Fault Diagnosis from Raw Sensor Data Using Deep Neural Networks Considering Temporal Coherence

Self Cite

Due to the noise accompanied with rolling element bearing fault signal, it can reduce the accuracy of faulty diagnoses. In order to improve the robustness of a faulty diagnosis, this study proposed a fault diagnosis model based on modified local linear embedding (M-LLE) algorithm. Aiming at the characteristics of rolling element bearing fault data, the vibration signal was first analyzed in time domain and frequency domain to construct high dimension eigenvectors. Next, the high-dimensional eigenvectors can be reduced to low-dimensional eigenvectors by M-LLE algorithm. In the M-LLE algorithm, the Mahalanobis distance (MD) metric is adopted to replace Euclidean distance in traditional neighborhood construction and L1-norm is used to standardize weight matrix, which can enhance the anti-noise ability of the Local Linear Embedding (LLE) algorithm. Finally, fault diagnosis results can be obtained when low-dimensional rolling element bearing fault data is classified by K-Nearest Neighbor (KNN) classifier. By simulating the noisy artificial data sets in different degrees, the proposed algorithm can get the perfect local structure of manifolds. The effectiveness of M-LLE algorithm can be proved. In addition, experimental results of real rolling element bearing data which provided by the University of Cincinnati show that the accuracies of all kinds of faults can reach 100%. It can be deemed that the proposed fault diagnosis model can effectively improve the accuracy of fault diagnosis.

Section: Characteristic Equation Numbermentioning

confidence: 99%

Section: Characteristic Equation Numbermentioning

confidence: 99%

Modified Local Linear Embedding Algorithm for Rolling Element Bearing Fault Diagnosis

Yao

et al. 2017

Self Cite

“…The DNN training process is thoroughly presented in the following sections. DNN is a stacked layer model in which the layers are connected together and there are no connections of nodes within the same layer [16]. A DNN includes an input layer, an output layer, and a few hidden layers placed between them in the model.…”

Section: Dnn For Defect Degradation Predictionmentioning

confidence: 99%

“…With more and more data available to us, it is essential to use intelligent learning models that can extract useful information from the measured data for fault detection and diagnosis. The developed techniques based on machine learning [12,13] and deep learning [14][15][16] have generally been applied in estimating the defect severity of bearings and in diagnosing those defects under varying conditions. These approaches are an effective solution for big data analytics, which are common nowadays [17][18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Effective Prediction of Bearing Fault Degradation under Different Crack Sizes Using a Deep Neural Network

Nguyen

Kim

2018

Exact evaluation of the degradation levels in bearing defects is one of the most essential works in bearing condition monitoring. This paper proposed an efficient evaluation method using a deep neural network (DNN) for correct prediction of degradation levels of bearings under different crack size conditions. An envelope technique was first used to capture the characteristic fault frequencies from acoustic emission (AE) signals of bearing defects. Accordingly, a health-related indicator (HI) calculation was performed on the collected envelope power spectrum (EPS) signals using a Gaussian window method to estimate the fault severities of bearings that served as an appropriate dataset for DNN training. The proposed DNN was then trained for effective prediction of bearing degradation using the Adam optimization-based backpropagation algorithm, in which the synaptic weights were optimally initialized by the Xavier initialization method. The effectiveness of the proposed degradation prediction approach was evaluated through different crack size experiments (3, 6, and 12 mm) of bearing faults.

“…Nevertheless, inimical operating environments and cyclic stuffing can lead to substantial wear in bearings, exhibiting in the form of exterior cracks [3]. If these surface cracks go undetected, it can lead to unexpected shutdowns, resulting in financial inefficiency, as well as human injuries [4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Bearing Fault Diagnosis under Variable Rotational Speeds Using Stockwell Transform-Based Vibration Imaging and Transfer Learning

Hasan

Kim

2018

In this paper, discrete orthonormal Stockwell transform (DOST)-based vibration imaging is proposed as a preprocessing step for supporting load and rotational speed invariant scenarios for signals of various health conditions. For any health condition, features can easily be extracted from its generated health pattern. To automate the feature selection process, a convolutional neural network (CNN)-based transfer learning (TL) approach for diagnosis has also been introduced. Transfer learning allows an established model to use feature knowledge obtained under one set of working conditions through hidden layers to diagnose faults that occur under other working conditions. The network learns from the massive source dataset, and that knowledge is applied to the target data to identify faults. Using the bearing dataset of Case Western Reserve University, the proposed approach yields an average 99.8% classification accuracy and, specifically, 99.99% for healthy condition (HC), 99.95% for inner race fault (IRF), 99.96% for ball fault (BF), 99.68% for outer race fault for 12 o’clock sensor position (ORF@12), 99.93% for outer race fault for 3 o’clock sensor position (ORF@3), and 99.89% for outer race fault for 6 o’clock sensor position (ORF@6). In this paper, the proposed approach is compared with conventional artificial neural networks (ANNs), support vector machines (SVMs), hierarchical CNNs, and deep autoencoders. The proposed approach outperforms these conventional methods in the accuracy under all working conditions.