The speed of rotating parts is often affected by different working conditions in mechanical equipment, which results in more complications in the feature mapping relationship. However, existing methods that address the large fluctuation problem in rotational speed have been formulated merely to improve test accuracy and do not consider the effects of irregular fluctuation frequency on the fault samples located at the class boundary. Thus, to distinguish the health conditions under frequent or irregular fluctuation speeds, this paper explores an enhanced sparse filtering (SF) algorithm based on maximum classifier discrepancy to diagnose the fault conditions caused by speed fluctuation. It considers the superiority of the task-specific decision boundary and adversarial training for the fault diagnosis network. Unlike traditional SF methods, the proposed framework introduces the Wasserstein distance to reduce the domain discrepancy between the source domain and the target domain and then uses the probability output discrepancy of the classifier to locate the fuzzy fault samples on the class boundary. This paper conducts theoretical analysis and experimental comparison and verifies the performance advantages of the framework through bearing and gear experiments under large speed fluctuation conditions. The proposed model also shows an excellent performance even when the speed fluctuates frequently.
Effective fault diagnosis is essential to ensure the safe and reliable operation of equipment. In recent years, several transfer learning-based methods for diagnosing faults under variable working conditions have been developed. However, these models are designed to completely match the feature distributions between different domains, which is difficult to accomplish because each domain has unique characteristics. To solve this problem, we propose a framework based on the maximum classifier discrepancy with marginal probability distribution adaptation that focuses on task-specific decision boundaries. Specifically, this method captures ambiguous target samples through the predicted discrepancy between two classifiers for the target samples. Furthermore, marginal probability distribution adaptation facilitates the capture of target samples located far from the source domain, and these target samples are brought closer to the source domain through adversarial training. Experimental results indicate that the proposed method demonstrates higher performance and generalization ability than existing fault diagnosis methods.
In recent times, machine learning has shown its efficiency in the field of fault diagnosis. Nevertheless, in many real-world applications, the basic data are often collected under the condition of machine working condition change, thereby leading to large distribution divergences. Thus, we propose the novel general normalized maximum mean discrepancy (GNMMD) feature-learning method to overcome the limitation of unstable conditions. The proposed algorithm can efficiently handle high-dimensional inputs by enforcing three constraints on the matrix of the learned features, and can optimize the objective function-based generalized norm features and MMD. First, this study analyzes the mapping characteristics of the generalized norm. Second, the feature selection approach based on GNMMD is further studied. Third, the current research also discusses the effects of different choices of norm on the diagnosis performance. Lastly, the data sets of the rolling bearing and planetary gear under unstable conditions are used to verify that the proposed method can achieve superior results.
As a practical tool for big data processing, deep learning not only has drawn extensive attentions in the inherent law and representation level of sample data, but also has been widely concerned in the field of mechanical intelligent fault diagnosis. In deep learning models, autoencoder (AE) and its derivative models can automatically extract useful features from big data, and many researchers have successfully applied them to the field of intelligent fault diagnosis. However, these studies always neglect two important points as follows: (1) the model training process will not be ideal when the original training dataset is insufficient; (2) the learning content of the network model is not clear. In order to surmount the above deficiencies, this paper proposes a novel framework named Data-enhanced Stacked Autoencoders (DESAE), which consists of a data enhancement module and a fault classification module. In the data enhancement module, SAE is adopted to generate simulated signals to strengthen the insufficient training data. In the fault classification module, the enhanced dataset is used to train another SAE model for fault type recognition. Meanwhile, two bearing datasets are employed to validate the efficiency of the proposed method. The experimental results show that the proposed method is superior to the method without enhanced data. In addition, the visual analysis of the learning characteristics in each layer of DESAE is presented, which is helpful to understand the working process of DESAE. INDEX TERMS Intelligent fault diagnosis, deep learning, data-enhanced stacked auto-encoders, insufficient training data, simulated signals.
The problem of insufficient datasets has long been a hot topic in the field of prognosis and health management of rotary machines. Generative adversarial network (GAN) and other data augmentation algorithms can solve the problem of insufficient samples. However, the premise of the above method is the signal collected at a constant speed rather than at large speed fluctuation. To deal with data augmentation under large speed fluctuation, this paper proposes an effective deep learning method, namely, domain adaptive efficient sub-pixel network (DAESPN). The core idea of DAESPN is to enhance the resolution of the original sample for data augmentation. The DAESPN framework is implemented as follows: after the data passes through the fully connected neural network, the multi-feature maps of the four channels are outputted. A group of high resolution (HR) features is obtained through the sub-pixel fully connected layer. In addition, maximum mean discrepancy (MMD) and mean square error (MSE) are used to construct the loss function of the model. Experimental results of gearbox and bearing datasets show that the DAESPN model has strong feasibility to carry out data augmentation for fault diagnosis of rotating machines under speed fluctuation condition. In addition, the feature learning process of DAESPN is visually displayed and analyzed.
In the real production of industry, in order to solve the problem that it is usually difficult to obtain correctly labeled samples, data augmentation algorithms have received more and more attention. Many efficient deep learning models have been successfully applied to the intelligent fault diagnosis of rotating machinery. However, the premise of the above method is the working conditions of the machinery are constant. It is inevitable that the equipment runs under large speed fluctuation in real industries. To achieve data augmentation under the condition of variable speed, an efficient sub-pixel deep residual neural network (ESPDRN) is proposed. The ESPDRN framework is implemented as follows: utilize low resolution (LR) samples as input to the network, to effectively learn high-level and extract feature maps by constructing a deep residual network. Through sub-pixel convolution layers to arrange the LR features of multi-channels periodically and get a set of ultra high resolution features, and the data points are augmented 16 times compared to raw data. Statistical indicators and experimental results demonstrate that the proposed ESPDRN model can effectively generate data under the condition of variable speed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.