Tacho-less sparse CNN to detect defects in rotor-bearing systems at varying speed

Kumar, Anil; Vashishtha, Govind; Gandhi, C.P.; Tang, Hesheng; Xiang, Jiawei

doi:10.1016/j.engappai.2021.104401

Cited by 59 publications

(19 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fully connected layers are a type of artificial neural network where all nodes and neurons of the architecture in one layer are connected to the next layers. The features are kept in the nodes in the layers and the learning process is entered by changing the weight and bias values 27 . After the fully connected layers, the activation function is used to get the classification output.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A novel convolutional neural network‐based approach for brain tumor classification using magnetic resonance images

Cinar

Kaya

2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Brain tumor is a disease that seriously threatens human health and can often be treated with risky surgeries. Experts detect brain tumor with high resolution magnetic resonance (MR) images. However, the expected accuracy value could not be reached in the studies carried out so far. The aim of this study is to develop a new approach for detecting brain tumor types using MR images. In the proposed approach, it is designed a CNN-based neural network from scratch. The results of the method were compared with existing networks. The proposed approach detected glioma tumors with 99.64%, meningiomas tumor with 96.53%, pituitary tumors with 98.39% and an average of 98.32% accuracy. The developed CNN based model is also compared with deep CNN models such as ResNet50, VGG19, DensetNet121 and InceptionV3, which are operated by transfer learning method. The results show that the proposed approach outperforms other deep neural networks.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The features are kept in the nodes in the layers and the learning process is entered by changing the weight and bias values. 27 After the fully connected layers, the activation function is used to get the classification output.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

A novel convolutional neural network‐based approach for brain tumor classification using magnetic resonance images

Cinar

Kaya

2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…In CLs, the inputs evolve with multiple convolution cores and then output features are produced by the activation unit. The formula expression of these operations can be given by equation 10 [23].…”

Section: 𝑦 = 𝐹(𝑥{𝑊𝑖})+ ℎ(𝑥) (8)mentioning

confidence: 99%

Deep Transfer Learning-Based Broken Rotor Fault Diagnosis For Induction Motors

DİŞLİ

Gedikpınar

Şengür

2023

Turkish Journal of Science and Technology

View full text Add to dashboard Cite

Modern industrial drives use induction motors (IM) due to their starting and running torque requirements and four-quadrant operation. The voltages and currents of each of the three phases as well as the acceleration and velocity signals may be used to identify failures in the rotor bars of the motor. In the past, traditional signal processing-based feature extraction approaches and machine learning algorithms have been used for the diagnosis of the number of broken rotor bars for a failed IM. In this paper, a new scheme is investigated for the determination of the number of broken rotor bars. Specifically, the deep learning approaches are examined for the mentioned purposes. To this end, transfer learning approaches on the convolutional neural network (CNN) are presented. For denoising, initially, a bandpass filter is employed, and then the signals are converted to time-frequency images by using the continuous wavelet transform (CWT). The obtained images are used for the fine-tuning of the pre-trained ResNet18 model and the deep feature extraction and classification with the support vector machine (SVM) classifier. The classification accuracy is used for performance evaluation metrics. Moreover, the experiments show that the highest accuracy score of 100% is obtained with the deep features that are extracted from the mechanical vibration signal and current signal. On the other hand, a performance comparison with the published approaches is also carried out. Finally, the comparisons show that the proposed method produces better accuracy scores than the compared methods.

show abstract

“…He et al [22] proposed a CNN-based fault diagnosis method for the rotor-bearing systems using small labeled infrared thermal images as model input. Kumar et al [23] proposed a sparse CNN-based fault diagnosis for rotor-bearing systems at varying speeds by developing sparsity cost in the existing cost function of a CNN to enhance the learning capability of the CNN.…”

Section: Introductionmentioning

confidence: 99%

An Improved Convolutional-Neural-Network-Based Fault Diagnosis Method for the Rotor–Journal Bearings System

Luo

Lin

Peng³

et al. 2022

Machines

View full text Add to dashboard Cite

More layers in a convolution neural network (CNN) means more computational burden and longer training time, resulting in poor performance of pattern recognition. In this work, a simplified global information fusion convolution neural network (SGIF-CNN) is proposed to improve computational efficiency and diagnostic accuracy. In the improved CNN architecture, the feature maps of all the convolutional and pooling layers are globally convoluted into a corresponding one-dimensional feature sequence, and then all the feature sequences are concatenated into the fully connected layer. On this basis, this paper further proposes a novel fault diagnosis method for a rotor–journal bearing system based on SGIF-CNN. Firstly, the time-frequency distributions of samples are obtained using the Adaptive Optimal-Kernel Time–Frequency Representation algorithm (AOK-TFR). Secondly, the time–frequency diagrams of the training samples are utilized to train the SGIF-CNN model using a shallow information fusion method, and the trained SGIF-CNN model can be tested using the time–frequency diagrams of the testing samples. Finally, the trained SGIF-CNN model is transplanted to the equipment’s online monitoring system to monitor the equipment’s operating conditions in real time. The proposed method is verified using the data from a rotor test rig and an ultra-scale air separator, and the analysis results show that the proposed SGIF-CNN improves the computing efficiency compared to the traditional CNN while ensuring the accuracy of the fault diagnosis.

show abstract

Tacho-less sparse CNN to detect defects in rotor-bearing systems at varying speed

Cited by 59 publications

References 49 publications

A novel convolutional neural network‐based approach for brain tumor classification using magnetic resonance images

A novel convolutional neural network‐based approach for brain tumor classification using magnetic resonance images

Deep Transfer Learning-Based Broken Rotor Fault Diagnosis For Induction Motors

An Improved Convolutional-Neural-Network-Based Fault Diagnosis Method for the Rotor–Journal Bearings System

Contact Info

Product

Resources

About