Detection of Pitting in Gears Using a Deep Sparse Autoencoder

Qu, Yongzhi; He, M.; Deutsch, Jason; He, David

doi:10.3390/app7050515

Cited by 54 publications

(24 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, P f is the fitness of particle, and the size of the fitness corresponds to the distance between each bird and food. The extremum of individual P b and extremum of population g b can be updated according to particle fitness, and then we can use the individual extremum and the population extremum to calculate the particle velocity and position, as shown in equations (27) and (28)…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

A domain adaptation model for early gear pitting fault diagnosis based on deep transfer learning network

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part O:

Self Cite

View full text Add to dashboard Cite

In recent years, research on gear pitting fault diagnosis has been conducted. Most of the research has focused on feature extraction and feature selection process, and diagnostic models are only suitable for one working condition. To diagnose early gear pitting faults under multiple working conditions, this article proposes to develop a domain adaptation diagnostic model–based improved deep neural network and transfer learning with raw vibration signals. A particle swarm optimization algorithm and L2 regularization are used to optimize the improved deep neural network to improve the stability and accuracy of the diagnosis. When using the domain adaptation diagnostic model for fault diagnosis, it is necessary to discriminate whether the target domain (test data) is the same as the source domain (training data). If the target domain and the source domain are consistent, the trained improved deep neural network can be used directly for diagnosis. Otherwise, the transfer learning is combined with improved deep neural network to develop a deep transfer learning network to improve the domain adaptability of the diagnostic model. Vibration signals for seven gear types with early pitting faults under 25 working conditions collected from a gear test rig are used to validate the proposed method. It is confirmed by the validation results that the developed domain adaptation diagnostic model has a significant improvement in the adaptability of multiple working conditions.

show abstract

Section: Particle Swarm Optimizationmentioning

confidence: 99%

A domain adaptation model for early gear pitting fault diagnosis based on deep transfer learning network

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part O:

Self Cite

View full text Add to dashboard Cite

show abstract

“…Acc is the proportion of true decisions in all tests, and Sen and Spe represent the proportion of positive and negative cases that were detected correctly, respectively. The formulation is shown in Equations (19)- (21). We used Sen to evaluate the classification accuracy of these methods.…”

Section: Comprehensive Comparison Of Classifier Performancementioning

confidence: 99%

“…To reveal the deeper connection between the variables and create a proper representation of physical meaning, this paper proposes a novel feature extraction scheme for complex system fault diagnosis using deep learning and sparse representation. Deep learning allows computational models composed of multiple processing layers to learn the representation of data [18][19][20][21]. The backpropagation algorithm (BP algorithm) is applied after the weights training step in deep learning to discover intricate structures in large data sets, and the BP algorithm makes up the disadvantage of gradient diffusion in pretraining weights of the network.…”

Section: Introductionmentioning

confidence: 99%

Fisher Discriminative Sparse Representation Based on DBN for Fault Diagnosis of Complex System

Tang

Chai

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

Fault detection and diagnosis in the chemical industry is a challenging task due to the large number of measured variables and complex interactions among them. To solve this problem, a new fault diagnosis method named Fisher discriminative sparse representation (FDSR), based on deep belief network (DBN), is proposed in this paper. We used DBN to extract the features of all faulty and normal modes. Features extracted by the DBN were used to learn subdictionaries, then the overcomplete dictionary was constructed by cascading all subdictionaries in order, and each dictionary atom corresponded to class labels. The Fisher discrimination criterion (FDC) was applied to the dictionary learning to ensure smaller within-class scatter but greater between-class scatter. The quadratic programming method was applied to estimate the sparse coefficients simultaneously class by class. Therefore, both the reconstruction error and sparse coefficients were discriminative, so that the reconstruction error after sparse coding can be used for pattern classification. An experiment performed on the Tennessee Eastman (TE) process indicated that compared with the traditional monitoring methods, the FDSR based on DBN produced more interpretable results and achieved superior performance for feature extraction and classification in the field of complex system fault diagnosis. T-distributed stochastic neighbor embedding (t-SNE) appropriately visualized the performance of the proposed method and produced reliable fault diagnosis results.

show abstract

“…Morsy et al [5] applied continuous wavelet transform, fast Fourier transform algorithm, and order analysis measurements to detect artificial pitting defects in the gear by tracking acceleration and gearbox response under different loads. Qu et al [6] presented unsupervised sparse autoencoder combined with dictionary learning 7 1 for fault diagnosis of gear pitting.…”

Section: Introductionmentioning

confidence: 99%

Gear pitting level diagnosis using vibration signals with an improved inception structure

et al. 2018

Vib. proced.

Self Cite

View full text Add to dashboard Cite

Gear pitting fault is common in mechanical devices. At present, most of the gear pitting fault detection methods are based on the manual extraction of the frequency domain features from vibration signals. This paper presents a method for gear pitting fault level diagnosis using vibration signals with an improved inception network. The presented method directly applies to the vibration signals to automatically extract features and diagnose the level of the gear pitting fault using deep learning. The presented method has been validated with vibration data collected for 7 gear pitting conditions from gear pitting fault tests. The validation results have shown that the presented method can effectively classify the levels of the gear pitting faults. In comparison with traditional convolutional neural network, the diagnosis accuracy has been significantly improved with the presented method.

show abstract

Detection of Pitting in Gears Using a Deep Sparse Autoencoder

Cited by 54 publications

References 30 publications

A domain adaptation model for early gear pitting fault diagnosis based on deep transfer learning network

A domain adaptation model for early gear pitting fault diagnosis based on deep transfer learning network

Fisher Discriminative Sparse Representation Based on DBN for Fault Diagnosis of Complex System

Gear pitting level diagnosis using vibration signals with an improved inception structure

Contact Info

Product

Resources

About