Batch-normalized deep neural networks for achieving fast intelligent fault diagnosis of machines

Wang, Jinrui; Li, Shunming; An, Zenghui; Jiang, Xingxing; Qian, Weiwei; Ji, Shanshan

doi:10.1016/j.neucom.2018.10.049

Cited by 214 publications

(104 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further improve vanishing and exploding gradients problem, batch normalization technique [45] is applied in the networks in this paper. The purpose of batch normalization is to linearly transform layer's inputs to ones with zero means and unit variances, making them de-correlated and be kept in the active region of the activation functions, without corrupting the learned features.…”

Section: Variable Initialization and Batch Normalizationmentioning

confidence: 99%

A novel deep neural network based approach for sparse code multiple access

et al. 2020

View full text Add to dashboard Cite

Sparse code multiple access (SCMA) has been one of non-orthogonal multiple access (NOMA) schemes aiming to support high spectral efficiency and ubiquitous access requirements for 5G wireless communication networks. Conventional SCMA approaches are confronting remarkable challenges in designing low complexity high accuracy decoding algorithm and constructing optimum codebooks. Fortunately, the recent spotlighted deep learning technologies are of significant potentials in solving many communication engineering problems. Inspired by this, we explore approaches to improve SCMA performances with the help of deep learning methods. We propose and train a deep neural network (DNN) called DL-SCMA to learn to decode SCMA modulated signals corrupted by additive white Gaussian noise (AWGN). Putting encoding and decoding together, an autoencoder called AE-SCMA is established and trained to generate optimal SCMA codewords and reconstruct original bits. Furthermore, by manipulating the mapping vectors, an autoencoder is able to generalize SCMA, thus a dense code multiple access (DCMA) scheme is proposed. Simulations show that the DNN SCMA decoder significantly outperforms the conventional message passing algorithm (MPA) in terms of bit error rate (BER), symbol error rate (SER) and computational complexity, and AE-SCMA also demonstrates better performances via constructing better SCMA codebooks. The performance of deep learning aided DCMA is superior to the SCMA.As depicted in Fig. 1, consider J users transmitting data bits over the same K sub-carriers of OFDM, here K < J such that overloading is provided. According to SCMA encoder, each user maps every m = log 2 (M ) bits into a K-dimensional complex codeword c with only N non-zero elements standing for QAM modulation and LDS spreading combination, here N < K. The overlapping degree is d f = JN K , and overloading ratio is λ = J K . There are M codewords forming a codebook for each user and each codebook is unique. The encoding procedure can be described by c = f (b), where b ∈ B log2(M ) and c ∈ C ⊂ C K with |C| = M . Function f is actually a mapping matrix which

show abstract

Section: Variable Initialization and Batch Normalizationmentioning

confidence: 99%

A novel deep neural network based approach for sparse code multiple access

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Due to the time-space correlation of the vibration signal in the degradation process of rolling bearing, a new prognosis model based on MCLSTM is proposed. Specifically, the MCLSTM is constructed by stacking multiple ConvLSTM units, and then batch normalization [39] technology is added between each ConvLSTM layer. After that, a dense layer is employed.…”

Section: Architecture Of the Proposed Networkmentioning

confidence: 99%

A Reliable Prognosis Approach for Degradation Evaluation of Rolling Bearing Using MCLSTM

Huang

et al. 2020

Sensors

View full text Add to dashboard Cite

Prognostics and health management technology (PHM), a measure to ensure the reliability and safety of the operation of industrial machinery, has attracted attention and application adequately. However, how to use the monitored information to evaluate the degradation of rolling bearings is a significant issue for its predictive maintenance and autonomic logistics. This work presents a reliable health prognosis approach to estimate the health indicator (HI) and remaining useful life (RUL) of rolling bearings. Firstly, to accurately capture the degradation process, a novel health index (HI) is constructed based on correlation kurtosis for different iteration periods and a Gaussian process latency variable model (GPLVM). Then, a multiple convolutional long short-term memory (MCLSTM) network is proposed to predict HI values and RUL values. Finally, we perform experimental datasets of rolling bearings, demonstrating that the presented method surpasses other state-of-the-art prognosis approaches. The results also confirm the feasibility of the presented method in industrial machinery.

show abstract

“…Its use is to normalize and scale the inputs from previous layers which in turn results in faster training and lower validation errors [15]. Using BN layers before activation layers has been shown to be successful in mitigating the internal covariant shift problem in the task of predicting faults in bearings and gearboxes [16]. Keras provides various activation functions via the Activation layer implementation: RELU, LeakyRELU, ELU, SELU, as well as the classical sigmoid and tanh.…”

Section: Convolutional Neural Network (Cnn) Modelmentioning

confidence: 99%

An End-to-End, Real-Time Solution for Condition Monitoring of Wind Turbine Generators

et al. 2020

View full text Add to dashboard Cite

Data-driven wind generator condition monitoring systems largely rely on multi-stage processing involving feature selection and extraction followed by supervised learning. These stages require expert analysis, are potentially error-prone and do not generalize well between applications. In this paper, we introduce a collection of end-to-end Convolutional Neural Networks for advanced condition monitoring of wind turbine generators. End-to-end models have the benefit of utilizing raw, unstructured signals to make predictions about the parameters of interest. This feature makes it easier to scale an existing collection of models to new predictive tasks (e.g., new failure types) since feature extracting steps are not required. These automated models achieve low Mean Squared Errors in predicting the generator operational state (40.85 for Speed and 0.0018 for Load) and high accuracy in diagnosing rotor demagnetization failures (99.67%) by utilizing only raw current signals. We show how to create, deploy and run the collection of proposed models in a real-time setting using a laptop connected to a test rig via a data acquisition card. Based on a sampling rate of 5 kHz, predictions are stored in an efficient time series database and monitored using a dynamic visualization framework. We further discuss existing options for understanding the decision process behind the predictions made by the models.

show abstract

Batch-normalized deep neural networks for achieving fast intelligent fault diagnosis of machines

Cited by 214 publications

References 13 publications

A novel deep neural network based approach for sparse code multiple access

A novel deep neural network based approach for sparse code multiple access

A Reliable Prognosis Approach for Degradation Evaluation of Rolling Bearing Using MCLSTM

An End-to-End, Real-Time Solution for Condition Monitoring of Wind Turbine Generators

Contact Info

Product

Resources

About