Towards understanding sparse filtering: A theoretical perspective

Zennaro, Fabio Massimo; Chen, Ke

doi:10.1016/j.neunet.2017.11.010

Cited by 34 publications

(19 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For deep learning methods, for instance, deep belief networks [5], sparse filtering [6], and autoencoders (AEs) [7,8], the main assumption is that the datasets applied to train and test the model have the same feature distribution. Unfortunately, the raw vibration signals are usually obtained under variable working cases in practical applications, which show deviation from the assumption [9,10].…”

Section: Introductionmentioning

confidence: 99%

A Novel Domain Adaptation-Based Intelligent Fault Diagnosis Model to Handle Sample Class Imbalanced Problem

Zhang

Shao

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

As the key component to transmit power and torque, the fault diagnosis of rotating machinery is crucial to guarantee the reliable operation of mechanical equipment. Regrettably, sample class imbalance is a common phenomenon in industrial applications, which causes large cross-domain distribution discrepancies for domain adaptation (DA) and results in performance degradation for most of the existing mechanical fault diagnosis approaches. To address this issue, a novel DA approach that simultaneously reduces the cross-domain distribution difference and the geometric difference is proposed, which is defined as MRMI. This work contains three parts to improve the sample class imbalance issue: (1) A novel distance metric method (MVD) is proposed and applied to improve the performance of marginal distribution adaptation. (2) Manifold regularization is combined with instance reweighting to simultaneously explore the intrinsic manifold structure and remove irrelevant source-domain samples adaptively. (3) The ℓ2-norm regularization is applied as the data preprocessing tool to improve the model generalization performance. The gear and rolling bearing datasets with class imbalanced samples are applied to validate the reliability of MRMI. According to the fault diagnosis results, MRMI can significantly outperform competitive approaches under the condition of sample class imbalance.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Domain Adaptation-Based Intelligent Fault Diagnosis Model to Handle Sample Class Imbalanced Problem

Zhang

Shao

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…SF is just a two-layer neural network, which is much simpler than DBN and AEs. Therefore, SF can overcome the parameter tuning difficulty and converge easily to an optimal solution [28]. Meanwhile, SF attempts to learn discriminative features by optimizing the sparsity of latent features, instead of learning the principal components of the input data [29].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Mechanical Fault Feature Learning Based on Consistency Inference-Constrained Sparse Filtering

et al. 2020

View full text Add to dashboard Cite

In machinery fault diagnosis, a large amount of monitoring data is often unlabeled, while the number of labeled data is limited. Therefore, learning effective features from massive unlabeled data is a challenging issue for machinery fault diagnosis. In this paper, a simple unsupervised feature learning method, consistency inference-constrained sparse filtering (CICSF), is proposed to learn mechanical fault features with enhanced clustering performance for fault diagnosis. Firstly, inspired by the data augmentation strategy, consistency inference of latent representations for time series (CILRTS) is derived, which infers that training data instances segmented from the same time series should possess consistent latent feature representations. Then, CILRTS is integrated into sparse filtering (SF) as an additional constraint in the latent feature space. The developed CICSF method can optimize the inter-class sparsity and intra-class similarity of the feature distribution simultaneously. Thus, it can learn more effective features from massive unlabeled data. Finally, based on CICSF, a semi-supervised machinery fault diagnosis method is developed. After unsupervised feature learning by CICSF, a softmax regression classifier is trained with limited labeled data to realize machinery fault diagnosis. Experimental results on bearing and gearbox datasets verify the effectiveness of the proposed method. Moreover, comparisons with standard SF and several auto-encoder (AE) variants validate its superiority in unsupervised feature learning and fault diagnosis using limited labeled data. INDEX TERMS Unsupervised feature learning, machinery fault diagnosis, consistent inference of latent representations for time series, sparse filtering, auto-encoder

show abstract

“…Classical unsupervised learning methods include kernel principle component analysis (KPCA) [30], restricted Boltzmann machine (RBM) [31], sparse autoencoder (SAE) [32], and sparse filtering (SF) [33]. Compared with other approaches, SF optimizes feature sparsity distribution instead of modeling data distribution [34]. It is different from other conventional or novel neural network (NN) structures such as variable NNs in fault diagnosis application [35].…”

Section: Introductionmentioning

confidence: 99%

Combining Spatial Filtering and Sparse Filtering for Coaxial-Moving Sound Source Separation, Enhancement and Fault Diagnosis

Xiong

Ouyang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The wayside acoustic detector system is a potential technique in ensuring the safety of traveling vehicles. However, multisource aliasing and Doppler distortion in acquired acoustic signals decrease the accuracy of machine diagnosis. The conventional multisource separation schemes fail to solve the coaxial-moving sound source (CMSS) problem by constructing time-frequency filters and designing one-dimensional time-varying spatial filters. To address this issue, this paper combines spatial filtering with sparse filtering to solve this problem. Spatial filtering could suppress but not eliminate undesired sources. Sparse filtering has no capability of coping with non-stationary signals with Doppler distortion. The combination of spatial filtering and sparse filtering could make up their shortcomings and effectively solve the CMSS problem. The proposed scheme has two main advantages of eliminating residual interferences completely and suppressing background noise effectively. The simulation and experimental cases verify the effectiveness of the proposed method. The results indicate the potential of the proposed method to improve the performance of wayside acoustic detector systems.

show abstract

Towards understanding sparse filtering: A theoretical perspective

Cited by 34 publications

References 37 publications

A Novel Domain Adaptation-Based Intelligent Fault Diagnosis Model to Handle Sample Class Imbalanced Problem

A Novel Domain Adaptation-Based Intelligent Fault Diagnosis Model to Handle Sample Class Imbalanced Problem

Unsupervised Mechanical Fault Feature Learning Based on Consistency Inference-Constrained Sparse Filtering

Combining Spatial Filtering and Sparse Filtering for Coaxial-Moving Sound Source Separation, Enhancement and Fault Diagnosis

Contact Info

Product

Resources

About