Abstract:Aiming at the fault diagnosis issue of rotating machinery, a novel method based on the deep learning theory is presented in this paper. By combining one-dimensional convolutional neural networks (1D-CNN) with self-normalizing neural networks (SNN), the proposed method can achieve high fault identification accuracy in a simple and compact architecture configuration. By taking advantage of the self-normalizing properties of the activation function SeLU, the stability and convergence of the fault diagnosi… Show more
“…The 1D-CNN performs convolutional calculation on a 1D signal [ 19 ]. 1D-CNN is a good model because 1D filters can detect different spatial shapes in one dimensional matrix [ 20 ]. 1D-CNN utilizes several 1D convolutional layers followed by max-pooling layers, and dynamic fully connected layers with ReLu activation functions.…”
When the displacement of an object is evaluated using sensor data, its movement back to the starting point can be used to correct the measurement error of the sensor. In medicine, the movements of chest compressions also involve a reciprocating movement back to the starting point. The traditional method of evaluating the effects of chest compression depth (CCD) is to use an acceleration sensor or gyroscope to obtain chest compression movement data; from these data, the displacement value can be calculated and the CCD effect evaluated. However, this evaluation procedure suffers from sensor errors and environmental interference, limiting its applicability. Our objective is to reduce the auxiliary computing devices employed for CCD effectiveness evaluation and improve the accuracy of the evaluation results. To this end, we propose a one-dimensional convolutional neural network (1D-CNN) classification method. First, we use the chest compression evaluation criterion to classify the pre-collected sensor signal data, from which the proposed 1D-CNN model learns classification features. After training, the model is used to classify and evaluate sensor signal data instead of distance measurements; this effectively avoids the influence of pressure occlusion and electromagnetic waves. We collect and label 937 valid CCD results from an emergency care simulator. In addition, the proposed 1D-CNN structure is experimentally evaluated and compared against other CNN models and support vector machines. The results show that after sufficient training, the proposed 1D-CNN model can recognize the CCD results with an accuracy rate of more than 95%. The execution time suggests that the model balances accuracy and hardware requirements and can be embedded in portable devices.
“…The 1D-CNN performs convolutional calculation on a 1D signal [ 19 ]. 1D-CNN is a good model because 1D filters can detect different spatial shapes in one dimensional matrix [ 20 ]. 1D-CNN utilizes several 1D convolutional layers followed by max-pooling layers, and dynamic fully connected layers with ReLu activation functions.…”
When the displacement of an object is evaluated using sensor data, its movement back to the starting point can be used to correct the measurement error of the sensor. In medicine, the movements of chest compressions also involve a reciprocating movement back to the starting point. The traditional method of evaluating the effects of chest compression depth (CCD) is to use an acceleration sensor or gyroscope to obtain chest compression movement data; from these data, the displacement value can be calculated and the CCD effect evaluated. However, this evaluation procedure suffers from sensor errors and environmental interference, limiting its applicability. Our objective is to reduce the auxiliary computing devices employed for CCD effectiveness evaluation and improve the accuracy of the evaluation results. To this end, we propose a one-dimensional convolutional neural network (1D-CNN) classification method. First, we use the chest compression evaluation criterion to classify the pre-collected sensor signal data, from which the proposed 1D-CNN model learns classification features. After training, the model is used to classify and evaluate sensor signal data instead of distance measurements; this effectively avoids the influence of pressure occlusion and electromagnetic waves. We collect and label 937 valid CCD results from an emergency care simulator. In addition, the proposed 1D-CNN structure is experimentally evaluated and compared against other CNN models and support vector machines. The results show that after sufficient training, the proposed 1D-CNN model can recognize the CCD results with an accuracy rate of more than 95%. The execution time suggests that the model balances accuracy and hardware requirements and can be embedded in portable devices.
“…In this layer, the input features first pass through multiple one-dimensional convolutional layers. Next, in order to differentiate the output of the convolutional layer and solve the problems of overfitting and poor robustness due to perturbations and noise interference, the scaled exponential linear unit [24] is selected as the activation function to perform a non-linear transformation on the output of the convolutional layer. Subsequently, max-pooling with several kernel sizes is adopted to perform dimensionality reduction operations.…”
Section: Multi-feature Fusion Based On Weakly Supervised Learning 331...mentioning
Multi-feature fusion has been widely used to enhance recognition accuracy for different health stages of rail, which may lead to high-dimensionality and information redundancy of signal. In addition, conventional supervised methods require plenty of labeled samples with class information, which can lead to significant time and economic costs. In order to improve the effectiveness of the electromagnetic acoustic emission (EMAE) technique in rail crack defect recognition, a novel method including multi-feature fusion based on weakly supervised learning and recognition threshold construction, is proposed in this paper. First, a mechanism contains of multi-feature extraction and feature selection, is developed to fully reflect the information of different health stages of rail and avoid interference caused by the ineffective features. Then, the effective features and a novel weakly unsupervised label are input into the self-normalizing convolutional neural network and long short-term memory (SCNN-LSTM) model to construct the rail health indicator (RHI). Finally, the recognition threshold is calculated by the characteristics of RHI, to achieve crack recognition automatically. Furthermore, the experimental results under different working conditions demonstrate that the proposed method achieves higher recognition performance than other existing methods in rail crack defect recognition.
“…1. Dropout 37,38 regularizes the neural network to reduce complex compatibility between neurons and prevent overfitting. Dropout is expressed as: where: P(P i =1)=p, belonging to Bernoulli random variable probability distribution; P is the probability that sample I generates 1; Ba is the number of models in class I neurons.…”
A novel fault diagnosis method based on Improved Singular Value Decomposition (SVD), S-transformation and Improved Convolutional Neural Networks (ICNN) is proposed for the non-stationary, nonlinear, interfered by strong background noise and difficult feature extraction problems of rolling bearing vibration signal of the road heading machine. Firstly, the original signal is constructed into a Hankel matrix which was decomposed by SVD. The effective singular values are selected according to the curvature spectrum of the singular values for signal recon-struction, and the reconstructed signals are transformed by S to generate the feature map, which is input into ICNN adaptive feature extraction for the fault identification. Secondly, the im-proved convolutional neural network uses VGG16 as a Bottleneck structure, introduces the bot-tleneck structure, selects input data with different sizes for feature extraction, adds Fine Tune on the basis of ICNN, and finally realizes fault classification and recognition through network pa-rameter adjustment. The proposed method is applied to the fault diagnosis of road heading ma-chine rolling bearings, and the accuracy rate is 98.2%, which is 9.55% higher than the classic VGG16 model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.