A deep Boltzmann machine and multi-grained scanning forest ensemble collaborative method and its application to industrial fault diagnosis

Hu, Guangzheng; Li, Huifang; Xia, Yuanqing; Luo, Lixuan

doi:10.1016/j.compind.2018.04.002

Cited by 80 publications

(30 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other researchers have endeavored to improve the classification accuracy by combining deep learning models with other models, such as the multi-grained cascade forest [164], fisher discriminative dictionary learning [165] and deep quantum neural network [166]. One commonality is they all used the deep learning model to learn feature representations and the other model to increase discriminative power.…”

Section: ) Structured Datamentioning

confidence: 99%

A Review on Deep Learning Applications in Prognostics and Health Management

et al. 2019

View full text Add to dashboard Cite

Deep learning has attracted intense interest in Prognostics and Health Management (PHM), because of its enormous representing power, automated feature learning capability and best-in-class performance in solving complex problems. This paper surveys recent advancements in PHM methodologies using deep learning with the aim of identifying research gaps and suggesting further improvements. After a brief introduction to several deep learning models, we review and analyze applications of fault detection, diagnosis and prognosis using deep learning. The survey validates the universal applicability of deep learning to various types of input in PHM, including vibration, imagery, time-series and structured data. It also reveals that deep learning provides a one-fits-all framework for the primary PHM subfields: fault detection uses either reconstruction error or stacks a binary classifier on top of the network to detect anomalies; fault diagnosis typically adds a soft-max layer to perform multi-class classification; prognosis adds a continuous regression layer to predict remaining useful life. The general framework suggests the possibility of transfer learning across PHM applications. The survey reveals some common properties and identifies the research gaps in each PHM subfield. It concludes by summarizing some major challenges and potential opportunities in the domain.

show abstract

Section: ) Structured Datamentioning

confidence: 99%

A Review on Deep Learning Applications in Prognostics and Health Management

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Therefore, manual The most common model-based, few-shot learning technology is embedding learning [29]: the training set and testing set are denoted D train and D test , the embedding function F projects the training sample data X train ∈ D train to a low-dimensional space Z, the embedding function g projects the testing samples X test ∈ D test to Z, then a similarity equation S is used to predict the embedding similarity between classes. Zhang [30] used a Siamese network for bearing fault diagnosis, Vinyal [11] proposed a matching network as a semi-supervised method to assign unlabeled samples to augment D train via soft-assignment during learning, Sung [31] used a relational network to embed samples into the status space at the same time, and used a convolutional neural network to automatically find similarities between different image categories, and Snell [32] proposed a prototypical network, Instead of comparing f (x test ) with each f (xi) where xi ∈ D train , the prototypical network only compares f (x test ) with the class prototypes in D train . For class n, the prototype is calculated by the formula…”

Section: Few-shot Learningmentioning

confidence: 99%

Few-Shot Rolling Bearing Fault Diagnosis with Metric-Based Meta Learning

Wang

Kong

et al. 2020

Sensors

View full text Add to dashboard Cite

Fault diagnosis methods based on deep learning and big data have achieved good results on rotating machinery. However, the conventional deep learning method of bearing fault diagnosis is mostly based on laboratory artificial simulation data, and there is an error with actual fault data, which will reduce the generalization performance of the deep learning method. In addition, labeled data are very precious in real industrial environment. Due to expensive equipment and personnel safety issues, it is difficult to obtain a large amount of high-quality fault labeling data. Therefore, in this paper, we propose a metric-based meta-learning method named Reinforce Relation Network (RRN) for diagnosing bearing faults with few-shot samples. In the proposed method, a 1D convolution neural network is used to extract fault features, and a metric learner is used to predict the similarity between samples under different transfer conditions. Label smoothing and the Adabound algorithm are utilized to further improve the performance of network classification. The performance of the proposed method is verified on a dataset which contains artificial damage and natural damage data. The comparison studies with other methods demonstrate the superiority of the proposed method in the few-shot scenario.

show abstract

“…Since x and z are real-value random variables on the probability space, the expect values of x and z can defined as the integral of x and z, respectively. Therefore, (14) can be re-written as…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

“…Due to the fast training of ESN, Long et al [13] proposed a deep echo state network optimized by particle swarm optimization to fault diagnosis of a wind turbine gearbox. Hu et al [14] present an approach with deep Boltzmann machine and multi-grained scanning forest to effectively deal with industrial fault diagnosis. Wang et al [15] proposed a new deep neural network model based on a deep Boltzmann machine for condition prognosis.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator

Cabrera

Sánchez

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Data-driven machine learning techniques play an important role in fault diagnosis, safety, and maintenance of the industrial robotic manipulator. However, these methods require data that, more often that not, are hard to obtain, especially data collected from fault condition states and, without enough and appropriated (balanced) data, no acceptable performance should be expected. Generative adversarial networks (GAN) are receiving a significant interest, especially in the image analysis field due to their outstanding generative capabilities. This paper investigates whether or not GAN can be used as an oversampling tool to compensate for an unbalanced data set in an industrial manipulator fault diagnosis task. A comprehensive empirical analysis is performed taking into account six different scenarios for mitigating the unbalanced data, including classical under and oversampling (SMOTE) methods. In all of these, a wavelet packet transform is used for feature generation while a random forest is used for fault classification. Aspects such as loss functions, learning curves, random input distributions, data shuffling, and initial conditions were also considered. A non-parametric statistical test of hypotheses reveals that all GAN based fault-diagnosis outperforms both under and oversampling classical methods while, within GAN based methods, an average accuracy difference as high as 1.68% can be achieved.

show abstract

A deep Boltzmann machine and multi-grained scanning forest ensemble collaborative method and its application to industrial fault diagnosis

Cited by 80 publications

References 22 publications

A Review on Deep Learning Applications in Prognostics and Health Management

A Review on Deep Learning Applications in Prognostics and Health Management

Few-Shot Rolling Bearing Fault Diagnosis with Metric-Based Meta Learning

Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator

Contact Info

Product

Resources

About