pre-trained model and transferred to new working conditions to achieve satisfactory fault diagnosis results based on limited training samples. Several comprehensive experiments are implemented to confirm the excellent performance of the proposed schemes, especially efficiently addressing the challenges of model training and fault diagnosis in new working conditions with scarce samples. [ABSTRACT FROM AUTHOR]

Through the application of deep learning and multi-sensor data, fault features can be automatically extracted and valuable information can be integrated to tackle intricate challenges in motor bearing fault diagnosis. Most existing fusion models focus primarily on the original time series signal with information extraction largely restricted to the time domain (without extensions into multiple transformation domains). Also, in most fusion models, the sensor fusion level is kept relatively simple which could lead to the oversight of correlations and complementarities among the information. To enhance the recognition capability of diagnostic network features, in this paper, we propose a novel framework for motor bearing fault diagnosis from the perspectives of multi-transformation domain and multi-source data fusion. Within this framework, feature extraction and fusion from various source data are achieved in the time domain, frequency domain, and time–frequency domain. Distinct independent networks are set up within these domains: one network is designated for overseeing feature fusion, while the others are dedicated to extracting features from individual sensors. To support the extraction of pivotal features across multiple fusion layers in various transformation domains, several fusion nodes are inserted between the layers of the multiple feature extraction networks and the feature summarization network. Furthermore, a channel attention mechanism is introduced as a fusion strategy that serves to pinpoint the significance of different features, thus enhancing the efficiency of feature extraction. Experimental evaluation reveals the efficacy of the proposed model and highlights its noteworthy performance attributes such as scalability and universality. [ABSTRACT FROM AUTHOR]